1. A method for monitoring and operating a machine (103) using a non-invasive health monitoring system (101) in a computing environment (100), the method comprising: receiving, by a non-invasive health monitoring system (101), one or more sensor data (213) from a machine (103), wherein the one or more sensor data (213) comprises one or more external sensor data and one or more internal sensor data, wherein the one or more external sensor data corresponds to one or more non-invasive sensors (115) connected externally to the machine (103) via a communication network (113); determining, by the non-invasive health monitoring system (101), a type of the machine (103) connected to the one or more non-invasive sensors (115) based on the received one or more sensor data (213); training, by non-invasive health monitoring system (101), one or more learning models (109) based on the received one or more sensor data (213) and the determined type of the machine (109); processing, by non-invasive health monitoring system (101), the received one or more sensor data (213) using the one or more trained learning models (109); determining, by non-invasive health monitoring system (101), one or more Key Performance Indicators (KPI’s) of the machine (103) based on the processed one or more sensor data (215); determining, by non-invasive health monitoring system (101), a health condition and performance level of the machine (103) based on the determined one or more KPI’s, using the one or more trained learning models (103); creating, by non-invasive health monitoring system (101), a visual representation data (217) of the one or more processed sensor data (215) based on the determined health condition and the performance level of the machine (103), wherein the visual representation data (217) comprises a status and the performance level indication of the machine (103); simulating, by non-invasive health monitoring system (101), the one or more processed sensor data (215) in a virtual environment based on the created visual representation data (215), comprising the status and performance level indication of the machine; determining, by non-invasive health monitoring system (101), a deviation level in the one or more processed sensor data (215) based on the simulated one or more processed data; determining, by non-invasive health monitoring system (101), one or more malfunctions of the machine (103) based on the determined deviation level; recommending, by non-invasive health monitoring system (101), one or more actions to rectify the determined one or more malfunctions using the one or more trained learning models (109); and outputting, by non-invasive health monitoring system (101), the visual representation data (217) and the recommended one or more actions, to one or more users (117) through a user interface (119), based on a user profile.

2. The method as claimed in claim 1, wherein the one or more non-invasive sensors (115) comprises vibration sensors, weight sensors, Revolution Per Minute (RPM sensors), temperature sensors, energy sensors, and proximity sensors.

3. The method as claimed in claim 1, wherein the one or more KPI’s comprises at least one of a vibration value, a proximity value, a Revolutions Per Minute (RPM) value, a weight value, an energy value, a power value, a power factor value, a voltage value, a current value, a frequency value, a safety value, and a runtime value associated with the machine (103).

4. The method as claimed in claim 1, wherein the visual representation data (217) comprises real-time operational data of the one or more non-invasive sensors (115), historical data of the one or more non-invasive sensors (115), profile data of the one or more users (117), and attendance data of the one or more users (117).

5. The method as claimed in claim 1, wherein outputting the visual representation data (217) of the one or more processed sensor data (215), comprises: identifying, by the non-invasive health monitoring system (101), the one or more non-invasive sensor values to be in an abnormal level based on the one or more processed sensor data (215); prioritizing, by the non-invasive health monitoring system (101), the one or more processed sensor data (215) based on the identified one or more non-invasive sensor values in the abnormal level; creating, by the non-invasive health monitoring system (101), the visual representation data (217) of the one or more processed sensor data (215) based on the prioritization; and outputting, by the non-invasive health monitoring system (101), the visual representation (217) data of the one or more processed sensor data (215) in the hierarchical manner to the one or more users (117) through the user interface (119).

6. The method as claimed in claim 1, wherein outputting the visual representation data (217) and the recommended one or more actions, to one or more users (117) through the user interface (119), based on the user profile, further comprises: determining, by the non-invasive health monitoring system (101), unique barcode (505) present on the machine (103), scanned by the one or more users (117), wherein the one or more users (117) scan the unique barcode (505) present on the machine (103) using a scanning system associated with the one or more users (117); determining, by the non-invasive health monitoring system (101), one or more logged data inputted by the one or more users (117) through the user interface (119), based on the determined unique barcode (505), wherein the one or more logged data comprises log-in time and log-out time of the one or more users (117); determining, by the non-invasive health monitoring system (101), user profile of the one or more users (117) based on the one or more logged data; and outputting, by the non-invasive health monitoring system (101), the visual representation data (217) of the processed one or more sensor data (215) and the recommended one or more actions, to one or more users (117) through the user interface (119), based on the determined user profile and the determined unique barcode (505).

7. The method as claimed in claim 1, wherein processing the received one or more sensor data (213) using the one or more trained learning models (109) comprises: analyzing, by the non-invasive health monitoring system (101), the one or more received sensor data (213) using one or more trained learning models (109); identifying, by the non-invasive health monitoring system (101), trends and patterns of the different operating conditions of the machine (103) by simulating the analyzed one or more sensor data (213), using the one or more trained learning models (109), wherein the one or more learning models (109) are trained to continuously learn and adapt the different operating conditions of the machine (103); and determining, by the non-invasive health monitoring system (101), one or more suggestions for adjusting settings of the machine (103) based on the identified trends and patterns.

8. The method as claimed in claim 1, wherein recommending the one or more actions, to one or more users (117) through the user interface (119), based on the user profile comprises: receiving, by the non-invasive health monitoring system (101), one or more real-time user feedback data from the one or more users (117) through the user interface (119), using the one or more trained learning models (109), wherein the one or more trained learning models (109) comprises at least one or more Natural Language Processing (NLP) models for automatically receiving voice commands and natural language queries in real-time, from the one or more users (117); determining, by the non-invasive health monitoring system (101), behavior data of the one or more users (117) by analyzing the received one or more real-time user feedback data, wherein the behavior data of the one or more users (117) corresponds to interaction behavior of the one or more users with the machine (103); performing, by the non-invasive health monitoring system (101), a personalization of the user interface (119) based on the determined behavior data of the one or more users (117), wherein the personalization of the user interface (119) corresponds to generating suggestions to the one or more users (117) related to the operation of the machine (103); creating, by the non-invasive health monitoring system (101), a personalized data of the one or more users (117) based on the performed personalization; and outputting, by the non-invasive health monitoring system (101), the personalized data to the one or more users (117) in real-time through the user interface (119).

9. The method as claimed in claim 1, wherein the non-invasive health monitoring system (101) generates one or more alerts to the one or more users (117) through multimedia, based on the determined one or more malfunctions of the machine (103).

10. A non-invasive health monitoring system (101) for monitoring and operating a machine (103) in a computing environment (100), the non-invasive health monitoring system (101) comprises: a processor (105); and a memory (107) coupled with the processor (105), wherein the processor (105) is configured to: receive one or more sensor data (213) from a machine (103), wherein the one or more sensor data (213) comprises one or more external sensor data and one or more internal sensor data, wherein the one or more external sensor data corresponds to one or more non-invasive sensors (115) connected externally to the machine (103) via a communication network (113); determine a type of the machine (103) connected to the one or more non-invasive sensors (115) based on the received one or more sensor data (213); train one or more learning models (109) based on the received one or more sensor data (213) and the determined type of the machine (103); process the received one or more sensor data (213) using the one or more trained learning models (109); determine one or more Key Performance Indicators (KPI’s) of the machine (103) based on the processed one or more sensor data (215); determine a health condition and performance level of the machine (103) based on the determined one or more KPI’s, using the one or more trained learning models (109); create a visual representation data (217) of the one or more processed sensor data (215) based on the determined health condition and the performance level of the machine (103), wherein the visual representation data (217) comprises a status and the performance level indication of the machine (103); simulate the one or more processed sensor data (215) in a virtual environment based on the created visual representation data (217), comprising the status and performance level indication of the machine (103); determine a deviation level in the one or more processed sensor data (215) based on the simulated one or more processed data; determine one or more malfunctions of the machine (103) based on the determined deviation level; recommend one or more actions to rectify the determined one or more malfunctions using the one or more trained learning models (109); and output the visual representation data (217) and the recommended one or more actions, to one or more users (117) through a user interface (119), based on a user profile.

11. The non-invasive health monitoring system (101) as claimed in claim 10, wherein the one or more non-invasive sensors (115) comprises vibration sensors, weight sensors, Revolution Per Minute (RPM sensors), temperature sensors, energy sensors, and proximity sensors.

12. The non-invasive health monitoring system (101) as claimed in claim 10, wherein the one or more KPI’s comprises at least one of a vibration value, a proximity value, a Revolutions Per Minute (RPM) value, a weight value, an energy value, a power value, a power factor value, a voltage value, a current value, a frequency value, a safety value, and a runtime value associated with the machine (103).

13. The non-invasive health monitoring system (101) as claimed in claim 10, wherein the visual representation data (217) comprises real-time operational data of the one or more non-invasive sensors (115), historical data of the one or more non-invasive sensors (115), profile data of the one or more users (117), and attendance data of the one or more users (117).

14. The non-invasive health monitoring system (101) as claimed in claim 10, wherein to output the visual representation data (217) of the one or more processed sensor data (215), the processor (105) is configured to: identify the one or more non-invasive sensor values to be in an abnormal level based on the one or more processed sensor data (215); prioritize the one or more processed sensor data (215) based on the identified one or more non-invasive sensor values in the abnormal level; create the visual representation data (217) of the one or more processed sensor data (215) based on the prioritization; and output the visual representation data (217) of the one or more processed sensor data (215) in the hierarchical manner to the one or more users (117) through the user interface (119).

15. The non-invasive health monitoring system (101) as claimed in claim 10, wherein to output the visual representation data (217) and the recommended one or more actions, to one or more users (117) through the user interface (119), based on the user profile, the processor (105) is configured to: determine unique barcode (505) present on the machine (103), scanned by the one or more users (117), wherein the one or more users (117) scan the unique barcode (505) present on the machine (103) using a scanning system associated with the one or more users (117); determine one or more logged data inputted by the one or more users (117) through the user interface (119), based on the determined unique barcode (505), wherein the one or more logged data comprises log-in time and log-out time of the one or more users (117); determine user profile of the one or more users (117) based on the one or more logged data; and output the visual representation data (217) of the processed one or more sensor data (215) and the recommended one or more actions, to one or more users (117) through the user interface (119), based on the determined user profile and the determined unique barcode (505).

16. The non-invasive health monitoring system (101) as claimed in claim 10, wherein to process the received one or more sensor data (213) using the one or more trained learning models (109), the processor (105) is configured to: analyze the one or more received sensor data (213) using one or more trained learning models (109); identify trends and patterns of the different operating conditions of the machine (103) by simulating the analyzed one or more sensor data, using the one or more trained learning models (109), wherein the one or more learning models (109) are trained to continuously learn and adapt the different operating conditions of the machine (103); and determine one or more suggestions for adjusting settings of the machine (103) based on the identified trends and patterns.

17. The non-invasive health monitoring system (101) as claimed in claim 10, wherein to recommend the one or more actions, to one or more users (117) through the user interface (119), based on the user profile, the processor (105) is configured to: receive one or more real-time user feedback data from the one or more users (117) through the user interface (119), using the one or more trained learning models (109), wherein the one or more trained learning models (109) includes at least one or more Natural Language Processing (NLP) models for automatically receiving voice commands and natural language queries in real-time, from the one or more users (117); determine behavior data of the one or more users (117) by analyzing the received one or more real-time user feedback data, wherein the behavior data of the one or more users (117) corresponds to interaction behavior of the one or more users (117) with the machine (103); perform a personalization of the user interface (119) based on the determined behavior data of the one or more users (117), wherein the personalization of the user interface (119) corresponds to generating suggestions to the one or more users (117) related to the operation of the machine (103); create a personalized data of the one or more users (117) based on the performed personalization; and output the personalized data to the one or more users (117) in real-time through the user interface (119).

18. The non-invasive health monitoring system (101) as claimed in claim 10, wherein the non-invasive health monitoring system (101) generates one or more alerts to the one or more users (117) through multimedia, based on the determined one or more malfunctions of the machine (103).

Description:FORM 2
THE PATENTS ACT 1970
[39 OF 1970]
&
THE PATENTS RULES, 2003

COMPLETE SPECIFICATION
[See section 10; Rule 13]

NON-INVASIVE HEALTH MONITORING SYSTEM FOR MONITORING AND OPERATING MACHINE IN COMPUTING ENVIRONMENT AND METHOD THEREOF

APPLICANT:
a) Name: Indian Institute of Science
b) Nationality: Indian
c) Address: Indian Institute of Science, C.V. Raman
Road, Bangalore - 560012, Karnataka, India

PREAMBLE TO THE DESCRIPTION
The following specification particularly describes the invention and the manner in which it is to be performed. 
TECHNICAL FIELD
[0001] Embodiments of the present disclosure generally relate to monitoring systems. In particular, the present disclosure relates to a method and non-invasive health monitoring system for monitoring and operating a machine in a computing environment.
BACKGROUND
[0002] The advent of Industry 4.0 has revolutionized manufacturing, integrating cyber-physical systems, Internet of Things (IoT), cloud computing, and advanced data analytics to establish smart factories at the forefront of industrial innovation. However, Small and Medium-sized Enterprises (SMEs) confront substantial hurdles in adopting these transformative technologies due to their reliance on legacy machinery. In other words, legacy machines refer to any equipment or software that is of such age or condition that it is no longer warrantied or supported by the manufacturer or developer. These machines often lack the connectivity and monitoring capabilities necessary for leveraging Industry 4.0's potential, particularly in real-time data acquisition and proactive maintenance strategies. Further, the key obstacles of the legacy machines opted by the SME’s include constrained finances, limiting investment in necessary sensor systems and integrations, and a shortage of technical expertise for effective implementation and maintenance.
[0003] Compounding this challenge are traditional upgrade methods that typically involve invasive modifications or costly replacements, causing disruptions to operations and imposing financial strains. However, the existing traditional invasive technologies requires more of mechanical modifications, and proprietary sensor integrations. This provides a drawback of high cost, extensive downtime, requirement for specialized expertise, and potential voiding of existing warranties. In other words, the adoption of advanced monitoring technologies in SMEs is hindered by the necessity for invasive modifications to legacy machinery, which leads to difficulties in accessing and analyzing data for actionable insights, and the absence of scalable solutions for data collection and real-time monitoring. Further, in the existing invasive technologies, inadequate alert systems further exacerbate delays in responding to machine failures and anomalies, thereby impacting overall operational efficiency.
[0004] Further, the existing technologies, rely upon new equipment purchases, which includes state-of-the-art smart machinery with built-in IoT and data analytics capabilities. However, this leads to prohibitive capital investment, long lead times for deployment, and training requirements for operators, which is currently infeasible in the real-world applications.
[0005] To overcome this, non-invasive sensor technologies are employed in existing market, which includes basic sensor add-ons, and standalone monitoring systems. However, the existing non-invasive technologies face some of the limitations such as limited functionality, poor integration with existing Information Technology (IT) infrastructure, lack of comprehensive data management, and insufficient real-time analytics.
[0006] Therefore, a need exists for a novel solution that overcomes the above-said problems. Therefore, there is a need in the art to provide a method and non-invasive health monitoring system for monitoring and operating a machine in a computing environment, to address the aforementioned deficiencies in the art.
SUMMARY
[0007] This summary is provided to introduce a selection of concepts, in a simple manner, which is further described in the detailed description of the disclosure. This summary is neither intended to identify key or essential inventive concepts of the subject matter nor to determine the scope of the disclosure.
[0008] An aspect of the present disclosure provides a method for monitoring and operating a machine using a non-invasive health monitoring system in a computing environment. The method includes receiving, by a system, one or more sensor data from a machine. In an embodiment, the one or more sensor data comprises one or more external sensor data and one or more internal sensor data, in which the one or more external sensor data may correspond to one or more non-invasive sensors connected externally to the machine via a communication network. The method then includes determining, by the system, a type of the machine connected to the one or more non-invasive sensors based on the received one or more sensor data, and training one or more learning models based on the received one or more sensor data and the determined type of the machine. Further, the method includes processing, by the system, the received one or more sensor data using the one or more trained learning models, and determining one or more Key Performance Indicators (KPI’s) of the machine based on the processed one or more sensor data. Furthermore, the method includes determining a health condition and performance level of the machine based on the determined one or more KPI’s, using the one or more trained learning models. Furthermore, the method includes creating, by the system, a visual representation data of the one or more processed sensor data based on the determined health condition and the performance level of the machine. In an embodiment, the visual representation data may comprise a status and the performance level indication of the machine. Furthermore, the method includes simulating, by the system, the one or more processed sensor data in a virtual environment based on the created visual representation data, comprising the status and performance level indication of the machine. Furthermore, the method includes determining, by the system, a deviation level in the one or more processed sensor data based on the simulated one or more processed data, and determining one or more malfunctions of the machine based on the determined deviation level. Subsequently, the method includes recommending, by the system, one or more actions to rectify the determined one or more malfunctions using the one or more trained learning models. Finally, the method includes outputting, by the system, the visual representation data and the recommended one or more actions, to one or more users through a user interface, based on a user profile.
[0009] Another aspect of the present disclosure includes a non-invasive health monitoring system for monitoring and operating a machine in a computing environment. The non-invasive health monitoring system comprises a processor and a memory, coupled with the processor. The processor is configured to receive one or more sensor data from a machine. In an embodiment, the one or more sensor data comprises one or more external sensor data and one or more internal sensor data, in which the one or more external sensor data corresponds to one or more non-invasive sensors connected externally to the machine via a communication network. Further, the processor is configured to determine a type of the machine connected to the one or more non-invasive sensors based on the received one or more sensor data, and train one or more learning models based on the received one or more sensor data and the determined type of the machine. Furthermore, the processor is configured to process the received one or more sensor data using the one or more trained learning models, and determine one or more Key Performance Indicators (KPI’s) of the machine based on the processed one or more sensor data. Furthermore, the processor is configured to determine a health condition and performance level of the machine based on the determined one or more KPI’s, using the one or more trained learning models. Furthermore, the processor is configured to create a visual representation data of the one or more processed sensor data based on the determined health condition and the performance level of the machine. In an embodiment, the visual representation data may comprise a status and the performance level indication of the machine. Furthermore, the processor is configured to simulate the one or more processed sensor data in a virtual environment based on the created visual representation data, comprising the status and performance level indication of the machine. Furthermore, the processor is configured to determine a deviation level in the one or more processed sensor data based on the simulated one or more processed data, and determine one or more malfunctions of the machine based on the determined deviation level. Subsequently, the processor is configured to recommend one or more actions to rectify the determined one or more malfunctions using the one or more trained learning models. Finally, the processor is configured to output the visual representation data and the recommended one or more actions, to one or more users through a user interface, based on a user profile.
[0010] To further clarify the advantages and features of the present disclosure, a more particular description of the disclosure will follow by reference to specific embodiments thereof, which are illustrated in the appended figures. It is to be appreciated that these figures depict only typical embodiments of the disclosure and are therefore not to be considered limiting in scope. The disclosure will be described and explained with additional specificity and detail with the appended figures.
BRIEF DESCRIPTION OF ACCOMPANYING DRAWINGS
[0011] The disclosure will be described and explained with additional specificity and detail with the accompanying figures in which:
[0012] FIG. 1 illustrates an exemplary computing environment for monitoring and operating a machine using a non-invasive health monitoring system, in accordance with an embodiment of the present disclosure;
[0013] FIG. 2 illustrates a detailed internal block diagram of the non-invasive health monitoring system, for monitoring and operating a machine in a computing environment, in accordance with an embodiment of the present disclosure;
[0014] FIG. 3 illustrates an internal hardware architecture of the non-invasive health monitoring system, as shown in FIG. 2, in accordance with an embodiment of the present disclosure;
[0015] FIG. 4 illustrates an exemplary illustration of safety operation performed by the non-invasive health monitoring system, for monitoring and operating a machine in a computing environment, in accordance with an embodiment of the present disclosure;
[0016] FIG. 5 illustrates an exemplary representation of unique barcodes present on the ID of the one or more users, and the machine, in accordance with an embodiment of the present disclosure;
[0017] FIGs. 6A-6E illustrates an exemplary representation of visualization section of an operator dashboard, in accordance with an embodiment of the present disclosure;
[0018] FIGs. 7A-7C illustrates an exemplary representation of visualization section of a manager dashboard, in accordance with an embodiment of the present disclosure;
[0019] FIG. 8 illustrates an exemplary representation of sensor failure alert for an energy sensor, in accordance with an embodiment of the present disclosure; and
[0020] FIGs. 9A-9B illustrates a flow chart representation of method for monitoring and operating a machine using a non-invasive health monitoring system in a computing environment, in accordance with an embodiment of the present disclosure.
[0021] Further, those skilled in the art will appreciate that elements in the figures are illustrated for simplicity and may not have necessarily been drawn to scale. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the figures by conventional symbols, and the figures may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the figures with details that will be readily apparent to those skilled in the art having the benefit of the description herein.

DETAILED DESCRIPTION
[0022] For simplicity and illustrative purposes, the present disclosure is described by referring mainly to examples thereof. The examples of the present disclosure described herein may be used together in different combinations. In the following description, details are set forth in order to provide an understanding of the present disclosure. It will be readily apparent, however, that the present disclosure may be practiced without limitation to all these details. Also, throughout the present disclosure, the terms “a” and “an” are intended to denote at least one of a particular element. The terms “a” and “an” may also denote more than one of a particular element. As used herein, the term “includes” means includes but not limited to, the term “including” means including but not limited to. The term “based on” means based at least in part on, the term “based upon” means based at least in part upon, and the term “such as” means such as but not limited to. The term “relevant” means closely connected or appropriate to what is being performed or considered.
[0023] For the purpose of promoting an understanding of the principles of the disclosure, reference will now be made to the embodiment illustrated in the figures and specific language will be used to describe them. It will nevertheless be understood that no limitation of the scope of the disclosure is thereby intended. Such alterations and further modifications in the illustrated system, and such further applications of the principles of the disclosure as would normally occur to those skilled in the art are to be construed as being within the scope of the present disclosure. It will be understood by those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the disclosure and are not intended to be restrictive thereof.
[0024] In the present document, the word “exemplary” is used herein to mean “serving as an example, instance, or illustration”. Any embodiment or implementation of the present subject matter described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments. The terms “comprise”, “comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that one or more devices or sub-systems or elements or structures or components preceded by “comprises… a” does not, without more constraints, preclude the existence of other devices, sub-systems, additional sub-modules. Appearances of the phrase “in an embodiment”, “in another embodiment”, “in an exemplary embodiment” and similar language throughout this specification may, but not necessarily do, all refer to the same embodiment.
[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this disclosure belongs. The system, methods, and examples provided herein are only illustrative and not intended to be limiting. A computer system (standalone, client, or server, or computer-implemented system) configured by an application may constitute a “module” (or “subsystem”) that is configured and operated to perform certain operations. In one embodiment, the “module” or “subsystem” may be implemented mechanically or electronically, so a module includes dedicated circuitry or logic that is permanently configured (within a special-purpose processor) to perform certain operations. In another embodiment, a “module” or a “subsystem” may also comprise programmable logic or circuitry (as encompassed within a general-purpose processor or other programmable processor) that is temporarily configured by software to perform certain operations. Accordingly, the term “module” or “subsystem” should be understood to encompass a tangible entity, be that an entity that is physically constructed permanently configured (hardwired), or temporarily configured (programmed) to operate in a certain manner and/or to perform certain operations described herein.
[0026] Embodiments described herein provide a method and a non-invasive health monitoring system (also hereafter referred to as system) for monitoring and operating a machine in a computing environment. The method includes receiving, by a system, one or more sensor data from a machine. In an embodiment, the one or more sensor data comprises one or more external sensor data and one or more internal sensor data, in which the one or more external sensor data may correspond to one or more non-invasive sensors connected externally to the machine via a communication network. The method then includes determining, by the system, a type of the machine connected to the one or more non-invasive sensors based on the received one or more sensor data, and training one or more learning models based on the received one or more sensor data and the determined type of the machine. Further, the method includes processing, by the system, the received one or more sensor data using the one or more trained learning models, and determining one or more Key Performance Indicators (KPI’s) of the machine based on the processed one or more sensor data. Furthermore, the method includes determining, by the system, a health condition and performance level of the machine based on the determined one or more KPI’s, using the one or more trained learning models. Furthermore, the method includes creating, by the system, a visual representation data of the one or more processed sensor data based on the determined health condition and the performance level of the machine. In an embodiment, the visual representation data may comprise a status and the performance level indication of the machine. Furthermore, the method includes simulating, by the system, the one or more processed sensor data in a virtual environment based on the created visual representation data, comprising the status and performance level indication of the machine. Furthermore, the method includes determining, by the system, a deviation level in the one or more processed sensor data based on the simulated one or more processed data, and determining one or more malfunctions of the machine based on the determined deviation level. Subsequently, the method includes recommending, by the system, one or more actions to rectify the determined one or more malfunctions using the one or more trained learning models. Finally, the method includes outputting, by the system, the visual representation data and the recommended one or more actions, to one or more users through a user interface, based on a user profile.
[0027] Referring now to the drawings, and more particularly to FIG. 1 through FIG. 9, where reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments, and these embodiments are described in the context of the following exemplary system and/or method.
[0028] FIG. 1 illustrates an exemplary computing environment 100 for monitoring and operating a machine 103 using a non-invasive health monitoring system 101, in accordance with an embodiment of the present disclosure. As illustrated in FIG. 1, environment 100 may include a non-invasive health monitoring system 101, which further includes a processor 105, a memory 107, one or more learning models 109, and a database 111. Further, the computing environment 100 includes a machine 103, in which the non-invasive health monitoring system 101 may be connected to the machine 103 through a communication network 113. In an embodiment, the machine 103 may include, for example, but not limited to, a legacy machine.
[0029] The machine 103 comprises one or more non-invasive sensors 115, such as for example 115a, 115b, ……115n. In an embodiment, the one or more non-invasive sensors 115 may be connected externally to the machine 103, through the communication network 113. Furthermore, in an embodiment, the one or more non-invasive sensors 115 may include, for example, but not limited to, vibration sensors, weight sensors, Revolution Per Minute (RPM) sensors, temperature sensors, energy sensors, and proximity sensors.
[0030] In an embodiment, the processor 105 may be configured to receive one or more sensor data from the machine 103, in which the one or more sensor data comprises one or more external sensor data and one or more internal sensor data. Further, in an embodiment, the one or more external sensor data may be collected from the one or more non-invasive sensors 115.
[0031] Further, the processor 105 may be configured to determine a type of the machine 103 connected to the one or more non-invasive sensors 115, based on the received one or more sensor data, and train one or more learning models 109 based on the received one or more sensor data and the determined type of the machine 103. In an embodiment, the one or more learning models may be stored in the memory 107.
[0032] Furthermore, the processor 105 may be configured to process the received one or more sensor data using the one or more trained learning models 109, and determine one or more Key Performance Indicators (KPI’s) of the machine 103 based on the processed one or more sensor data. In an embodiment, the database 111 may be configured to store the processed one or more sensor data. Further, in an embodiment, the one or more KPI’s may include, for example, but not limited to, a vibration value, a proximity value, a Revolutions Per Minute (RPM) value, a weight value, an energy value, a power value, a power factor value, a voltage value, a current value, a frequency value, a safety value, and a runtime value associated with the machine 103.
[0033] Furthermore, the processor 105 may be configured to determine a health condition and performance level of the machine 103 based on the determined one or more KPI’s, using the one or more trained learning models 109.
[0034] Furthermore, the processor 105 may be configured to create a visual representation data of the one or more processed sensor data based on the determined health condition and the performance level of the machine 103. In an embodiment, the visual representation data may comprise a status and the performance level indication of the machine 103.
[0035] Furthermore, the processor 105 may be configured to simulate the one or more processed sensor data in a virtual environment based on the created visual representation data, comprising the status and performance level indication of the machine 103, and determine a deviation level in the one or more processed sensor data based on the simulated one or more processed data.
[0036] Furthermore, the processor 105 may be configured to determine one or more malfunctions of the machine 103 based on the determined deviation level, and recommend one or more actions to rectify the determined one or more malfunctions using the one or more trained learning models 109.
[0037] Subsequently, the processor 105 may be configured to output the visual representation data and the recommended one or more actions, to one or more users 117 through a user interface 119, based on a user profile. In an embodiment, the non-invasive health monitoring system 101 may be connected to the user interface through a network 121 (as shown in FIG. 1).
[0038] FIG. 2 illustrates a detailed internal block diagram of the non-invasive health monitoring system 201, for monitoring and operating a machine 103 in a computing environment 100, in accordance with an embodiment of the present disclosure.
[0039] In an embodiment, the non-invasive health monitoring system 201 is similar to the non-invasive health monitoring system 101 of FIG. 1. The non-invasive health monitoring system 201 may include, without limiting to, a processor 203, an I/O interface 205, and a memory 207 storing instructions, executable by the processor 203, which, on execution, may cause the non-invasive health monitoring system 201 to monitor and operate the machine in computing environment 100. In an embodiment, the memory 207 may include data 209 and one or more modules 211. In an embodiment, each of the one or more modules 211 may be a hardware unit which may be outside the memory 207 and coupled with the non-invasive health monitoring system 201. In an embodiment, the data 209 may include for example, a sensor data 213, a processed sensor data 215, and a visual representation data 217. Further in an embodiment, the one or more modules 211 may include a sensor data receiving module 219, a learning models training module 221, a sensor data processing module 223, a visual representation data creation module 225, a sensor data simulation module 227, a deviation level determining module 229, a malfunction determining module 231, an action recommendation module 233, and an outputting module 235.
[0040] In an embodiment, the sensor data receiving module 219 may be configured to receive one or more sensor data 213 from the machine 103, in which the one or more sensor data 213 may comprise one or more external sensor data and one or more internal sensor data. Further, in an embodiment, the one or more external sensor data may be collected from the one or more non-invasive sensors 115. Further, in an embodiment, the sensor data receiving module 219 may be configured to determine a type of the machine 103 connected to the one or more non-invasive sensors 115, based on the received one or more sensor data 213.
[0041] In an embodiment, the learning models training module 221 may be configured to train one or more learning models 109 based on the received one or more sensor data 213 and the determined type of the machine 103. In an embodiment, the one or more learning models 109 may be stored in the memory 107 (as shown in FIG. 1).
[0042] In an embodiment, the sensor data processing module 223 may be configured to process the received one or more sensor data 213 using the one or more trained learning models 109, and determine one or more Key Performance Indicators (KPI’s) of the machine 103 based on the processed one or more sensor data 215. This may be achieved by analyzing the one or more received sensor data 213 using one or more trained learning models 109, and identifying trends and patterns of the different operating conditions of the machine 103 by simulating the analyzed one or more sensor data 213, using the one or more trained learning models 109, in which the one or more learning models 109 may be trained to continuously learn and adapt the different operating conditions of the machine 103. Further, processing the received one or more sensor data 213 using the one or more trained learning models 109 may be achieved by determining one or more suggestions for adjusting settings of the machine based on the identified trends and patterns. In an embodiment, the one or more KPI’s may include, for example, but not limited to, a vibration value, a proximity value, a Revolutions Per Minute (RPM) value, a weight value, an energy value, a power value, a power factor value, a voltage value, a current value, a frequency value, a safety value, and a runtime value associated with the machine 103.
[0043] Further, in an embodiment, the sensor data processing module 223 may be configured to determine a health condition and performance level of the machine 103 based on the determined one or more KPI’s, using the one or more trained learning models 109.
[0044] In an embodiment, the visual representation data creation module 225 may be configured to create a visual representation data 217 of the one or more processed sensor data 215 based on the determined health condition and the performance level of the machine 103. In an embodiment, the visual representation data 217 may comprise a status and the performance level indication of the machine 103. Further, in an embodiment, visual representation data 217 may include, for example, but not limited to, real-time operational data of the one or more non-invasive sensors 115, historical data of the one or more non-invasive sensors 115, profile data of the one or more users 117, and attendance data of the one or more users 117.
[0045] In an embodiment, the sensor data simulation module 227 may be configured to simulate the one or more processed sensor data 215 in a virtual environment based on the created visual representation data 217, comprising the status and performance level indication of the machine 103.
[0046] In an embodiment, the deviation level determining module 229 may be configured to determine a deviation level in the one or more processed sensor data 215 based on the simulated one or more processed data.
[0047] In an embodiment, the malfunction determining module 231 may be configured to determine one or more malfunctions of the machine 103 based on the determined deviation level.
[0048] In an embodiment, the action recommendation module 233 may be configured to recommend one or more actions to rectify the determined one or more malfunctions using the one or more trained learning models 109. To perform this, the action recommendation module 233 may be configured to receive one or more real-time user feedback data from the one or more users 117 through the user interface 119, using the one or more trained learning models 109. In an embodiment, the one or more trained learning models may include, for example, but not limited to, one or more Natural Language Processing (NLP) models for automatically receiving voice commands and natural language queries in real-time, from the one or more users 117. Further, the action recommendation module 233 may determine behavior data of the one or more users 117 by analyzing the received one or more real-time user feedback data, in which the behavior data of the one or more users 117 may correspond to interaction behavior of the one or more users 117 with the machine 103. Furthermore, action recommendation module 233 may perform a personalization of the user interface 119 based on the determined behavior data of the one or more users 117. In an embodiment, the personalization of the user interface 117 may correspond to generating suggestions to the one or more users 117 related to the operation of the machine 103. Furthermore, the action recommendation module 233 may create a personalized data of the one or more users 117 based on the performed personalization, and may finally output the personalized data to the one or more users 117 in real-time through the user interface 119.
[0049] In an embodiment, the outputting module 235 may be configured to output the visual representation data 217 and the recommended one or more actions, to one or more users 117 through a user interface 119, based on a user profile. In order to achieve this, the outputting module 235 may be configured to identify the one or more non-invasive sensor values to be in an abnormal level based on the one or more processed sensor data 215, and prioritize the one or more processed sensor data 215 based on the identified one or more non-invasive sensor values in the abnormal level. Further, the outputting module 235 may create the visual representation data 217 of the one or more processed sensor data 215 based on the prioritization, and may output the visual representation data 217 of the one or more processed sensor data 215 in the hierarchical manner to the one or more users 117 through the user interface 119.
[0050] In an embodiment, the outputting module 235 may be configured to determine unique barcode present on the machine 103, scanned by the one or more users 117, in which the one or more users 117 may scan the unique barcode present on the machine 103 using a scanning system (not shown in FIG. 2) associated with the one or more users 117. Further, the outputting module 235 may determine one or more logged data inputted by the one or more users 117 through the user interface 119, based on the determined unique barcode. In an embodiment, the one or more logged data may include, without limiting to, log-in time and log-out time of the one or more users 117. Further, the outputting module 235 may determine user profile of the one or more users 117 based on the one or more logged data, and may output the visual representation data 217 of the processed one or more sensor data 215 and the recommended one or more actions, to one or more users 117 through the user interface 119, based on the determined user profile and the determined unique barcode.
[0051] FIG. 3 illustrates an internal hardware architecture of the non-invasive health monitoring system 201, as shown in FIG. 2, in accordance with an embodiment of the present disclosure.
[0052] In an embodiment, as shown in FIG. 3, the architecture 300 comprises one or more sensors 301, in which the one or more sensors 301 may be installed on the machine 103 (as shown in FIG. 1), such as a legacy machine. In an embodiment, the one or more sensors 301 may include, for example, but not limited to, one or more non-invasive sensors 115 (as shown in FIG. 1).
[0053] Further, the architecture 300 comprises an Arduino board 303 such as, for example, but not limited to, Arduino nano ESP32. In an embodiment, the one or more sensors 301 may be connected externally to the machine 103, through the communication network 113 (as shown in FIG. 1). Furthermore, in an embodiment, the one or more sensors 301 may include, for example, but not limited to, vibration sensors, weight sensors, Revolution Per Minute (RPM) sensors, temperature sensors, energy sensors, and proximity sensors.
[0054] Further, the Arduino board 303 may receive one or more sensor data 213 from the machine 103, in which the one or more sensor data 213 may comprise one or more external sensor data and one or more internal sensor data. In an embodiment, the Arduino board 303 may serve as the central processing unit, for collecting data from the one or more sensors 301.
[0055] Furthermore, the Arduino board 303 may process the sensor data 213 and may send one or more Hyper Text Transfer Protocol (HTTP) requests containing the sensor data 213 to a router 305. In an embodiment, the Arduino board 303 may have built-in Wireless-Fidelity (Wi-Fi) capabilities, enabling data transmission to the router 305.
[0056] In an embodiment, the router 305 may receive the one or more HTTP requests from the Arduino board 303 and may route the sensor data 213 to a host server 307. Further, in an embodiment, the router 305 may also facilitate the connection to mobile dashboards 309 associated with the one or more users 117 for providing the sensor data 213 to the one or more users 117.
[0057] In an embodiment, the host server 307 may include a web server 307a, a Hypertext Preprocessor (PHP) script 307b, and a database 307c. The web server 307a may receive the sensor data 213 from the router 305. Further, the PHP script processes the sensor data 213 and stores the processed sensor data 215 in the database 307. In an embodiment, the PHP script 307b may correspond to one or more learning models 109 (as shown in FIG. 1), which may be responsible for processing the received one or more sensor data 213. For example, the one or more learning models may include, for example, but not limited to, Artificial Intelligence (AI) algorithms, and Machine Learning (ML) algorithms.
[0058] In first aspect, the AI and ML algorithms may be configured to perform predictive maintenance by predicting potential failures and maintenance needs based on the data collected from the one or more non-invasive sensors 115. For example, the AI and ML algorithms may perform data collection and preprocessing, in which the one or more non-invasive sensors 115 sensors may continuously collect data on various parameters like temperature, vibration, pressure, and operational efficiency. Further, the sensor data 213 may be pre-processed to remove noise and irrelevant information. In an embodiment, techniques such as normalization, outlier detection, and data augmentation can be used to enhance data quality.
[0059] Further, in an embodiment, the AI and ML algorithms may train one or more learning models 109 using historical data. For example, supervised learning techniques such as regression, decision trees, and neural networks may be employed to understand patterns and predict failures. Further, unsupervised learning methods like clustering and anomaly detection may be used to identify unusual patterns that might indicate potential issues.
[0060] Furthermore, in an embodiment, the AI and ML algorithms may monitor real-time data to predict potential failures before they occur. In an embodiment, alerts and recommendations may be generated for the one or more users 117, allowing them to take preventive actions, thus reducing downtime and maintenance costs.
[0061] In second aspect, the AI and ML algorithms may be configured to detect anomalies in operations of the machine 103, in which the anomalies may indicate malfunctions or inefficiencies. For example, the AI and ML algorithms may identify and extract one or more key features that influence performance of the machine 103. In an embodiment, the one or more key features may include sensor readings, operational cycles, and environmental conditions. Further, the AI and ML algorithms may then identify deviations from the norm, flagging potential issues for further investigation.
[0062] In third aspect, the AI and ML algorithms may optimize operations of the machine 103 to enhance performance and efficiency. For example, the AI and ML algorithms may analyze the sensor data 213 to identify trends and patterns that indicate optimal operating conditions. Further, the AI and ML algorithms may suggest adjustments to settings of the machine 103 to improve performance and efficiency. In an embodiment, reinforcement learning algorithms may be used to continuously learn and adapt operations of the machine 103 for optimal performance. The reinforcement learning algorithms may simulate different scenarios, continuously improving efficiency of the machine 103 and reducing energy consumption.
[0063] In fourth aspect, the AI and ML algorithms may enhance the Human Machine Interface (HMI) by making it more intuitive and responsive to needs of the one or more users 117. For example, Natural Language Processing (NLP) may be used to enable voice commands and natural language queries, making it easier for the one or more users 117 to interact with the non-invasive health monitoring system 101. Further, AI-driven chatbots may provide real-time assistance and troubleshooting support to the one or more users 117. Furthermore, the AI and ML algorithms may analyze interactions of the one or more users 117 with the HMI to understand common behaviors and preferences. In an embodiment, the HMI may be personalized to individual one or more users 117, offering shortcuts and suggestions based on usage patterns of the one or more users 117.
[0064] In fifth aspect, the AI and ML algorithms may streamline data management and provide deeper insights through advanced analytics. For example, the AI and ML algorithms may automate the collection, cleaning, and processing of large volumes of the sensor data 213. Further, the AI and ML algorithms may classify and organize data, making it more accessible and useful for decision-making. Furthermore, the AI and ML algorithms may provide advanced analytics capabilities, such as predictive modeling, trend analysis, and real-time monitoring dashboards to the one or more users 117. Theses analytics tools may help the one or more users 117 to make informed decisions, optimize maintenance schedules, and improve overall operational efficiency.
[0065] In sixth aspect, AI/ML may improve safety of the one or more users 117 by predicting and preventing hazardous conditions. For example, the AI and ML algorithms may analyze the sensor data 213 to detect unsafe operating conditions, such as excessive vibrations or overheating. Further, the AI and ML algorithms may notify the one or more users 117 of potential dangers, allowing the one or more users 117 to take immediate action. Furthermore, the AI and ML algorithms may automatically shut down or adjust operations of the machine 103 in response to detected hazards, reducing the risk of accidents. In an embodiment, predictive models may also be forecasted when maintenance is needed to prevent unsafe conditions from developing.
[0066] In an embodiment, the architecture 300 may comprise a software package such as a Cross-Platform, Apache, MySQL, PHP, and Perl (XAMPP) Control Panel 311, that may provide a local server environment. For example, the XAMPP Control Panel 311 may include the web server 307a such as, for example, but not limited to, Apache, and may also include the database 307c such as for example, but not limited to, MySQL database. Further, in an embodiment, the XAMPP Control Panel 311 may include other tools necessary for running the PHP script 307b and managing the database 307c.
[0067] For example, the MySQL database may serve as the central repository for the storage and management of the sensor data 213. The database schema may be meticulously designed to accommodate the diverse types of the sensor data 213 generated by the retrofitted legacy machines. This may involve creating tables for each sensor type, with appropriate fields to store timestamps, sensor readings, and any relevant metadata. Data types and constraints may be enforced to ensure data integrity and consistency. To safeguard the valuable sensor data, robust data integrity measures may be implemented. Further, input validation may be performed at both the Arduino board 303 level and the web server 307 to prevent erroneous or malicious data from entering the database 307c. Constraints, such as primary keys and foreign keys, may be defined to enforce relationships between tables and maintain referential integrity. Additionally, regular backups of the database may be scheduled to mitigate the risk of data loss due to hardware failures or other unforeseen events. The database 307c may be structured in a manner that facilitates efficient querying and analysis of the sensor data 213. This may involve creating indexes on frequently queried fields, optimizing query performance, and utilizing appropriate data aggregation techniques. The well-organized database 317c may enable the generation of meaningful reports, identification of trends, and extraction of insights that can be leveraged to optimize machine performance, predict maintenance needs, and enhance overall operational efficiency.
[0068] Further, the architecture 300 comprises a Grafana interface 313 for visualization of the processed sensor data 215. In an embodiment, the Grafana interface 313 may include, without limiting to, MySQL data source 315, and a Grafana software 317.
[0069] In an embodiment, the MySQL data source 315 may query the database 317c for processed sensor data 215 stored in the database 307c, and may create one or more dashboards for monitoring the status of the machine 103. In an embodiment, the PHP script 307b may determine one or more Key Performance Indicators (KPI’s) of the machine 103 based on the processed one or more sensor data 215, and may determine a health condition and performance level of the machine 103 based on the determined one or more KPI’s, using the one or more trained learning models 109. Furthermore, in an embodiment, upon receiving the processed sensor data 215 from the database 307c, the Grafana software 317 may create a visual representation data 217 of the one or more processed sensor data 215 based on the determined health condition and the performance level of the machine 103, in which the visual representation data may comprise a status and the performance level indication of the machine 103.
[0070] For example, the processed sensor data 215 stored in the database 307c may be transformed into actionable insights through data visualization using the Grafana software 317. In an embodiment, the Grafana software 317 may be an open-source visualization and analytics platform, which may be chosen for its flexibility, scalability, and extensive customization options. Further, the MySQL data source 315 may be configured within the Grafana software 317 to establish a connection with the database 307c. This connection may enable the Grafana software 317 to query the database 307c in real-time and retrieve the latest sensor data 213. Finally, the Grafana software 317 may present the processed sensor data 215 in a visually appealing and intuitive manner through one or more dashboards.
[0071] In an embodiment, as shown in FIG. 3, the one or more dashboards may include, for example, but not limited to, an operator dashboard 319, and a manager dashboard 321. The operator dashboard 319 may display real-time data and visualizations relevant to operator 319a of the machine 103, in which the real-time data and visualizations may help the operator 319a to monitor the status and performance of the machine 103. Further in an embodiment, the manager dashboard 321 may provide a higher-level overview of machine 103 performance and health, including aggregated, historical data and trends, to a manager 321a associated with the machine 103. Furthermore, the manager dashboard 321 may include alerts for sensor malfunctions and threshold breaches, aiding in health monitoring of the machine 103. In an embodiment, the operator 319a and the manager 321a may access the dashboard on the interfaces of devices such as Personal Computer (PC)/tablet devices, which may allow the operator 319a and the manager 321a to monitor status of the machine 103.
[0072] In an embodiment, the architecture 300 may comprise an alerts manager 323 for managing alerts for sensor failures and threshold breaches. In an embodiment, the alerts manager 323 may be responsible simulating the one or more processed sensor data 215 in a virtual environment based on the created visual representation data 217, and may determine a deviation level in the one or more processed sensor data 215 based on the simulated one or more processed sensor data 215. Further, the alerts manager 323 may determine one or more malfunctions of the machine 103 based on the determined deviation level, and may generate one or more alerts to the one or more users 117 such as the manager 321a (as shown in FIG. 3), through multimedia, based on the determined one or more malfunctions of the machine 103. For example, the alerts manager 323 may send email notifications such as sensor malfunction and threshold breach alerts via mail 325 to the manager 321a, when there is a sensor malfunction or when the processed sensor data 215 exceeds predefined threshold values. This ensures timely awareness and intervention in the non-invasive sensor monitoring system 201.
[0073] FIG. 4 illustrates an exemplary illustration of safety operation performed by the non-invasive health monitoring system 101, for monitoring and operating a machine 103 in a computing environment 100, in accordance with an embodiment of the present disclosure.
[0074] As illustrated in FIG. 4, when the machine 103 operates during safety logic set value to for example, but not limited to, greater than 5 Revolutions Per Minute (RPM), if the hands 401 of the one or more users 117 or any part or workpiece comes within the safe zone, then, one or more proximity sensors 401 send a safety hazard signal which may be then translated into various forms (multimodal), which may include buzzer sounding 403, email alert 405, dashboard visualization 407 for the one or more users 117, to see if there are frequent safety compromises. In an embodiment, the one or more users 117 may include, for example, but not limited to, the operator 319a and the manager 321a (as shown in FIG. 3). This may help to keep the one or more users 117 safe, as well as the machine 103 free of any liabilities.
[0075] FIG. 5A and FIG. 5B illustrates an exemplary representation of unique barcodes 505 present on the ID card 503 of the one or more users 117, and the machine 103, in accordance with an embodiment of the present disclosure.
[0076] As shown in FIG. 5A, the one or more users 117 such as for example, but not limited to a user 501 may be equipped with an ID card 503, mentioned with a name of the user 501 as ABC, ID as 123, and role as for example, but not limited to, operator (as shown in FIG. 5A). In an embodiment, the user 501 may include, for example, but not limited to, the operator 319a.
[0077] Further, as shown in FIG. 5A and FIG. 5B, the machine 103 and the ID card 503 may include unique barcodes 505. In an embodiment, the machine 103 may include, for example, but not limited to, a workpiece 507 (as shown in FIG. 5B). The user 501 may scan their unique barcodes 505 of the ID card 503 to record their attendance and working hours. This data may be used to calculate productivity of the user 501 and may track labor utilization.
[0078] Further, the user 501 may scan the unique barcodes 505 present on the workpiece 507 to input the unique identifier of the workpiece 507. This may trigger the display of relevant product information, including engineering drawings and specifications in a dashboard (not shown in FIG. 5) such as for example, but not limited to, an operator dashboard 319 (as shown in FIG. 3).
[0079] Furthermore, in an embodiment, the dashboard may incorporate a value entering section that may allow the user 501 to input crucial information through scanning of the one or more barcodes 505. For example, the user 501 may manually input the number of workpiece 507 that may be completed during shift of the user 501. This may serve as a benchmark for performance evaluation and production planning. Furthermore, after machining a part, the user 501 may scan the unique barcodes 505 under either “QC Passed” or “QC Failed” to log the quality status. This data may be used to calculate the first pass yield and scrap rate, providing insights into the manufacturing process’s efficiency and effectiveness.
[0080] FIGs. 6A-6E illustrates an exemplary representation of visualization section of an operator dashboard 601, in accordance with an embodiment of the present disclosure. In an embodiment, the operator dashboard 601 is similar to the operator dashboard of 319 of FIG. 3.
[0081] In an embodiment, as shown in FIG. 6A, the operator dashboard 601 may include an installation guide panel which may display video demos created using unity 3D, providing the user 501 with step-by-step instructions on sensor installation and placement for different types of machines. This ensures consistent and accurate data collection. In an embodiment, the user 501 may include, for example, but not limited to, the operator 319a.
[0082] In an embodiment, as shown in FIG. 6B, the operator dashboard 601 further comprises an operator information panel, which may display name, photo, role, employee ID, sign-in time, sign-out time, and shift duration of an operator 603. This information helps track operator performance and attendance. In an embodiment, the operator 603 is similar to the operator 319a of FIG. 3.
[0083] In an embodiment, as shown in FIG. 6C, the operator dashboard 601 may furthermore include a product information panel, which may provide detailed information about the currently processed product, including the engineering drawing, product name, ID, completion status, delay status, QC pass or fail count, initial and final weight, scrap weight, and total scrap for the day. This comprehensive view allows the operator 603 to monitor product quality and identify potential issues.
[0084] In an embodiment, as shown in FIG. 6D, the operator dashboard 601 may furthermore include a machine time updates panel, which may display runtime, setup time, and downtime associated with the machine 103, in a linear bar graph and a pie chart. This visualization may help the operator 603 to track machine 103 utilization and identify potential bottlenecks.
[0085] Furthermore, in an embodiment, as shown in FIG. 6E, the operator dashboard 601 may include a machine parameter panel, which may display various machine parameters in real time, including RPM, current, voltage, frequency, power, power factor, number of near misses, and number of accidents. Additionally, it may display time-series charts for motor vibrations and temperature. This comprehensive view allows the operator 603 to monitor machine 103 health and detect anomalies promptly.
[0086] In an embodiment, the operator dashboard 601, as depicted in FIGs. 6A-6E may tailored for operator 603 of the machine 103. The operator dashboard 601 may display real-time information on critical machine parameters, such as temperature, vibration, and current consumption. Further, the operator dashboard 601 may utilize various visualization elements, such as gauges, line charts, and bar graphs, to present the data clearly and concisely. This may allow the operator 603 to quickly assess the health of the machine 103 and identify any anomalies or potential issues that require immediate attention. Furthermore, the operator dashboard 601 may be optimized for viewing on mobile devices, enabling the operator 603 to monitor the machine 103 remotely and receive timely alerts. In other words, the operator dashboard 601 may be designed to provide real-time data with a refresh rate of 200 milliseconds and guidance to the operator 603 of the machine 103, enhancing situational awareness of the operator 603, and enabling the operator 603 take proactive measures to maintain optimal machine 103 performance and product quality.
[0087] FIGs. 7A illustrates an exemplary representation of visualization section of a manager dashboard 701, in accordance with an embodiment of the present disclosure. In an embodiment, the manager dashboard 701 is similar to the manager dashboard 321 of FIG. 3.
[0088] As shown in FIG. 7A, the manager dashboard 701 may include a machine status section, which may present a time-series chart displaying historical data for current, voltage, power, energy consumption, frequency, power factor, vibration (x, y, z axes), and temperature. The manager such as for example, but not limited to, the manager 321a may filter the data by selecting a specific year, month, and day to analyze trends over time. Additionally, a real-time indicator may display the current status (RUNNING or STOPPED) of the machine 103, offering immediate insight into the operational state of machine 103.
[0089] In an embodiment, as shown in FIG. 7A, the same parameter ‘voltage’ is shown as a live, gauge form for the operator 603 in operator dashboard 601 (as shown in FIG. 6E), but in a line chart (historical data) form for the manager 321a in the manager dashboard 701. This may ensure that all the appropriate hierarchy levels have the data in the desired form shown to the manager 321a. This further may help in data decluttering and thus, minimizing cognitive overload.
[0090] In an embodiment, as shown in FIG. 7B, the manager dashboard 701 may include a machine operator performance section, which may allow the manager 312a to assess individual operator performance such as the operator 601. By selecting an employee ID, the manager 321a may view the employee’s photo, name, and role. A calendar view may display the employee’s presence status (present/absent) and shift hours for each day of a selected month. Further. the manager 321a may also view a summary of the total number of days the employee was present in that month. Furthermore, the machine operator performance section may include records of near misses and accidents logged during the employee’s machine operation, providing insights into safety performance and potential training needs.
[0091] In an embodiment, as shown in FIG. 7C, the manager dashboard 701 may include a KPI’s trend section, which may present the trends of key performance indicators (KPIs) including availability, productivity, quality, and Overall Equipment Effectiveness (OEE), in a horizontal bar graph format. Each KPI may be expressed as a percentage, allowing the manager 312a to quickly assess the performance of the machine 103 relative to established targets. Similar to the machine status section (as shown in FIG. 7A), the manager 321a may filter the KPI data by selecting a specific date range, enabling trend analysis and identification of areas for improvement.
[0092] In an embodiment, the manager dashboard 701 may be designed for managers such as for example, but not limited to, the manager 321a, and supervisors. The manager dashboard 701 may provide a broader perspective on performance of the machine 103, incorporating historical trends, comparative analyses, and key performance indicators (KPIs). Further, the manager dashboard 701 may include visualizations to facilitate in-depth analysis and decision-making. Furthermore, the manager dashboard 701 may enable the manager 321a to identify long-term patterns, assess the overall equipment effectiveness (OEE), and make strategic decisions regarding maintenance, upgrades, or replacements.
[0093] FIG. 8 illustrates an exemplary representation of sensor failure alert for an energy sensor, in accordance with an embodiment of the present disclosure.
[0094] In an embodiment, one or more alerting rules may be defined within Grafana software 317 (as shown in FIG. 3) to specify the conditions that trigger an alert. The one or more alerting rules may be based on specific sensor data metrics and thresholds. For example, an alert may be triggered if the temperature of a critical component exceeds a safe operating limit. Further, the alert may be triggered if the vibration level of the machine 103 exceeds a predefined threshold. Furthermore, the alert may be triggered if the current drawn by the machine 103 deviates significantly from normal operating conditions. Furthermore, the alert may be triggered if the energy meter detects a sudden spike or drop in power consumption. Subsequently, the alert may be triggered if any of the sensor values (Temperature, RPM, Vibration) returns null, indicating a sensor failure. Furthermore, in an embodiment, the one or more alerting rules may be customized to suit the specific requirements of the machine 103 and the desired level of sensitivity.
[0095] In an embodiment, the alerts manager 323 may include one or more features for managing and tracking alerts. This may include acknowledge alerts feature, which may allow the one or more users 117 to confirm that they have seen the alert and are taking appropriate action.
[0096] Further, in an embodiment, the alerts manager 323 may include silence alerts feature, which may temporarily disable specific alerts for a defined period. This may be useful for planned maintenance activities or other situations where temporary deviations from normal operating conditions are expected.
[0097] Furthermore, in an embodiment, the alerts manager 323 may include view alert history feature, which may allow the one or more users 117 to review past alerts and track the performance of the machine 103 over time.
[0098] As shown in FIG. 8, a sample alert rule titled “Sensor failure - Energy” may be configured to trigger when there is an error in the energy sensor data. The Grafana software 317 may be connected to the MySQL data source 315 and may be grouped under “Rule.” The alert may be set to notify through email. In specific instance of FIG. 8, the alert is triggered on June 12, 2024, at 10:23:00. By leveraging Grafana software 317 alerting capabilities, the non-invasive health monitoring system 101 may effectively monitor the health and performance of the machine 103, providing timely notifications to relevant personnel and enabling proactive maintenance and troubleshooting. This may ultimately contribute to the overall reliability and efficiency of the manufacturing process.
[0099] FIGs. 9A-9B illustrates a flow chart representation of a method 900 for monitoring and operating the machine 103 using a non-invasive health monitoring system 101 in a computing environment 100, in accordance with an embodiment of the present disclosure.
[00100] At step 901, the method 900 includes receiving, by the non-invasive health monitoring system 101, the one or more sensor data 213 from the machine 103. In an embodiment, the one or more sensor data may comprise one or more external sensor data and one or more internal sensor data, in which the one or more external sensor data corresponds to one or more non-invasive sensors 115 connected externally to the machine 103 via the communication network 113.
[00101] At step 902, the method 900 includes determining, by the non-invasive health monitoring system 101, a type of the machine 103 connected to the one or more non-invasive sensors 115, based on the received one or more sensor data 213.
[00102] At step 903, the method 900 includes training, by the non-invasive health monitoring system 101, one or more learning models 109 based on the received one or more sensor data 213 and the determined type of the machine 103. In an embodiment, the one or more learning models 109 may be stored in the memory 107 (as shown in FIG. 1).
[00103] At step 904, the method 900 includes processing, by the non-invasive health monitoring system 101, the received one or more sensor data 213 using the one or more trained learning models 109.
[00104] At step 905, the method 900 includes determining, by the non-invasive health monitoring system 101, one or more Key Performance Indicators (KPI’s) of the machine 103 based on the processed one or more sensor data 215. This may be achieved by analyzing the one or more received sensor data 213 using one or more trained learning models 109, and identifying trends and patterns of the different operating conditions of the machine 103 by simulating the analyzed one or more sensor data 213, using the one or more trained learning models 109, in which the one or more learning models 109 may be trained to continuously learn and adapt the different operating conditions of the machine 103. Further, processing the received one or more sensor data 213 using the one or more trained learning models 109 may be achieved by determining one or more suggestions for adjusting settings of the machine based on the identified trends and patterns. In an embodiment, the one or more KPI’s may include, for example, but not limited to, a vibration value, a proximity value, a Revolutions Per Minute (RPM) value, a weight value, an energy value, a power value, a power factor value, a voltage value, a current value, a frequency value, a safety value, and a runtime value associated with the machine 103.
[00105] At step 906, the method 900 includes determining, by the non-invasive health monitoring system 101, a health condition and performance level of the machine 103 based on the determined one or more KPI’s, using the one or more trained learning models 109.
[00106] At step 907, the method 900 includes creating, by the non-invasive health monitoring system 101, a visual representation data 217 of the one or more processed sensor data 215 based on the determined health condition and the performance level of the machine 103. In an embodiment, the visual representation data 217 may comprise a status and the performance level indication of the machine 103. Further, in an embodiment, visual representation data 217 may include, for example, but not limited to, real-time operational data of the one or more non-invasive sensors 115, historical data of the one or more non-invasive sensors 115, profile data of the one or more users 117, and attendance data of the one or more users 117.
[00107] At step 907, the method 900 includes simulating, by the non-invasive health monitoring system 101, the one or more processed sensor data 215 in a virtual environment based on the created visual representation data 217, comprising the status and performance level indication of the machine 103.
[00108] At step 908, the method includes determining, by the non-invasive health monitoring system 101, a deviation level in the one or more processed sensor data 215 based on the simulated one or more processed data.
[00109] At step 909, the method 900 includes determining, by the non-invasive health monitoring system 101, one or more malfunctions of the machine 103 based on the determined deviation level.
[00110] At step 910, the method includes recommending, by the non-invasive health monitoring system 101, one or more actions to rectify the determined one or more malfunctions using the one or more trained learning models 109. To perform this, the action recommendation module 233 may be configured to receive one or more real-time user feedback data from the one or more users 117 through the user interface 119, using the one or more trained learning models 109. In an embodiment, the one or more trained learning models may include, for example, but not limited to, one or more Natural Language Processing (NLP) models for automatically receiving voice commands and natural language queries in real-time, from the one or more users 117. Further, the action recommendation module 233 may determine behavior data of the one or more users 117 by analyzing the received one or more real-time user feedback data, in which the behavior data of the one or more users 117 may correspond to interaction behavior of the one or more users 117 with the machine 103. Furthermore, action recommendation module 233 may perform a personalization of the user interface 119 based on the determined behavior data of the one or more users 117. In an embodiment, the personalization of the user interface 117 may correspond to generating suggestions to the one or more users 117 related to the operation of the machine 103. Furthermore, the action recommendation module 233 may create a personalized data of the one or more users 117 based on the performed personalization, and may finally output the personalized data to the one or more users 117 in real-time through the user interface 119.
[00111] At step 911, the method 900 includes outputting, by the non-invasive health monitoring system 101, the visual representation data 217 and the recommended one or more actions, to one or more users 117 through a user interface 119, based on a user profile. In order to achieve this, the outputting module 235 may be configured to identify the one or more non-invasive sensor values to be in an abnormal level based on the one or more processed sensor data 215, and prioritize the one or more processed sensor data 215 based on the identified one or more non-invasive sensor values in the abnormal level. Further, the outputting module 235 may create the visual representation data 217 of the one or more processed sensor data 215 based on the prioritization, and may output the visual representation data 217 of the one or more processed sensor data 215 in the hierarchical manner to the one or more users 117 through the user interface 119.
[00112] The present disclosure offers a comprehensive, user-friendly, non-invasive solution that is both cost-effective and easy to implement. In other words, the use of non-invasive sensors in the present disclosure allows for easy integration with existing machinery without the need for any mechanical modifications. Further, the solution is portable and can be deployed across any legacy machine employed in tool cutting.
[00113] The Grafana dashboards disclosed in the present disclosure provides user-friendly interfaces for real-time monitoring and analytics, accessible to both operators and managers. Further, present disclosure employs an alerting system which enables proactive maintenance by notifying stakeholders of potential issues like sensor failures and threshold breach before they escalate, reducing downtime and maintenance costs.
[00114] Furthermore, the non-invasive nature of the present disclosure eliminates the need for costly mechanical modifications or new equipment purchases, making it accessible to SMEs with limited budgets. In overall scenario, the non-invasive health monitoring system of the present disclosure aims to provide SMEs with a modular, scalable, and cost-effective solution for monitoring legacy machinery, facilitating informed decision-making and proactive maintenance strategies.
[00115] Subsequently, by integrating AI and ML into the digital transformation of legacy machines for SMEs, the present disclosure significantly enhances machine performance, operator safety, and overall operational efficiency. This approach not only modernizes existing machinery but also provides a scalable, cost-effective solution that addresses the unique challenges faced by SMEs.
[00116] One of the ordinary skills in the art will appreciate that techniques consistent with the present disclosure are applicable in other contexts as well without departing from the scope of the disclosure.
[00117] What has been described and illustrated herein are examples of the present disclosure. The terms, descriptions, and figures used herein are set forth by way of illustration only and are not meant as limitations. Many variations are possible within the spirit and scope of the subject matter, which is intended to be defined by the following claims and their equivalents in which all terms are meant in their broadest reasonable sense unless otherwise indicated.
[00118] The written description describes the subject matter herein to enable any person skilled in the art to make and use the embodiments. The scope of the subject matter embodiments is defined by the claims and may include other modifications that occur to those skilled in the art. Such other modifications are intended to be within the scope of the claims if they have similar elements that do not differ from the literal language of the claims or if they include equivalent elements with insubstantial differences from the literal language of the claims.
[00119] The embodiments herein may comprise hardware and software elements. The embodiments that are implemented in software include but are not limited to, firmware, resident software, microcode, and the like. The functions performed by various modules described herein may be implemented in other modules or combinations of other modules.
[00120] A description of an embodiment with several components in communication with each other does not imply that all such components are required. On the contrary, a variety of optional components are described to illustrate the wide variety of possible embodiments of the invention. When a single device or article is described herein, it will be apparent that more than one device/article (whether or not they cooperate) may be used in place of a single device/article. Similarly, where more than one device or article is described herein (whether or not they cooperate), it will be apparent that a single device/article may be used in place of the more than one device or article, or a different number of devices/articles may be used instead of the shown number of devices or programs. The functionality and/or the features of a device may be alternatively embodied by one or more other devices which are not explicitly described as having such functionality/features. Thus, other embodiments of the invention need not include the device itself.
[00121] The illustrated steps are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries may be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, and the like., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope and spirit of the disclosed embodiments. Also, the words "comprising," "having," "containing," and "including," and other similar forms are intended to be equivalent in meaning and be open-ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items or meant to be limited to only the listed item or items. It must also be noted that as used herein and in the appended claims, the singular forms “a”, “an”, and “the” include plural references unless the context clearly dictates otherwise.
[00122] Finally, the language used in the specification has been principally selected for readability and instructional purposes, and it may not have been selected to delineate or circumscribe the inventive subject matter. It is therefore intended that the scope of the invention be limited not by this detailed description, but rather by any claims that issue on an application based here on. Accordingly, the embodiments of the present invention are intended to be illustrative, but not limited, of the scope of the invention, which is outlined in the following claims.
REFERRAL NUMERALS:
Reference number Description
100 Computing environment
101 Non-invasive health monitoring system
103 Machine
105 Processor
107 Memory
109 Learning models
111 Database
113 Communication network
115 Non-invasive sensors
117 Users
119 User interface
121 Network
203 Processor
205 I/O Interface
207 Memory
209 Data
211 Modules
213 Sensor data
215 Processed sensor data
217 Visual representation data
219 Sensor data receiving module
221 Learning models training module
223 Sensor data processing module
225 Visual representation data creation module
227 Sensor data simulation module
229 Deviation level determining module
231 Malfunction determining module
233 Action recommendation module
235 Outputting module
301 Sensors
303 Arduino board
305 Router
307 Host server
307a Web server
307b PHP script
307c Database
309 Dashboard on mobile
311 XAMPP control panel
313 Grafana interface
315 MySQL data source
317 Grafana software
319 Operator dashboard
319a Operator
321 Manager dashboard
321a Manager
323 Alerts manager
325 sensor malfunction and threshold breach alerts via mail
401 Hands
403 Proximity sensors
405 Buzzer sounding
407 Email alert
409 Dashboard visualization

501 User
503 ID card
505 Unique barcodes
507 Workpiece
601 Operator dashboard
603 Operator
701 Manager dashboard
, C , Claims:We Claim:
1. A method for monitoring and operating a machine (103) using a non-invasive health monitoring system (101) in a computing environment (100), the method comprising:
receiving, by a non-invasive health monitoring system (101), one or more sensor data (213) from a machine (103), wherein the one or more sensor data (213) comprises one or more external sensor data and one or more internal sensor data, wherein the one or more external sensor data corresponds to one or more non-invasive sensors (115) connected externally to the machine (103) via a communication network (113);
determining, by the non-invasive health monitoring system (101), a type of the machine (103) connected to the one or more non-invasive sensors (115) based on the received one or more sensor data (213);
training, by non-invasive health monitoring system (101), one or more learning models (109) based on the received one or more sensor data (213) and the determined type of the machine (109);
processing, by non-invasive health monitoring system (101), the received one or more sensor data (213) using the one or more trained learning models (109);
determining, by non-invasive health monitoring system (101), one or more Key Performance Indicators (KPI’s) of the machine (103) based on the processed one or more sensor data (215);
determining, by non-invasive health monitoring system (101), a health condition and performance level of the machine (103) based on the determined one or more KPI’s, using the one or more trained learning models (103);
creating, by non-invasive health monitoring system (101), a visual representation data (217) of the one or more processed sensor data (215) based on the determined health condition and the performance level of the machine (103), wherein the visual representation data (217) comprises a status and the performance level indication of the machine (103);
simulating, by non-invasive health monitoring system (101), the one or more processed sensor data (215) in a virtual environment based on the created visual representation data (215), comprising the status and performance level indication of the machine;
determining, by non-invasive health monitoring system (101), a deviation level in the one or more processed sensor data (215) based on the simulated one or more processed data;
determining, by non-invasive health monitoring system (101), one or more malfunctions of the machine (103) based on the determined deviation level;
recommending, by non-invasive health monitoring system (101), one or more actions to rectify the determined one or more malfunctions using the one or more trained learning models (109); and
outputting, by non-invasive health monitoring system (101), the visual representation data (217) and the recommended one or more actions, to one or more users (117) through a user interface (119), based on a user profile.
2. The method as claimed in claim 1, wherein the one or more non-invasive sensors (115) comprises vibration sensors, weight sensors, Revolution Per Minute (RPM sensors), temperature sensors, energy sensors, and proximity sensors.
3. The method as claimed in claim 1, wherein the one or more KPI’s comprises at least one of a vibration value, a proximity value, a Revolutions Per Minute (RPM) value, a weight value, an energy value, a power value, a power factor value, a voltage value, a current value, a frequency value, a safety value, and a runtime value associated with the machine (103).
4. The method as claimed in claim 1, wherein the visual representation data (217) comprises real-time operational data of the one or more non-invasive sensors (115), historical data of the one or more non-invasive sensors (115), profile data of the one or more users (117), and attendance data of the one or more users (117).
5. The method as claimed in claim 1, wherein outputting the visual representation data (217) of the one or more processed sensor data (215), comprises:
identifying, by the non-invasive health monitoring system (101), the one or more non-invasive sensor values to be in an abnormal level based on the one or more processed sensor data (215);
prioritizing, by the non-invasive health monitoring system (101), the one or more processed sensor data (215) based on the identified one or more non-invasive sensor values in the abnormal level;
creating, by the non-invasive health monitoring system (101), the visual representation data (217) of the one or more processed sensor data (215) based on the prioritization; and
outputting, by the non-invasive health monitoring system (101), the visual representation (217) data of the one or more processed sensor data (215) in the hierarchical manner to the one or more users (117) through the user interface (119).
6. The method as claimed in claim 1, wherein outputting the visual representation data (217) and the recommended one or more actions, to one or more users (117) through the user interface (119), based on the user profile, further comprises:
determining, by the non-invasive health monitoring system (101), unique barcode (505) present on the machine (103), scanned by the one or more users (117), wherein the one or more users (117) scan the unique barcode (505) present on the machine (103) using a scanning system associated with the one or more users (117);
determining, by the non-invasive health monitoring system (101), one or more logged data inputted by the one or more users (117) through the user interface (119), based on the determined unique barcode (505), wherein the one or more logged data comprises log-in time and log-out time of the one or more users (117);
determining, by the non-invasive health monitoring system (101), user profile of the one or more users (117) based on the one or more logged data; and
outputting, by the non-invasive health monitoring system (101), the visual representation data (217) of the processed one or more sensor data (215) and the recommended one or more actions, to one or more users (117) through the user interface (119), based on the determined user profile and the determined unique barcode (505).
7. The method as claimed in claim 1, wherein processing the received one or more sensor data (213) using the one or more trained learning models (109) comprises:
analyzing, by the non-invasive health monitoring system (101), the one or more received sensor data (213) using one or more trained learning models (109);
identifying, by the non-invasive health monitoring system (101), trends and patterns of the different operating conditions of the machine (103) by simulating the analyzed one or more sensor data (213), using the one or more trained learning models (109), wherein the one or more learning models (109) are trained to continuously learn and adapt the different operating conditions of the machine (103); and
determining, by the non-invasive health monitoring system (101), one or more suggestions for adjusting settings of the machine (103) based on the identified trends and patterns.
8. The method as claimed in claim 1, wherein recommending the one or more actions, to one or more users (117) through the user interface (119), based on the user profile comprises:
receiving, by the non-invasive health monitoring system (101), one or more real-time user feedback data from the one or more users (117) through the user interface (119), using the one or more trained learning models (109), wherein the one or more trained learning models (109) comprises at least one or more Natural Language Processing (NLP) models for automatically receiving voice commands and natural language queries in real-time, from the one or more users (117);
determining, by the non-invasive health monitoring system (101), behavior data of the one or more users (117) by analyzing the received one or more real-time user feedback data, wherein the behavior data of the one or more users (117) corresponds to interaction behavior of the one or more users with the machine (103);
performing, by the non-invasive health monitoring system (101), a personalization of the user interface (119) based on the determined behavior data of the one or more users (117), wherein the personalization of the user interface (119) corresponds to generating suggestions to the one or more users (117) related to the operation of the machine (103);
creating, by the non-invasive health monitoring system (101), a personalized data of the one or more users (117) based on the performed personalization; and
outputting, by the non-invasive health monitoring system (101), the personalized data to the one or more users (117) in real-time through the user interface (119).
9. The method as claimed in claim 1, wherein the non-invasive health monitoring system (101) generates one or more alerts to the one or more users (117) through multimedia, based on the determined one or more malfunctions of the machine (103).
10. A non-invasive health monitoring system (101) for monitoring and operating a machine (103) in a computing environment (100), the non-invasive health monitoring system (101) comprises:
a processor (105); and
a memory (107) coupled with the processor (105), wherein the processor (105) is configured to:
receive one or more sensor data (213) from a machine (103), wherein the one or more sensor data (213) comprises one or more external sensor data and one or more internal sensor data, wherein the one or more external sensor data corresponds to one or more non-invasive sensors (115) connected externally to the machine (103) via a communication network (113);
determine a type of the machine (103) connected to the one or more non-invasive sensors (115) based on the received one or more sensor data (213);
train one or more learning models (109) based on the received one or more sensor data (213) and the determined type of the machine (103);
process the received one or more sensor data (213) using the one or more trained learning models (109);
determine one or more Key Performance Indicators (KPI’s) of the machine (103) based on the processed one or more sensor data (215);
determine a health condition and performance level of the machine (103) based on the determined one or more KPI’s, using the one or more trained learning models (109);
create a visual representation data (217) of the one or more processed sensor data (215) based on the determined health condition and the performance level of the machine (103), wherein the visual representation data (217) comprises a status and the performance level indication of the machine (103);
simulate the one or more processed sensor data (215) in a virtual environment based on the created visual representation data (217), comprising the status and performance level indication of the machine (103);
determine a deviation level in the one or more processed sensor data (215) based on the simulated one or more processed data;
determine one or more malfunctions of the machine (103) based on the determined deviation level;
recommend one or more actions to rectify the determined one or more malfunctions using the one or more trained learning models (109); and
output the visual representation data (217) and the recommended one or more actions, to one or more users (117) through a user interface (119), based on a user profile.

11. The non-invasive health monitoring system (101) as claimed in claim 10, wherein the one or more non-invasive sensors (115) comprises vibration sensors, weight sensors, Revolution Per Minute (RPM sensors), temperature sensors, energy sensors, and proximity sensors.
12. The non-invasive health monitoring system (101) as claimed in claim 10, wherein the one or more KPI’s comprises at least one of a vibration value, a proximity value, a Revolutions Per Minute (RPM) value, a weight value, an energy value, a power value, a power factor value, a voltage value, a current value, a frequency value, a safety value, and a runtime value associated with the machine (103).
13. The non-invasive health monitoring system (101) as claimed in claim 10, wherein the visual representation data (217) comprises real-time operational data of the one or more non-invasive sensors (115), historical data of the one or more non-invasive sensors (115), profile data of the one or more users (117), and attendance data of the one or more users (117).
14. The non-invasive health monitoring system (101) as claimed in claim 10, wherein to output the visual representation data (217) of the one or more processed sensor data (215), the processor (105) is configured to:
identify the one or more non-invasive sensor values to be in an abnormal level based on the one or more processed sensor data (215);
prioritize the one or more processed sensor data (215) based on the identified one or more non-invasive sensor values in the abnormal level;
create the visual representation data (217) of the one or more processed sensor data (215) based on the prioritization; and
output the visual representation data (217) of the one or more processed sensor data (215) in the hierarchical manner to the one or more users (117) through the user interface (119).

15. The non-invasive health monitoring system (101) as claimed in claim 10, wherein to output the visual representation data (217) and the recommended one or more actions, to one or more users (117) through the user interface (119), based on the user profile, the processor (105) is configured to:
determine unique barcode (505) present on the machine (103), scanned by the one or more users (117), wherein the one or more users (117) scan the unique barcode (505) present on the machine (103) using a scanning system associated with the one or more users (117);
determine one or more logged data inputted by the one or more users (117) through the user interface (119), based on the determined unique barcode (505), wherein the one or more logged data comprises log-in time and log-out time of the one or more users (117);
determine user profile of the one or more users (117) based on the one or more logged data; and
output the visual representation data (217) of the processed one or more sensor data (215) and the recommended one or more actions, to one or more users (117) through the user interface (119), based on the determined user profile and the determined unique barcode (505).
16. The non-invasive health monitoring system (101) as claimed in claim 10, wherein to process the received one or more sensor data (213) using the one or more trained learning models (109), the processor (105) is configured to:
analyze the one or more received sensor data (213) using one or more trained learning models (109);
identify trends and patterns of the different operating conditions of the machine (103) by simulating the analyzed one or more sensor data, using the one or more trained learning models (109), wherein the one or more learning models (109) are trained to continuously learn and adapt the different operating conditions of the machine (103); and
determine one or more suggestions for adjusting settings of the machine (103) based on the identified trends and patterns.

17. The non-invasive health monitoring system (101) as claimed in claim 10, wherein to recommend the one or more actions, to one or more users (117) through the user interface (119), based on the user profile, the processor (105) is configured to:
receive one or more real-time user feedback data from the one or more users (117) through the user interface (119), using the one or more trained learning models (109), wherein the one or more trained learning models (109) includes at least one or more Natural Language Processing (NLP) models for automatically receiving voice commands and natural language queries in real-time, from the one or more users (117);
determine behavior data of the one or more users (117) by analyzing the received one or more real-time user feedback data, wherein the behavior data of the one or more users (117) corresponds to interaction behavior of the one or more users (117) with the machine (103);
perform a personalization of the user interface (119) based on the determined behavior data of the one or more users (117), wherein the personalization of the user interface (119) corresponds to generating suggestions to the one or more users (117) related to the operation of the machine (103);
create a personalized data of the one or more users (117) based on the performed personalization; and
output the personalized data to the one or more users (117) in real-time through the user interface (119).
18. The non-invasive health monitoring system (101) as claimed in claim 10, wherein the non-invasive health monitoring system (101) generates one or more alerts to the one or more users (117) through multimedia, based on the determined one or more malfunctions of the machine (103).