A method for synchronizing data of electromechanical devices and a system thereof

Abstract

The present disclosure discloses a method and a system for synchronizing data of electromechanical devices. The method includes obtaining, by processor (202), plurality of 5 signals of one or more electromechanical devices. The plurality of signals is sampled at different sampling frequencies and is segregated into a plurality of groups based on respective sampling frequency. The method includes extracting using a Deep Learning (DL) model (212), by processor (202), one or more features for each of the plurality of groups. The method includes determining using the DL model (212), by processor (202), first relation between one 0 or more features for each of plurality of groups. The method includes determining using DL model (212), a second relation of one or more features between plurality of groups using first relation. The method includes synchronizing, by the processor (202), plurality of signals based on first relation and second relation. 5 To be published with Fig. 3a.

Description

P240322W001A METHOD FOR SYNCHRONIZING DATA OF ELECTROMECHANICAL DEVICES AND A SYSTEM THEREOFTECHNICAL FIELD

[0001] The present disclosure relates to data synchronization. More particularly, the present disclosure relates to a method and a system for synchronizing data of electromechanical devices.BACKGROUND

[0002] Generally, large volumes of data are generated from various electromechanical devices. The generated data cannot be stored at very high sampling frequency as it requires huge amount of memory, computation cost, and high data transmission rate. Hence, the data from different electromechanical devices are generated at different sampling frequencies. In order to synchronize the original data, the data from the different electromechanical devices is extracted, and then the data is combined. Combining the data includes normalizing and standardizing data. However, the data from the different electromechanical devices may be stored at different sampling frequencies (e.g., seconds, minutes, hours, days, weeks and the like) making it difficult to combine. Conventionally, to combine the data of different sampling frequencies, the data of different sampling frequencies is either up sampled or down sampled.

[0003] The process of up-sampling increases the number of data samples in a dataset. The upsampling technique either replicates the same data or synthetically generates more data points. More data points are generated by interpolating the existing data using various techniques such as linear interpolation, nearest neighbor, cubic spline, shape preservation, and the like. In upsampling technique, since the data points are assumed or are replicated, the analysis may be misleading. Moreover, the efficiency of synchronization is reduced. Hence, the process of upsampling has limitations of reduced accuracy and precision of the interpolated data, introduced redundancy, extra memory and computation overhead which result in poor performance.

[0004] The process of down-sampling reduces the amount of data samples in the dataset. The down-sampling technique normalizes the data points. The down-sampling technique may also approximate the data points to reduce the data points thereby reducing the data points / data samples. In down-sampling technique, since the data points are reduced / approximated, there is a data loss. There is a data loss due to smoothening of data in the process of down-sampling.P240322W001Therefore, the analysis may be misleading, and the efficiency of synchronization reduces. Further, a separate model may be trained for each sampling frequency which increases the complexity of the said model.

[0005] The information disclosed in this background of the disclosure section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.SUMMARY

[0006] The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description.

[0007] In an embodiment, a method for synchronizing data of electromechanical devices is disclosed. The method includes obtaining, by a processor, a plurality of signals of one or more electromechanical devices. The plurality of signals is sampled at different sampling frequencies and the plurality of signals is segregated into a plurality of groups based on respective sampling frequency. The method includes extracting using a Deep Learning (DL) model, by the processor, one or more features for each of the plurality of groups. The method includes determining using the DL model, by the processor, a first relation between the one or more features for each of the plurality of groups. The method includes determining using the DL model, a second relation of the one or more features between the plurality of groups using the first relation. The method includes synchronizing, by the processor, the plurality of signals based on the first relation and the second relation.

[0008] In an embodiment, a system for synchronizing data of electromechanical devices is disclosed. The system includes a memory that stores processor-executable instructions. The system includes a processor configured to execute the processor-executable instructions stored in the memory and thereby configured to obtain a plurality of signals of one or more electromechanical devices. The plurality of signals is sampled at different sampling frequencies and the plurality of signals is segregated into a plurality of groups based on respective samplingP240322W001 frequency. The fault reporting event comprises a first timestamp associated with a fault of the electromechanical device. The processor is configured extract using a DL model one or more features for each of the plurality of groups. The processor is configured to determine a first relation between the one or more features for each of the plurality of groups using the DL model. The processor is configured to determine a second relation of the one or more features between the plurality of groups using the first relation using the DL model. The processor is configured to synchronize the plurality of signals based on the first relation and the second relation.BRIEF DESCRIPTION OF THE DRAWINGS

[0009] 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. The same numbers are used throughout the figures to reference features and components. Some embodiments of at least one of device and methods in accordance with embodiments of the present subject matter are now described, by way of example only, and with reference to the accompanying figures, in which:

[0010] Fig. 1 illustrates an exemplary environment in which some embodiments of the present disclosure may be practiced;

[0011] Fig. 2 illustrates an apparatus for synchronizing data of electromechanical devices, in accordance with an embodiment of the present disclosure;

[0012] Fig. 3a illustrates a block diagram of a method for synchronizing data of electromechanical devices, in accordance with an embodiment of the present disclosure;

[0013] Fig. 3b illustrates a block diagram of a method for synchronizing data of electromechanical devices, in accordance with another embodiment of the present disclosure;

[0014] Fig. 4 illustrates an exemplary method for synchronizing data of electromechanical devices, in accordance with an embodiment of the present disclosure; andP240322W001

[0015] Fig. 5 illustrates a block diagram of an exemplary computer system for synchronizing data of electromechanical devices, in accordance with some embodiments of the present disclosure.DETAILED DESCRIPTION

[0016] 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.

[0017] While the disclosure is susceptible to various modifications and alternative forms, specific embodiment thereof has been shown by way of example in the drawings and will be described in detail below. It should be understood, however that it is not intended to limit the disclosure to the particular forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternative falling within the spirit and the scope of the disclosure.

[0018] The terms “comprises”, “comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device, or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a device or system or apparatus proceeded by “comprises. . . a” does not, without more constraints, preclude the existence of other elements or additional elements in the device, system, or apparatus.

[0019] In the following detailed description of the embodiments of the disclosure, reference is made to the accompanying drawings that form a part hereof, and in which are shown by way of illustration specific embodiments in which the disclosure may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense.P240322W001

[0020] Various embodiments of the present disclosure are hereinafter explained with reference to Figs. 1-5.

[0021] Fig. 1 illustrates an environment 100 in which some embodiments of the present disclosure may be practiced. The environment 100 exemplarily depicts one or more sources 102, a system 104 and a communication network 106. The one or more sources 102 may include, but not limited to, a database, a user or an operator, an electromechanical device, and the like. The database may comprise information related to the operation of the field device.

[0022] In an embodiment, the electromechanical device is constantly monitored and the data from the electromechanical device is used for further analysis. The data from the electromechanical device may be monitored for anomaly detection, failure prediction, field device health monitoring, root cause analysis and the like.

[0023] Generally, data from the electromechanical device may be received at different sampling frequencies such as seconds, minutes, hours, days, weeks and the like based on the electromechanical device. For example, the data from a motor may be received every day whereas the data from a drive may be received every hour. Each data point in the data received from the electromechanical device is important for the respective application i.e., anomaly detection, failure prediction, field device health monitoring and the like. For example, consider the case failure prediction, the field device may start to transmit faulty data before 5 hours from total failure. As data from the motor is sampled at different frequencies, the data is synchronized to a single sampling frequency (for example, sampling frequency of one day) using one or more techniques such as, up-sampling, down-sampling and the like. In this embodiment, to synchronize the data using the one or more techniques, the data has to be stored in a memory. Storing the data utilizes more space and requires large memory devices. Further, when the data is up-sampled to a sampling frequency of 24 hours. In this embodiment, though the faulty data starts 5 hours before the total failure, since the data is up-sampled to 24 hours, the data points relevant to the faulty data may be smoothed. Therefore, the fault prediction model may not be able to predict or prevent the complete failure of the motor.

[0024] In an embodiment, the system 104 is deployed for synchronizing the data received at different sampling frequencies from the one or more electromechanical devices. The pluralityP240322W001 of signals may be obtained from the one or more sources 102 via a communication network 106 as shown in Fig. 1. The communication network 106 may be a wired network, a wireless network, or a combination of wired and wireless networks. Some non-limiting examples of the wired networks may include the Ethernet, the Local Area Network (LAN), a fiber-optic network, and the like. Some non-limiting examples of the wireless networks may include the Wireless LAN (WLAN), cellular networks, Bluetooth or ZigBee networks, and the like. An example of the communication network 106 is the Internet. In another embodiment, the system 104 may be internally coupled to the one or more sources 102 to receive the plurality of signals .

[0025] The operations performed by the system 104 are explained in detail next with reference to Fig. 2.

[0026] Fig. 2 illustrates the system 104 for synchronizing data of electromechanical devices, in accordance with an embodiment of the present disclosure.

[0027] The system 104 is depicted to include a processor 202, a memory 204, an Input / Output (I / O) module 206, and a communication interface 208. It may be noted that, in some embodiments, the system 104 may include more or fewer components than those depicted herein. The various components of the system 104 may be implemented using hardware, software, firmware, or any combinations thereof. Further, the various components of the system 104 may be operably coupled with each other. More specifically, various components of the system 104 may be capable of communicating with each other using communication channel media (such as buses, interconnects, etc.).

[0028] In one embodiment, the processor 202 may be embodied as a multi-core processor, a single core processor, or a combination of one or more multi-core processors and one or more single core processors. For example, the processor 202 may be embodied as one or more of various processing devices, such as a coprocessor, a microprocessor, a controller, a digital signal processor (DSP), a processing circuitry with or without an accompanying DSP, or various other processing devices including, a microcontroller unit (MCU), a hardware accelerator, a special-purpose computer chip, or the like.

[0029] In one embodiment, the memory 204 is capable of storing machine executable instructions 205, referred to herein as instructions 205, and a Deep Learning (DL) model 212.P240322W001The data may be received from a database 210 or from the one or more electromechanical devices. In an embodiment, the DL model 212 is trained using only healthy data from the one or more electromechanical devices such that the DL model 212 may detect any irregularity i .e . , unhealthy data. In an embodiment, the processor 202 is embodied as an executor of software instructions. As such, the processor 202 is capable of executing the instructions 205 stored in the memory 204 to perform one or more operations described herein.

[0030] The term “DL model(s)” used herein refers to a model that has been trained on a set of data to recognize certain patterns and / or make certain decisions without further human intervention. The DL models process data inspired by a human brain. DL models can recognize complex patterns in pictures, text, sounds, and other data to produce accurate insights and predictions. In an embodiment, the DL model uses neural networks to teach computers to process data like humans. Some examples of neural network models may include, but are not limited to, a Feedforward Neural Network (FNN), the Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), a Gated Recurrent Unit (GRU), the Long short-term memory (LSTM), the Bidirectional Long Short-Term Memory (BiLSTM), and / or a combination of two or more of the neural networks. The LSTM model is a type of deep neural network designed to capture historical time series data and predict long-term nonlinear series. In an embodiment, the DL models are autoencoder models. The autoencoder models are selfsupervised models that are used to reduce the size of input data by recreating it. The autoencoder models are developed using one or more neural network models.

[0031] The memory 204 can be any type of storage accessible to the processor 202 to perform respective functionalities. For example, the memory 204 may include one or more volatile or non-volatile memories, or a combination thereof. For example, the memory 204 may be embodied as semiconductor memory, such as flash memory, mask ROM, PROM (programmable ROM), EPROM (erasable PROM), RAM (random access memory), etc. and the like.

[0032] In an embodiment, the processor 202 is configured to execute the instructions 205 to: (1) obtain a plurality of signals of one or more electromechanical devices. The plurality of signals is sampled at different sampling frequencies and the plurality of signals is segregated into a plurality of groups based on respective sampling frequency, (2) extract one or more features for each of the plurality of groups using the DL model 212, (3) determine a first relationP240322W001 between the one or more features for each of the plurality of groups using the DL model 212, (4) determine using the DL model 212, a second relation of the one or more features between the plurality of groups using the first relation, and (5) synchronize the plurality of signals based on the first relation and the second relation.

[0033] In an embodiment, the I / O module 206 may include mechanisms configured to receive inputs from and provide outputs to an operator of the system 104 (not shown in FIGS). The term ‘operator of the system 104’ as used herein may refer to one or more individuals whether directly or indirectly, associated with managing the system 104. In an embodiment, the output may be provided to the fault prediction model, data labelling model, and the like. To enable reception of inputs and provide outputs to the system 104, the I / O module 206 may include at least one input interface and at least one output interface. In an example, the operator of the system 104 may configure the system 104 via the at least one input interface. Examples of the input interface may include, but are not limited to, a keyboard, a mouse, a joystick, a keypad, a touch screen, soft keys, a microphone. Examples of the output interface may include, but are not limited to, a display such as a light emitting diode display, a thin-film transistor (TFT) display, a liquid crystal display, an active-matrix organic light-emitting diode (AMOLED) display, a microphone, a speaker, a ringer, and the like.

[0034] In an embodiment, the communication interface 208 may include mechanisms configured to communicate with other entities in the environment 100, for example, the one or more sources 102. In an embodiment, the communication interface 208 of the system 104 receives the data (i.e., the plurality of signals associated with the one or more electromechanical devices) from the one or more sources 102 and sends the synchronized signals, for example, to the prediction model.

[0035] The system 104 is depicted to be in operative communication with the database 210. In one embodiment, the database 210 is configured to store data associated with the plurality of electromechanical devices. In an embodiment, the database 210 is configured to store a variety of DL models 212 based on different specifications. The variety ofDL models 212 may include neural network models such as, but is not limited to, the FNN, the CNN, the RNN, the GRU, the LSTM, the BiLSTM, and / or combination of two or more of the neural network models.P240322W001

[0036] The database 210 may include multiple storage units such as hard disks and / or solid- state disks in a redundant array of inexpensive disks (RAID) configuration. In some embodiments, the database 210 may include a storage area network (SAN) and / or a network attached storage (NAS) system. In one embodiment, the database 210 may correspond to a distributed storage system, wherein individual databases are configured to store information.

[0037] FIG. 3a-b. illustrates a block diagram of method 300 for synchronizing data of electromechanical devices. Figs. 3a-4b are explained with respect to the DL model 212 being an autoencoder model developed using the one or more neural network models. However, the DL model 212 may not be limited to an autoencoder.

[0038] Fig. 3a illustrated a Multiple Input Multiple Output (MIMO) type of DL model 212 for synchronizing data of electromechanical devices. In an embodiment, the plurality of signals is received from the plurality of electromechanical devices. The plurality of signals (X'i, X2i, X3i, .... X!2, X22, X32, .... X' , X23, X33....) is sampled at different sampling frequencies (for e.g., seconds, minutes, hours, days, etc.). The plurality of signals (X'i, X2i, X3i, .... X^, X22, X32, . . . . X*3, X23, X33 . . . .) is segregated into a plurality of groups (for e.g., 302, 304, 306, etc.) based on respective sampling frequency. The plurality of signals (X'i, X2i, X3i, .... X*2, X22, X32, .... X*3, X23, X33... .) may be depicted as Xbawhere, a is the number of signals with the sampling frequency b. Each signal group (302, 304, 306) with the same sampling frequency is provided to a corresponding autoencoder in autoencoder layer 320. For example, the plurality of signals (X'i, X2i, X3i, . . . . ) with the sampling frequency 1 (i.e., second sampling frequency) may be given to one autoencoder layer. Similarly, the plurality of signals (X*2, X22, X32, ... .) with the sampling frequency 2 (e.g., minute sampling frequency) may be given to another autoencoder and the plurality of signals (X^, X23, X33 . . . .) with the sampling frequency 3 (e.g., hour sampling frequency) may be given to yet another autoencoder layer. The autoencoder layer may include, but is not limited to the FNN, the CNN, the RNN, the GRU, the LSTM, the BiLSTM, and / or combination of two or more of the autoencoder models. In an embodiment, 320 may be an independent auto encoder layer. The autoencoder layer 320 extracts one or more features for each of the plurality of groups (302, 304, 306).

[0039] In an embodiment, the one or more features from the autoencoder layer 320 (i.e., from the independent autoencoder) is received by an autoencoder 322 layer. The autoencoder layerP240322W001322 determines a first relation between the one or more features for each of the plurality of groups (302, 304, 306). A relation as used herein may be a function that defines a relation between the one or more features, a relation in patterns of the plurality of signals, and the like. In an embodiment, consider there is no relationship between the one or more features. In such a case the function that the one or more features are independent of each other is the relation and all the features independent of one another are considered. For example, consider a motor as the electromechanical device. The data may include a signal associated with the speed of the motor, a signal associated with the voltage of the motor, and the like. A relation function may be used to determine the relation between the speed and the voltage of the motor. The relation between the voltage and speed of the motor is that they are proportional to each other i .e . , when the voltage of the motor increases the speed of the motor also increases. The relation function, i.e., the relation between the voltage and speed is determined. The system 104 may synchronize the signal associated with speed using the signal associated with voltage and the relation function.

[0040] In another embodiment, the one or more features from the layer 320 may be provided to external models, systems, or a user for performing additional analysis from the extracted features. Hence, the present disclosure can be applied for feature extraction from multivariate time series signals of different sampling frequencies.

[0041] In an embodiment, the autoencoder layer 324 determines a second relation 312 of the one or more features between the plurality of groups (302, 304, 306) using the first relation 310. In an embodiment, the second relation 312 may be determined using a predefined number of layers ofthe DL model 212. The number of layers of the DLmodel 212 is based on the data, an application of the system 104 and the like. For example, consider the motor as the electromechanical device. The first relation may include a relation between the speed of the motor and the voltage of the motor (at minute sampling frequency). Consider a signal associated with a temperature of the motor is received at a different sampling frequency, for example, hourly. The second relation may be used to determine a relationship between the speed, the voltage and the temperature of the motor. The relationship between the voltage and speed of the motor is that they are proportional to each other i.e., when the voltage of the motor increases the speed of the motor also increases. The relation between the voltage and temperature of the motor may be that they are proportional to each other i.e., when the voltageP240322W001 of the motor increases the temperature of the motor also increases. The relationship function i.e., the relation between the voltage, the speed and the temperature are determined i.e., they are proportional to each other. The system 104 may synchronize the signal associated with speed using the signal associated with voltage or the temperature and the relation function.

[0042] In an embodiment, the autoencoder layer 326 determines a third relation 314 of the one or more features between the plurality of groups (302, 304, 306) using the second relation 312. The number of layers of the DL model 212 is determined by a subject matter expert, based on the application (e.g., fault prediction model for motors).

[0043] In an embodiment, the autoencoder layer 326 may decode the relation determined in previous layer to synchronize data. In an embodiment, the output may be the synchronized data. In another embodiment, the output may be the one or more features extracted. In another embodiment, the output may be complete reconstruction of the plurality of signals (X'I, X2i, X3i, .... X!2, X22, X32, .... X' , X23, X33....). In this embodiment, the DL model 212 is the autoencoder. The autoencoder has two parts: an encoder and a decoder. The encoder is applied to compress the plurality of signals into lower dimensional latent space representation and the decoder is applied to un-compress the encoded data into original dimensional space to get the reconstructed signal i.e., the plurality of signals (X11, X2i, X3i, .... X*2, X22, X32, .... X*3, X23, X33....). In another embodiment, consider the data associated with signals X'i, X22 and X23 includes data that can be used for fault prediction, then, a relation data between X'i, X22 and X23 may be labelled as fault classification data and transmitted to a classification model. Therefore, the output of the DL model 212 may be labelled data (Y i, Y2, Y3 (as show in Fig. 3b, 340, 342, 343)) based on a type of relation data, in this embodiment, data from different sampling frequencies may be combined together and given as output. Fig. 3b illustrates a Multiple Input Single Output (MISO) type of DL model 212.

[0044] The sequence of operations of the method 300 need not be necessarily executed in the same order as they are presented. Further, one or more operations may be grouped together and performed in form of a single step, or one operation may have several sub-steps that may be performed in parallel or in sequential manner.

[0045] Fig. 4 illustrates a flow chart of method 400 for synchronizing data of electromechanical devices.P240322W001

[0046] At 402, the system 104 obtains the plurality of signals (X1i, X2i, X3i, .... X^, X22, X32, . . . . X' , X23, X33 . . . .) of one or more electromechanical devices, wherein the plurality of signals (X1!, X2i, X3i, .... X*2, X22, X32, .... X*3, X23, X33....) is sampled at different sampling frequencies. The sampling frequencies may include, but is not limited to, seconds, minutes, hours, days and weeks. The plurality of signals (X'i, X2i, X3i, .... X^, X22, X32, .... X^, X23, X33... .) is segregated into a plurality of groups (302, 304, 306) based on respective sampling frequency.

[0047] At 402, the system 104 extracts one or more features for each of the plurality of groups (302, 304, 306) using the DL model 212. The DL model 212 may be the autoencoder model. The autoencoder model may include, but is not limited to, the FNN, the CNN, the RNN, the GRU, the LSTM, the BiLSTM, and / or combination of two or more of the autoencoder models.

[0048] At 404, the DL model 212 determines the first relation (310) between the one or more features for each of the plurality of groups (302, 304, 306). The relation as used herein may be the function that defines the relation between the one or more features, a relation in patterns of the plurality of signals, and the like. In an embodiment, consider that there is no relation between the one or more features, the function that the one or more features are independent of each other is the relation and all the features independent of one another are considered. For example, consider a motor as the electromechanical device. The data may include a signal associated with the speed of the motor, a signal associated with the voltage of the motor, and the like. The relationship between the voltage and speed of the motor is that they are proportional to each other i.e., when the voltage of the motor increases the speed of the motor also increases. The relationship function, i.e., the relation between the voltage and speed, is determined. The system 104 may synchronize the signal associated with speed using the signal associated with voltage and the relation function.

[0049] At 406, the DL model 212 determines the second relation (312) of the one or more features between the plurality of groups using the first relation. For example, consider the motor as the electromechanical device. The first relation may include a relation between the speed of the motor and the voltage of the motor (at minute sampling frequency). Consider a signal associated with a temperature of the motor is received at a different sampling frequency, for example, hourly. The second may be used to determine a relationship between the speed,P240322W001 the voltage and the temperature of the motor. The relationship between the voltage and speed of the motor is that they are proportional to each other i.e., when the voltage of the motor increases the speed of the motor also increases. The relationship between the voltage and temperature of the motor may be that they are proportional to each other i.e., when the voltage of the motor increases the temperature of the motor also increases. The relationship function i.e., the relation between the voltage, the speed and the temperature are determined i.e., they are proportional to each other. The system 104 may synchronize the signal associated with speed using the signal associated with voltage or the temperature and the relation function.

[0050] At 408, the DL model 212 synchronizes the plurality of signals (X'I, X2i, X3i, .... X^, X22, X32, .... X' , X23, X33. . . .) based on the first relation 310 and the second relation 312. In an embodiment, the output may be the synchronized signals, In another embodiment, the output may be the one or more features. In another embodiment, the output may be complete reconstruction ofthe plurality of signals (X1!, X2i, X3i, .... X*2, X22, X32, .... X X23, X33... .). In this embodiment, the DL model 212 is the autoencoder. The autoencoder has two parts: an encoder and a decoder. The encoder is applied to compress the plurality of signals into lower dimensional latent space representation and the decoder is applied to un-compress the encoded data into original dimensional space to get the reconstructed signal i.e., the plurality of signals (X1!, X2i, X3i, .... X*2, X22, X32, .... X*3, X23, X33... .). In yet another embodiment, the output of the DL model 212 may be labelled data (Y i, Y2, Y3 (as show in Fig. 3b, 340, 342, 343)). In this embodiment, each of the outputs may be of different sampling frequency.

[0051] The disclosed method 400 with reference to Fig. 4, may be implemented using software including computer-executable instructions stored on one or more computer-readable media (e.g., non-transitory computer-readable media, such as one or more optical media discs, volatile memory components (e.g., DRAM or SRAM), or non-volatile memory or storage components (e.g., hard drives or solid-state non-volatile memory components, such as Flash memory components) and executed on a computer (e.g., any suitable computer, such as a laptop computer, net book, Web book, tablet computing device, smart phone, or other mobile computing device). Such software may be executed, for example, on a single local computer.

[0052] The sequence of operations of the method 400 need not be necessarily executed in the same order as they are presented. Further, one or more operations may be grouped together andP240322W001 performed in form of a single step, or one operation may have several sub-steps that may be performed in parallel or in sequential manner.

[0053] Fig. 5 illustrates a block diagram of an exemplary computer system 500, for implementing embodiments consistent with the present disclosure. The computer system 500 may be, without limitation to, the system 104. The computer system 500 may include a central processing unit (“CPU” or “processor”) 501. The processor 501 may include at least one data processor for executing processes. The processor 501 may include specialized processing units such as, integrated system (bus) controllers, memory management control units, floating point units, graphics processing units, digital signal processing units, etc.

[0054] The processor 501 may be disposed in communication with one or more input / output (I / O) devices 505 and 509 via I / O interface 507. The I / O interface 507 may employ communication protocols / methods such as, without limitation, audio, analog, digital, monaural, RCA, stereo, IEEE- 1394, serial bus, universal serial bus (USB), infrared, PS / 2, BNC, coaxial, component, composite, digital visual interface (DVI), high-definition multimedia interface (HDMI), RF antennas, S-Video, VGA, IEEE 5O2.n / b / g / n / x, Bluetooth, cellular (e.g., code-division multiple access (CDMA), high-speed packet access (HSPA+), global system for mobile communications (GSM), long-term evolution (LTE), WiMax, or the like), etc.

[0055] Using the I / O interface 507, the computer system 500 may communicate with one or more I / O devices 508 and 509. For example, the input devices 508 may be an antenna, keyboard, mouse joystick, (infrared) remote control, camera, card reader, fax machine, dongle, biometric reader, microphone, touch screen, touchpad, trackball, stylus, scanner, storage device, transceiver, video device / source, etc. The output devices 509 may be a printer, fax machine, video display (e.g., cathode ray tube (CRT), liquid crystal display (LCD), lightemitting diode (LED), plasma, Plasma display panel (PDP), Organic light-emitting diode display (OLED) or the like), audio speaker, etc.

[0056] In some embodiments, the processor 501 may be disposed in communication with external elements such as external computer systems, servers, network elements. The network interface 510 may employ connection protocols including, without limitation, direct connect,P240322W001Ethernet (e.g., twisted pair 10 / 100 / 1000 Base T), transmission control protocol / intemet protocol (TCP / IP), token ring, IEEE 802.11a / b / g / n / x, etc.

[0057] In some embodiments, the processor 501 may be disposed in communication with a memory 503 (e.g., RAM, ROM, etc.) via a storage interface 502. The storage interface 502 may connect to memory 503 including, without limitation, memory drives, removable disc drives, etc., employing connection protocols such as, serial advanced technology attachment (SATA), Integrated Drive Electronics (IDE), IEEE-1394, Universal Serial Bus (USB), fibre channel, Small Computer Systems Interface (SCSI), etc. The memory drives may further include a drum, magnetic disc drive, magneto-optical drive, optical drive, Redundant Array of Independent Discs (RAID), solid-state memory devices, solid-state drives, etc.

[0058] The memory 503 may store a collection of program or database components, including, without limitation, user interface 504, an operating system 505, a web browser 506 etc. In some embodiments, computer system 500 may store user / application data, such as, the data, variables, records, etc., as described in this disclosure. Such databases may be implemented as fault-tolerant, relational, scalable, secure databases such as Oracle ® or Sybase®.

[0059] The operating system 505 may facilitate resource management and operation of the computer system 500. Examples of operating systems include, without limitation, APPLE MACINTOSH® OS X, UNIX®, UNIX-like system distributions (E G., BERKELEY SOFTWARE DISTRIBUTION™ (BSD), FREEBSD™, NETBSD™, OPENBSD™, etc ), LINUX DISTRIBUTIONS™ (E G., RED HAT™, UBUNTU™, KUBUNTU™, etc ), IBM™ OS / 2, MICROSOFT™ WINDOWS™ (XP™, VISTA™ / 7 / 8, 10 etc ), APPLE® IOS™, GOOGLE® ANDROID™, BLACKBERRY® OS, or the like.

[0060] In some embodiments, the computer system 500 may implement the web browser 506 stored program components. The web browser 506 may be a hypertext viewing application, such as MICROSOFT® INTERNET EXPLORER®, GOOGLE™ CHROME™, MOZILLA® FIREFOX®, APPLE® SAFARI®, etc. Secure web browsing may be provided using Secure Hypertext Transport Protocol (HTTPS), Secure Sockets Layer (SSL), Transport Layer Security (TLS), etc. Web browsers 506 may utilize facilities such as AJAX, DHTML, ADOBE® FLASH®, JAVASCRIPT®, JAVA®, Application Programming Interfaces (APIs), etc. In some embodiments, the computer system 500 may implement a mail server stored programP240322W001 component. The mail server may be an Internet mail server such as Microsoft Exchange, or the like. The mail server may utilize facilities such as Active Server Pages (ASP), ACTIVEX®, ANSI® C++ / C#, MICROSOFT®, NET, CGI SCRIPTS, JAVA®, JAVASCRIPT®, PERL®, PHP, PYTHON®, WEBOBJECTS®, etc. The mail server may utilize communication protocols such as Internet Message Access Protocol (IMAP), Messaging Application Programming Interface (MAPI), MICROSOFT® exchange, Post Office Protocol (POP), Simple Mail Transfer Protocol (SMTP), or the like. In some embodiments, the computer system 500 may implement a mail client stored program component. The mail client may be a mail viewing application, such as APPLE® MAIL, MICROSOFT® ENTOURAGE®, MICROSOFT® OUTLOOK®, MOZILLA® THUNDERBIRD®, etc.

[0061] The present disclosure provides a method and system for synchronizing data of electromechanical devices. The present disclosure enables complete synchronization of the input signals without using up-sampling, down-sampling and the like. This minimizes loss of data, thereby increasing the efficiency of the model. Further, the model is trained using healthy data of different sampling frequencies at the same time. Therefore, the time consumed in training the model is decreased. Furthermore, the system is robust and is less complex. The present disclosure may predict unhealthy data accurately, thereby enables reduced downtime of the electromechanical device.

[0062] The described operations may be implemented as a method, system or article of manufacture using standard programming and / or engineering techniques to produce software, firmware, hardware, or any combination thereof. The described operations may be implemented as code maintained in a “non-transitory computer readable medium”, where a processor may read and execute the code from the computer readable medium. The processor is at least one of a microprocessor and a processor capable of processing and executing the queries. A non-transitory computer readable medium may include media such as magnetic storage medium (e.g., hard disk drives, floppy disks, tape, etc.), optical storage (CD-ROMs, DVDs, optical disks, etc.), volatile and non-volatile memory devices (e.g., EEPROMs, ROMs, PROMs, RAMs, DRAMs, SRAMs, Flash Memory, firmware, programmable logic, etc.), etc. Further, non-transitory computer-readable media may include all computer-readable media except for a transitory. The code implementing the described operations may further be implemented in hardware logic (e.g., an integrated circuit chip, Programmable Gate Array (PGA), Application Specific Integrated Circuit (ASIC), etc.).P240322W001

[0063] 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 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, the singular forms “a,” “an,” and “the” include plural references unless the context clearly dictates otherwise.

[0064] 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., are non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, non-volatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media.

[0065] 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. Accordingly, the disclosure of the embodiments of the disclosure is intended to be illustrative, but not limiting, of the scope of the disclosure.P240322W001

[0066] With respect to the use of substantially any plural and / or singular terms herein, those having skill in the art can translate from the plural to the singular and / or from the singular to the plural as is appropriate to the context and / or application. The various singular / plural permutations may be expressly set forth herein for sake of clarity.

Claims

P240322W001We Claim:

1. A method for synchronizing data of electromechanical devices comprising: obtaining, by a processor (202), a plurality of signals of one or more electromechanical devices, wherein the plurality of signals is sampled at different sampling frequencies and wherein the plurality of signals is segregated into a plurality of groups (302, 304, 306) based on respective sampling frequency; extracting using a Deep Learning (DL) model (212), by the processor (202), one or more features for each of the plurality of groups (302, 304, 306); determining using the DL model (212), by the processor (202), a first relation (310) between the one or more features for each of the plurality of groups (302, 304, 306); determining using the DL model (212), a second relation (312) of the one or more features between the plurality of groups (302, 304, 306) using the first relation (310); and synchronizing, by the processor (202), the plurality of signals based on the first relation (310) and the second relation (312).

2. The method as claimed in claim 1, wherein the DL model (212) is trained using healthy data associated with the one or more electromechanical devices.

3. The method as claimed in claim 1, wherein the determining the first relation (310) between the plurality of signals is performed using a predefined number of layers of the DL model (212).

4. The method as claimed in claim 1, wherein the determining the second relation (312) between the plurality of signals is performed using a predefined number of layers of the DL model (212).

5. The method as claimed in claim 1, wherein the DL model (212) is an autoencoder.

6. A system for synchronizing data of electromechanical devices, the system comprises: a processor (202); andP240322W001 a memory, wherein the memory stores processor-executable instructions, which, on execution, cause the processor (202) to: obtain a plurality of signals of one or more electromechanical devices, wherein the plurality of signals is sampled at different sampling frequencies and wherein the plurality of signals is segregated into a plurality of groups (302, 304, 306) based on respective sampling frequency; extract using a DL model (212) one or more features for each of the plurality of groups (302, 304, 306); determine using the DL model (212) a first relation (310) between the one or more features for each of the plurality of groups (302, 304, 306); determine using the DL model (212), a second relation (312) of the one or more features between the plurality of groups (302, 304, 306) using the first relation (310); and synchronize the plurality of signals based on the first relation (310) and the second relation (312).

7. The system as claimed in claim 6, wherein the DL model (212) is trained using healthy data of the one or more electromechanical devices.

8. The system as claimed in claim 6, wherein the processor (202) determines the first relation (310) between the plurality of signals using a predefined number of layers of the DL model (212).

9. The system as claimed in claim 6, wherein the processor (202) determines the second relation (312) between the plurality of signals using a predefined number of layers of the DL model (212).

10. The system as claimed in claim 6, wherein the DL model (212) is an autoencoder.

Images