A method for predicting incipient faults in electrical equipment

Abstract

The present disclosure relates to method of predicting incipient faults in electrical equipment (102). The method comprises receiving values of primary parameters from primary datasets associated with electrical equipment (102), generating scenarios corresponding to incipient faults associated with electrical equipment (102), using virtual representation model (106) of electrical equipment (102), where scenarios are generated by varying values of pre-defined parameters of electrical equipment (102) with respect to pre-defined conditions corresponding to incipient faults, determining, effect of each of scenarios on values of primary parameters, estimating atypical parameters for each scenario based on effect and primary parameters, estimating secondary datasets corresponding to each scenario, using primary datasets, where secondary datasets are estimated based on primary parameters and atypical parameters, predicting at least one incipient fault using an Artificial Intelligence (AI) model (108) trained based on primary datasets and secondary datasets of electrical equipment (102).

Description

TITLE: “A METHOD FOR PREDICTING INCIPIENT FAULTS IN ELECTRICAL EQUIPMENT”TECHNICAL FIELD

[0001] The present disclosure generally relates to data analytics in electrical equipment. More particularly, the present disclosure relates to a method for predicting incipient faults in the electrical equipment.BACKGROUND

[0002] Electrical equipment is an equipment used for generation, conversion, transmission, distribution, or utilization of electric energy. Examples of such electrical equipment includes electric machines, motors, transformers, switchgear, measuring instruments, protective devices, and the like. The electrical equipment is expected to work with high availability and reduced downtime. A failure or fault in the electrical equipment affects the availability of the electrical equipment. One such fault in the electrical equipment includes incipient faults. Incipient faults are faults that slowly develop in time, leading to process failure. Therefore, it is required to predict such incipient faults so that necessary corrective actions are taken to prevent outages and reduce down times.

[0003] Conventional fault prediction techniques use data analytic techniques such as Artificial Intelligence (Al) systems to predict the incipient faults in the electrical equipment. The Al systems require a large amount of data including multiple input parameters of the electrical equipment to accurately predict the incipient faults in the electrical equipment. However, it is quite difficult to receive data of the electrical equipment including multiple input parameters in industries such as power industries. The electrical equipment includes input parameters which are not measurable or difficult to measure in particular industrial environments. Hence, only limited parameters such as current and voltage are provided as input parameters to the Al systems. This reduces accuracy of the Al systems in predicting the incipient faults in the electrical equipment.

[0004] The information disclosed in this background of the disclosure section is only for enhancement of understanding of the general background of the invention, and it should not betaken 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

[0005] In an embodiment, the present disclosure discloses a method of predicting incipient faults in electrical equipment. The method comprises receiving values of one or more primary parameters from primary datasets associated with an electrical equipment. Further, the method comprises generating a plurality of scenarios, corresponding to a plurality of incipient faults associated with the electrical equipment, using a virtual representation model of the electrical equipment. The plurality of scenarios is generated by varying values of a plurality of pre-defined parameters of the electrical equipment with respect to one or more pre-defined conditions corresponding to the plurality of incipient faults. The method comprises determining an effect of each of the plurality of scenarios on the values of the one or more primary parameters. Furthermore, the method comprises estimating one or more atypical parameters for each scenario of the plurality of scenarios, based on the determined effect and the one or more primary parameters. The method comprises estimating secondary datasets corresponding to each of the plurality of scenarios, using the primary datasets. The secondary datasets are estimated based on the one or more primary parameters and the one or more atypical parameters. Thereafter, the method comprises predicting at least one incipient fault of the plurality of incipient faults using an Artificial Intelligence (Al) model associated with the electrical equipment. The Al model is trained based on the primary datasets and the secondary datasets of the electrical equipment.

[0006] In an embodiment, the one or more primary parameters comprises at least one of, electrical parameters and mechanical parameters of the electrical equipment.

[0007] In an embodiment, the virtual representation model is disconnected from the electrical equipment.

[0008] In an embodiment, the one or more atypical parameters and the secondary datasets are estimated using a Kalman Filter. In an embodiment, the Kalman Filter is tuned with one or more primary parameters and the one or more atypical parameters of an electrical equipment.

[0009] In an embodiment, the method comprises performing a mitigation action, based on a severity level associated with the at least one incipient fault, upon predicting the at least one incipient fault.

[0010] In an embodiment, the method is implemented in one of, the electrical equipment, an edge platform, and a cloud platform.

[0011] In an embodiment, the one or more primary parameters comprise measurable parameters of the electrical equipment, and the one or more atypical parameters comprise derived parameters of the electrical equipment that are not measurable.

[0012] In an embodiment, the present disclosure discloses a method of predicting incipient faults in electrical equipment. The method comprises receiving values of one or more primary parameters from primary datasets associated with an electrical equipment. Further, the method comprises generating a plurality of scenarios, corresponding to a plurality of incipient faults associated with the electrical equipment, by varying values of a plurality of pre-defined parameters of the electrical equipment. Furthermore, the method comprises estimating one or more atypical parameters for each scenario of the plurality of scenarios, based on the one or more primary parameters and an effect of the plurality of scenarios on the one or more primary parameters. Thereafter, the method comprises estimating secondary datasets corresponding to each of the plurality of scenarios, using the primary datasets. The secondary datasets are estimated based on the one or more primary parameters and the one or more atypical parameters. The primary datasets and the secondary datasets are used for training an Artificial Intelligence (Al) model to predict at least one incipient fault of the plurality of incipient faults.

[0013] 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.BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWINGS

[0014] The novel features and characteristics of the disclosure are set forth in the appended claims. The disclosure itself, however, as well as a preferred mode of use, further objectives, and advantages thereof, will best be understood by reference to the following detailed description ofan illustrative embodiment when read in conjunction with the accompanying figures. One or more embodiments are now described, by way of example only, with reference to the accompanying figures wherein like reference numerals represent like elements and in which:

[0015] Figure 1 illustrates an exemplary environment for predicting incipient faults in electrical equipment, in accordance with some embodiments of the present disclosure;

[0016] Figure 2 shows an exemplary flow chart illustrating method steps for predicting incipient faults in electrical equipment, in accordance with some embodiments of the present disclosure;

[0017] Figure 3 shows exemplary illustration for estimating one or more atypical parameters and secondary datasets, in accordance with some embodiments of the present disclosure;

[0018] Figures 4A-4D show exemplary illustrations for estimating one or more atypical parameters, in accordance with some embodiments of the present disclosure;

[0019] Figure 5 illustrates a detailed diagram of a system for predicting incipient faults in electrical equipment, in accordance with some embodiments of the present disclosure; and

[0020] Figure 6 illustrates a block diagram of an exemplary computer system for predicting incipient faults in electrical equipment, in accordance with some embodiments of the present disclosure.

[0021] It should be appreciated by those skilled in the art that any block diagram herein represents conceptual views of illustrative systems embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudo code, and the like represent various processes which may be substantially represented in computer readable medium and executed by a computer or processor, whether or not such computer or processor is explicitly shown.DETAILED DESCRIPTION

[0022] 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 subjectmater described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0023] 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 alternatives falling within the scope of the disclosure.

[0024] 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 system or apparatus proceeded by “comprises ... a” does not, without more constraints, preclude the existence of other elements or additional elements in the system or apparatus.

[0025] The term “one or more primary parameters” refers to measurable parameters of an electrical equipment.

[0026] The term “primary datasets” refers to measurable data of the electrical equipment and design data of the electrical equipment.

[0027] The term “virtual representation model” refers to a virtual replica of the electrical equipment used for, but not limited to, simulation, integration, testing, monitoring, and maintenance of the electrical equipment.

[0028] The term “plurality of pre-defined parameters” refers to fault-specific parameters and operational parameters of the electrical equipment.

[0029] The term “one or more pre-defined conditions” refers to conditions that are defined to predict specific incipient faults in the electrical equipment.

[0030] Generally, failures or faults occur in an electrical equipment which affects the availability of the electrical equipment. One such fault in the electrical equipment includes incipient faults which slowly develop in time, leading to process failure. It is required to predict such incipient faults so that necessary corrective actions are taken to prevent outages and reduce down times.

[0031] Accordingly, the present disclosure provides a method for predicting incipient faults in electrical equipment. The present disclosure generates multiple scenarios corresponding to different incipient faults in the electrical equipment. The present disclosure determines an effect of these scenarios corresponding to the incipient faults on primary parameters (or measurable parameters). Then, the present disclosure uses the determined effect to estimate atypical parameters (or non-measurable parameters) associated with the electrical equipment. The present disclosure enables generation of multiple datasets corresponding to different scenarios based on the primary parameters and estimated atypical parameters. Hence, the present disclosure enables generating meaningful input parameters from available limited measurements. These multiple datasets including the estimated atypical parameters are additionally provided to Al systems, which increases accuracy of the Al systems in predicting the incipient faults in the electrical equipment.

[0032] Figure 1 illustrates an exemplary environment 100 for predicting incipient faults in electrical equipment, in accordance with some embodiments of the present disclosure. The exemplary environment 100 comprises an electrical equipment 102, a processor 104, a virtual representation model 106 associated with the electrical equipment 102, and an Artificial Intelligence (Al) model 108. The electrical equipment 102 includes an equipment used for generation, conversion, transmission, distribution, or utilization of electric energy. Examples of the electrical equipment 102 include generators, motors, transformers, switchgear, measuring instruments, protective devices, and the like. A person skilled in the art will appreciate that the electrical equipment 102 may comprise equipment other than the above-mentioned equipment. Faults may occur in the electrical equipment 102 which affects the availability of the electrical equipment 102. One such fault in the electrical equipment 102 includes incipient faults. The incipient faults are faults that slowly develop in time, leading to process failure. It is required to predict such incipient faults so that necessary corrective actions are taken to prevent outages and reduce down times. In the present disclosure, the processor 104 is used to predict the incipient faults in the electrical equipment 102. The processor 104 may be implemented in any computing device such as, a laptop computer, a desktop computer, a Personal Computer (PC), a notebook, asmartphone, a tablet, a server, a network server, a cloud-based server, an edge computing device, a processing device, router, and the like. The processor 104 may be part of a system. The system may be implemented in an edge platform, a cloud platform, or the electrical equipment 102.

[0033] Herein, the processor 104 receives values of one or more primary parameters from primary datasets associated with the electrical equipment 102. The one or more primary parameters may refer to measurable parameters of the electrical equipment 102. The measurable parameters may include parameters that may be measured in a specific industrial environment. The one or more primary parameters may comprise at least one of, electrical parameters and mechanical parameters of the electrical equipment 102. For example, the one or more primary parameters may include a current and a voltage of the electrical equipment 102. The primary datasets may comprise measurable data of the electrical equipment 102 and design data of the electrical equipment 102. For example, the primary datasets may comprise measurable data such as values of current and voltage of the electrical equipment 102 and the design data such as a current rating, a voltage rating, an electrical load rating, and so on.

[0034] Further, the processor 104 generates a plurality of scenarios, corresponding to a plurality of incipient faults associated with the electrical equipment 102, using a virtual representation model 106 of the electrical equipment 102. The virtual representation model 106 refers to a virtual replica of the electrical equipment 102 used for, but not limited to, simulation, integration, testing, monitoring, and maintenance of the electrical equipment 102. For instance, the virtual representation model 106 may include a digital twin of the electrical equipment 102. The processor 104 generates the plurality of scenarios by varying values of a plurality of pre-defined parameters of the electrical equipment 102 with respect to one or more pre-defined conditions corresponding to the plurality of incipient faults. The plurality of pre-defined parameters may comprise faultspecific parameters and operational parameters of the electrical equipment 102. For example, number of turns of coil, load, etc. The one or more pre-defined conditions may refer to conditions which are defined to predict specific incipient faults. For example, a pre-defined condition may include a value of a variable of the electrical equipment 102 being greater than a threshold value leading to a specific fault. Considering the electrical equipment 102 as a motor, for example, the processor 104 may generate a scenario corresponding to a broken rotor bar fault by varying a number of rotor bars of the motor that are broken from 1 to 6. In an embodiment, the virtual representation model 106 may be disconnected from the electrical equipment 102, while generating the plurality of scenarios. In the present disclosure, the virtual representation model106 is disconnected from the electrical equipment 102 to generate multiple scenarios by providing varying values of the plurality of pre-defined parameters of the electrical equipment 102 rather than field data or actual real-time data of the electrical equipment 102.

[0035] Then, the processor 104 may determine an effect of each of the plurality of scenarios on the values of the one or more primary parameters. For instance, in the above example, the processor 104 may determine the effect of four broken rotor bars in the motor on values of current of the motor. The processor 104 may estimate one or more atypical parameters for each scenario of the plurality of scenarios, based on the determined effect and the one or more primary parameters. The atypical parameters refer to parameters corresponding to non- measurable / derived parameters with respect to a specific industrial implementation of the electrical equipment 102. For example, an industry may not have speed sensors to measure the speed of the motor. In such a case, it may be difficult to receive data related to the speed of the motor. The speed may be considered as atypical parameter in such industry. In another example, an industry may not have sensors to measure an airgap flux. In such a case, it may be difficult to receive data related to the airgap flux in the motor. The airgap flux may be considered as atypical parameter in such industry. The processor 104 may estimate the one or more atypical parameters using a Kalman Filter. Particularly, the processor 104 provides the determined effect of the plurality of scenarios on the one or more primary parameters along with the one or more primary parameters to the Kalman filter, to estimate atypical. The Kalman Filter is tuned with the one or more primary parameters and the one or more atypical parameters of the electrical equipment 102.

[0036] The processor 104 estimates secondary datasets corresponding to each of the plurality of scenarios, using the primary datasets, based on the one or more primary parameters and the one or more atypical parameters. The processor 104 estimates the secondary datasets using the Kalman filter. The Kalman filter estimates additional datasets (the secondary datasets) corresponding to different scenarios, by using the one or more primary parameters and the one or more atypical parameters. Then, the processor 104 predicts an incipient fault using the Al model 108 associated with the electrical equipment 102. In an example, the Al model 108 may include a Random Forest classifier. The Al model 108 may provide an output 110 including the predicted incipient fault to a user. For example, the Al model 108 may display the predicted incipient fault to an operator on a user interface such as a dashboard. In the present disclosure, the Al model 108 is trained based on the primary datasets and the secondary datasets . The trained Al model 108 may be used in realtime to predict an incipient fault in the electrical equipment 102. In real-time, the one or moreprimary parameters (measurable parameters such as a voltage and a current of the electrical equipment 102) are continuously monitored. The one or more primary parameters are used to generate secondary datasets. An enhanced dataset including the primary datasets and the secondary datasets are provided to the trained Al model 108 to predict and output real time condition of the electrical equipment 102. The use of the enhanced dataset increases accuracy of the Al model 108 in predicting the incipient faults in the electrical equipment 102. The processor 104 may perform a mitigation action, based on a severity level associated with the at least one incipient fault.

[0037] In one implementation, the processor 104 may be part of a system implemented in an edge platform. In such embodiment, the processor 104 may estimate the secondary datasets in an edge device . In an embodiment, the Al model 108 may be implemented in the edge device for predicting the incipient faults using the primary datasets and the secondary datasets. In another embodiment, the Al model 108 may be implemented in the electrical equipment 102 or a cloud server. In this case, the processor 104 may transmit the primary datasets and the secondary datasets to the Al model 108 for predicting the incipient faults in the electrical equipment 102. In another implementation, the processor 104 may be part of a system implemented in a cloud computing platform. In such embodiment, the processor 104 may estimate the secondary datasets in the cloud server. In an embodiment, the Al model 108 may be implemented in the cloud server for predicting the incipient faults in the electrical equipment 102. In another embodiment, the Al model 108 may be implemented in the electrical equipment 102 or the edge device. In this case, the processor 104 may transmit the primary datasets and the secondary datasets to the Al model 108 for predicting the incipient faults in the electrical equipment 102. In another implementation, the processor 104 may be implemented in the electrical equipment 102. In an embodiment, the Al model 108 may be implemented in the electrical equipment 102 for predicting the incipient faults in the electrical equipment 102. In another embodiment, the Al model 108 may be implemented in the edge device or the cloud server. In this case, the processor 104 may transmit the primary datasets and the secondary datasets to the Al model 108 for predicting the incipient faults in the electrical equipment 102.

[0038] Figure 2 shows an exemplary flow chart illustrating method steps for predicting the incipient faults in the electrical equipment 102, in accordance with some embodiments of the present disclosure. As illustrated in Figure 2, the method 200 may comprise one or more steps. The method 200 may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components,data structures, procedures, modules, and functions, which perform particular functions or implement particular abstract data types.

[0039] The order in which the method 200 is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method. Additionally, individual blocks may be deleted from the methods without departing from the scope of the subject matter described herein. Furthermore, the method can be implemented in any suitable hardware, software, firmware, or combination thereof.

[0040] At step 201, values of one or more primary parameters are received from primary datasets associated with the electrical equipment 102. The one or more primary parameters may refer to measurable parameters of the electrical equipment 102. The measurable parameters may include parameters that may be measured in a specific industrial environment. For example, in a power industry, parameters such as current and voltage may be measurable parameters. The one or more primary parameters may comprise at least one of, electrical parameters and mechanical parameters of the electrical equipment 102. For example, considering the electrical equipment 102 as a motor, the one or more primary parameters may include electrical parameters such as a current and a voltage of the motor and mechanical parameters such as a torque of the motor. In another example, considering the electrical equipment 102 as a transformer, the one or more primary parameters may include electrical parameters such as a current and a voltage on at least one terminal of the transformer, and mechanical parameters such as dimensions of a core of the transformer.

[0041] The primary datasets may comprise measurable data of the electrical equipment 102 and design data of the electrical equipment 102. In an embodiment, the measurable data of the electrical equipment 102 may be available field data of the electrical equipment 102. The available field data may include multiple datasets comprising values of the one or more primary parameters. For example, considering the electrical equipment 102 as a motor, the primary datasets may comprise measurable data such as values of current and voltage of the motor. The design data of the motor may include a current rating, a voltage rating, an electrical load rating, and so on. In another example, considering the electrical equipment 102 as a transformer, the design data may include core magnetic properties of the transformer. A person skilled in the art will appreciate that the design data may include data / parameters other than the above-mentioned data / parameters, depending on a type of the electrical equipment 102. The values of the one or more primary parameters may be received from each dataset of the primary datasets. Considering the abovestated example, current values and voltage values of the motor may be received. In an embodiment,each dataset may include the values of the one or more primary parameters in form of a graph. For example, a dataset may include the values of the current of the motor over a period of time in the form of a time-series graph. Pre-processing may be performed to retrieve the values of the one or more primary parameters from the graph. A person skilled in the art will appreciate that the one or more primary parameters may be in any other forms in the one or more primary datasets.

[0042] At step 202, a plurality of scenarios corresponding to a plurality of incipient faults associated with the electrical equipment 102 may be generated. Herein, the plurality of incipient faults associated with the electrical equipment 102 maybe identified. In an embodiment, a user associated with the electrical equipment 102 may identify the plurality of incipient faults associated with the electrical equipment 102. For example, the user may be an operator of the electrical equipment 102. The user may identify the plurality of incipient faults based on historical data associated with the electrical equipment 102 or using a domain knowledge of the electrical equipment 102. In an example, considering the electrical equipment 102 as a motor, the plurality of incipient faults may include, voltage unbalance, broken rotor bar, stator intertum, and the like. The plurality of scenarios corresponding to the plurality of incipient faults may be generated using the virtual representation model 106 of the electrical equipment 102. In an example, considering the electrical equipment 102 as a motor, the virtual representation model 106 may include a digital twin of the motor.

[0043] The plurality of scenarios may be generated by varying values of a plurality of pre-defined parameters of the electrical equipment 102 with respect to one or more pre-defined conditions corresponding to the plurality of incipient faults. The plurality of pre-defined parameters may comprise fault-specific parameters and operational parameters of the electrical equipment 102. The plurality of pre-defined parameters is considered to determine a behaviour of the electrical equipment 102 for different fault-specific parameters and operational parameters. In an example, considering the electrical equipment 102 as a motor, the fault-specific parameters may include a number of broken bars of a rotor associated with a motor, a speed of the motor, a torque of the motor, and the like. The operational parameters may include a load of the motor, a type of load, a moment of inertia of rotor associated with the motor, and the like.

[0044] The one or more pre-defined conditions may refer to conditions which are defined to predict specific incipient faults. In an example, the one or more pre-defined conditions may be set by a user based on a nature of an incipient fault. Consider the incipient fault to be a broken rotor bar fault, the user may define a ratio of number of rotor bars that are broken and a total number of rotorbars of the motor. In an example, considering the number of rotor bars as 30, the number of rotor bars for occurrence of a fault may be 5. Considering the number of rotor bars as 50, the number of rotor bars for occurrence of a fault may be 10. The plurality of scenarios may be generated by varying values of the plurality of pre-defined parameters of the electrical equipment 102 with respect to the one or more pre-defined conditions corresponding to the plurality of incipient faults. Considering the electrical equipment 102 as a motor, for example, a scenario corresponding to a broken rotor bar fault may be generated by varying a number of broken rotor bars of the motor from ‘ 1’ to ‘6’, varying a load from no load to full load, and the like. A scenario corresponding to a stator intertum short circuit fault may be generated by varying a number of short-circuited turns of the motor from 1% to 5%, varying a load from no load to full load, and the like. In another example, considering the electrical equipment 102 as a transformer, a scenario corresponding to a winding turn to turn short circuit fault may be generated by varying a number of winding turns that are shorted. A scenario corresponding to a tank fault may be generated by varying oil levels in a tank associated with the transformer.

[0045] The varying values of the plurality of pre-defined parameters corresponding to each incipient fault may be provided to the virtual representation model 106 to generate the plurality of scenarios. In an embodiment, the virtual representation model 106 may be disconnected from the electrical equipment 102, while generating the plurality of scenarios. Generally, a difficulty may exist to simulate different incipient faults in an actual electrical equipment 102. Hence, in the present disclosure, the virtual representation model 106 is disconnected from the electrical equipment 102 to generate the plurality of scenarios rather than field data or actual real-time data of the electrical equipment 102. Referring to Figure 3, the virtual representation model 106 may generate the plurality of scenarios by varying the plurality of pre-defined parameters obtained from a database 304 of the electrical equipment 102. Figures 4A-4D illustrate the plurality of scenarios generated for a motor. Each of the plurality of scenarios corresponds to a healthy scenario, a voltage unbalance scenario, a broken rotor bar scenario, a stator intertum scenario, respectively. In Figures 4A-4D, ‘ids’ refers to stator current direct axis component, ‘iqs’ refers to stator current quadrature axis component, ’c])dr' refers to rotor flux direct axis component, ‘(j)qr’ refers to rotor flux quadrature axis component, and ‘co’ refers to speed of the motor.

[0046] Referring back to Figure 2, at step 203, an effect of each of the plurality of scenarios on the values of the one or more primary parameters may be determined. The effect of each of the plurality of scenarios on the values of the one or more primary parameters may be determined based on anoutput of the virtual representation model 106. For example, considering the scenario being generated by varying the load of the motor from no load to full load, an effect of the varying load may be determined on the current and the voltage of the motor. Further, considering the scenario being generated by varying the number of broken rotor bars of the motor from 1 to 6, an effect of the varying load may be determined on the current and the voltage of the motor. In the present disclosure, the effect of the plurality of scenarios on the one or more primary parameters may be determined to understand the behaviour of the electrical equipment 102 for different scenarios.

[0047] At step 204, one or more atypical parameters may be estimated for each scenario of the plurality of scenarios. The one or more atypical parameters comprise derived parameters of the electrical equipment 102 that are not measurable. The one or more atypical parameters may comprise non-measurable parameters with respect to a specific industrial environment in which the electrical equipment 102 is implemented. Consider an example of an industry in which speed sensors may be implemented to monitor a speed of a motor. In such a case, the speed may be a measurable parameter. However, in absence of such speed sensors, the speed may be an atypical or non-measurable parameter. In another example, an airgap flux in the motor may be difficult to measure from available field data. In such a case, the airgap flux may be an atypical parameter.

[0048] The one or more atypical parameters may be estimated for each scenario of the plurality of scenarios, based on the determined effect and the one or more primary parameters. Referring again to Figure 3, the one or more atypical parameters may be estimated using an estimator 302. In an embodiment, the estimator 302 may include a Kalman filter. The Kalman filter is an estimation technique in which a series of measurements observed over time are used, including statistical noise and other inaccuracies, and estimates of unknown variables are determined. In an embodiment, the estimation of the one or more atypical parameters may be performed using an Extended Kalman Filter. In another embodiment, the estimation of the one or more atypical parameters may be performed using Cubature Kalman Filter. In yet another embodiment, the estimation of the one or more atypical parameters may be performed using a Gaussian - sum filter. A person skilled in the art will appreciate that any other estimation techniques may be used to estimate the one or more atypical parameters.

[0049] Generally, the one or more primary parameters are provided to the Kalman filter to estimate data from the primary datasets. In the present disclosure, the determined effect and the one or more primary parameters are provided to the Kalman filter. The Kalman filter estimates the one or more atypical parameters based on the determined effect and the one or more primary parameters. Forexample, consider the one or more primary parameters as the current and the voltage of the motor. The Kalman filter considers the voltage and the current of the motor along with the determined effect of the plurality of scenarios on the current and the voltage. For instance, waveforms of the current and the voltage may vary for different scenarios. The Kalman filter considers varied waveforms of the current and the voltage. The Kalman filter may estimate the one or more atypical parameters such as a speed and an airgap flux of the motor, based on initial waveforms and the varied waveforms of the current and the voltage. Referring again to Figure 4A-4D, estimated parameters by the Kalman filter for various scenarios are shown in form of time-series waveforms. The time-series waveforms are shown for illustration purposes only and are not limited to such a form of representation of the estimated parameters. Hence, the present disclosure extends data estimated by the Kalman filter to additional parameters of the electrical equipment 102 other than the one or more primary parameters.

[0050] Referring back to Figure 2, at step 205, secondary datasets corresponding to each of the plurality of scenarios may be estimated, using the primary datasets. In an embodiment, the secondary datasets may be estimated using the Kalman Filter. The Kalman filter may estimate the secondary datasets based on the one or more primary parameters and the one or more atypical parameters. The Kalman Filter may be tuned with the one or more primary parameters and the one or more atypical parameters of the electrical equipment 102. The tuning of the Kalman filter may refer to defining the one or more primary parameters and the one or more atypical parameters. In an example, consider the one or more primary parameters includes the voltage and the current of the motor, and the one or more atypical parameters includes the speed and the airgap flux of the motor, equations of the voltage, the current, the speed, and the airgap flux may be defined in the Kalman Filter. The Kalman Filter may estimate the secondary datasets corresponding to each scenario, using the primary datasets. For instance, the Kalman Filter may estimate a first secondary dataset corresponding to a first scenario based on a first primary dataset. In an example, the Kalman Filter may receive a primary dataset of the motor, which includes values of the current and the voltage of the motor. The Kalman Filter may estimate a first secondary dataset corresponding to broken rotor bar scenario, using the primary dataset, based on the one or more primary parameters (the voltage and the current of the motor,) and the one or more atypical parameters (the speed and the airgap flux of the motor). In the present disclosure, the Kalman filter is able to estimate multiple datasets corresponding to different fault scenarios. Each dataset of the multiple datasets includes data estimated from the one or more primary parameters and the one or more atypical parameters. Hence, the present disclosure enables estimation of more meaningful datasets corresponding todifferent fault scenarios. Referring again to Figure 3, the secondary datasets estimated may be stored in the database 304.

[0051] Referring back to Figure 2, at step 206, at least one incipient fault of the plurality of incipient faults may be predicted using the Al model 108 associated with the electrical equipment 102. The Al model 108 may be used for predicting the plurality of incipient faults in the electrical equipment 102. Conventionally, an Al model is trained using the primary datasets of the electrical equipment 102. In the present disclosure, the Al model 108 may be trained based on the primary datasets and the secondary datasets of the electrical equipment 102. Hence, the present disclosure enables providing of enhanced datasets to the Al model 108, which increases accuracy of the Al model 108 in predicting the at least one incipient fault in the electrical equipment 102. Upon predicting the at least one incipient fault, a mitigation action may be performed to resolve the at least one incipient fault. In an embodiment, the mitigation action may be performed based on a severity level associated with the at least one incipient fault. For example, multiple levels of severity such as low severity level, medium severity level, and high severity level may be defined. In an example, such severity levels may be defined by an operator based on intensity of at least one incipient fault and effect of the at least one incipient fault in a process associated with the electrical equipment 102. The mitigation action may be performed based on the severity level. For example, when the at least one incipient fault is associated with the low severity level, the at least one incipient fault may be flagged to be reviewed by the operator. When the at least one incipient fault is associated with the high severity level, an alert message may be transmitted to the operator. Referring again to Figure 3, the one or more primary datasets and the one or more secondary datasets may be provided to the Al model 108 for predicting the at least one incipient fault.

[0052] Figure 5 illustrates a detailed diagram 500 of a system 502 implementing the processor 104 for predicting the incipient faults in the electrical equipment 102, in accordance with some embodiments of the present disclosure. The system 502 comprises an Input / Output (I / O) interface 504, a memory 506, and the processor 104. In some embodiments, the memory 506 may be communicatively coupled to the processor 104. The memory 506 stores instructions executable by the processor 104. The processor 104 may comprise at least one data processor for executing program components for executing user or system-generated requests. The memory 506 may be communicatively coupled to the processor 104. The memory 506 stores instructions, executable by the processor 104, which, on execution, may cause the processor 104 to predict the incipient faults in the electrical equipment 102.

[0053] In an embodiment, the memory 506 may include computation data 508 and one or more modules 510. The one or more modules 510 may be configured to perform the steps of the present disclosure using the computation data 508, to predict the incipient faults in the electrical equipment 102. In an embodiment, each of the one or more modules 510 may be a hardware unit which may be outside the memory 506 and coupled with the system 502. As used herein, the term modules 510 refers to an Application Specific Integrated Circuit (ASIC), an electronic circuit, a Field- Programmable Gate Arrays (FPGA), Programmable System-on-Chip (PSoC), a combinational logic circuit, and / or other suitable components that provide described functionality. The one or more modules 510 when configured with the described functionality defined in the present disclosure will result in a novel hardware. Further, the I / O interface 504 is coupled with the processor 104 through which an input signal or / and an output signal is communicated. For example, the system 502 may communicate with the electrical equipment 102 via the I / O interface 504.

[0054] In one implementation, the modules 510 may include, for example, an input module 524, a scenario generation module 526, an effect determination module 528, a data estimation module 530, a fault prediction module 532, and auxiliary modules 534. It will be appreciated that such aforementioned modules 510 may be represented as a single module or a combination of different modules. In one implementation, the computation data 508 may include, for example, input data 512, generation data 514, determination data 516, estimation data 518, prediction data 520, and auxiliary data 522.

[0055] In an embodiment, the input module 524 may be configured to receive values of the one or more primary parameters from the primary datasets associated with the electrical equipment 102. The one or more primary parameters may refer to measurable parameters of the electrical equipment 102. The one or more primary parameters may comprise at least one of, electrical parameters and mechanical parameters of the electrical equipment 102. The primary datasets may comprise measurable data of the electrical equipment 102 and design data of the electrical equipment 102. The input module 524 may receive the values of the one or more primary parameters from each dataset of the primary datasets. In an embodiment, each dataset may include the values of the one or more primary parameters in form of a graph. The input module 524 may perform pre-processing to retrieve the values of the one or more primary parameters from the graph. A person skilled in the art will appreciate that the one or more primary parameters may be in anyother forms in the one or more primary datasets. The values of the one or more primary parameters may be stored as the input data 512 in the memory 506.

[0056] In an embodiment, the scenario generation module 526 may be configured to receive the input data 512 from the input module 524. Further, the scenario generation module 526 may be configured to generate the plurality of scenarios corresponding to the plurality of incipient faults associated with the electrical equipment 102. The scenario generation module 526 may generate the plurality of scenarios corresponding to the plurality of incipient faults using the virtual representation model 106 of the electrical equipment 102. The scenario generation module 526 may generate the plurality of scenarios by varying values of a plurality of pre-defined parameters of the electrical equipment 102 with respect to one or more pre-defined conditions corresponding to the plurality of incipient faults. The plurality of scenarios corresponding to the plurality of incipient faults may be stored as the generation data 514 in the memory 506.

[0057] In an embodiment, the effect determination module 528 may be configured to receive the input data 512 from the input module 524 and the generation data 514 from the scenario generation module 526. Further, the effect determination module 528 may be configured to determine an effect of each of the plurality of scenarios on the values of the one or more primary parameters. The effect determination module 528 may determine the effect of each of the plurality of scenarios on the values of the one or more primary parameters based on an output of the virtual representation model 106. The determined effect may be stored as the determination data 516 in the memory 506.

[0058] In an embodiment, the data estimation module 530 may be configured to receive the input data 512 from the input module 524 and the determination data 516 from the effect determination module 528. Further, the data estimation module 530 may be configured to estimate the one or more atypical parameters for each scenario of the plurality of scenarios. The one or more atypical parameters comprise derived parameters of the electrical equipment 102 that are not measurable. The data estimation module 530 may estimate the one or more atypical parameters based on the determined effect and the one or more primary parameters. In an embodiment, the data estimation module 530 may include a Kalman filter. The Kalman filter estimates the one or more atypical parameters based on the determined effect and the one or more primary parameters. In an embodiment, the data estimation module 530 may be configured to estimate the secondary datasets corresponding to each of the plurality of scenarios, using the primary datasets. In an embodiment, the data estimation module 530 may estimate the secondary datasets using the Kalman Filter. TheKalman Filter may be tuned with the one or more primary parameters and the one or more atypical parameters ofthe electrical equipment 102. The Kalman Filter may estimate the secondary datasets corresponding to each scenario, using the primary datasets. The one or more atypical parameters and the secondary datasets may be stored as the estimation data 518 in the memory 506.

[0059] In an embodiment, the fault prediction module 532 may be configured to receive the input data 512 from the input module 524 and the estimation data 518 from the data estimation module 530. Further, the fault prediction module 532 may be configured to predict the at least one incipient fault of the plurality of incipient faults using the Al model 108 associated with the electrical equipment 102. The Al model 108 may be trained based on the primary datasets and the secondary datasets of the electrical equipment 102. Upon predicting the at least one incipient fault, a mitigation action may be performed to resolve the at least one incipient fault. In an embodiment, the mitigation action may be performed based on a severity level associated with the at least one incipient fault. The predicted at least one incipient fault may be stored as the prediction data 520 in the memory 506.

[0060] The auxiliary data 522 may store data, including temporary data and temporary files, generated by the one or more modules 510 for performing the various functions of the system 502. The one or more modules 510 may also include the auxiliary modules 534 to perform various miscellaneous functionalities of the system 502. The auxiliary data 522 may be stored in the memory 506. It will be appreciated that the one or more modules 510 may be represented as a single module or a combination of different modules.COMPUTER SYSTEM

[0061] Figure 6 illustrates a block diagram of an exemplary computer system 600 for implementing embodiments consistent with the present disclosure. In an embodiment, the computer system 600 may be used to implement the system 502. Thus, the computer system 600 may be used for predicting the incipient faults in the electrical equipment 102. In an embodiment, the computer system 600 may communicate with the electrical equipment 102, the virtual representation model 106, and the Al model 108 over a communication network 618. The computer system 600 may comprise a Central Processing Unit 604 (also referred as “CPU” or “processor”). The processor 604 may comprise at least one data processor. The processor 604 may includespecialized processing units such as integrated system (bus) controllers, memory management control units, floating point units, graphics processing units, digital signal processing units, etc.

[0062] The processor 604 may be disposed in communication with one or more input / output (I / O) devices (not shown) via I / O interface 602. The I / O interface 602 may employ communication protocols / methods such as, without limitation, audio, analog, digital, monoaural, RCA, stereo, IEEE (Institute of Electrical and Electronics Engineers) -1394, serial bus, universal serial bus (USB), infrared, PS / 2, BNC, coaxial, component, composite, digital visual interface (DVI), high- definition multimedia interface (HDMI), Radio Frequency (RF) antennas, S-Video, VGA, IEEE 8O2.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.

[0063] Using the I / O interface 602, the computer system 600 may communicate with one or more I / O devices. For example, the input device 620 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, sensors, etc. The output device 622 may be a printer, fax machine, video display (e.g., cathode ray tube (CRT), liquid crystal display (LCD), light-emitting diode (LED), plasma, Plasma display panel (PDP), Organic light-emitting diode display (OLED) or the like), audio speaker, etc.

[0064] The processor 604 may be disposed in communication with the communication network 618 via a network interface 606. The network interface 606 may communicate with the communication network 618. The network interface 606 may employ connection protocols including, without limitation, direct connect, Ethernet (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. The communication network 618 may include, without limitation, a direct interconnection, local area network (LAN), wide area network (WAN), wireless network (e.g., using Wireless Application Protocol), the Internet, etc. The network interface 606 may employ connection protocols include, but not limited to, direct connect, Ethernet (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, Bluetooth mesh, Zigbee, etc.

[0065] The communication network 618 includes, but is not limited to, a direct interconnection, an e-commerce network, a peer to peer (P2P) network, local area network (LAN), wide area network(WAN), wireless network (e.g, using Wireless Application Protocol), the Internet, Wi-Fi, and such. The first network and the second network may either be a dedicated network or a shared network, which represents an association of the different types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol / Intemet Protocol (TCP / IP), Wireless Application Protocol (WAP), etc., to communicate with each other. Further, the first network and the second network may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices, etc.

[0066] In some embodiments, the processor 604 may be disposed in communication with a memory 610 (e.g., RAM, ROM, etc. not shown in Figure 6) via a storage interface 608. The storage interface 608 may connectto memory 610 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), fiber 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.

[0067] The memory 610 may store a collection of program or database components, including, without limitation, user interface 612, an operating system 614, web browser 616 etc. In some embodiments, computer system 600 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®.

[0068] The operating system 614 may facilitate resource management and operation of the computer system 600. Examples of operating systems include, without limitation, APPLE MACINTOSH11OS X, UNIXR, 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 ), APPLERIOS™, GOOGLERANDROID™, BLACKBERRYROS, or the like.

[0069] In some embodiments, the computer system 600 may implement the web browser 616 stored program component. The web browser 616 may be a hypertext viewing application, for example MICROSOFT11INTERNET EXPLORER™, GOOGLERCHROME™0, MOZILLARFIREFOX™, APPLERSAFARI™, etc. Secure web browsing may be provided using SecureHypertext Transport Protocol (HTTPS), Secure Sockets Layer (SSL), Transport Layer Security (TLS), etc. Web browsers 616 may utilize facilities such as AJAX™, DHTML™, ADOBERFLASH™, JAVASCRIPT™, JAVA™, Application Programming Interfaces (APIs), etc. In some embodiments, the computer system 600 may implement a mail server (not shown in Figure) stored program 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 ASP™, ACTIVEX™, ANSI™ C++ / C#, MICROSOFT11, 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), MICROSOFT11exchange, Post Office Protocol (POP), Simple Mail Transfer Protocol (SMTP), or the like. In some embodiments, the computer system 600 may implement a mail client stored program component. The mail client (not shown in Figure) may be a mail viewing application, such as APPLERMAIL™, MICROSOFT11ENTOURAGE™, MICROSOFT11OUTLOOK™, MOZILLARTHUNDERBIRD™, etc.

[0070] 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, non-volatile memory, hard drives, Compact Disc Read-Only Memory (CD ROMs), Digital Video Disc (DVDs), flash drives, disks, and any other known physical storage media.

[0071] The present disclosure provides a method for predicting incipient faults in electrical equipment. The present disclosure enables generation of multiple datasets corresponding to different scenarios based on the primary parameters and estimated atypical parameters. Hence, the present disclosure enables generating meaningful input parameters from available limited measurements. These multiple datasets including the estimated atypical parameters are additionally provided to Al systems, which increases accuracy of the Al systems in predicting the incipient faults in the electrical equipment.

[0072] The terms "an embodiment", "embodiment", "embodiments", "the embodiment", "the embodiments", "one or more embodiments", "some embodiments", and "one embodiment" mean "one or more (but not all) embodiments of the invention(s)" unless expressly specified otherwise.

[0073] The terms "including", "comprising", “having” and variations thereof mean "including but not limited to", unless expressly specified otherwise.

[0074] The enumerated listing of items does not imply that any or all of the items are mutually exclusive, unless expressly specified otherwise. The terms "a", "an" and "the" mean "one or more", unless expressly specified otherwise.

[0075] A description of an embodiment with several components in communication with each other does not imply that all such components are required. On the contrary a variety of optional components are described to illustrate the wide variety of possible embodiments of the invention.

[0076] When a single device or article is described herein, it will be readily apparent that more than one device / article (whether or not they cooperate) may be used in place of a single device / article. Similarly, where more than one device or article is described herein (whether or not they cooperate), it will be readily apparent that a single device / article may be used in place of the more than one device or article or a different number of devices / articles may be used instead of the shown number of devices or programs. The functionality and / or the features of a device may be alternatively embodied by one or more other devices which are not explicitly described as having such functionality / features. Thus, other embodiments of the invention need not include the device itself.

[0077] The illustrated operations of Figure 2 show certain events occurring in a certain order. In alternative embodiments, certain operations may be performed in a different order, modified, or removed. Moreover, steps may be added to the above-described logic and still conform to the described embodiments. Further, operations described herein may occur sequentially or certain operations may be processed in parallel. Yet further, operations may be performed by a single processing unit or by distributed processing units.

[0078] 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 theinventive subject matter. It is therefore intended that the scope of the invention be limited not by this detailed description, but rather by any claims that issue on an application based here on. Accordingly, the disclosure of the embodiments of the invention is intended to be illustrative, but not limiting, of the scope of the invention, which is set forth in the following claims.

[0079] While various aspects and embodiments have been disclosed herein, other aspects and embodiments will be apparent to those skilled in the art. The various aspects and embodiments disclosed herein are for purposes of illustration and are not intended to be limiting, with the true scope being indicated by the following claims.Referral Numerals:

Claims

We claim:

1. A method of predicting incipient faults in an electrical equipment (102), the method comprising: receiving, by a processor (104), values of one or more primary parameters from primary datasets associated with an electrical equipment (102); generating, by the processor (104), a plurality of scenarios, corresponding to a plurality of incipient faults associated with the electrical equipment (102), wherein the plurality of scenarios is generated using a virtual representation model (106) of the electrical equipment (102) and by varying values of a plurality of pre-defined parameters of the electrical equipment (102) with respect to one or more pre-defined conditions corresponding to the plurality of incipient faults; determining, by the processor (104), an effect of each of the plurality of scenarios on the values of the one or more primary parameters; estimating, by the processor (104), one or more atypical parameters for each scenario of the plurality of scenarios, based on the determined effect and the one or more primary parameters; estimating, by the processor (104), secondary datasets, corresponding to each of the plurality of scenarios, using the primary datasets, wherein the secondary datasets are estimated based on the one or more primary parameters and the one or more atypical parameters; and predicting, by the processor (104), at least one incipient fault of the plurality of incipient faults using an Artificial Intelligence (Al) model (108) associated with the electrical equipment (102), wherein the Al model (108) is trained based on the primary datasets and the secondary datasets of the electrical equipment (102).

2. The method as claimed in claim 1, wherein the one or more primary parameters comprises at least one of electrical parameters or mechanical parameters of the electrical equipment (102).

3. The method as claimed in claim 1, wherein the virtual representation model (106) is disconnected from the electrical equipment (102).

4. The method as claimed in claim 1, wherein estimating the one or more atypical parameters and the secondary datasets is performed using a Kalman Filter.

5. The method as claimed in claim 4, wherein the Kalman Filter is tuned with one or more primary parameters and the one or more atypical parameters of an electrical equipment (102).

6. The method as claimed in claim 1, further comprising, upon predicting the at least one incipient fault: performing a mitigation action, based on a severity level associated with the at least one incipient fault.

7. The method as claimed in claim 1 is implemented in one of, the electrical equipment (102), an edge platform, and a cloud platform.

8. The method as claimed in claim 1, wherein the one or more primary parameters comprise measurable parameters of the electrical equipment (102), and the one or more atypical parameters comprise derived parameters of the electrical equipment (102) that are not measurable.

9. A method of predicting incipient faults in an electrical equipment (102), the method comprising: receiving, by a processor (104), values of one or more primary parameters from primary datasets associated with an electrical equipment (102); generating, by the processor (104), a plurality of scenarios, corresponding to a plurality of incipient faults associated with the electrical equipment (102), by varying values of a plurality of pre-defined parameters of the electrical equipment (102); estimating, by the processor (104), one or more atypical parameters for each scenario of the plurality of scenarios, based on the one or more primary parameters and an effect of the plurality of scenarios on the one or more primary parameters; and estimating, by the processor (104), secondary datasets, corresponding to each of the plurality of scenarios, using the primary datasets, wherein the secondary datasets are estimated based on the one or more primary parameters and the one or more atypical parameters, and wherein the primary datasets and the secondary datasets are used for training an Artificial Intelligence (Al) model (108) to predict at least one incipient fault of the plurality of incipient faults.

Images