A system and a method of classification of faults associated with digital substations

Abstract

The present disclosure relates to a system and method of classification of faults associated with digital substations. The method comprises receiving a disturbance record associated with each of a plurality of faults, from one or more lEDs (102) associated with the digital substation (101), upon occurrence of each fault. Further, the method comprises extracting one or more features associated with the fault variable by analysing the fault variable using a predefined feature extraction technique. Further, the method comprises determining one or more entropies for each of the one or more features. Thereafter, the method comprises classifying each of the fault into one of one or more fault types using a machine learning model (235) by analysing the one or more entropies and the one or more features. The present invention provides precise fault diagnosis for maintaining operational efficiencies and may minimize disruptions in the digital substation.

Description

TITLE: “A SYSTEM AND A METHOD OF CLASSIFICATION OF FAULTS ASSOCIATED WITH DIGITAL SUBSTATIONS”TECHNICAL FIELD

[0001] The present disclosure generally relates to fault management. More particularly, the present disclosure relates to a system and a method of classification of faults associated with digital substations.BACKGROUND

[0002] In recent years, digital substations have emerged as a significant technology in the power distribution sector. These advanced digital substations may utilize Intelligent Electronic Devices (lEDs) and sophisticated communication networks to gather real-time data, monitor system conditions, and facilitate more efficient operation and maintenance of power grids. Generally, these digital substations have the capability to monitor the system conditions and identify and manage various types of electrical faults that occur on a regular basis. These faults may have to be analysed accurately to take necessary actions so that they do not reoccur again. These faults have to analysed and corrected by removing noise and artefacts, and anomaly detection based on features extracted on these faults.

[0003] Traditionally, these faults are analysed and classified manually by trained personnel for fault correction. However, despite classifying the faults manually and correcting the same, the digital substations still operate inefficiently due to inaccurate diagnosis of faults. Moreover, the manual analysis is time-consuming, and prone to human error. Further, the conventional classification techniques utilize signal processing and soft computing techniques, however, these classifications are limited to classifying power quality of disturbance signals resulting in missing all relevant parameters that have led to the faults associated with the digital substations. Furthermore, because of performing the classification based on the aforementioned classification techniques, there are high chances of reoccurrence of the same faults due to inaccurate classification of faults.

[0004] Hence, there is a need for an improvised system and method for classification of faults associated with digital substations.

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

[0006] In an embodiment, the present disclosure provides a method of classification of faults associated with digital substations. The method comprises receiving, by a processor of a fault classification system, a disturbance record associated with each of a plurality of faults, from one or more Intelligent Electronic Devices (lEDs) associated with a digital substation, upon occurrence of each fault. Further, the method comprises, identifying, by the processor, a fault variable, among a plurality of variables in the disturbance record, based on a causal analysis of the disturbance record. Further, the method comprises extracting, by the processor, one or more features associated with the fault variable by analysing the fault variable using a predefined feature extraction technique. Further, the method comprises determining, by the processor, one or more entropies for each of the one or more features. Thereafter, the method comprises classifying, by the processor, each of the fault into one of one or more fault types using a machine learning model by analysing the one or more entropies and the one or more features.

[0007] In an embodiment, the present disclosure comprises a fault classification system for classification of faults associated with digital substations. The fault classification system comprises a processor and a memory. The memory stores processor-executable instructions, which, on execution, causes the processor to receive a disturbance record associated with each of a plurality of faults, from one or more Intelligent Electronic Devices (lEDs) associated with a digital substation, upon occurrence of each fault. Further, the processor is configured to identify a fault variable, among a plurality of variables in the disturbance record, based on a causal analysis of the disturbance record. Further, the processor is configured to extract one or more features associated with the fault variable by analysing the fault variable using a predefined feature extraction technique. Further, the processor is configured to determine one or more entropies for each of the one or more features. Thereafter, the processor is configured to classify each of the fault into one of one or more fault types using a machine learning model by analysing the one or more entropies and the one or more features.

[0008] 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

[0009] 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 of an 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:

[0010] FIG. 1 depicts a schematic representation of an environment for classification of faults associated with digital substations, in accordance with embodiments of the present disclosure;

[0011] FIG.2 illustrates a detailed block diagram of a fault classification system for classification of faults associated with digital substations, in accordance with embodiments of the present disclosure;

[0012] FIG.3 depicts a flowchart illustrating a method of classification of faults associated with digital substations, in accordance with embodiments of the present disclosure;

[0013] FIG.4 depicts a tabular representation of a disturbance record, in accordance with embodiments of the present disclosure; and

[0014] FIG.5 illustrates a block diagram of an exemplary computer system for implementing embodiments consistent with the present disclosure.

[0015] 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 besubstantially represented in computer readable medium and executed by a computer or processor, whether or not such computer or processor is explicitly shown.DETAILED DESCRIPTION

[0016] In the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or implementation of the present subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

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

[0018] The terms “comprises”, “comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a 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.

[0019] In recent years, digital substations have emerged as significant technology in the power distribution sector. These advanced digital substations may utilize Intelligent Electronic Devices (lEDs) and sophisticated communication networks to gather real-time data, monitor system conditions, and facilitate more efficient operation and maintenance of power grids. Traditionally, these faults are analysed and classified manually by trained personnel for fault correction. However, despite classifying the faults manually and correcting the same, the digital substations still operate inefficiently due to inaccurate diagnosis of faults. Moreover, the manual analysis is time-consuming, and prone to human error. Further, the conventional classification techniques utilize signal processing and soft computing techniques, however, these classifications are limited to classifying power quality of disturbance signals resulting in missing all relevant parameters that have led to the faults associated with the digital substations.

[0020] In order to address the one or more of the aforementioned problems, the present disclosure discloses a system and a method for classification of faults in a digital substation. The method comprises receiving, by a processor of a fault classification system, a disturbance record associated with each of a plurality of faults, from one or more Intelligent Electronic Devices (lEDs) associated with a digital substation, upon occurrence of each fault. Further, the method comprises, identifying, by the processor, a fault variable, among a plurality of variables in the disturbance record, based on a causal analysis of the disturbance record. Further, the method comprises extracting, by the processor, one or more features associated with the fault variable by analysing the fault variable using a predefined feature extraction technique. Further, the method comprises determining, by the processor, one or more entropies for each of the one or more features. Thereafter, the method comprises classifying, by the processor, each of the fault into one of one or more fault types using a machine learning model by analysing the one or more entropies and the one or more features.

[0021] The present disclosure aims to provide an enhanced method and system for precise fault diagnosis to maintain operational efficiency and minimize disruptions in a digital substation. The fault diagnosis as proposed may be based on acquiring one or more variables from a distribution system, reprocessing it to remove noise and artefacts, extracting relevant features that capture important characteristics of disturbances, selecting informative features for classification, and employing machine learning algorithms to categorize the records into different fault types. The proposed classification technique aims to improve system reliability, ensures safe efficient operation of the digital substation, and may further help in minimizing downtime and maintenance costs. This ensures optimal energy distribution and increase in the reliability of power distribution systems associated with the digital substations.

[0022] FIG. 1 depicts a schematic representation of an environment for classification of faults associated with digital substations (101), in accordance with embodiments of the present disclosure.

[0023] The environment (100) includes a digital substation (101) associated with Intelligent Electronic device (IED) (102i) to IED (102n), (collectively referred to as one or more lEDs (102)) and a fault classification system (104). The one or more lEDs (102) and the fault classification system (104) are communicatively coupled via the communication network (106). The digital substation (101) may monitor system conditions and facilitate maintenanceof power grids using the one or more lEDs (102) in power systems. The communication network (106) may be one of, a wired communication network, a wireless communication network or a combination of both wired and wireless communication network.

[0024] Consider a scenario where a fault has occurred in a household A associated with a digital substation (101). The fault may occur because of various factors such as but not limited to, poor quality insultation, power surges, conductor failures and the like.

[0025] In some embodiments, upon occurrence of the fault, the fault classification system (104) may receive a disturbance record associated with each of a plurality of faults from the one or more lEDs (102) associated with the digital substation (101). The disturbance record is a type of record that may include a plurality of parameters that have recurred at the time of occurrence of the fault. For example, if the fault is a short circuit in a household A, the associated disturbance record for this fault includes one or more variables including, but not limited to, signals indicating phase current values associated with the fault, signals indicating phase voltage values associated with the fault and the like.

[0026] In some embodiments, upon receiving the disturbance record, the fault classification system (104) may perform causal analysis of the disturbance record to identify a fault variable among the one or more variables. The fault variable is a type of variable that have caused the highest effect among the one or more variables resulting in the fault. For instance, based on the example in paragraph

[0025] , consider the normal voltage to be 250 volts and phase voltage determined to be 750 volts, and consider the normal current to be 10 amperes and the phase current determined in the is 15 amperes. In this example, an inference can be provided that the phase voltage determined is the fault variable among the plurality of variable due to highest difference between a normal value and the currently determined value. To identify the fault variable, the fault classification system (104) may generate a causal matrix based on causal analysis of the plurality of variables in the disturbance record. In some embodiments, for example, the causal matrix is generated based on Granger causality matrix technique. Thereafter, the fault classification system (104) may extract time series data of each of the plurality of variables and generate a causal matrix based on the causal analysis of the extracted time series data. Thereafter, the fault classification system may determine the most causing fault variable based on a frequency distribution estimation of the causal matrix. For example, phase current of 25 amperes have occurred the highest while a fault 1 occurred in the householdA as the highest frequency for the phase current was determined based on the frequency distribution estimation for the signals associated with one or more variables of the fault 1.

[0027] In some embodiments, the fault classification system (104) may extract one or more features associated with the fault variable. The fault classification system (104) may extract the one or more features by analysing the fault variable using a predefined feature extraction technique. The predefined feature extraction technique may include, but not limited to, time frequency analysis techniques embedded with convolution neural network. The feature extraction technique may include wavelet scattering transformation techniques with second level and third scale to extract the one or more features associated with the fault variable. However, these aforementioned wavelet scattering transformation techniques should not be construed as a limitation as the fault classification system (104) may extract the one or more using other feature extraction techniques. The one or more features are factors depicting an underlying cause that may have led to the fault associated with the fault variable.

[0028] In some embodiments, upon extracting the one or more features of the fault variable, the fault classification system (104) may determine one or more entropies for the one or more features. The one or more entropies may be one of, but not limited to, a spectral entropy and a fuzzy entropy. For example, based on the fuzzy entropy and the spectral entropy, a total of 32 features are obtained for each of the disturbance record based on obtaining 16 bands of coefficients on obtaining the one or more features using the wavelet scattering transformation technique. Thereafter, in some embodiments, the fault classification system (104) may classify each of the fault into one or more fault types. The fault classification system (104) may classify each of the fault by analysing the one or more entropies and the one or more features using a machine learning model. To classify each of the fault into the one or more fault types, the fault classification system (104) generates a feature set by combining the one or more entropies with the corresponding one or more features. The one or more entropies indicate non-linearity and relative complexity of the one or more features. Further, the fault classification system (104) may cluster the feature set into one or more clusters corresponding to the one or more fault types. For example, the fault classification system (104) may utilize Density-Based Spatial Clustering Of Applications With Noise (DBSCAN) clustering algorithm that uses Gower distance to determine the one or more clusters. Thereafter, the fault classification system (104) classifies the fault into the one or more fault types based on the clustering and generate a dataset. For example, each of the fault are assigned with a fault type upon clustering usingunsupervised clustering technique and labelled using the fault type. The fault types may be at least one of, but not limited to, an earth fault, an overcurrent fault, a short circuit fault, overvoltage fault, open circuit fault and the like. Based on repeating the process of classification for all the distribution records and generation of dataset, the machine learning model is trained and tested for determining the efficiency in classification any new disturbance record to a particular fault type.

[0029] In some embodiments, the machine learning model is trained based on historical disturbance records previously acquired from the digital substations (101) and historical classified fault types. Based on repeating the process of classification for all the distribution records, the machine learning model is trained and tested, resulting in accurate classification of faults. For instance, ten disturbance records were utilized for testing and rest of the analysed disturbance records may be utilized for training. These historical disturbance records previously acquired from the digital substations (101) and the historically classified fault types may be stored on a cloud network or an edge data network and may be utilized for accurate classification of faults.

[0030] FIG.2 depicts a block diagram (200) of a fault classification system (104) for classification of faults associated with digital substations (101), in accordance with embodiments of the present disclosure.

[0031] In some embodiments, the fault classification system (104) may include an Input / Output (BO) interface (201), a processor (203) and a memory (205). The BO interface (201) may be configured for receiving and transmitting an input signal or / and an output signal related to one or more operations of the fault classification system (104). The memory (205) may be communicatively coupled to the processor (203) and one or more modules (209). The processor (203) may be configured to perform one or more functions of the fault classification system (104) using data (207) and the one or more modules (209).

[0032] In an embodiment, the data (207) stored in the memory (205) may include without limiting to disturbance record (211), fault data (213), fault variable data (215), fault features data (217), entropy data (219), fault type (221) and auxiliary data (223). In some implementations, the data (207) may be stored within the memory (205) in the form of various data structures. Additionally, the data (207) may be organized using data models. The auxiliarydata (223) may include various temporary data and files generated by the different components of the fault classification system (104).

[0033] In some embodiments, the disturbance record (211) is a type of record that includes a list of variables that may have led to a fault. For example, consider the fault is a short circuit in a household A and the associated disturbance record (211) includes one or more variables such as, but not limited to, signals indicating phase current values associated with the fault, signals indicating phase voltage values associated with the fault, power factor of transmission lines and the like. For instance, based on the aforementioned example, during the short circuit, the phase current and the phase voltage is generated at a higher rate such as 50 ampers and 500 volts, respectively, when compared to a normal scenario of generation of the phase current and the phase voltage such as 10 amperes and 100 volts in the household, respectively.

[0034] In some embodiments, the fault data (213) may include fault that occurs in a digital substation (101). The fault is an abnormal condition that may have occurred due to various scenarios in the digital substations (101). The one or more scenarios may include one of poor quality insultation, power surges, transformers and rotating machine failures, conductor failures and the like.

[0035] In some embodiments, the fault variable data (215) may include identified fault variables among the one or more variables that may have factored as an highest factor in leading to the fault in the digital substation (101). The one or more variables are present in the disturbance record (211). For example, phase current generation of 25 amperes have occurred the highest as that showcased highest frequency in signals associated with the aforementioned phase current generation, while a short circuit occurred in a household when compared to a normal scenario in a household.

[0036] In some embodiments, the fault features data (217) may include one or more features obtained based on analysing the fault variable. The one or more features indicate the factors that may have led to the fault.

[0037] In some embodiments, the entropy data (219) may include one or more entropies indicating non-linearity and relative complexity of the one or more features. The one or more entropies may be one of, but not limited to, spectral entropy and fuzzy entropy. For example,based on determined fuzzy entropy and spectral entropy, a total of 32 features are obtained for each of the disturbance record (211) based on obtaining 16 bands of coefficients on obtaining the one or more features using the wavelet scattering transformation technique.

[0038] In some embodiments, the fault type (221) may include categories of each of fault into a type based on analysis of the one or more entropies and the one or more features. The fault type (221) may be at least one of, but not limited to, an earth fault, an overcurrent fault, a short circuit fault, overvoltage fault, open circuit fault and the like.

[0039] As explained above, the processor (203) and the one or more modules (209) of the fault classification system (104) process the data (207). In an implementation, the one or more modules (209) may include, without limiting to, an, a receiving module (225), a fault variable identification module (227), a feature extraction module (229), an entropy determination module (231), a classification module (233), a machine learning model (235) and auxiliary modules (239). In an embodiment, the auxiliary modules (239) may be used to perform various miscellaneous functionalities of the fault classification system (104). It will be appreciated that such one or more modules (209) may be represented as a single module or a combination of different modules.

[0040] In some embodiments, upon occurrence of the fault in the household 2 associated with the digital substation (101), the receiving module (225) may be configured to receive the disturbance record (211) associated with each of a plurality of faults from one or more lEDs (102) associated with the digital substation (101).

[0041] In some embodiments, the fault variable identification module (227) may be configured to identify the fault variable among a plurality of variables in the disturbance record (211) based on frequency distribution estimation. To identify the fault variable, the fault variable identification module (227) maybe configured to extract a time series data of each of the plurality of variables in the disturbance record (211) and generate a causal matrix based on the causal analysis of the time series data. Thereafter, the fault variable identification module (227) may be configured to identify the fault variable based on the frequency distribution estimation of the causal matrix.

[0042] In some embodiments, the feature extraction module (229) may be configured to extract the one or more features by analysing the fault variable using a predefined feature extractiontechnique such as time frequencies analysis technique embedded with a convolution neural network.

[0043] In some embodiments, the entropy determination module (231) may be configured to determine the one or more entropies for each of the one or more features.

[0044] In some embodiments, the classification module (233) may be configured to classify each of the faults into one or more fault types by analysing the one or more entropies and the one or more features using the machine learning model (235). The machine learning model (235) is trained based on historical disturbance records previously acquired from the digital substation (101). To classify the faults, the classification module (233) may generate a feature set by combining the one or more entropies with corresponding one or more features, cluster the feature set into one or more clusters corresponding to the one or more fault types. Thereafter, the classification module (233) may classify and label the faults into the one or more fault types based on the clustering.

[0045] Henceforth, the process of classification of faults associated with the digital substation (101) with the help of one or more examples for better understanding of the present disclosure. However, the one or more examples should not be considered as limitation of the present disclosure.

[0046] Consider a scenario in a city, wherein a fault is reoccurring after every 4 hours in a layout. To accurately classify the faults, the fault classification system performs the following steps as given below. At step one, upon occurrence of a fault A in a household A associated with a digital substation 1, the fault classification system receives a disturbance record from IED 1 associated with the digital substation 1. As shown in FIG.4, the disturbance record include one or more variables including phase current A, phase current B, phase voltage A, phase voltage B. Consider the phase current A to be 25 amperes, phase current B to be 30 amperes, phase voltage A to be 300 volts, phase voltage B to be 400 volts. At step two, a fault variable is identified by generating a causal matrix for the one or more variables based on granger causality matrix and time series data is extracted for the causal matrix. An inference is obtained that the time series for phase current B and phase voltage B have the highest variation when compared to the phase current A and the phase voltage A. Hence, the fault variable is phase current B and phase voltage B. At step three, one or more features of the phase currentB and the phase voltage B are determined by analysing the phase current B and the phase voltage B based on performing time frequency analysis of the phase current B and the phase voltage B . Furthermore, at step four, one or more entropies are extracted for the one or more features. These aforementioned steps provide an inference on the correct one or more underlying features that have led to the fault A such that based on continuous touching of wires near trees at every two hours, there was a drastic change in the phase current B and phase voltage B resulting in the fault A. Thereafter, at step five, the fault A is classified as short circuit based on classification of the fault by analysing the one or more entropies and the one or more features using the machine learning model. In some embodiments, the plurality of variables may also be referred as one or more variables.

[0047] FIG.3 depicts a flowchart illustrating a method (300) determining of classification of faults associated with digital substations (101), in accordance with embodiments of the present disclosure.

[0048] As illustrated in the FIG.3, the method (300) includes one or more blocks illustrating the method (300) of classification of faults associated with digital substations (101). The method (300) 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 functions or implement abstract data types.

[0049] The order in which the method (300) 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 (300). Additionally, individual blocks may be deleted from the methods without departing from the spirit and scope of the subject matter described herein. Furthermore, the method (300) can be implemented in any suitable hardware, software, firmware, or combination thereof.

[0050] Upon occurrence of each fault, at block 302, the method (300) includes receiving, by a processor (203) of a fault classification system (104), a disturbance record (211) associated with each of a plurality of faults, from one or more Intelligent Electronic Devices (lEDs) (102) associated with a digital substation (101).

[0051] At block 304, the method (300) includes identifying, by the processor (203), a fault variable, among a plurality of variables in the disturbance record (211), based on a causal analysis of the disturbance record (211).

[0052] At block 306, the method (300) includes extracting, by the processor (203), one or more features associated with the fault variable by analysing the fault variable using a predefined feature extraction technique.

[0053] At block 308, the method (300) includes determining, by the processor (203), one or more entropies for each of the one or more features.

[0054] At block 310, the method (300) includes classifying, by the processor (203), each of the fault into one of one or more fault types using a machine learning model (235) by analysing the one or more entropies and the one or more features.

[0055] In some embodiments, upon validation of the machine learning model (235) associated with the fault classification system (104), it was determined that the automated classification of the fault types resulted in a better, accurate and faster detection of the fault types when compared to conventional manual classification of fault types. The 100% validation was achieved based on training the machine learning model up to 200 epochs.

[0056] The present disclosure aims to provide an enhanced method and system for precise fault diagnosis to maintain operational efficiency and minimize disruptions in a digital substation. This aforementioned advantage may be based on acquiring one or more variables from a distribution system, reprocessing it to remove noise and artefacts, extracting relevant features that capture important characteristics of disturbances, selecting informative features for classification, and employing machine learning algorithms to categorize the records into different fault types. The proposed classification technique aims to improve system reliability, ensures safe efficient operation of the digital substation, and may further help in minimizing downtime and maintenance costs. This ensures optimal energy distribution and increase in the reliability of power distribution systems associated with the digital substations.

[0057] FIG.5 illustrates a block diagram of an exemplary computer system (500) for implementing embodiments consistent with the present disclosure.

[0058] In an embodiment, the computer system (500) may be a fault classification system (104) as illustrated in FIG. 2, which may be used for classifying faults associated with a digital substation (101) based on faults received from Intelligent Electronic Devices (102) using a machine learning model (235). The computer system (500) may include a central processing unit (“CPU” or “processor” or “memory controller”) (502). The processor (502) may comprise at least one data processor for executing program components for executing user- or systemgenerated business processes. The processor (502) may include specialized processing units such as integrated system (bus) controllers, memory controllers / memory management control units, floating point units, graphics processing units, digital signal processing units, etc.

[0059] The processor (502) may be disposed in communication with one or more Input / Output (VO) devices (511) and (512) via VO interface (501). The VO interface (501) may employ communication protocols / methods such as, without limitation, audio, analog, digital, stereo, IEEE®- 1394, serial bus, Universal Serial Bus (USB), infrared, PS / 2, BNC, coaxial, component, composite, Digital Visual Interface (DVI), high-definition multimedia interface (HDMI), Radio Frequency (RF) antennas, S-Video, Video Graphics Array (VGA), IEEE® 802. 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) or the like), etc. Using the VO interface (501), the computer system (500) may communicate with one or more VO devices (511) and (512).

[0060] In some embodiments, the processor (502) may be disposed in communication with a communication network (509) via a network interface (503). The network interface (503) may communicate with the communication network (509). The network interface (503) may employ connection protocols including, without limitation, direct connect, Ethernet (e.g., twisted pair 10 / 100 / 1000 Base T), Transmission Control Protocol / Internet Protocol (TCP / IP), token ring, IEEE® 802.1 la / b / g / n / x, etc.

[0061] In an implementation, the communication network (509) may be implemented as one of the several types of networks, such as intranet or Local Area Network (LAN) and such within the organization. The communication network (509) may either be a dedicated network or a shared network, which represents an association of several types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission ControlProtocol / Internet Protocol (TCP / IP), Wireless Application Protocol (WAP) etc., to communicate with each other. Further, the communication network (509) may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices, etc.

[0062] In some embodiments, the processor (502) may be disposed in communication with a memory (505) (e.g., RAM (513), ROM (514), etc. as shown in FIG. 5) via a storage interface (504). The storage interface (504) may connect to memory (505) 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.

[0063] The memory (505) may store a collection of program or database components, including, without limitation, user / application interface (506), an operating system (507), a web browser (508), and the like. In some embodiments, the computer system (500) may store user / application data (506), such as the data, variables, records, etc. as described in this invention. Such databases may be implemented as fault-tolerant, relational, scalable, secure databases such as Oracle® or Sybase®.

[0064] The operating system (507) may facilitate resource management and operation of the computer system (500). Examples of operating systems include, without limitation, APPLE® MACINTOSH® OS X®, UNIX®, UNIX-like system distributions (E.G., BERKELEY SOFTWARE DISTRIBUTION® (BSD), FREEBSD®, NETBSD®, OPENBSD, etc.), LINUX® DISTRIBUTIONS (E.G., RED HAT®, UBUNTU®, KUBUNTU®, etc.), IBM® OS / 2®, MICROSOFT® WINDOWS® (XP®, VISTA® / 7 / 8, 10 etc.), APPLE® IOS®, GOOGLE ™ ANDROID ™, BLACKBERRY® OS, or the like.

[0065] The user interface (506) may facilitate display, execution, interaction, manipulation, or operation of program components through textual or graphical facilities. For example, the user interface (506) may provide computer interaction interface elements on a display system operatively connected to the computer system (500), such as cursors, icons, check boxes,menus, scrollers, windows, widgets, and the like. Further, Graphical User Interfaces (GUIs) may be employed, including, without limitation, APPLE® MACINTOSH® operating systems’ Aqua®, IBM® OS / 2®, MICROSOFT® WINDOWS® (e.g., Aero, Metro, etc.), web interface libraries (e.g., ActiveX®, JAVA®, JAVASCRIPT®, AJAX, HTML, ADOBE® FLASH®, etc.), or the like.

[0066] The web browser (508) may be a hypertext viewing application. Secure web browsing may be provided using Secure Hypertext Transport Protocol (HTTPS), Secure Sockets Layer (SSL), Transport Layer Security (TLS), and the like. The web browsers (508) may utilize facilities such as AJAX, DHTML, ADOBE® FLASH®, JAVASCRIPT®, JAVA®, Application Programming Interfaces (APIs), and the like. Further, the computer system (500) may implement a mail server stored program component. The mail server may utilize facilities such as ASP, ACTIVEX®, ANSI® C++ / C#, MICROS OFT®,. NET, CGI SCRIPTS, JAVA®, JAVASCRIPT®, PERL®, PHP, PYTHON®, WEBOBJECTS®, etc. The mail server may utilize communication protocols such as Internet Message Access Protocol (IMAP), Messaging Application Programming Interface (MAPI), MICROSOFT® exchange, Post Office Protocol (POP), Simple Mail Transfer Protocol (SMTP), or the like. In some embodiments, the computer system (500) may implement a mail client stored program component. The mail client may be a mail viewing application, such as APPLE® MAIL, MICROSOFT® ENTOURAGE®, MICROSOFT® OUTLOOK®, MOZILLA® THUNDERBIRD®, and the like.

[0067] Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present invention. 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., non-transitory. Examples include Random Access Memory (RAM), Read-Only Memory (ROM), volatile memory, non volatile memory, hard drives, Compact Disc (CD) ROMs, Digital Video Disc (DVDs), flash drives, disks, and any other known physical storage media.

[0068] 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.

[0069] The terms "including", "comprising", “having” and variations thereof mean "including but not limited to", unless expressly specified otherwise.

[0070] 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.

[0071] 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.

[0072] 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.

[0073] Finally, the language used in the specification has been principally selected for readability and instructional purposes, and it may not have been selected to delineate or circumscribe the inventive subject matter. 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.

[0074] 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 classification of faults associated with digital substations (101), the method comprising: receiving, by a processor (203) of a fault classification system (104), a disturbance record (211) associated with each of a plurality of faults, from one or more Intelligent Electronic Devices (lEDs) (102) associated with a digital substation (101), upon occurrence of each fault; identifying, by the processor (203), a fault variable, among a plurality of variables in the disturbance record (211), based on a causal analysis of the disturbance record (211); extracting, by the processor (203), one or more features associated with the fault variable by analysing the fault variable using a predefined feature extraction technique; determining, by the processor (203), one or more entropies for each of the one or more features; and classifying, by the processor (203), each of the fault into one of one or more fault types by analysing the one or more entropies and the one or more features using a machine learning model (235).

2. The method as claimed in claim 1, wherein identifying the fault variable comprising: extracting a time series data of each of the plurality of variables in the disturbance record (211); generating a causal matrix based on the causal analysis of the time series data; and determining the fault variable based on a frequency distribution estimation of the causal matrix.

3. The method as claimed in claim 1, wherein classifying the fault comprising: generating a feature set by combining the one or more entropies with corresponding one or more features; clustering the feature set into one or more clusters corresponding to the one or more fault types; and classifying the fault into one of one or more fault types based on the clustering.

4. The method as claimed in claim 1, wherein the predefined feature extraction technique includes time frequency analysis.

5. The method as claimed in claim 1, further comprising training the machine learning model (235) based on historical disturbance records previously acquired from the digital substations (101).

6. A fault classification system (104) for classification of faults associated with digital substations (101), the fault classification system (104) comprising: a memory (205) configured to store instructions executable by a processor (203); the processor (203) configured to execute the instructions stored in the memory (205) to: receive a disturbance record (211) associated with each of a plurality of faults, from one or more Intelligent Electronic Devices (lEDs) (102) associated with a digital substation (101), upon occurrence of each fault; identify a fault variable, among a plurality of variables in the disturbance record (211), based on a causal analysis of the disturbance record (211); extract one or more features associated with the fault variable by analysing the fault variable using a predefined feature extraction technique; determine one or more entropies for each of the one or more features; and classify each of the fault into one of one or more fault types by analysing the one or more entropies and the one or more features using a machine learning model (235).

7. The fault classification system (104) as claimed in claim 6, wherein for identifying the fault variable the processor (203) is configured to: extract a time series data of each of the plurality of variables in the disturbance record (211); generate a causal matrix based on the causal analysis of the time series data; and determine the fault variable based on a frequency distribution estimation of the causal matrix.

8. The fault classification system (104) as claimed in claim 6, wherein for classifying the fault, the processor (203) is configured to: generate a feature set by combining the one or more entropies with corresponding one or more features; cluster the feature set into one or more clusters corresponding to the one or more fault types; and classify the fault into one of one or more fault types based on the clustering.

9. The fault classification system (104) as claimed in claim 6, wherein the predefined feature extraction technique includes time frequency analysis techniques technique.

10. The fault classification system (104) as claimed in claim 6, wherein the processor (203) is further configured to train the machine learning model (235) based on historical disturbance records previously acquired from the digital substations (101).

Images