BACKGROUND

[001] Embodiments of the present specification relate generally to monitoring of an industrial asset, and more particularly to a condition monitoring device and a corresponding method of condition monitoring for electric equipment in an industrial system.

[002] Efficient operation of industrial systems such as power generation plants requires monitoring of assets such as electric drive trains for ensuring availability of electric equipment such as electric drives and motors without unscheduled interruption. Conventional approaches schedule preventive maintenance activities at regular intervals to detect equipment faults and correct them. The time interval between two successive maintenance schedules is primarily determined based on average life of assets. However, this approach is inherently suboptimal for not being able to incorporate additional known variations in life span information. Recently, sophisticated techniques capable of generating prognostics and/or diagnostic information are being used to predict imminent breakdown of equipment/assets in the industrial systems. Along with the progress in artificial intelligence technology and development of machine learning techniques for predicting future operational states of complex systems, the computational, and storage requirements of the asset monitoring is increasing. With deployment of cloud technologies, the asset monitoring is implemented by distributed systems introducing newer complexities in data acquisition and transmission of data required for generating advanced analytics used by the asset monitoring systems.

[003] Condition monitoring devices used in newer systems such as a distributed system have inbuilt intelligence and are able to provide smart functionalities with availability of enhanced computation resources. However, there are several implementation challenges faced by the conventional condition monitoring devices. First of all, the data to be acquired and the techniques to be adopted are dependent on type of equipment faults. To identify a variety of faults, a large amount of equipment data is to be acquired. Further, in systems such as drive train, there may be interactions between various subsystems and accurate root cause analysis needs data from all subsystems. It is not possible for condition monitoring devices working in isolation to collect data from multiple equipments. In general, the same condition monitoring device may not be able to support different data needs required to assess multiple asset conditions. In some cases, equipment fault detection may require data to be sampled at higher sampling rates resulting in increased amount of data. Processing of large amount of data may not be supported by the condition monitoring devices due to limited processing capabilities or due to having fixed configurations. When the processing is performed at the server, transferring of huge amount of data to the server from the condition monitoring devices may be prohibitively expensive or infeasible in certain bandwidth constrained environments.

[004] There is a need for newer data condition monitoring techniques for supporting advanced analytics in distributed asset monitoring systems.

BRIEF DESCRIPTION [005] In accordance with one aspect of the present specification, a method for monitoring condition of electric equipment in an industrial system comprising an electric motor and an electric drive is disclosed. The method includes acquiring, by a data logger, a first dataset corresponding to a first configuration, where the data logger is communicatively coupled to the electric equipment. The first configuration is characterised by a first subset of operating parameters among a plurality of operating parameters of the industrial system obtained from a plurality of sensors and a first set of sampling rate values corresponding to the first subset of operating parameters. The first subset of operating parameters corresponds to the electric equipment. The method further includes determining, by a processor unit, an equipment condition based on a comparison of a performance indicator derived from the first dataset with a corresponding reference value. The method also includes identifying, by the processor unit, a second configuration based on the equipment condition. The second configuration is characterized by at least one of a second sampling rate for at least one of the first subset of operating parameters, and a second subset of operating parameters. The method includes initiating, by the processor unit, acquisition of the second dataset corresponding to the second configuration by a system analyzer. The second dataset is collected by at least one of the data logger and a remote data logger coupled to a second equipment of the industrial system. The second dataset is transferred to a system analyzer for generating an equipment fault.

[006] In accordance with another aspect of the present specification, a condition monitoring device coupled to electric equipment in an industrial system comprising an electric motor and an electric drive is disclosed. The device includes a memory unit configured to store a first configuration, and a second configuration. The first configuration is characterized by a first subset of operating parameters among a plurality of operating parameters of the industrial system obtained from a plurality of sensors and a first set of sampling rate values corresponding to the first subset of operating parameters. The second configuration is characterized by at least one of a second sampling rate for at least one of the first subset of operating parameters, and a second subset of operating parameters. The device further includes a data logger communicatively coupled to the electric equipment and configured to acquire a first dataset corresponding to the first configuration. The first dataset corresponds to the electric equipment. The device also includes a processor unit operatively coupled to the data logger and the memory unit and configured to acquire, using the data logger, the first dataset by sampling each operating parameter in the first subset of operating parameters using a corresponding sampling rate in the first set of sampling rate values. The processor unit is further configured to determine an equipment condition based on a comparison of a performance indicator derived from the first dataset with a corresponding reference value. The processor unit is also configured to identify the second configuration based on the equipment condition. Further, the processor unit is configured to initiate acquisition of a second dataset corresponding to the second configuration. The second dataset is collected by at least one of the data logger and a remote data logger coupled to a second equipment of the industrial system. The second dataset is transferred to a system analyzer for generating an equipment fault. DRAWINGS

[007] These and other features and aspects of embodiments of the present invention will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:

[008] FIG. 1 is a diagrammatic illustration of a health monitoring system of an industrial asset having condition monitoring devices in accordance with an exemplary embodiment;

[009] FIG. 2 is a block diagram illustrating a condition monitoring device in accordance with an exemplary embodiment;

[0010] FIG. 3 is a diagrammatic illustration of a system analyzer in accordance with an exemplary embodiment;

[0011] FIG. 4 is a schematic illustrating a two stage architecture of the health monitoring system with an alternate configuration of the condition monitoring device in accordance with an exemplary embodiment; and

[0012] FIG. 5 is a flow chart of a method of condition monitoring in accordance with an exemplary embodiment.

DETAILED DESCRIPTION

[0013] As will be described in detail hereinafter, techniques for monitoring of an industrial system are presented. More particularly, a condition monitoring device and a corresponding method of condition monitoring of electric equipment in an industrial system are presented.

[0014] The term ‘industrial system’ may refer to a power plant or a manufacturing unit commissioned typically in a single geographic location. The term ‘equipment’ is used to refer to one or more devices, machines or subsystems of an industrial system. The equipment may be electric machines such as, but not limited to, a motor, a generator and a transformer, or a mechanical system such as, but not limited to, a mechanical drive train. The term ‘asset’ used herein may be an equipment or a subsystem of the industrial system. The term ‘equipment condition’ is used to refer to a condition of the equipment such as a fault or an abnormality in its operation, or to an operating condition of the equipment, condition of a subsystem, an abnormal condition or a fault condition of one of a device, or a subsystem of the industrial system. The phrase “operating parameter” refers to an electrical parameter or a mechanical parameter such as, but not limited to, a current, a voltage, a temperature and a vibration. The phrase “operating parameter values” refers to sampled values of an operating parameter. The term ‘configuration’ refers to a list of operating parameters and corresponding sampling rates, stored in memory as a table or a linked list. The term ‘condition monitoring device’ is typically used to refer to a field device associated with one equipment and configured to monitor its condition. The condition monitoring device may be disposed on an equipment and configured to sense operating parameters such as, but not limited to, a temperature value and vibration value. Alternatively, the condition monitoring device may be communicatively coupled with an equipment and configured to access a memory unit within the equipment. The configuration information is used by a data logger to acquire data corresponding to the specified operating parameters at specified rate.

[0015] FIG. 1 is a diagrammatic illustration of a health monitoring system 100 of an industrial system 102 having a condition monitoring device 104 in accordance with an exemplary embodiment. In one embodiment, the industrial system 102 is a drive train having equipment such as a motor 106, a gear box (not shown in the FIG. 1), and an electric drive unit 108. The industrial system 102 is one of a plurality of similar industrial systems 102, 110 installed at multiple geographic locations. It may be noted that the industrial system 110 includes equipment 112, 114 similar to the electric drive 108 and the motor 106 respectively. Each of the electric drive unit 108 and the motor 106 are monitored by a corresponding condition monitoring device 104, 116 respectively. The condition monitoring devices 104, 116 are configured to receive operating parameters of respective equipment 108, 106 and determine corresponding equipment conditions. Further, the condition monitoring devices 104, 116 are in turn coupled to a system analyzer 118 configured to generate advanced analytics suitable for determining accurate prognostics and equipment condition 120 of one or more electric equipment 106, 108 in the industrial system 102. It may be noted herein that the term equipment condition also includes an operating condition generated due to interaction of two or more equipments of the industrial system 102. The system analyzer 118 may be provided on a computer server co-located with an electric equipment or remotely connected through an EDGE device. In one embodiment, the system analyzer 118 is realized as software as a service supported by cloud systems 122. The system analyzer 118 is configured to receive operating parameter values 124 from multiple devices 108, 106 of the industrial system 102, optionally via condition monitoring devices 104, 116. The operating parameters 124 are selected based on analytics required to monitor the devices 104, 106 and are acquired by the condition monitoring devices 104, 106. The system analyzer 118 is further configured to perform combined processing of the operating parameters 124 of devices 106, 108 to precisely determine operating conditions created due to interaction amongst two or more devices of the industrial system 102.

[0016] The system analyzer 118 is also configured to receive operating parameters 126 corresponding to devices 112, 114 of other industrial systems 110 located in different geographical locations. The devices 112 and 114 of the industrial system 110 are monitored by respective condition monitoring devices 128, 130. The operating parameters 126 are selected based on analytics required to monitor the devices 112, 114 and acquired by the condition monitoring devices 128 and 130 respectively. The system analyzer 118 is configured to leverage similarities in operation of geographically distributed industrial system 110 to generate efficient advanced analytics and update machine learning software used by the health monitoring system 100 at periodic intervals.

[0017] In embodiments of the present specification, the condition monitoring devices 104, 116, 128, 130 are configured to perform condition monitoring in two stages. Although the two-stage condition monitoring is explained here with reference to the condition monitoring device 104, the monitoring mechanism is applicable for other condition monitoring devices 116, 128 and 130 as well. Specifically, in the first stage, the condition monitoring device 104 is configured to monitor one or more operating parameters of the electric drive 108 to determine a condition of the electric drive. Further, the condition monitoring device 104 is configured to identify additional data or additional operating parameters required for generating advance analytics based on the condition of the electric drive 108. The additional data may include higher sampling rate data for the same operating parameters, while additional operating parameters may include one or more supplementary operating parameters of the electric drive, and/or one or more operating parameters of the motor 106. The condition monitoring device 104 is configured to provide operating parameters of the electric drive 108 to the system analyzer 118. The operating parameters of the electric drive 108 provided to the system analyzer 118 includes values of the one or more operating parameters used to determine the condition of the electric drive 108 and values as required for the supplementary operating parameters. Optionally, according to certain equipment conditions, the condition monitoring device 104 is also configured to initiate acquisition of one or more operating parameters of the motor 106 via the condition monitoring device 116. It may be noted that the motor 106 is a remote equipment with reference to the equipment 108 and the condition monitoring device 116 is remote to the condition monitoring device 104. The acquired operating parameters of the motor 106 are transmitted to the system analyzer 118. The operating parameters of the electric drive 108 and optionally the operating parameters of the motor 106 are processed by the system analyzer 118 to generate an equipment fault.

[0018] The acquisition of the operating parameters of the motor 106 and transmission of the acquired motor operating parameters to the system analyzer 118 may be performed by the condition monitoring device 116 independently without further involvement of the condition monitoring device 104. Similarly, the processing of the operating parameters of the electric drive 108 and the motor 106 is performed by the system analyzer 118 independently without the involvement of the condition monitoring device 104. In another embodiment, the condition monitoring device 104 may assist acquisition, transmission and processing activities of the remote condition monitoring device 116 and the system analyzer 118. After the completion of processing by the system analyzer 118, the equipment fault may be sent to a human machine interface (HMI) device such as, but not limited to, a display device and a printer device. In addition, the condition monitoring device 104 may also be configured to receive signals from the condition monitoring device 116 and the system analyzer 118 upon completion of the activities of transmission and processing respectively.

[0019] FIG. 2 is a block diagram 200 illustrating working of a condition monitoring device 202 in accordance with an exemplary embodiment. The condition monitoring device 202 is coupled to a first equipment 204 of an industrial system 242, a second condition monitoring device 206 configured to monitor a second equipment 244 of the industrial system 242, and a system analyzer 208 (same as numeral 118 of FIG. 1). The second equipment 244 is a remote equipment with reference to the first equipment 204 and the second condition monitoring device 206 is remote to the first condition monitoring device 202. The second condition monitoring device 206 includes a data logger (not shown in FIG. 2) of its own and this data logger is referred herein as a “remote data logger”. The condition monitoring device 202 may be one of 104, 116, 128, and 130 of FIG. 1. In one embodiment, when the condition monitoring device 202 is 104 of FIG. 1, the first equipment 204 corresponds to the electric drive 108, the second electric equipment 244 corresponds to the motor 106 and the second condition monitoring device 206 corresponds to 116. The condition monitoring device 202 includes at least one data logger, a memory unit 216 and a processor unit 214 communicatively coupled to each other by a communication bus 218.

[0020] In the illustrated embodiment, the condition monitoring device 202 includes a first data logger 210 and a second data logger 212. In one embodiment, the first data logger 210 and the second data logger 212 are communicatively coupled to the memory unit 216 and configured to access data logger configurations stored in a predetermined memory location(s). The first data logger 210 is configured to generate a first dataset 230 while operating in a first configuration 226. The first configuration 226 is characterized by a first subset of operating parameters 222 from amongst a plurality of operating parameters 220 and a first set of sampling rate values. The plurality of operating parameters 220 is generated by the industrial system 242 and measured by a plurality of sensors (not shown in FIG. 2). The first data logger 210 is configured to acquire the first dataset 230 by sampling the first subset of operating parameters 222 at the first set of sampling rate values. In one embodiment, the first configuration 226 is a pre-set configuration specifying the first subset of operating parameters 222 and their corresponding sampling rate values. The pre-set configuration may either be determined off-line or provided by a user and is stored in the memory unit 216. In such an embodiment, the first data logger is configured to obtain the pre-set configuration from the memory unit 216. The plurality of operating parameters 220 includes first electric equipment parameters 246 and the second electric equipment parameters 248. The first subset of operating parameters 222 includes operating parameters acquired from the first electric equipment 204 via a first subset of the plurality of sensors.

[0021] The second data logger 212 is configured to generate a supplementary dataset 234 by sampling the same operating parameters at a higher sampling rate or a different set of operating parameters including supplementary operating parameters 224 of the electric drive 204. Although the illustrated embodiment includes two data loggers, it may be noted herein that the condition monitoring device 202 may include only one data logger 210 configured to generate the first dataset 230 and the supplementary dataset 234. The supplementary dataset 234 may be part of a second dataset 232 to be provided to the system analyzer 208. In some of the embodiments, the second dataset 232 may include a first part 238 contributed by the condition monitoring device 202 configured to monitor the first electric equipment 204 and a second part 236 contributed by the second condition monitoring device 206 configured to monitor the second electric equipment 244. The second part 236 includes motor data obtained from sampling one or more operating parameters of the electric motor 244. The first part 238 of the second dataset 232 may include whole or part of the first dataset 230 and whole or part of the supplementary dataset 234.

[0022] The memory unit 216 is configured to store the first configuration 226 used to generate the first dataset 230 and a second configuration 228 used to generate the second dataset 232. The second configuration 228 includes a second subset of operating parameters and a second set of sampling rate values. In one embodiment, the second subset of operating parameters is same as the first subset of parameters 222. However, in such an embodiment, the second configuration is characterized by a second sampling rate in the second set of sampling rate values for at least one of the first subset of operating parameters. In a second embodiment, the second subset of operating parameters includes supplementary operating parameters 224 of the first electric equipment (electric drive) 204 and may have non- overlapping elements with the first subset of operating parameters. The second dataset 232 in such embodiments is generated completely by the condition monitoring device 202. In a third embodiment, the second subset of operating parameters may include operating parameters 240 from the second equipment (electric motor) 244 optionally with one or more of the first subset of operating parameters 222 and the supplementary operating parameters 224.

[0023] In one embodiment, the memory unit 216 is a random access memory (RAM) configured to store the first dataset 230, the supplementary dataset 234, the first configuration 226 and the second configuration 228. The memory unit 216 may also be configured to store diagnostic information required to identify the condition of the electric drive or the electric motor using the first dataset 230. Further, the memory unit 216 may also store a mapping between various conditions of the electric drive with corresponding second configurations. The RAM may be dynamic RAM requiring frequent refreshing of memory contents and static RAM usable as cache memory. In another embodiment, the memory unit 216 may be a read only memory (ROM) such as, but not limited to, programmable ROM (PROM), erasable PROM (EPROM), and electronically erasable PROM (EEPROM). The memory unit 216 may include multiple memory modules of different types. The memory unit 216 is accessible by the first data logger 210, the second data logger 212 and the processor unit 214. The memory unit 216 also includes a set of instructions (or programs) executable by the processor unit 214 to perform functionalities of acquisition of operating parameters 220, generation of the first dataset 230, and identification of the second configuration 228. The set of instructions may also help in acquiring the supplementary dataset 234, initiating data generation by the second condition monitoring device 206 and processing by the system analyzer 208.

[0024] The processor unit 214 is communicatively coupled to all the other units 210, 212, 216 of the condition monitoring device 202 and configured to perform computing and control functions required by the two-stage condition monitoring technique disclosed in embodiments of the present specification. The processor unit 214 may include one or more computing elements such as microcontrollers, general purpose processors, application specific integrated circuits (ASICs) and field programmable gate array (FPGA). The processor unit 214 in some embodiments may also include an EDGE processor communicatively coupled with the condition monitoring device 202 providing an intermediate processing option before system processor.

[0025] The processor unit 214 is configured to retrieve the sequence of instructions stored in the memory unit 216 and execute them to perform various tasks to be performed by the condition monitoring device 202. Specifically, the processor unit 214 is configured to retrieve the first configuration 226 from the memory unit 216 and select a first subset of operating parameters 222 from amongst the plurality of operating parameters 220. The processor unit 214 is further configured to acquire the first dataset 230 by sampling each operating parameter in the first subset of operating parameters with corresponding sampling rate values among the plurality of first set of sampling rate values.

[0026] A plurality of performance indicators representative of a plurality of equipment conditions are derived from the data corresponding to the first subset of operating parameters. The first dataset may also include the plurality of performance indicators. Specifically, the plurality of performance indicators may be generated by processing the first dataset 230 using at least one of a feature extraction technique, a pattern recognition technique, a statistical parameter related to one or more parameters of the first subset. The plurality of performance indicators may also be generated by processing the first subset of operating parameters using a neural network-based model such as a Bayesian belief network (BBN) and radial basis network (RBN). As an example, the first subset of operating parameters includes, but is not limited to, a drive current, a drive frequency, and a drive voltage. The processor unit 214 is configured to process the first dataset 230 to identify equipment condition such as, but not limited to, current abnormality, voltage abnormality, switch failure and thermal abnormality of the electric drive 204. In one embodiment, sample values (or performance indicators) of the first dataset corresponding to each of the operating parameters are compared with a corresponding pre-determined threshold value. When the sample values (performance indicators) used in the comparison operation exceed (or are below, or differ from the threshold, as the case may be) the pre-determined threshold value, the processor unit 214 is configured to select an equipment condition based on parameters and their values involved in the comparison. Specifically, when a performance indicator exceeds the predetermined threshold value in the comparison operation, one or more operating parameters associated with the performance indicator are identified. Further, an equipment associated with the performance indicator and/or the operating parameters is identified. Further, an equipment condition corresponding to identified operating parameters and/or performance indicator may also be determined. It may be noted herein that a mapping between abnormal performance indicators, operating parameters, equipment identifiers and equipment conditions are identified offline and stored in the memory unit 216 and mapped to the different configurations. As an example, when a peak spectral value in the drive current is larger than a corresponding pre-determined threshold value, an abnormal drive current is identified. In such a scenario, the processor unit 214 may determine an unbalance condition in the electric drive. In other embodiments, abnormality of operating parameters may be determined by other statistical processing of the first dataset. Further, it is envisaged that the condition of the electric drive may be determined based on more than one abnormal operating parameters, and performance indicators.

[0027] If all the operating parameters (and/or performance indicators) are found to be normal by the processor unit 214, then all equipment in the industrial system 242 are considered to be operating in the normal condition. In such a scenario, the processor unit 214 is configured to continue processing of the first dataset till an abnormal value is found in any one of the operating parameters.

[0028] The processor unit 214, upon determination of an abnormal condition of the electric drive, is configured to retrieve the second configuration 228 based on the determined condition of the first electric equipment (electric drive) 204. The second configuration includes one or more operating parameters 220 necessary to determine a condition of the industrial system 242 with an enhanced confidence level or better accuracy. Then, the processor unit 214 is configured to initiate acquisition of the second dataset 232 corresponding to the second configuration. Here, the processor unit 214 is configured to acquire data corresponding to the electric equipment using the second configuration as first part of the second dataset 232. Specifically, the processor unit 214 is configured to identify the supplementary data or operating parameters 224 corresponding to the electric equipment 204 which are not part of the first subset of operating parameters 222. Further, the processor unit 214 is configured to acquire, using the second data logger 212 to generate the supplementary dataset 234 corresponding to the supplementary operating parameters included in the second configuration. Then, the processor unit 214 is configured to generate the first part 238 of the second dataset 232 by combining the supplementary dataset 234 suitably with the first dataset 230 using the information in the second configuration. In one embodiment, the performance indicator parameters corresponding to the first dataset may be considered while generating the first part 238 of the second dataset 232.

[0029] Further, the processor unit 214 is also configured to communicate a list of operating parameters of the second electric equipment (electric motor) 244 that is specified in the second configuration to the condition monitoring device 206 and initiates acquisition of second part 236 of the second dataset by the remote condition monitoring device 206. In some embodiments, the processor unit 214 is configured to enable transfer of the first part 238 and optionally the second part 236 to the system analyzer 208. The second dataset 232 facilitates to generate a precise condition of at least one of the equipment of the industrial system 242 at the system analyzer 208. In one embodiment, the system analyzer 208 is configured to perform combined processing of the second dataset to determine a condition of at least one of the motor 244 and the electric drive 204.

[0030] FIG. 3 is a diagrammatic illustration of a condition monitoring system 300 with internal details of a system analyzer 302 in accordance with an exemplary embodiment. It may be noted that the system analyzer 302 is communicatively coupled with a first industrial system having an electric drive 304 and an electric motor 310 and a second industrial system having an electric drive 306 and a motor 308 as explained previously with reference to FIG. 1 and FIG. 2. The system analyzer 302 is also communicatively coupled to a human-machine interface (HMI) device 312 configured to receive a precise condition of at least one of the equipment 304, 310. The system analyzer 302 includes an analytics generator 314, a database unit 316, a server unit 318 and a data fuser 320 communicatively coupled with each other as shown by 322.

[0031] The data fuser 320 is communicatively coupled to the electric drive 304 and the electric motor 310 of the first industrial system and configured to utilize the dataset received from one equipment or combine the datasets received from both the equipment to generate the second dataset. The analytics generator 314 is configured to generate advanced analytics using the second dataset as received from one equipment, or the datasets received from different equipment. In one embodiment, the analytics generator 314 is configured to employ machine learning techniques to generate advanced analytics. In another embodiment, the analytics generator 314 is configured to employ deep learning techniques to generate the advanced analytics. The analytics generator is also able to perform one or more statistical analysis such as, but not limited to, regression, classification and trend analysis. The database unit 316 is configured to store historical data from the industrial systems, data driven models used by various machine learning and deep learning techniques, and structural parameters of models used by the analytics generator 314. The server unit 318 is able to provide computational support to generate advanced analytics, train or retrain the computationally intensive machine learning models and perform combined processing of large number of operating parameters in the second dataset sampled at higher rates.

[0032] FIG. 4 is a schematic 400 illustrating a two-stage architecture of the condition monitoring system with an alternate configuration of the condition monitoring device in accordance with an exemplary embodiment. The schematic 400 shows an electric drive 402 monitored by a condition monitoring device 406 and an electric motor 404 monitored by a second condition monitoring device (not shown in FIG. 4) as the first stage of the two-stage architecture. The condition monitoring device 406 is coupled to the electric drive 402 and includes a data logger 408 interconnected with a processor unit 410 via a communications bus 418. The condition monitoring device 406 is also communicatively coupled to a system analyzer 414 as well as to a remote data logger 412 of the second condition monitoring device monitoring the electric motor 404. The remote data logger 412 is also connected to the system analyzer 414. The condition monitoring device 406 (and the remote data logger 412) in conjunction with the system analyzer 414 forms a second stage of the two-stage architecture in the schematic 400.

[0033] In this embodiment, the data logger 408 generates the first dataset and the processor unit 410 is configured to determine a first condition(s) of the electric drive 402 as part of the first stage of processing. The data logger 408 is also configured to generate either whole of the second dataset or a first part of the second dataset as part of the second stage of processing. As part of the second stage of processing, the condition monitoring device 406 is configured to establish communication with the remote condition monitoring device as per the condition, and initiate acquisition of a second part of the second dataset via the remote data logger 412. The remote data logger 412 is further configured transfer the second part of the data to the system analyzer 414 for determining at least one of a second condition of the electric drive 402 and a condition of the electric motor 404. The condition determined by the system analyzer 414 is provided to an human machine interface (HMI) device 416. The HMI device 416 may be a display device configured to display the determined condition, an audio device configured to generate an audio signal representative of the determined condition, or a printer device configured to printout a report of the determined condition.

[0034] FIG. 5 is a flow chart 500 of a method of monitoring condition of electric equipment in an industrial system in accordance with an exemplary embodiment. The method 500 includes acquiring a first dataset corresponding to a first configuration as illustrated in step 502. The step 502 of acquiring the first dataset is performed by a data logger of a condition monitoring device configured to monitor the electric drive. The first configuration is characterized by a first subset of operating parameters among a plurality of operating parameters of the industrial system. In an embodiment considered herein, the industrial system corresponds to a power plant having an electric drive and an electric motor. The equipment referred herein corresponds to the electric drive although the method of condition monitoring is equally applicable to the electric motor. The plurality of operating parameters is obtained from a plurality of sensors disposed on equipment of the industrial system. The first configuration is further characterized by a first set of sampling rate values corresponding to the first subset of operating parameters. The first subset of operating parameters corresponds to the electric equipment.

[0035] In one example, an operating parameter of the electric drive is an unbalance current. In another example, an operating parameter of the electric motor is vibration data. Another example for operating parameter of the electric motor is a motor current. The first subset of operating parameters may include, but not limited to, bearing condition parameter, DC bus voltage, and supply voltage, and a surface temperature of the motor. In one embodiment, the step 502 of acquiring the first dataset includes obtaining a pre-set configuration from a memory unit. The pre-set configuration includes the first subset of operating parameters and the first set of sampling rate values. The step 502 also includes sampling the first subset of operating parameters with corresponding sampling rate values from the first set of sampling rate values to generate the first dataset.

[0036] The method 500 further includes determining an equipment condition as step 504 based on a comparison of a performance indicator derived from the first dataset with a corresponding reference value. The equipment condition is determined by a processor unit of the condition monitoring device configured to monitor the electric drive. The step 504 of determining the equipment condition includes generating at least one performance indicator by processing the first dataset. The step 504 further includes comparing the at least one performance indicator with a corresponding predetermined threshold value. The step 504 of determining the equipment condition also includes selecting the equipment condition based on the comparison.

[0037] In the example of unbalance current parameter, the current sample values are compared with a predetermined current threshold value as part of the first stage analysis. When the current sample value is greater than the predetermined current threshold value, an unbalance current condition in the electric drive is detected. In another example, sequence analysis of the motor current data provides an indication of a turn-to-turn fault and a phase to ground fault. In a further example, motor current signature analysis may determine mechanical problems.

[0038] At step 506, the method 500 includes identifying a second configuration based on the equipment condition. The second configuration is characterized by at least one of a second sampling rate for at least one of the first subset of operating parameters, and a second subset of operating parameters. The step 506 of identifying the second configuration further includes retrieving a mapping of the second subset of operating parameters and a second set of sampling rate values corresponding to the second subset of operating parameters.

[0039] In one example of a second stage analysis, when an electric drive condition is detected, the second configuration specifying the second subset of operating parameters is identified using the detected electric drive condition. In this example, the second subset of operating parameters includes drive current, DC bus voltage of the electric drive, motor current and motor vibration with corresponding higher sampling rate values, supply voltage. In another example, when a bearing condition of the electric motor is detected, the second configuration specifying motor current and motor vibration is identified. In yet another example, when skin-temperature condition of the motor is detected, the second configuration specifying motor current to be acquired from the electric drive, motor temperature, motor skin temperature at a lower sampling rate value is identified.

[0040] The method 500 includes initiating acquisition of the second dataset corresponding to the second configuration as illustrated in step 508. The step 508 of initiating acquisition of the second dataset includes acquiring, by the data logger, data corresponding to the electric equipment using the second configuration. The acquired data corresponding to the electric equipment is referred herein as first part of the second dataset. Further, the step 508 includes transferring, by the data logger, the first part of the second dataset to the system analyzer. The step 508 also includes communicating, by the processor unit, the second configuration to a second condition monitoring device coupled to a second equipment of the industrial system. Optionally, the step 508 includes enabling the second condition monitoring device for acquisition of data corresponding to the second equipment using the second configuration. The acquired data corresponding to the second equipment is referred herein as the second part of the second dataset. The step 508 also includes transferring the second part of the second dataset to the system analyzer.

[0041] The method 500 also includes transferring 510 the second dataset for generating an equipment fault presented via a human-machine interface. The step 510 of transferring includes combined processing of the second dataset by the system analyzer to determine a condition of at least one of the motor and the electric drive.

[0042] As an example, when an electric drive condition is detected, a machine learning based classifier is used on performance indicators derived from spectral analysis of motor current, sequence analysis of motor current, DC bus voltage analysis and motor current signature analysis to determine root cause of the unbalance condition from the electric drive. In another example, when a bearing condition is detected in the first stage of analysis, machine learning classifier is used on performance indicators derived from resonant frequency values from the electric drive, motor current values to determine if remedial action of strengthening the motor mounting is required. In yet another example, when a temperature condition of the motor is detected in the first stage of analysis, performance indicators derived using correlation analysis between the motor skin temperature and estimated motor temperature, motor current signature analysis, may be used to determine the root cause of the motor. The second stage analysis is able to identify if the temperature condition of the motor corresponds to one of the overloading of motor, high ambient temperature, a poor cooling of the motor or high harmonic condition in the motor current.