DESC:METHOD AND SYSTEM FOR CONTINUOUS REAL-TIME MONITORING OF ASSET HEALTH IN AN INDUSTRIAL ENVIRONMENT

TECHNICAL FIELD
[0001] The present disclosure generally relates to methods and systems for monitoring in industrial environments, and more particularly relates to method and system for continuous real-time monitoring of asset health using integrated camera device.
BACKGROUND
[0002] In heavy industrial environments, encompassing large-scale manufacturing (e.g., aircraft, ships, trucks, automobiles, and industrial machines), energy production (e.g., oil and gas plants, renewable energy facilities), energy extraction (e.g., mining, drilling), construction of large buildings, and others, intricate machinery, devices, and workflows are employed. Operators are tasked with optimizing the design, development, deployment, and operation of various technologies within these environments to enhance overall performance. Traditionally, data collection in such settings has relied on human-operated dedicated data collectors, often storing sensor data in batches on media like tape or hard drives for subsequent analysis. These batches are then typically sent to a central office for processing, including signal processing and analysis, to diagnose issues and propose operational improvements. This process historically occurs over weeks or months and is based on limited datasets.

[0003] The advent of the Internet of Things (IoT) has enabled continuous connectivity among a broader array of devices, primarily in consumer settings like lights and thermostats. However, leveraging IoT in complex industrial environments remains challenging due to limited data availability and the complexity of handling data from multiple sensors, hindering the development of effective "smart" solutions for industry. Consequently, there is a pressing need for enhanced methods and systems for data collection and utilization in heavy industrial environments to enable improved monitoring, control, intelligent problem diagnosis, and operational optimization.

[0004] Industrial systems across various environments face several challenges in utilizing data from numerous sensors. These challenges include fluctuating computing resources and network capabilities due to system upgrades or replacements, mobility of equipment, and the high costs and risks associated with equipment upgrades. Moreover, industrial systems are often situated in harsh environments where network connectivity is inconsistent, and noise sources such as vibration and electromagnetic interference are prevalent. Additionally, certain components of these systems operate under extreme conditions involving high pressure, temperature, and corrosive materials. Industrial processes also exhibit high variability in operating parameters and nonlinear responses to deviations from nominal operations. Consequently, sensing requirements evolve with time, process stages, equipment aging, and operating conditions.

[0005] Existing industrial processes typically employ conservative sensing configurations, detecting numerous parameters that are unnecessary for most operations or accepting risks without detecting occasionally utilized parameters critical for system characterization. Moreover, these systems lack flexibility in rapidly configuring sensed parameters in real-time and managing system variance, such as intermittent network availability. Despite the common use of similar components across industrial systems, such as pumps, mixers, and tanks, current systems lack mechanisms to leverage data from similar components employed in different processes or to integrate data from external systems in real-time sensor planning and execution, often due to competitive concerns.

[0006] There is a growing need for continuous real-time asset health monitoring in heavy industrial environments, where intricate machinery and workflows are employed. Traditional methods of data collection rely on periodic inspections and manual measurements, resulting in delayed diagnostics and improvements based on limited datasets. However, with the advent of the Internet of Things (IoT) and advancements in sensor technology, there is an opportunity to overcome these challenges and develop effective "smart" solutions for industry.

SUMMARY
[0007] The present invention discloses a method and a system for IOT-enabled continuous real-time monitoring of asset health using acoustic and thermal cameras. The system comprises an integrated camera device comprising an acoustic camera and a thermal camera, a laser device for locating an anomaly in an industrial environment, and a plurality of sensors to detect a plurality of characteristics in the industrial environment. The system is configured to locate an area/equipment to be monitored and capture sound waves and visual data of the area using acoustic cameras and temperature changes in the area using thermal cameras. The sound and thermal data are further analysed in real-time using machine learning algorithms to detect an anomaly in the industrial environment. The present solution enables early detection of anomalies, predictive maintenance, remote monitoring, and seamless integration with existing systems, ultimately enhancing operational efficiency, reducing downtime, and optimizing asset performance across various industries.

[0008] In one aspect of the present disclosure, a system for continuous real-time monitoring of asset health in an industrial facility is disclosed. The system comprises at least one IOT device positioned in proximity to at least one equipment of the industrial facility, the IOT device comprises a single board computer comprising at least one processing unit and a memory unit, a user interface unit interfaced with the at least one processing unit, an integrated camera unit interfaced with the at least one processing unit. The integrated camera unit comprises at least one RGB camera, at least one acoustic camera comprising a plurality of array of digital microphones connected with at least one field programmable gate array (FPGA) or system-on-chip (SOC) and at least one thermal camera. The visual data, sound data and thermal data of the at least one area or equipment in industrial facility to be monitored are captured by the integrated camera unit, processed to generate fused data and analysed to detect at least one deviation or change by the at least one processing unit thereto identify or predict at least one anomaly associated in the area or equipment in the industrial facility.

[0009] In another aspect of the present disclosure, a method for continuous real-time monitoring of asset health in an industrial facility is disclosed. The method comprises the steps of: simultaneously and continuously monitoring visual data, sound data and thermal data of the at least one area or equipment in industrial facility to be monitored by an integrated camera unit comprising at least one RGB camera, at least one acoustic camera and at least one thermal camera, receiving the visual data, sound data and thermal data and generating a fused data of the at least one area or equipment in industrial facility by applying a fusion process by at least one processing unit, analysing the fused data of the at least one area or equipment in industrial facility by applying an artificial intelligence and a machine learning process by at least one processing unit, and detecting at least one deviation or change in the fused data from the analysis of the fused data for identifying or predicting at least one anomaly associated in the area or equipment in the industrial facility by at least one processing unit.

BRIEF DESCRIPTION OF THE DRAWINGS
[0010] Figure 1 illustrates a system (1000) for continuous real-time monitoring of asset health in an industrial facility in accordance with an exemplary embodiment of the present disclosure.
[0011] Figure 2 illustrates a schematic of the IOT device in accordance with the present disclosure.
[0012] Figure 3 illustrates a schematic of the system and processes with list of anomalies detected using the integrated AI based camera unit.

DETAILED DESCRIPTION
[0013] The present invention discloses a method and a system for IOT-enabled continuous real-time monitoring of asset health using acoustic and thermal cameras. The system integrates acoustic cameras and thermal cameras with real-time thermal mapping for continuous asset health monitoring, and fire detection. The system ensures safety through early hazard detection and provides real-time thermal insights for efficient operations. The system involves with IOT enabled automated controls and remote monitoring of asset health using an integrated setup.

[0014] In an embodiment of the present invention, a system for continuous real-time monitoring of asset health in an industrial facility is disclosed. The system comprises at least one IOT device positioned in proximity to at least one equipment of the industrial facility, the IOT device comprises a single board computer comprising at least one processing unit and a memory unit, a user interface unit interfaced with the at least one processing unit, an integrated camera unit interfaced with the at least one processing unit. The integrated camera unit comprises at least one RGB camera, at least one acoustic camera comprising a plurality of array of digital microphones connected with at least one field programmable gate array (FPGA) or system-on-chip (SOC) and at least one thermal camera. The visual data, sound data and thermal data of the at least one area or equipment in industrial facility to be monitored are captured by the integrated camera unit, processed to generate fused data and analysed to detect at least one deviation or change by the at least one processing unit thereto identify or predict at least one anomaly associated in the area or equipment in the industrial facility.

[0015] In an embodiment of the present invention, the system further comprises a laser device for locating at least one area or equipment in industrial facility to be monitored.

[0016] In an embodiment of the present invention, the system further comprises a plurality of sensors positioned directly on or in proximity to, at least one equipment of the industrial facility to detect a plurality of characteristics of at least one equipment and the industrial facility.

[0017] In an embodiment of the present invention, the plurality of sensors comprises: a gas sensor for monitoring a leakage of gas, a pressure sensor for monitoring pressure, a level sensor for monitoring levels, a flow sensor for monitoring a flow of fluid, in at least one equipment of the industrial facility.

[0018] In an embodiment of the present invention, the IOT device further comprises a wireless communication module communicably connected to at least one server via internet.

[0019] In an embodiment of the present invention, The system as claimed in claim 1, wherein the user interface unit comprises a touch screen display unit.

[0020] In an embodiment of the present invention, the field programmable gate array (FPGA) is interfaced with the plurality of array of digital microphones for collecting digital output from each of microphones on the array and filtering the output to generate sound data.

[0021] In another embodiment of the present disclosure, a method for continuous real-time monitoring of asset health in an industrial facility is disclosed. The method comprises the steps of: simultaneously and continuously monitoring visual data, sound data and thermal data of the at least one area or equipment in industrial facility to be monitored by an integrated camera unit comprising at least one RGB camera, at least one acoustic camera and at least one thermal camera, receiving the visual data, sound data and thermal data and generating a fused data of the at least one area or equipment in industrial facility by applying a fusion process by at least one processing unit, analysing the fused data of the at least one area or equipment in industrial facility by applying an artificial intelligence and a machine learning process by at least one processing unit, and detecting at least one deviation or change in the fused data from the analysis of the fused data for identifying or predicting at least one anomaly associated in the area or equipment in the industrial facility by at least one processing unit.

[0022] In another embodiment of the present disclosure, the method further comprises predicting by at least one processing unit, a malfunction of the equipment in the industrial facility or an action to correct the at least one anomaly associated in the area or equipment in the industrial facility .

[0023] In another embodiment of the present disclosure, the method further comprises notifying by at least one processing unit, a user about the at least one of: the anomaly identified, the malfunction predicted and an action to correct the at least one anomaly associated in the area or an equipment in the industrial facility.

[0024] In another embodiment of the present disclosure, at least one anomaly associated in the area or equipment in the industrial facility comprises missing of at least one personal protective equipment comprising helmet, vest, gloves, mask, abnormal human temperature, smoke or Fire, overheating, sudden temperature spikes of assets, Irregular heat patterns, Abnormal mechanical noise and Leak of fluids.

[0025] In another embodiment of the present disclosure, the action to correct the at least one anomaly associated in the area or equipment comprises predictive maintenance based on noise patterns.

[0026] In another embodiment of the present disclosure, the method further comprises automatically locating at least one area or equipment in industrial facility to be to be monitored by at least one laser device based on the at least one deviation or change in the fused data detected.

[0027] In another embodiment of the present disclosure, analysing the fused data of the at least one area or equipment in industrial facility by applying an artificial intelligence and a machine learning process comprises learning or training through a history data comprising the visual data, sound data and thermal data data, fused data and list of deviations, anomalies associated with the fused data received from a database of the serve and comparing fused data of the at least one area or equipment with the history data.

[0028] In another embodiment of the present disclosure, the predicted malfunction comprises failure of the equipment /machinery.

[0029] In another embodiment of the present disclosure, the visual data comprises color images of the at least one area or equipment in the industrial facility monitored by the at least one RGB camera, the sound data comprises representation of real-time position of the sound source and the intensity of the sound generated from the at least one area or equipment in the industrial facility monitored by the at least one acoustic camera, the thermal data comprises thermal images of the at least one area or equipment in industrial facility monitored by the at least one thermal camera.

[0030] Figure 1 illustrates a system (1000) for continuous real-time monitoring of asset health in an industrial facility in accordance with an exemplary embodiment of the present disclosure. The system comprises an Internet of Things (IOT) device (100) positioned in proximity to an equipment of the industrial facility. The IOT device (100) comprises a single board computer (110) comprising a processing unit (1110) and a memory unit (1120), a user interface unit (120) interfaced with the processing unit (1110), an integrated camera unit (130) interfaced the processing unit (1110). The integrated camera unit (130) comprises an RGB camera (1310), an acoustic camera (1320) comprising a plurality of array of digital microphones connected with a field programmable gate array (FPGA) (1325) or system-on-chip (SOC) and a thermal camera (1330).

[0031] The system further comprises a laser device (200) for locating an anomaly in an industrial environment, and a plurality of sensors (300) positioned directly on or in proximity to the equipment pf the industrial facility to detect a plurality of characteristics in the industrial environment. In an embodiment of the present disclosure, the plurality of sensors (300) comprises a gas sensor, a pressure sensor, a level sensor, and a flow sensor.

[0032] In an embodiment, the system may be located in an industrial environment and may comprise a plurality of IOT devices, and each IOT device comprises an integrated camera unit comprising an acoustic camera and a thermal camera, a laser device for locating the anomaly in the industrial environment. The acoustic cameras visualize sound sources in a specific area of the industrial environment. These cameras use an array of microphones to detect sound waves and then generate visual representations of the sound sources. Figure 2 illustrates a schematic of the IOT device in accordance with the present disclosure.

[0033] The plurality of IOT devices are strategically positioned in the industrial environment for monitoring the acoustic signatures of various equipment and processes. In an example of the present disclosure, the plurality of IOT devices are positioned at a plurality of locations/areas of an oil processing facility and a gas processing facility. In another example of the present disclosure, the plurality of IOT devices are positioned on a plurality of equipment of the oil processing facility and the gas processing facility. The acoustic cameras are used to collect a background noise in industrial environments. The background noise often contains a valuable information about the health and performance of equipment. By analysing changes in background noise patterns, anomalies associated with equipment malfunction, degradation, or abnormal temperature rises can be detected.

[0034] The IOT device integrates acoustic cameras, and thermal cameras, and RGB cameras into the monitoring system. The IOT devices may be placed directly on equipment or in proximity to critical components to measure temperature changes accurately. The IOT device is an AI based integrated camera device capable of collecting data in real-time using advanced machine learning algorithms and artificial intelligence. The AI based integrated camera can detect anomalies in sound patterns, identify potential equipment malfunctions, and correlate temperature changes with potential issues.

[0035] In another embodiment of the present disclosure, the integrated camera unit (130) comprises one or more RGB cameras (1310), one or more acoustic cameras (1320), and one or more thermal cameras (1330).

[0036] In an embodiment, the system (1000) comprises components to analyze the data from the AI based integrated camera, such components comprise a single board computer (110) (e.g., embedded computing board, portable artificial intelligence (AI) computer, NVIDIA® Jetson Nano™). In at least one embodiment, the single-board computer (110) comprises one or more machine learning models such as deep learning models (e.g., neural networks (NNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs)). In at least one embodiment, single-board computer (110) runs multiple machine learning models in parallel. In at least one embodiment, single-board computer (110) comprises a graphics processing unit (GPU), a central processing unit (CPU), a hardware AI (e.g., deep learning) accelerator, and memory (e.g., random access memory (RAM), read-only memory (ROM), embedded multimedia card (eMMC), low-power double data rate (LPDDR)).

[0037] In at least one embodiment, one or more machine learning models learns or gets trained through a history data comprising the visual data, sound data and thermal data data, fused data and list of deviations, anomalies associated with the fused data received from a database of the server, and compare fused data of the at least one area or equipment with the history data and detecting at least one deviation or change in the fused data from the analysis of the fused data. Further, the models predict an anomaly associated in the area or equipment in the industrial facility by at least one processing unit (1110). Further, models predict a malfunction of the equipment in the industrial facility or an action to correct the anomaly associated in the area or equipment in the industrial facility.

[0038] The laser device of the system is typically used for locating a specific instrument or area to be monitored in the environment. In an embodiment, a user may manually locate the area to be monitored using the laser device. The laser device emits light and focuses to the specific area to be monitored.

[0039] In another embodiment, the laser device automatically selects the area or the instrument to be monitored based on monitoring of multiple properties associated with the area and instrument. In the embodiment, the plurality of sensors may be located directly on equipment or in proximity to critical components of the instrument monitoring of multiple properties.

[0040] In an exemplary embodiment, a gas sensor monitors a leakage of gas from an instrument in the gas processing facility and the laser device automatically selects the particular instrument to be monitored using the integrated acoustic and thermal cameras.

[0041] In an exemplary embodiment, the user interface unit (120) comprise a touch screen display unit for delivering real-time data, alerts and notifications to the user. In the IOT device (100) The field programmable gate array (FPGA) unit (1325) is interfaced with the plurality of array of digital microphones for collecting digital output from each of microphones on the array and filtering the output to generate sound data. The FPGA collects digital output from each of the microphones on the array, and applies a filter to denoise the output and extracts key features from the output. The position of the sound source and their intensity is determined from the resultant filtered values.

[0042] The IOT device (100) further comprises a wireless communication module (140) communicably connected to one or more external servers (400) via the internet. The external server (400) may comprise a database storing present and history data comprising the visual data, sound data and thermal data data, fused data and list of deviations and list of anomalies associated with various equipment and the industrial facilities.

[0043] By continuous monitoring color, sound and temperature in the industrial environment, a large volume of data comprising visual data, sound data and thermal data of the area or equipment in industrial facility to be monitored are generated from RGB cameras (1310), acoustic cameras (1320), and thermal cameras (1330). The visual data comprises color images of the area or equipment in the industrial facility monitored by the RGB camera. The sound data comprises representation of real-time position of the sound source and the intensity of the sound generated from the area or equipment in the industrial facility monitored by the acoustic camera. The thermal data comprises thermal images of the area or equipment in the industrial facility being monitored by thermal camera.

[0044] In an embodiment, the present invention involves fusion processes to produce fused data from all the color, sound and thermal data in the industrial environment. The collected data from the RGB cameras, the acoustic cameras and temperature sensors are processed in real-time to generate the fused data by applying multi modal analysis of fusion process. Further, machine learning and artificial intelligence processes can be employed to analyze patterns, detect anomalies, and predict potential failures.

[0045] In another embodiment of the present disclosure, a method for continuous real-time monitoring of asset health in an industrial facility is disclosed. The method comprises the steps of: simultaneously and continuously monitoring visual data, sound data and thermal data of an area or equipment in industrial facility to be monitored by an integrated camera unit (130) comprising a RGB camera (1310), an acoustic camera (1320) and a thermal camera (1330), receiving the visual data, sound data and thermal data and generating a fused data of the area or equipment in industrial facility by applying a fusion process by a processing unit (1110), analysing the fused data of the area or equipment in industrial facility by applying an artificial intelligence and a machine learning process by the processing unit (1110), and detecting a deviation or a change in the fused data from the analysis of the fused data for identifying or predicting an anomaly associated in the area or equipment in the industrial facility by the processing unit (1110). The fused data of the area or equipment in industrial facility is analysed by applying an artificial intelligence and a machine learning process. The artificial intelligence and a machine learning process comprises learning or training through a history data comprising the visual data, sound data and thermal data, fused data and list of deviations, anomalies associated with the fused data received from a database of the server; and comparing fused data of the area or equipment with the history data for detecting a deviation or a change in the fused data from the analysis of the fused data.

[0046] The method further comprises predicting, by the processing unit (1110) a malfunction of the equipment in the industrial facility or an action to correct the anomaly associated in the area or equipment in the industrial facility.

[0047] The method further comprises notifying, by the processing unit (1110) a user about the at least one of: the anomaly identified, the malfunction predicted and an action to correct the anomaly associated in the area or an equipment in the industrial facility. The anomaly associated in the area or equipment in the industrial facility may comprise one of the following: missing of personal protective equipment comprising helmet, vest, gloves, mask, abnormal human temperature, smoke or fire, overheating, sudden temperature spikes of assets, irregular heat patterns, abnormal mechanical noise and leak of fluids. The action to correct the anomalies associated in the area or equipment may comprise predictive maintenance based on noise patterns. The predicted malfunction may comprise a failure of the equipment /machinery. Figure 3 illustrates a schematic of the system and processes with list of anomalies detected using the integrated AI based camera unit.

[0048] In another embodiment of the present disclosure, the method further comprises automatically locating the area or equipment in industrial facility to be monitored by the laser device (200) based on the deviation or change in the fused data detected.

[0049] By continuously monitoring the ambient sound and temperature levels when the assets are in optimal condition, the system can detect deviations from a baseline of normal operating conditions, indicating potential issues or abnormalities. Any deviations from the established baseline are flagged as anomalies. These anomalies could indicate various issues such as overheating, equipment malfunctions, leaks, or other potential hazards. The system can prioritize these anomalies based on their severity and likelihood of causing disruptions. When anomalies are detected, the system generates alerts and notifications in real-time. These alerts can be sent using the wireless module to designated personnel via email, SMS, or integrated into a centralized monitoring dashboard for immediate action.

[0050] By continuously monitoring temperature and sound, along with employing predictive analytics, the system can forecast potential equipment failures before they occur. This enables proactive maintenance, reducing downtime and minimizing costly repairs. The monitoring system can be integrated with existing maintenance management systems to streamline workflows. Work orders can be automatically generated based on the identified issues, and maintenance schedules can be optimized to address critical issues promptly. The system can be accessed remotely, allowing personnel to monitor asset health and temperature conditions from anywhere with an internet connection. This capability is especially valuable for overseeing assets spread across multiple locations or in remote areas.

[0051] Over time, the system can learn from historical data and improve its accuracy in detecting anomalies and predicting failures. Regular feedback loops and updates to the algorithms ensure that the system remains effective in safeguarding assets and optimizing operations.

[0052] Continuous real-time temperature and asset health monitoring using acoustic cameras leveraging background noise is an innovative approach with several potential applications, particularly in industrial settings where equipment reliability and performance are critical.

[0053] With the continuous real-time monitoring, advanced signal processing techniques and integrating data from acoustic and thermal cameras, the present invention enables proactive detection of anomalies in asset behaviour in industries, facilitating immediate intervention and maintenance to minimize costly downtime and enhance overall asset reliability.
,CLAIMS:We Claim:

1. A system (1000) for continuous real-time monitoring of asset health in an industrial facility, the system comprising:
at least one IOT device (100) positioned in proximity to at least one equipment of the industrial facility, the IOT device comprises:
a single board computer (110) comprising at least one processing unit (1110) and a memory unit (1120);
a user interface unit (120) interfaced with the at least one processing unit (1110);
an integrated camera unit (130) interfaced with the at least one processing unit (1110), wherein the integrated camera unit (130) comprises:
at least one RGB camera (1310),
at least one acoustic camera (1320) comprising a plurality of array of digital microphones with at least one field programmable gate array (FPGA) (1325) or system-on-chip (SOC) and
at least one thermal camera (1330);
wherein visual data, sound data and thermal data of the at least one area or equipment in industrial facility to be monitored are captured by the integrated camera unit (130), processed to generate fused data and analysed to detect at least one deviation or change by the at least one processing unit thereto identify or predict at least one anomaly associated in the area or equipment in the industrial facility.

2. The system as claimed in claim 1, wherein the system (1000) further comprises a laser device (200) for locating at least one area or equipment in industrial facility to be monitored.

3. The system as claimed in claim 1, wherein the system further comprises a plurality of sensors (300) positioned directly on or in proximity to, at least one equipment of the industrial facility to detect a plurality of characteristics of at least one equipment and the industrial facility.

4. The system as claimed in claim 1, wherein the plurality of sensors (300) comprises:
a gas sensor for monitoring a leakage of gas, a pressure sensor for monitoring pressure, a level sensor for monitoring levels, a flow sensor for monitoring a flow of fluid, in at least one equipment of the industrial facility.

5. The system as claimed in claim 1, wherein the IOT device (100) further comprises a wireless communication module (140) communicably connected to at least one server (400) via internet.

6. The system as claimed in claim 1, wherein the user interface unit (120) comprises a touch screen display unit.

7. The system as claimed in claim 1, wherein the field programmable gate array (FPGA) (1325) is interfaced with the plurality of array of digital microphones for collecting digital output from each of microphones on the array and filtering the output to generate sound data.

8. A method for continuous real-time monitoring of asset health in an industrial facility, the method comprises the steps of:
simultaneously and continuously monitoring visual data, sound data and thermal data of the at least one area or equipment in industrial facility to be monitored by an integrated camera unit (130) comprising at least one RGB camera (1310), at least one acoustic camera (1320) and at least one thermal camera (1330);
receiving the visual data, sound data and thermal data and generating a fused data of the at least one area or equipment in industrial facility by applying a fusion process by at least one processing unit (1110);
analysing the fused data of the at least one area or equipment in industrial facility by applying an artificial intelligence and a machine learning process by at least one processing unit (1110); and
detecting at least one deviation or change in the fused data from the analysis of the fused data for identifying or predicting at least one anomaly associated in the area or equipment in the industrial facility by at least one processing unit (1110).

9. The method as claimed in claim 8, wherein the method further comprises predicting, by at least one processing unit (1110) a malfunction of the equipment in the industrial facility or an action to correct the at least one anomaly associated in the area or equipment in the industrial facility .

10. The method as claimed in claim 9, wherein the method further comprises notifying, by at least one processing unit (1110) a user about the at least one of: the anomaly identified, the malfunction predicted and an action to correct the at least one anomaly associated in the area or an equipment in the industrial facility.

11. The method as claimed in claim 10, wherein at least one anomaly associated in the area or equipment in the industrial facility comprises:
a) missing of at least one personal protective equipment comprising helmet, vest, gloves, mask;
b) abnormal human temperature
c) smoke or Fire
d) overheating
e) sudden temperature spikes of assets
f) Irregular heat patterns
g) Abnormal mechanical noise and
h) Leak of fluids

12. The method as claimed in claim 10, wherein the action to correct the at least one anomaly associated in the area or equipment comprises predictive maintenance based on noise patterns.

13. The method as claimed in claim 8, wherein the method further comprises automatically locating at least one area or equipment in industrial facility to be monitored by at least one laser device (200) based on the at least one deviation or change in the fused data detected.

14. The method as claimed in claim 8, wherein analysing the fused data of the at least one area or equipment in industrial facility by applying an artificial intelligence and a machine learning process comprises:
learning or training through a history data comprising the visual data, sound data and thermal data data, fused data and list of deviations, anomalies associated with the fused data received from a database of the server (400); and
comparing fused data of the at least one area or equipment with the history data.

15. The method as claimed in claim 8, wherein the predicted malfunction comprises failure of the equipment /machinery.

16. The method as claimed in claim 8, wherein visual data comprises color images of the at least one area or equipment in the industrial facility monitored by the at least one RGB camera (1310).

17. The method as claimed in claim 8, wherein sound data comprises representation of real-time position of the sound source and the intensity of the sound generated from the at least one area or equipment in the industrial facility monitored by the at least one acoustic camera (1320).

18. The method as claimed in claim 8, wherein thermal data comprises thermal images of the at least one area or equipment in industrial facility monitored by the at least one thermal camera (1330).