Power grid fault diagnosis method and system based on artificial intelligence technology

Abstract

The present application relates to the field of power grid system fault diagnosis, especially to a power grid fault diagnosis method and system based on artificial intelligence technology, in the process of diagnosing complex power grid faults, according to the type of the obtained fault information, the fault information is divided into numerical information and text information, the two different types of information are input into different artificial intelligence models, which avoids the situation that the input information dimension is too large, causing the artificial intelligence model training amount is large and the requirement for hardware is high; at the same time, according to the different applicability of the model to the data type, the convolutional neural network model is used for fault diagnosis for numerical information, and the BP convolutional neural network model is used for fault diagnosis for text information, and then the final diagnosis conclusion is determined according to the two diagnosis results, which greatly improves the accuracy of fault diagnosis.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of power system fault diagnosis, in particular to a power grid fault diagnosis method and system based on artificial intelligence technology. BACKGROUND

[0002] In recent years, with the continuous expansion of China's power grid scale, the interconnection between different regions is becoming closer and closer, which can improve the power supply reliability and operation economy. At the same time, with the increasing complexity of the power grid structure, the impact on the system when the power grid fails will also be greater, and the control center will receive a large number of alarm information. Relying solely on the working experience of the on-duty personnel to judge the fault components and the actual action of the on-site relay protection will inevitably miss some information, such as the inability to quickly and accurately isolate the fault, which may evolve into a cascading failure, leading to the expansion of the fault area and causing huge economic losses. Moreover, in the case of multiple faults causing multiple devices to almost simultaneously alarm and existing problems such as protection or circuit breaker refusal, misoperation, and loss of action information, the diagnosis process becomes even more complex, which may lead to misjudgment by the staff, prolonged maintenance time, and even safety accidents. Therefore, it is necessary to develop a diagnosis method to quickly distinguish between fault components and false alarm information to achieve rapid fault removal and safe and stable operation of the power grid.

[0003] In the prior art, there are two main ideas for complex power grid fault diagnosis, one is to use a rule-based model to achieve fault diagnosis, and the other is to use a data-driven model to achieve fault diagnosis. For example, a power grid fault diagnosis method, system and device are disclosed in Chinese patent CN112000923A, which forms a two-dimensional computer visualized power flow data matrix CVPFM from the power flow data; maps the CVPFM to the HSV color space to obtain a computer visualized power flow picture CVPFI; and combines the CVPFI before and after the fault into a DCVPFI. Using the DCVPFI to replace the numerical form of the power grid power flow data as the input of the CNN can better extract the spatial and temporal information contained in the power flow and then judge the location of the system failure; however, the above-mentioned rule-based power grid fault diagnosis method will have high model complexity due to the complexity of the logical constraints and the difficulty of knowledge representation when facing a more complex power grid. In addition, a large amount of alarm information needs to be screened and classified during the establishment of the rule-based model, which increases the workload of the rule-based model.

[0004] In addition, in the data-driven fault diagnosis method, the existing technology mainly diagnoses the electrical quantity information collected by the wide-area measurement system and the power management system, and lacks research on the text information in the alarm information, which results in low accuracy of fault diagnosis and cannot meet the high-quality development of modern complex power grids. Therefore, there is an urgent need for a technical solution to improve the accuracy of fault diagnosis in complex power grid topologies. SUMMARY

[0005] The technical problem solved by the present application is to provide a power grid fault diagnosis method and system based on artificial intelligence technology to improve the accuracy of fault diagnosis.

[0006] To achieve the above-mentioned purpose, according to one aspect of the present application, a power grid fault diagnosis method based on artificial intelligence technology is provided, comprising the following steps:

[0007] Step 1: classify the alarm information of the power grid after the fault occurs, and divide the alarm information into two categories according to the signal type: one is numerical information, and the other is text information;

[0008] Step 2: using a first artificial intelligence model to diagnose the power grid fault of the numerical information;

[0009] Step 3: using a second artificial intelligence model to diagnose the power grid fault of the text information;

[0010] Step 4: determining whether the power grid diagnosis conclusion obtained in step 2 is the same as the power grid diagnosis conclusion obtained in step 3; if they are the same, it is determined as the final fault of the power grid, if they are different, an expert is involved to diagnose the power grid fault.

[0011] Preferably, the numerical information includes fault voltage amplitude, fault voltage phase, fault current amplitude, fault current phase, etc.; due to the complexity of the power grid topology structure, the switching quantity information is likely to appear inaction, misoperation, etc., therefore, the present application does not use the switching quantity information as the input data for power grid fault diagnosis;

[0012] Preferably, the text information includes fault description text reported by the monitoring system;

[0013] Preferably, the first artificial intelligence model is a first deep learning model;

[0014] Preferably, the first deep learning model is a convolutional neural network model, and the specific process of the first deep learning model for power grid fault diagnosis is as follows:

[0015] Step 2.1: build a power grid topology structure model through a simulation system and set different fault points to obtain a plurality of fault sample sets;

[0016] Specifically, the power grid topology structure model can be built through a Simulink platform;

[0017] Step 2.2: data preprocessing of the fault sample set;

[0018] Specifically, the homogenization processing formula is:

[0019]

[0020] Wherein, x i ′ is the normalized electrical value, xi is the i-th electrical value, x min and x max are the minimum and maximum values in the column of data, respectively;

[0021] Step 2.3: constructing a first deep learning model;

[0022] Preferably, the first deep learning model is a convolutional neural network model, which includes an input layer, a convolutional layer, a pooling layer, a fully connected layer and a classification layer;

[0023] Step 2.4: dividing the fault sample set into a training set and a test set according to a ratio of 8:2; and training the first deep learning model to obtain optimal network parameters;

[0024] Preferably, a loss function is constructed to determine the appearance of optimal network parameters, and the formula of the loss function is known in the art and will not be described in detail here. Meanwhile, the test set is input into the trained model to verify the effectiveness of the model.

[0025] Step 2.5: inputting the preprocessed numerical information actually collected into the first deep learning model to obtain a power grid diagnosis conclusion;

[0026] Preferably, the power grid diagnosis conclusion includes fault type and fault location.

[0027] Preferably, the second artificial intelligence model is a second deep learning model, which is a BP neural network model;

[0028] Preferably, the specific process of the second deep learning model for fault diagnosis of the power grid is as follows:

[0029] Step 3.1: obtaining text type information in historical faults collected by the system as a sample set;

[0030] Step 3.2: using a word segmentation model to vectorize the sample set;

[0031] Preferably, each piece of text type information is segmented according to the power station, the equipment, the equipment description and the action description, and a word vector is generated; then a text vector is generated according to the word vector, so that each piece of text type information is converted into a text vector;

[0032] Step 3.3: Labeling each of the sample sets with a fault event for obtaining a fault sample set for training the second deep learning model;

[0033] Step 3.4: Building and training the second deep learning model;

[0034] Specifically, the second deep learning model is a BP neural network model; the network structure of the BP neural network model includes three input layers, three hidden layers and three output layers, the forward propagation process of the BP neural network is used to calculate the output of the network, and the backward propagation process is used to adjust the network weight according to the error feedback, the input of the BP neural network is the text vector, and the output is the result of the power grid fault diagnosis;

[0035] Preferably, the sample set is divided into a training sample set, a verification sample set and a test sample set;

[0036] The training sample set is input into the BP neural network model, the BP neural network model is trained, and at the same time, the error of the BP neural network model is evaluated by using the verification sample set, if the error continues to decrease, the training is continued until the preset error precision is met; after the training is completed, the trained BP neural network model is verified by using the test sample set, and whether the accuracy requirement is met is determined;

[0037] Step 3.5: After the actually collected text type information is processed by the step 3.2, the text type information is input into the second deep learning model, so that the power grid diagnosis conclusion is obtained;

[0038] Preferably, the power grid diagnosis conclusion of the embodiment is the same as that of the first deep learning network model, and includes the fault type and the fault position.

[0039] According to another aspect of the present application, a power grid fault diagnosis system based on artificial intelligence technology is provided for diagnosing power grid faults, which adopts the power grid fault diagnosis method based on artificial intelligence technology described above; the system further comprises:

[0040] An alarm information classification module is configured to classify the alarm information of the power grid after the fault occurs;

[0041] A first fault diagnosis module is configured to diagnose the power grid fault of the numerical type information by using the first artificial intelligence model;

[0042] A second fault diagnosis module is configured to use a second artificial intelligence model to diagnose the fault of the power grid based on the text type information.

[0043] A final fault determination module is configured to determine whether the power grid diagnosis conclusion obtained in the step 2 is the same as the power grid diagnosis conclusion obtained in the step 3, and if so, determine the final fault of the power grid, and if not, the expert intervention is required to diagnose the fault of the power grid.

[0044] According to another aspect of the present application, a computer readable storage medium is also provided, and the computer readable storage medium stores a data processing program, and the data processing program is executed by a processor to implement the above-mentioned power grid fault diagnosis method based on artificial intelligence technology.

[0045] Based on the above technical solution, the power grid fault diagnosis method and system based on artificial intelligence technology provided by the present application has the following technical effects:

[0046] In the present application, when diagnosing the fault of a complex power grid, the obtained fault information is divided into numerical type information and text type information according to the type of the fault information, so as to avoid the situation that the dimension of the input information is too large, and the artificial intelligence model requires a large amount of training and high hardware requirements. At the same time, for the same fault, according to the applicability of the model to different types of data, the convolutional neural network model is used to diagnose the fault of the numerical type information, and the BP convolutional neural network model is used to diagnose the fault of the text type information, and then the final diagnosis conclusion is determined according to the two diagnosis results, which greatly improves the accuracy of the fault diagnosis. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0048] Figure 1 A flowchart of a power grid fault diagnosis method based on artificial intelligence technology provided by the present application is shown in the figure.

[0049] Figure 2 A flowchart of a first deep learning model for diagnosing the fault of a power grid provided by the present application is shown in the figure.

[0050] Figure 3 A flowchart of a second deep learning model for diagnosing the fault of a power grid provided by the present application is shown in the figure.

[0051] Figure 4 A schematic diagram of a power grid fault diagnosis system based on artificial intelligence technology provided by the present application is shown in the figure. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0053] The following first describes the concepts involved in this application with reference to the accompanying drawings. It should be noted that the following description of each concept is only for the purpose of making the content of this application easier to understand and does not limit the scope of protection of this application.

[0054] Embodiment 1. In the example of this embodiment, in order to achieve the above-mentioned purpose, a power grid fault diagnosis method based on artificial intelligence technology is provided, and a deep learning model is used as an artificial intelligence model for fault diagnosis of complex power grids. Traditional fault diagnosis is a labor-intensive process that requires professional knowledge and experience of relevant system-related features. Such knowledge and experience sometimes cost a high price. Deep learning, as an artificial intelligence technology, uses artificial intelligence to intelligently perform fault diagnosis, which can effectively improve the accuracy of fault diagnosis. Of course, this embodiment can also use other artificial intelligence models as the power grid fault diagnosis model in this application. Again, this does not constitute a limitation on the scope of protection of this application.

[0055] like Figure 1 As shown, a power grid fault diagnosis method based on artificial intelligence technology includes the following steps:

[0056] Step 1: Classify the alarm information of the power grid after the fault occurs;

[0057] For complex power grids, when a fault occurs, a lot of alarm information will be generated in the power grid because different topological structures of the power grid contain multiple monitoring devices. For example, the data acquisition and monitoring control system will generate fault descriptions, protection action signals, SOE signals, etc. The wide area measurement system will generate the amplitude of the fault voltage, the phase angle of the fault voltage, the amplitude of the fault current, the phase angle of the fault current, etc. The relay protection fault information management system will generate fault recording signals, protection action signals, etc. Faced with such a large number of signals, if they are fully input into the artificial intelligence model, this will undoubtedly generate a huge amount of calculation. In addition, different types of signals need to be converted into signals of the same type, which will invisibly lose some implicit information, resulting in inaccurate fault diagnosis. Therefore, this embodiment divides the alarm information into two categories according to different signal types: one is numerical information and the other is text information.

[0058] Further, in the embodiment, the numerical information includes: fault voltage amplitude, fault voltage phase, fault current amplitude, fault current phase, etc.; due to the complexity of the power grid topology structure, the switching quantity information is likely to be refused or misoperated, therefore, the embodiment does not use the switching quantity information as the input data of the power grid fault diagnosis;

[0059] Further, in the embodiment, the text information includes: fault description text reported by the monitoring system;

[0060] Step 2: using the first artificial intelligence model to perform power grid fault diagnosis on the numerical information;

[0061] Further, the first artificial intelligence model is a first deep learning model;

[0062] Further, the first deep learning model is a convolutional neural network model, as shown in the following figure: Figure 2 As shown in the figure, the specific process of the first deep learning model for power grid fault diagnosis is as follows:

[0063] Step 2.1: build a power grid topology structure model through a simulation system, and set different fault points to obtain a plurality of fault sample sets;

[0064] Specifically, the power grid topology structure model can be built through a Simulink platform; the Simulink platform is a visual simulation tool in MATLAB developed by Mathworks Company of the United States, which is a module diagram environment for multi-domain simulation and model-based design. It supports system design, simulation, automatic code generation, and continuous testing and verification of embedded systems, and provides a graphical editor, a customizable module library, and a solver, which can be used for dynamic system modeling and simulation.

[0065] Exemplarily, in the embodiment, a power grid topology structure model of 6 regions, 25 busbars, and 12 power supply sources is built in the Simulink platform, wherein the 25 busbars are 110kv busbars, the 12 power supply sources include 6 direct current power supply systems and 6 alternating current power supply systems, the set fault types are single-phase ground fault, three-phase ground fault, single-phase short circuit fault, and three-phase pipeline fault, etc.; and 1024 fault sample data sets are provided;

[0066] Step 2.2: data preprocessing of the fault sample set;

[0067] Since the fault sample set contains a plurality of data samples, it is necessary to perform normalization processing on each column of data in the fault sample set; specifically, the normalization processing formula is as follows:

[0068]

[0069] ′

[0070] Among them, x i is the normalized electrical value, xi is the ith electrical value, x min and x max They are the minimum and maximum values ​​in the column data respectively;

[0071] Step 2.3: Build the first deep learning model;

[0072] Specifically, the first deep learning model is a convolutional neural network model, which includes an input layer, a convolution layer, a pooling layer, a fully connected layer, and a classification layer;

[0073] Step 2.4: Divide the fault sample set into a training set and a test set in a ratio of 8:2; and train the first deep learning model to obtain the optimal network parameters;

[0074] Specifically, a loss function is constructed to determine the optimal network parameters. The specific loss function formula is an existing technology and will not be described in detail here. At the same time, the test set is input into the trained model to verify the effectiveness of the model.

[0075] Step 2.5: After preprocessing, the actually collected numerical information is input into the first deep learning model to obtain the power grid diagnosis conclusion;

[0076] Specifically, the power grid diagnosis conclusion of this embodiment includes the fault type and fault location. For example, the power grid fault diagnosis conclusion includes a single-phase grounding fault of a certain bus section, a single-phase grounding fault of a certain line section, a three-phase grounding fault of a certain bus section, a three-phase grounding fault of a certain line section, etc.

[0077] Step 3: Use the second artificial intelligence model to perform power grid fault diagnosis on the text information;

[0078] Specifically, the second artificial intelligence model is a second deep learning model, and the second deep learning model is a BP neural network model;

[0079] Specifically, if Figure 3 As shown in FIG, the specific process of using the second deep learning model to diagnose power grid faults is as follows:

[0080] Step 3.1: Obtain text information from historical faults collected by the system as a sample set;

[0081] Step 3.2: Use the word segmentation model to vectorize the sample set;

[0082] Specifically, each piece of text type information is segmented according to the power station, the equipment, the equipment description and the action description, and a word vector is generated; then a text vector is generated according to the word vector, so that each piece of text type information is converted into a text vector;

[0083] Step 3.3: Label each sample set with a fault event for obtaining a fault sample set for training the second deep learning model;

[0084] Step 3.4: Building and training the second deep learning model;

[0085] Specifically, the second deep learning model is a BP neural network model; the network structure of the BP neural network model includes three input layers, three hidden layers and three output layers, the forward propagation process of the BP neural network is used to calculate the output of the network, the backward propagation process is used to adjust the network weight according to the error feedback, the input of the BP neural network is the text vector, and the output is the result of the power grid fault diagnosis;

[0086] Further, the sample set is divided into a training sample set, a verification sample set and a test sample set;

[0087] The training sample set is input into the BP neural network model, the BP neural network model is trained, and at the same time, the error of the BP neural network model is evaluated by using the verification sample set, if the error continues to decrease, the training is continued until the preset error precision is met; after the training is completed, the trained BP neural network model is verified by using the test sample set, and whether the accuracy requirement is met is determined;

[0088] Step 3.5: The text type information actually collected is processed by step 3.2 and then input into the second deep learning model, so that the power grid diagnosis conclusion is obtained;

[0089] Specifically, the power grid diagnosis conclusion of the embodiment is the same as that of the first deep learning network model, including the fault type and the fault position.

[0090] Step 4: determining whether the power grid diagnosis conclusion obtained in step 2 and the power grid diagnosis conclusion obtained in step 3 are the same; if they are the same, the final fault of the final power grid is determined, if they are different, manual intervention is performed for the diagnosis of the power grid fault.

[0091] In the example of the embodiment two, as shown in Figure 4 a power grid fault diagnosis system based on artificial intelligence technology is provided for diagnosing the power grid fault, which adopts the power grid fault diagnosis method based on artificial intelligence technology in the embodiment one; the system further includes:

[0092] an alarm information classification module for classifying the alarm information of the power grid after the fault occurs;

[0093] The first fault diagnosis module is configured to diagnose the fault of the power grid by using the first artificial intelligence model on the numerical information.

[0094] The second fault diagnosis module is configured to diagnose the fault of the power grid by using the second artificial intelligence model on the text information.

[0095] The final fault determination module is configured to determine whether the power grid diagnosis conclusion obtained in step 2 is the same as the power grid diagnosis conclusion obtained in step 3; if yes, the final fault of the power grid is determined; if no, the diagnosis of the fault of the power grid is performed by manual intervention.

[0096] In embodiment three, a computer readable storage medium is provided, and a data processing program is stored on the computer readable storage medium. The data processing program is executed by a processor to implement the power grid fault diagnosis method based on the artificial intelligence technology in embodiment one.

[0097] Those skilled in the art should understand that the embodiments herein can be provided as a method, device (apparatus), or computer program product. Therefore, the embodiments herein can be in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. The embodiments herein include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile discs (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer, and the like. In addition, it is well known to those skilled in the art that a communication medium generally includes computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and can include any information delivery medium.

[0098] Herein, the methods, devices (apparatuses) and computer program products according to the embodiments herein are described with reference to flowcharts and / or block diagrams. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus generate a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The device for implementing the functions specified in one flow or multiple flows and / or blocks Figure 1 The device for implementing the functions specified in one flow or multiple flows and / or blocks

[0099] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flow Figure 1 The flow or flows and / or blocks Figure 1 The flow or flows and / or blocks

[0100] The above embodiments and / or implementations are only used to illustrate the preferred embodiments and / or implementations of the present application, and not intended to limit the scope of the embodiments of the present application in any form. Any person skilled in the art can make some changes or modifications as other equivalent embodiments without departing from the scope of the technical means disclosed in the present application, but should be considered as the same technology or embodiments as the present application.

Claims

1. A power grid fault diagnosis method based on artificial intelligence technology, characterized in that: The following steps are involved: Step 1: Classify the alarm information of the power grid after the fault occurs. According to the different signal types, the alarm information is divided into two categories: one is numerical information and the other is text information; Step 2: Using a first artificial intelligence model to perform power grid fault diagnosis on the numerical information; the first artificial intelligence model is a convolutional neural network model; Step 3: Use the second artificial intelligence model to perform power grid fault diagnosis on the text information; the second artificial intelligence model is a BP neural network model; the specific process of using the second artificial intelligence model to perform power grid fault diagnosis is as follows: Step 3.1: Obtain text information from historical faults collected by the system as a sample set; Step 3.2: Use a word segmentation model to vectorize the sample set; Step 3.3: labeling each sample set with a fault event label to obtain a fault sample set for training the BP neural network model; Step 3.4: Building and training the BP neural network model; Step 3.5: After the text information actually collected is processed in step 3.2, it is input into the BP neural network model to obtain the power grid diagnosis conclusion; Step 4: Determine whether the power grid diagnosis conclusion obtained in step 2 is the same as the power grid diagnosis conclusion obtained in step 3; if they are the same, determine it as the final fault of the final power grid; if they are different, experts intervene to diagnose the power grid fault.

2. The power grid fault diagnosis method based on artificial intelligence technology according to claim 1 is characterized in that: The numerical information includes: fault voltage amplitude, fault voltage phase, fault current amplitude, and fault current phase; the text information includes: fault description text reported by the monitoring system.

3. The power grid fault diagnosis method based on artificial intelligence technology according to claim 2 is characterized in that: The specific process of using the first artificial intelligence model to diagnose power grid faults is as follows: Step 2.1: Build a power grid topology model through the simulation system and set different fault points to obtain multiple fault sample sets; Step 2.2: Perform homogenization preprocessing on the data of the fault sample set; The homogenization pretreatment formula is: Where x′ i is the normalized electrical value, xi is the ith electrical value, x min and x max are the minimum and maximum values ​​in the data respectively; Step 2.3: Construct a first deep learning model; the first deep learning model is a convolutional neural network model, and the convolutional neural network model includes an input layer, a convolution layer, a pooling layer, a fully connected layer, and a classification layer; Step 2.4: Divide the fault sample set into a training set and a test set in a ratio of 8:2; and train the first deep learning model to obtain optimal network parameters; Step 2.5: After preprocessing, the actually collected numerical information is input into the first deep learning model to obtain the power grid diagnosis conclusion.

4. The power grid fault diagnosis method based on artificial intelligence technology according to claim 3 is characterized in that: The grid topology model is constructed using the Simulink platform.

5. The power grid fault diagnosis method based on artificial intelligence technology according to claim 1 is characterized in that: The power grid diagnosis conclusion includes the fault type and the fault location.

6. The power grid fault diagnosis method based on artificial intelligence technology according to claim 1 is characterized in that: The specific steps of step 3.2 are as follows: each piece of text information is segmented according to plant, equipment, equipment description, and action description, and a word vector is generated; then a text vector is generated based on the word vector, thereby converting each piece of text information into a text vector.

7. A power grid fault diagnosis system based on artificial intelligence technology, using the power grid fault diagnosis method according to any one of claims 1 to 6, the system further comprising: An alarm information classification module is used to classify the alarm information of the power grid after a fault occurs; a first fault diagnosis module, configured to perform power grid fault diagnosis on numerical information using a first artificial intelligence model; A second fault diagnosis module, configured to use a second artificial intelligence model to perform power grid fault diagnosis on the text information; The final fault determination module is used to determine whether the power grid diagnosis conclusion obtained in step 2 is the same as the power grid diagnosis conclusion obtained in step 3; if they are the same, it is determined as the final fault of the final power grid; if they are different, experts intervene to diagnose the power grid fault.

Images