Claims:

1. A processor-implemented method (300) for usage monitoring of equipment using a set of sensors comprising:
receiving a plurality of input data from a plurality of equipment, via one or more hardware processors using a set of sensors, wherein the plurality of input data comprises of an accelerometer (accData) data, a magnetometer (magData) data, and a sound level sensor (sndData) data (302);
pre-processing the plurality of input data to obtain a set of pre-processed data, via the one or more hardware processors, using a plurality of processing techniques, wherein the set of pre-processed data comprises a normalized accelerometer (normalized acc data), a normalized magnetometer (normalized mag data), a normalized sound level sensor (a normalized snd data) (304);
extracting a set of relevant features from the set of pre-processed data, via the one or more hardware processors, using a plurality of feature techniques, wherein the set of relevant features comprises an accelerometer data feature (acc data feature), a magnetometer data feature (mag data feature), and a sound level sensor data feature (snd data feature) (306);
generating a usage monitoring model based on the set of relevant features, via the one or more hardware processors, using a model generation technique (308);
receiving a plurality of real time input data from the plurality of equipment, via the one or more hardware processors, using the set of sensors (310);
pre-processing and extracting a set of real time relevant features from the plurality of real time input data, via the one or more hardware processors, using the plurality of processing techniques and the plurality of feature techniques (312); and
monitoring a usage of the plurality of equipment based on the set of real time relevant features via the one or more hardware processors, using the usage monitoring model (314).

2. The method of claim 1, wherein the plurality of equipment comprises of several equipment in a shared laboratory facility, wherein the plurality of equipment has different objectives and different underlying processes.

3. The method of claim 1, wherein monitoring a usage of the plurality of equipment comprises a contact sensing-based monitoring of the usage of the plurality of equipment based on vibration, magnetic field variability and intensity of sound levels of usage of the plurality of equipment using the set of sensors.

4. The method of claim 1, wherein the set of sensors comprises of an accelerometer, a magnetometer, and a sound level sensor.

5. The method of claim 1, wherein the pre-processing the plurality of input data using the plurality of processing techniques comprises performing one or more of computation, interpolation and normalization of resultant vectors.

6. The method of claim 1, wherein the extraction of the set of relevant features using the plurality of feature techniques (400) comprises:
extracting the acc data feature based on the plurality feature techniques comprising a windowing technique and a feature extraction technique, wherein the feature extraction technique includes a power spectral density technique (402);
extracting the mag data feature based on the plurality feature techniques comprising the windowing technique and the feature extraction technique, wherein the feature extraction technique includes a standard deviation technique (404); and
extracting the snd data feature based on the plurality feature techniques comprising the windowing technique and the feature extraction technique, wherein the feature extraction technique includes a mean computation technique (406).

7. The method of claim 1, wherein the usage monitoring model is a tree bagger model generated using the model generation technique, wherein using the model generation technique comprises generating a feature vector using the set of relevant features and generating the usage monitoring model using the feature vector based on a random forest classification technique.

8. The method of claim 1, wherein the monitoring is performed based on a transition state of the plurality of real time input data using the usage monitoring model.

9. A system (100), comprising:
a memory (102) storing instructions;
one or more communication interfaces (106); and
one or more hardware processors (104) coupled to the memory (102) via the one or more communication interfaces (106), wherein the one or more hardware processors (104) are configured by the instructions to:
receive a plurality of input data from a plurality of equipment, via one or more hardware processors using a set of sensors, wherein the plurality of input data comprises of an accelerometer (accData) data, a magnetometer (magData) data, and a sound level sensor (sndData) data;
pre-process the plurality of input data to obtain a set of pre-processed data, via the one or more hardware processors, using a plurality of processing techniques, wherein the set of pre-processed data comprises a normalized accelerometer (normalized acc data), a normalized magnetometer (normalized mag data), a normalized sound level sensor (a normalized snd data);
extract a set of relevant features from the set of pre-processed data, via the one or more hardware processors, using a plurality of feature techniques, wherein the set of relevant features comprises an accelerometer data feature (acc data feature), a magnetometer data feature (mag data feature), and a sound level sensor data feature (snd data feature);
generate a usage monitoring model based on the set of relevant features, via the one or more hardware processors, using a model generation technique;
receive a plurality of real time input data from the plurality of equipment, via the one or more hardware processors, using the set of sensors;
pre-processing and extracting a set of real time relevant features from the plurality of real time input data, via the one or more hardware processors, using the plurality of processing techniques and the plurality of feature techniques; and
monitoring a usage of the plurality of equipment based on the set of real time relevant features via the one or more hardware processors, using the usage monitoring model.

10. The system of claim 9, wherein the one or more hardware processors are configured by the instructions to perform the pre-processing the plurality of input data using the plurality of processing techniques comprises performing one or more of computation, interpolation and normalization of resultant vectors.

11. The system of claim 9, wherein the one or more hardware processors are configured by the instructions to perform the extraction of the set of relevant features using the plurality of feature techniques comprises:
extracting the acc data feature based on the plurality feature techniques comprising a windowing technique and a feature extraction technique, wherein the feature extraction technique includes a power spectral density technique;
extracting the mag data feature based on the plurality feature techniques comprising the windowing technique and the feature extraction technique, wherein the feature extraction technique includes a standard deviation technique; and
extracting the snd data feature based on the plurality feature techniques comprising the windowing technique and the feature extraction technique, wherein the feature extraction technique includes a mean computation technique.

12. The system of claim 9, wherein the one or more hardware processors are configured by the instructions to generate the usage monitoring model, wherein the usage generation model is a tree bagger model generated using the model generation technique, where using the model generation technique comprises generating a feature vector using the set of relevant features and generating the usage monitoring model using the feature vector based on a random forest classification technique.

13. The system of claim 9, wherein the one or more hardware processors are configured by the instructions to perform the monitoring based on a transition state of the plurality of real time input data using the usage monitoring model.
, Description:FORM 2

THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003

COMPLETE SPECIFICATION
(See Section 10 and Rule 13)

Title of invention:
METHOD AND A SYSTEM FOR USAGE MONITORING OF EQUIPMENT USING A SET OF SENSORS

Applicant:
Tata Consultancy Services Limited
A company Incorporated in India under the Companies Act, 1956
Having address:
Nirmal Building, 9th Floor,
Nariman Point, Mumbai 400021,
Maharashtra, India

The following specification particularly describes the invention and the manner in which it is to be performed.
TECHNICAL FIELD

The disclosure herein generally relates to usage monitoring of equipment, and, more particularly, to a method and a system for usage monitoring of equipment using a set of sensors, wherein the set of sensors comprises of an accelerometer, a magnetometer, and a sound level sensor.

BACKGROUND

Monitoring of a usage state of a device or an equipment is one of the important scenarios in IoT (Internet of Things). The monitoring of the usage status of equipment is highly useful in IoT for resource optimization, billing, and monitoring purposes. Shared laboratory facility is an example scenario for monitoring equipment usage status, as sharing equipment are a major accelerator for innovations.
However, monitoring equipment usage in a shared laboratory facility is challenging as equipment are generally shared across various entities and the multiple equipment’s that are shared also have different underlying physical processes. Further, the shared equipment can be monitored for usage based on accessing lab record and control systems, however this technique can determine who was using an equipment, but to estimate how long the equipment was in running state, remains a challenge to be solved.
The state of art techniques for monitoring of equipment usage in a shared laboratory facility includes power-line monitoring. However, one of the major challenges of power-line monitoring includes deployment issues, including common power lines, concealed, highly insulated and inaccessible power line. Further few other existing techniques utilize specialized usages monitoring systems, wherein custom solutions are built specifically for each type of equipment, however building specific usage monitoring systems is time consuming and costly. Hence there is a need for economic, less complicated and a generic method and system for monitoring equipment usage in a shared laboratory facility.

SUMMARY

Embodiments of the present disclosure present technological improvements as solutions to one or more of the above-mentioned technical problems recognized by the inventors in conventional systems. For example, in one embodiment, a method for usage monitoring of equipment using a set of sensors is provided. The system includes a memory storing instructions, one or more communication interfaces, and one or more hardware processors coupled to the memory via the one or more communication interfaces, wherein the one or more hardware processors are configured by the instructions to receive a plurality of input data from a plurality of equipment using a set of sensors, wherein the plurality of input data comprises of an accelerometer (accData) data, a magnetometer (magData) data, and a sound level sensor (sndData) data. The system is further configured to pre-process the plurality of input data to obtain a set of pre-processed data using a plurality of processing techniques, wherein the set of pre-processed data comprises a normalized acc data, a normalized mag data, a normalized snd data. The system is further configured to extract a set of relevant features from the set of pre-processed data using a plurality of feature techniques, wherein the set of relevant features comprises an acc data feature, a mag data feature, and a snd data feature. The system is further configured to generate a usage monitoring model based on the set of relevant features using a model generation technique. The system is further configured to receive a plurality of real time input data from the plurality of equipment, via the one or more hardware processors, using the set of sensors. The system is further configured to pre-process and extract a set of real time relevant features from the plurality of real time input data, using the plurality of processing techniques and the plurality of feature techniques. The system is further configured to monitor a usage of the plurality of equipment based on the set of real time relevant features using the usage monitoring model.
In another aspect, a method for usage monitoring of equipment using a set of sensors is provided. The method includes receiving a plurality of input data from a plurality of equipment using a set of sensors, wherein the plurality of input data comprises of an accelerometer (accData) data, a magnetometer (magData) data, and a sound level sensor (sndData) data. The method further includes pre-processing the plurality of input data to obtain a set of pre-processed data using a plurality of processing techniques, wherein the set of pre-processed data comprises a normalized acc data, a normalized mag data, a normalized snd data. The method further includes extracting a set of relevant features from the set of pre-processed data using a plurality of feature techniques, wherein the set of relevant features comprises an acc data feature, a mag data feature, and a snd data feature. The method further includes generating a usage monitoring model based on the set of relevant features using a model generation technique. The method further includes receiving a plurality of real time input data from the plurality of equipment, via the one or more hardware processors, using the set of sensors. The method further includes pre-processing and extracting a set of real time relevant features from the plurality of real time input data, using the plurality of processing techniques and the plurality of feature techniques. The method further includes monitoring a usage of the plurality of equipment based on the set of real time relevant features using the usage monitoring model.
In yet another aspect, a non-transitory computer readable medium for usage monitoring of equipment using a set of sensors is provided. The program includes receiving a plurality of input data from a plurality of equipment using a set of sensors, wherein the plurality of input data comprises of an accelerometer (accData) data, a magnetometer (magData) data, and a sound level sensor (sndData) data. The program further includes pre-processing the plurality of input data to obtain a set of pre-processed data using a plurality of processing techniques, wherein the set of pre-processed data comprises a normalized acc data, a normalized mag data, a normalized snd data. The program further includes extracting a set of relevant features from the set of pre-processed data using a plurality of feature techniques, wherein the set of relevant features comprises an acc data feature, a mag data feature, and a snd data feature. The program further includes generating a usage monitoring model based on the set of relevant features using a model generation technique. The program further includes receiving a plurality of real time input data from the plurality of equipment, via the one or more hardware processors, using the set of sensors. The program further includes pre-processing and extracting a set of real time relevant features from the plurality of real time input data, using the plurality of processing techniques and the plurality of feature techniques. The program further includes monitoring a usage of the plurality of equipment based on the set of real time relevant features using the usage monitoring model.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles:
FIG.1 illustrates an exemplary system for usage monitoring of equipment using a set of sensors according to some embodiments of the present disclosure.
FIG.2 is a functional block diagram of the system of FIG. 1, according to some embodiments of the present disclosure.
FIG.3A and FIG.3B is a flow diagram illustrating a method (300) for usage monitoring of equipment using a set of sensors in accordance with some embodiments of the present disclosure.
FIG.4 is a flow diagram illustrating a method (400) for extraction of the set of relevant features using the plurality of feature techniques during usage monitoring of equipment using a set of sensors in accordance with some embodiments of the present disclosure.
FIG.5 is a graph illustrating a robust transition report (feature extraction) for an accelerometer (accData) data during usage monitoring of equipment using a set of sensors in accordance with some embodiments of the present disclosure.
FIG.6 is a graph illustrating a robust transition report (feature extraction) for a magnetometer (magData) data during usage monitoring of equipment using a set of sensors in accordance with some embodiments of the present disclosure.
FIG.7 is a graph illustrating a robust transition report (feature extraction) for a sound level sensor (sndData) data during usage monitoring of equipment using a set of sensors in accordance with some embodiments of the present disclosure.
FIG.8 is a graph illustrating a separation across the three feature dimensions during usage monitoring of equipment using a set of sensors in accordance with some embodiments of the present disclosure.

DETAILED DESCRIPTION OF EMBODIMENTS

Exemplary embodiments are described with reference to the accompanying drawings. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the scope of the disclosed embodiments.
Referring now to the drawings, and more particularly to FIG. 1 through FIG.8, where similar 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.
FIG.1 is a functional block diagram of a system 100 for usage monitoring of equipment using a set of sensors in accordance with some embodiments of the present disclosure.
In an embodiment, the system 100 includes a processor(s) 104, communication interface device(s), alternatively referred as input/output (I/O) interface(s) 106, and one or more data storage devices or a memory 102 operatively coupled to the processor(s) 104. The system 100 with one or more hardware processors is configured to execute functions of one or more functional blocks of the system 100.
Referring to the components of the system 100, in an embodiment, the processor(s) 104, can be one or more hardware processors 104. In an embodiment, the one or more hardware processors 104 can be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the one or more hardware processors 104 is configured to fetch and execute computer-readable instructions stored in the memory 102. In an embodiment, the system 100 can be implemented in a variety of computing systems including laptop computers, notebooks, hand-held devices such as mobile phones, workstations, mainframe computers, servers, a network cloud and the like.
The I/O interface(s) 106 can include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, a touch user interface (TUI) and the like and can facilitate multiple communications within a wide variety of networks N/W and protocol types, including wired networks, for example, LAN, cable, etc., and wireless networks, such as WLAN, cellular, or satellite. In an embodiment, the I/O interface (s) 106 can include one or more ports for connecting a number of devices (nodes) of the system 100 to one another or to another server.
The memory 102 may include any computer-readable medium known in the art including, for example, volatile memory, such as static random-access memory (SRAM) and dynamic random-access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes.
Further, the memory 102 may include a database 108 configured to include information regarding historic data associated with the set of sensors. The memory 102 may comprise information pertaining to input(s)/output(s) of each step performed by the processor(s) 104 of the system 100 and methods of the present disclosure. In an embodiment, the database 108 may be external (not shown) to the system 100 and coupled to the system via the I/O interface 106.
Functions of the components of the system 100 are explained in conjunction with functional overview of the system 100 as given in FIG.2 and flow diagram of FIGS.3A and 3B for usage monitoring of equipment using a set of sensors.
The system 100 supports various connectivity options such as BLUETOOTH®, USB, ZigBee and other cellular services. The network environment enables connection of various components of the system 100 using any communication link including Internet, WAN, MAN, and so on. In an exemplary embodiment, the system 100 is implemented to operate as a stand-alone device. In another embodiment, the system 100 may be implemented to work as a loosely coupled device to a smart computing environment. The components and functionalities of the system 100 are described further in detail.
FIG.2 is an example functional block diagram of the various modules of the system of FIG.1, in accordance with some embodiments of the present disclosure. As depicted in the architecture, the FIG.2 illustrates the functions of the modules of the system 100 that includes usage monitoring of equipment using a set of sensors.
The system 200 for usage monitoring of equipment using a set of sensors is configured to receive a plurality of input data from a plurality of equipment using a set of sensors, at an input data module 202. The input data module 202 is also configured to receive a plurality of real time input data from the plurality of equipment using the set of sensors.
The system 200 further comprises a pre-processor 204 configured for pre-processing the plurality of input data and the real time input data using the plurality of processing techniques. The plurality of input data is pre-processed to obtain a set of pre-processed data. The real time input data is pre-processing to obtain a set of real time pre-processed data.
The system 200 further comprises a relevant feature extractor 206 configured for extracting a set of relevant features and a set of real time relevant features using a plurality of feature techniques. The set of relevant features are extracted from the set of pre-processed data and the set of real time relevant features are extracted from the set of real time pre-processed data.
The system 200 further comprises a usage monitoring model 208. The usage monitoring model 208 is generated using the set of relevant features based a model generation technique. The system 200 further comprises a usage monitoring module 210 configured for monitoring a usage of the plurality of equipment based on the set of real time relevant features using the usage monitoring model.
The system 200 is configured for monitoring a usage of the plurality of equipment comprises a contact sensing-based monitoring of the usage of the plurality of equipment based on vibration, magnetic field variability and intensity of sound levels of usage of the plurality of equipment using the set of sensors. The system works in two modes – a training mode and a testing mode based on a user requirement. The training mode comprises of training the usage monitoring model with information regarding the usage of the plurality of equipment. The testing mode comprises of using the trained usage monitoring model to monitor the plurality of equipment.
The various modules of the system 100 and the functional blocks in FIG.2 are configured for usage monitoring of equipment using a set of sensors are implemented as at least one of a logically self-contained part of a software program, a self-contained hardware component, and/or, a self-contained hardware component with a logically self-contained part of a software program embedded into each of the hardware component that when executed perform the above method described herein.
Functions of the components of the system 200 are explained in conjunction with functional modules of the system 100 stored in the memory 102 and further explained in conjunction with flow diagram of FIGS.3A and FIG.3B. The FIG.3A and FIG.3B with reference to FIG.1, is an exemplary flow diagram illustrating a method 300 for usage monitoring of equipment using a set of sensors using the system 100 of FIG.1 according to an embodiment of the present disclosure.
The steps of the method of the present disclosure will now be explained with reference to the components of the system 100 for usage monitoring of equipment using a set of sensors and the modules (202-210) as depicted in FIG.2 and the flow diagrams as depicted in FIG.3A and FIG.3B. Although process steps, method steps, techniques or the like may be described in a sequential order, such processes, methods and techniques may be configured to work in alternate orders. In other words, any sequence or order of steps that may be described does not necessarily indicate a requirement that the steps to be performed in that order. The steps of processes described herein may be performed in any order practical. Further, some steps may be performed simultaneously.
At step 302 of the method (300), a plurality of input data is received from a plurality of equipment using the set of sensors in the input data module 202. The plurality of input data comprises of an accelerometer (accData) data, a magnetometer (magData) data, and a sound level sensor (sndData) data.
In an embodiment, the set of sensors comprises of an accelerometer, a magnetometer, and a sound level sensor. In an example scenario, the set of sensors comprises an embedded computing device having Inter-Integrated Circuit (I^2 C) interface for integrating the following sensors – (a) a triaxial accelerometer, (b) a triaxial magnetometer and (c) a contact microphone.
In an embodiment, the plurality of equipment comprises of several equipment in a shared laboratory facility, wherein the plurality of equipment has different objectives and different underlying processes. The shared laboratory facilities are a major accelerator for innovations in various research & development organizations, among students etc., In an example scenario the plurality of equipment include laboratory equipment’s such as centrifuges, motors, mechanical shakers, convection heaters and coolers. The laboratory equipment’s shared in the example scenario have different objectives and different underlying processes, wherein the objective of centrifuges is to separate various components of a fluid, while the cooler is a device that cools air, and the underlying process of the centrifuges is to use centrifugal force to separate various components of a fluid while the underlying process of the cooler is cooling through evaporation of water.
At step 304 of the method 300, the plurality of input data is pre-processed to obtain a set of pre-processed data in the pre-processor 204. The plurality of input data is pre-processed using a plurality of processing techniques. The set of pre-processed data comprises a normalized accelerometer meter data (normalized acc data), a normalized magnetometer data (normalized mag data), a normalized sound level sensor (normalized snd data).
In an embodiment, the pre-processing the plurality of input data using the plurality of processing techniques comprises performing one or more of computation, interpolation and normalization of a resultant vectors.
The accelerometer (accData) data is preprocessed to obtain the normalized acc data based on a plurality of processing techniques. The plurality of processing techniques comprises computation of a resultant vectors, interpolation and normalization. The accData is first pre-processed to compute resultant vectors (resultantAccData) based on techniques that include a L2Norm technique. Further the resultantAccData is interpolated based on techniques that include a Spline technique to obtain a interpolated data (interpolatedAccData), wherein the Spline technique minimizes overall surface curvature, resulting in a smooth surface that passes exactly through the input points and comprises computation of a spline curve and differentiation process. Finally, the interpolatedAccData is normalized based on techniques that include a minmax normalization technique to obtain the normalized acc data (normalizedAccData), wherein the minmax normalization technique comprises of fetching a minimum and maximum value from the interpolated data and replacing each value.
The magnetometer (magData) data is preprocessed to obtain the normalized mag data based on plurality of processing techniques. The plurality of processing techniques comprises computation of resultant vectors, interpolation and normalization. The magData is first pre-processed to compute resultant vectors (resultantMagData) based on techniques that include a L2Norm. Further the resultantMagData is interpolated based on techniques that include a Spline technique to obtain an interpolated data (interpolatedMagData), wherein the Spline technique minimizes overall surface curvature, resulting in a smooth surface that passes exactly through the input points and comprises computation of a spline curve and differentiation process. Finally, the interpolatedMagData is normalized based on techniques that include minmax normalization technique to obtain the normalized Mag data (normalizedMagData), wherein the minmax normalization technique comprises of fetching a minimum and maximum value from the interpolated data and replacing each value.
The sound level sensor (sndData) data is preprocessed to obtain the normalized snd data based on plurality of processing techniques. The plurality of processing techniques comprises computation of resultant vectors and interpolation. The sndData is first pre-processed to compute resultant vectors (resultantSndData) based on techniques that include L2Norm. Further the resultantSndData is interpolated based on techniques that include a Spline technique to obtain an interpolated data (interpolatedSndData), wherein the Spline technique minimizes overall surface curvature, resulting in a smooth surface that passes exactly through the input points and comprises computation of a spline curve and differentiation process.
At step 306 of the method 300, a set of relevant features is extracted from the set of pre-processed data by? the relevant feature extractor 206. The set of relevant features is extracted using a plurality of feature techniques. The set of relevant features comprises an acc data feature, a mag data feature, and a snd data feature.
In an embodiment, the extraction of the set of relevant features using the plurality of feature techniques. The plurality of feature techniques is extracted from the set of relevant features is explained with flow chart (400) as illustrated in FIG.4 comprises:
At step 402 of the method (400), the acc data feature is extracted from the normalizedAccData based on the plurality feature techniques. The plurality feature techniques comprise a windowing technique and a feature extraction technique. The feature extraction technique includes a power spectral density (PSD) technique.
In an embodiment, considering an example scenario, during the windowing technique a windowing formula is defined based on a window duration and a pre-defined sampling rate as defined by a user requirement. The PSD is the Fourier transform of an autocorrelation function, which provides the transformation from the time-domain to the frequency-domain.
At step 404 of the method (400), the mag data feature is extracted from the normalizedMagData based on the plurality feature techniques. The plurality feature techniques comprise the windowing technique and the feature extraction technique. The feature extraction technique includes a standard deviation (SD) technique.
In an embodiment, considering an example scenario, the windowing formula would be defined based on a window duration and a pre-defined sampling rate as defined by a user requirement. The SD is defined as a measure of dispersion of a set of data from its mean and includes a mean computation technique.
At step 406 of the method (400), the snd data feature is extracted from the normalizedSndData based on the plurality feature techniques. The plurality feature techniques comprise the windowing technique and the feature extraction technique. The feature extraction technique includes a standard deviation (SD) technique.
In an embodiment, considering an example scenario, the windowing formula would be defined based on a window duration and a pre-defined sampling rate as defined by a user requirement. The SD is defined as a measure of dispersion of a set of data from its mean and includes a mean computation technique.
Referring to FIG.3B, at step 308 of the method (300), a usage monitoring model is generated using the set of relevant features in the usage monitoring model 208. The usage monitoring model is generated using a model generation technique.
In an embodiment, the usage monitoring model is a tree bagger model generated using the model generation technique. The model generation technique comprises: (a) generating a feature vector using the set of relevant features and (b) generating the usage monitoring model using the feature vector based on a random forest classification technique. In an example scenario, the random forest classification technique is also referred to as a tree bagger model, is defined as TreeBagger (number_of_trees = 100, maximumDepth = 10, seed = random).
At step 310 of the method (300), a plurality of real time input data is received from the plurality of equipment in the input data module 202. The plurality of real time input data is received using the set of sensors.
In an embodiment, the set of sensors comprises of an accelerometer, a magnetometer, and a sound level sensor. In an example scenario, the set of sensors comprises a simple embedded computing device having Inter-Integrated Circuit (I^2 C) interface for integrating the following sensors – (a) a triaxial accelerometer, (b) a triaxial magnetometer and (c) a contact microphone.
In an embodiment, the plurality of equipment comprises of several equipment in a shared laboratory facility, wherein the plurality of equipment has different objectives and different underlying processes. The shared laboratory facilities are a major accelerator for innovations in various research & development organizations, among students etc., In an example scenario the plurality of equipment include mechanical shakers, centrifuges, convection heaters and coolers, compressors, refrigeration units etc.
At step 312 of the method (300), the plurality of real time input data is pre-processed, and a set of real time relevant features is extracted by the pre-processor 204 and the relevant feature extractor 206. The real time input data is pre-processed, and the set of real time relevant features is extracted using the plurality of processing techniques and the plurality of feature techniques.
In an embodiment, the pre-processing of the plurality of input data using the plurality of processing techniques comprises performing one or more of computation, interpolation and normalization of resultant vectors. Further the plurality feature techniques comprise a windowing technique and a feature extraction technique.
The real time accelerometer (RaccData) data is preprocessed to obtain the real time normalized acc data based on plurality of processing techniques. The plurality of processing techniques comprises computation of resultant vectors, interpolation and normalization.
The real time magnetometer (RmagData) data is preprocessed to obtain the real time normalized mag data based on plurality of processing techniques. The plurality of processing techniques comprises computation of resultant vectors, interpolation and normalization.
The real time sound level sensor (RsndData) data is preprocessed to obtain the real time normalized snd data based on plurality of processing techniques. The plurality of processing techniques comprises computation of resultant vectors and interpolation.
The real time acc data feature is extracted from the real time normalizedAccData based on the plurality feature techniques. The plurality feature techniques comprise a windowing technique and a feature extraction technique. The feature extraction technique includes a power spectral density technique.
The real time mag data feature is extracted from the real time normalizedMagData based on the plurality feature techniques. The plurality feature techniques comprise the windowing technique and the feature extraction technique. The feature extraction technique includes a standard deviation technique.
The real time snd data feature is extracted from the real time normalizedSndData based on the plurality feature techniques. The plurality feature techniques comprise the windowing technique and the feature extraction technique. The feature extraction technique includes a mean computation technique.
At step 314 of the method (300), the usage of the plurality of equipment is monitored based on the set of real time relevant features in the usage monitoring module 212. The usage of the plurality of equipment is monitored using the usage monitoring model 208.
In an embodiment, the monitoring is performed based on a transition state of the plurality of real time input data using the usage monitoring model. Each 10 second of set of real time relevant features is passed through the usage monitoring module 212 along with the transition state, wherein the transition state includes ON-OFF, OFF-ON transitions of each of the plurality of equipment. An outlier filter is utilized to remove high frequency transitions to build a robust transition report to be used for usage monitoring.
The usage of the plurality of equipment is monitored using the usage monitoring model and is displayed on the I/O interface(s) 106.
EXPERIMENTS:
An experiment has been conducted with a motor-based equipment, a compressor-based equipment and a flow-based equipment data, wherein the set of sensors are attached to a microcontroller and attached to the equipment.
The results are presented in three categories:
(a) Feature goodness,
(b) Model goodness and,
(c) Transfer learning ability
The results for feature goodness are shared as a robust transition report for an accelerometer (accData) data, a magnetometer (magData) data, and a sound level sensor (sndData) for transition states of ON and OFF state as illustrated in FIG.5, FIG.6 and FIG.7 respectively. The figures clearly show that each feature, wherein the accelerometer (accData) data represented as Feature 1 (F1), the magnetometer (magData) data represented as Feature 2 (F2), and the sound level sensor (sndData) represented as Feature 3 (F3) provides some level of separation though there are overlaps between classes. The data is mixed over three different class of machines and hence, the slight overlap can be well understood, as ambient conditions are also varying from place to place.
The model goodness is illustrated in Figure 8. The separation across the three feature dimensions produced by the bagger is clearly visible across the OFF and the ON transition state.
Considering the results for transfer learning, wherein a model was transferred to another motor-based equipment using full source data and 10% cross normalized target data for training, the following accuracy was obtained, which clearly shows that the model can be easily transfer learned.
[¦(&ON&OFF@ON&18&0@OFF&1&21)]
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.
The embodiments of present disclosure herein address an unresolved problem of for usage monitoring of equipment using a set of sensors. Monitoring of equipment usage in a shared laboratory facility is challenging as equipment are generally shared across various entities. Few existing techniques determine who was using an equipment, but to estimate how long the equipment was in running state, remains a challenge to be solved as each equipment has different underlying physical processes. The disclosure is contact sensing-based technique to monitor the usage of a variety of equipment using a set of sensors, wherein the set of sensors comprises of an accelerometer, a magnetometer, and a sound level sensor. The sensor data is pre-processed, and relevant features are extracted to generate a usage monitoring model, which is utilized for monitoring of equipment usage in a shared laboratory facility. The disclosed technique can be for a wide variety of machines and equipment’s, as they are simple to compute for on-device inferencing and also support transfer learned on a very small amount of data from new equipment.
It is to be understood that the scope of the protection is extended to such a program and in addition to a computer-readable means having a message therein; such computer-readable storage means contain program-code means for implementation of one or more steps of the method, when the program runs on a server or mobile device or any suitable programmable device. The hardware device can be any kind of device which can be programmed including e.g., any kind of computer like a server or a personal computer, or the like, or any combination thereof. The device may also include means which could be e.g., hardware means like e.g., an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a combination of hardware and software means, e.g., an ASIC and an FPGA, or at least one microprocessor and at least one memory with software processing components located therein. Thus, the means can include both hardware means and software means. The method embodiments described herein could be implemented in hardware and software. The device may also include software means. Alternatively, the embodiments may be implemented on different hardware devices, e.g., using a plurality of CPUs.
The embodiments herein can comprise hardware and software elements. The embodiments that are implemented in software include but are not limited to, firmware, resident software, microcode, etc. The functions performed by various components described herein may be implemented in other components or combinations of other components. For the purposes of this description, a computer-usable or computer readable medium can be any apparatus that can comprise, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
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 can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., 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 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.
Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer-readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., be non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, nonvolatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media.
It is intended that the disclosure and examples be considered as exemplary only, with a true scope of disclosed embodiments being indicated by the following claims.