Electric power system fault rapid diagnosis system based on artificial intelligence

Abstract

The invention relates to the technical field of fault diagnosis, and particularly discloses an electric power system fault rapid diagnosis system based on artificial intelligence, which comprises a state monitoring module, a fault diagnosis module, a data management module, a decision response module and a system configuration module, the fault diagnosis module is used for analyzing the real-time data, extracting fault information from the real-time data and determining the time and the position of a fault, and the data management module is responsible for receiving and storing the real-time data and carrying out information fusion on the data; according to the method, all the obtained data of the power system are analyzed and integrated, then the data are used for calculation to determine the fault moment and the fault position respectively, two kinds of diagnosis information are combined into a whole through OWA-based fusion, then mining is carried out through data of the area where the fault is located, proper coping suggestions are provided for workers, and the fault diagnosis efficiency is improved. And automatically executing emergency measures.

Description

Technical Field

[0001] The present invention belongs to the technical field of fault diagnosis, and in particular relates to an artificial intelligence-based rapid fault diagnosis system for an electric power system. Background Art

[0002] In smart grids, diagnosing the location of early faults is an important means of maintaining power supply reliability and conducting fault analysis. Once a power grid fails, it will spread rapidly in the distributed system and may cause secondary failures in the system. The development of modern society has put forward higher requirements for power systems in improving power supply reliability. However, due to the wide variety of nodes and different functions in the power system, the data generated by the operation of power system nodes is huge and complex. The workload of confirming the data of faults in the huge data is very huge and it is very easy to confirm.

[0003] At present, fault detection and diagnosis have been widely used in smart grids. One method is to use the information of phasor measurement units (PMUs) to detect the fault location of smart grids. PMUs receive synchronization signals from global positioning system satellites and determine the voltage and current phasors of substations. Since the measurement cost of PMUs is relatively high, in actual applications, only a few PMUs are usually used, and then the voltage of other power grids is calculated using Ohm's formula. Another is an intelligent detection method based on artificial neural networks, fuzzy logic, fuzzy Petri nets, support vector machines, decision trees, etc., which trains artificial intelligence models by using the data generated by node operation as training samples. Since the data generated by node operation is a large number of unlabeled data sets, the accuracy of fault diagnosis of the trained model is not ideal.

[0004] Therefore, it is necessary to propose an artificial intelligence-based rapid fault diagnosis system for power systems to at least partially solve the problems existing in the prior art.

[0005] The above information disclosed in this background technology is only used to increase the understanding of the background technology of the present invention and therefore, it may include information that does not constitute the prior art known to ordinary technicians in this field. Summary of the invention

[0006] The purpose of the present invention is to provide an artificial intelligence-based rapid fault diagnosis system for a power system to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] The artificial intelligence-based rapid fault diagnosis system for power systems includes: a state monitoring module, a fault diagnosis module, a data management module, a decision response module, and a system configuration module. The state monitoring module is responsible for collecting real-time data of the power system to ensure the accuracy and real-time nature of the data. The fault diagnosis module is used to analyze the real-time data to extract fault information therefrom and determine the time and location of the fault. The data management module is responsible for receiving and storing real-time data and performing information fusion on the data. The decision response module is used to provide fault handling suggestions based on the fault information or automatically execute preset emergency measures. The system configuration module is responsible for managing and setting various parameters and options of the system to ensure that the system operates as expected.

[0009] Preferably, the data management module transmits the acquired power system data through a data interface, and uses multi-threaded parallelism to implement parallel operation of data reception, splitting, sorting and storage, so as to reduce the impact of time delays caused by splitting and sorting on data integrity and stability.

[0010] The acquisition parameter database includes real-time data and historical storage data received by the data interface, and the input knowledge database includes conventional alarm limit parameters, indicator diagram feature criteria, fault diagnosis expert data, user-set parameters, and possible fault mapping relationships of diesel engines, generators, power grids, loads, etc. in the power system. The two databases together form the database foundation for big data analysis. During operation, knowledge can be added, modified, and deleted by a dedicated person under the conditions of permission as needed.

[0011] Preferably, the fault diagnosis module obtains the actual fault time and fault area based on the real-time monitoring data by determining the fault time based on the MSR indicator and locating the fault area based on the PMU data correlation analysis, classifies the detected anomalies, and determines the impact range of the fault.

[0012] Preferably, the status monitoring module monitors the data measured by the detection equipment in real time, and transmits it together with the collected inherent data of the power system to the data management module, while using historical fault data to focus on locations prone to faults, and displays real-time status parameters on the terminal interface.

[0013] Preferably, the status monitoring module uses the acquired monitoring data to generate a status parameter trend graph of each device, and combines the data management module to process the data to display it to the staff in a visual manner. At the same time, the status monitoring module will send alarm and prompt information based on the analysis results of the fault diagnosis module.

[0014] Preferably, after receiving the analysis result of the fault diagnosis module, the data management module uses the OWA operator to fuse the two types of diagnostic information, integrates it with the data in the fault time window, and then sends it to the decision response module through the data interface.

[0015] The fault time window extracts the known data of the fault location and its surrounding equipment based on the determined fault time and location with a preset time span, integrates it with the data of the fault time and location, and uses it as the data basis for subsequent determination of execution recommendations and emergency measures.

[0016] Diagnostic information fusion based on OWA operator: The OWA operator can be considered as a mapping from a space with dimension n to a space with dimension 1, which is represented by F:R n →R represents the associated weight vector W = [ω1, ω2, ..., ω n ] T Subject to the following relationship:

[0017]

[0018]

[0019] Where b k represents a1,…,a n The kth maximum value in , sample k can be in is the information of the g-th data source in the k-th sampling time, b k To obtain the optimal result for the sample, the weight vector W is obtained using the following criteria:

[0020]

[0021] Preferably, the decision response module uses data mining technology with the analysis results of the fault diagnosis module as the core, combines the data within the fault time window for analysis, determines the processing suggestions that meet the current fault type, provides them to the staff through the communication interface, and automatically executes emergency measures to achieve rapid response.

[0022] Preferably, the system configuration module implements the access of each module to the database through the LabSQL toolkit using Microsoft ADO technology and SQL language, provides an easy-to-operate interface for staff and automatically generates a fault diagnosis report. Staff can modify the system configuration information to adjust and add or delete preset emergency measures.

[0023] An electric power device, comprising a terminal device and a plurality of node devices; wherein the terminal device comprises a memory and a processor; the memory is connected to the processor and is used to store programs; the processor is used to implement the above-mentioned rapid fault diagnosis system by running the programs stored in the memory.

[0024] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the above-mentioned rapid fault diagnosis system.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] The present invention analyzes and integrates the various data obtained from the power system, and then uses the data to calculate and determine the fault time and fault location respectively, and uses OWA-based fusion to integrate the two types of diagnostic information into one, which can effectively combine different diagnostic information and diagnose the specific situation of the fault in advance. After that, the data of the fault area is mined to provide appropriate response suggestions to the staff, and automatically execute emergency measures, which can reduce the impact of the fault on the power system and avoid the expansion of the fault range of the power system.

[0027] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 This is a framework diagram of the power system fault rapid diagnosis system based on artificial intelligence of the present invention;

[0029] Figure 2 A flow chart of determining the fault time based on the MSR indicator of the present invention;

[0030] Figure 3 This is a flow chart of fault area location based on PMU data correlation analysis of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] It should be further understood that the term “and / or” used in the specification of this application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0033] Embodiment 1:

[0034] See also Figure 2-Figure 3 As shown, the artificial intelligence-based rapid fault diagnosis system for power systems includes: a fault diagnosis module for analyzing real-time data to extract fault information therefrom and determine the time and location of the fault; the fault diagnosis module obtains the actual fault time and fault area based on the real-time monitoring data by determining the fault time based on the MSR indicator and locating the fault area based on the PMU data correlation analysis, classifies the detected anomalies, and determines the impact range of the fault.

[0035] The steps of the fault moment determination process based on the MSR indicator are as follows:

[0036] (1) Collect PMU measurement data, extract the three-phase voltage amplitude (or three-phase voltage and three-phase current amplitude) of each PMU, and generate the original data matrix X;

[0037] (2) Determine the length and width of the real-time sliding time window, and obtain the real-time sliding time window matrix X at time t from X t , and for the matrix X t Standardization was performed as follows;

[0038]

[0039] In the formula, x i,j Represents the value of the i-th PMU vector at the j-th sampling point, and the length and width of the real-time sliding window are N w ×T w , i=1,2,...,N w ,j=1,2,...,T w ,μ(x i ) and σ(x i ) are x i The mean and standard deviation of μ(x i )=0,σ(x i )=1;

[0040] (3) The standard matrix Z is calculated as follows, and the eigenvalues ​​of Z and the corresponding circular rings are quantitatively obtained using a single ring;

[0041]

[0042]

[0043] Where Z is a random matrix X with L non-Hermitian features l The product of (l=1,2,...L), X u,l ∈C N×N is a random matrix X l The singular value equivalent matrix of u is the singular value equivalent matrix of X;

[0044] (4) The average spectral radius r of Z at time t is obtained as follows: MSR (t);

[0045]

[0046] In the formula, λ i are all eigenvalues ​​of X;

[0047] (5) Repeat steps (2) to (4) to calculate the average spectral radius r at each moment in real time MSR (t);

[0048] (6) Draw a graph showing the average spectral radius change trend and compare it with the average spectral radius r at the current moment. MSR (t) and the inner ring radius r2, if r MSR (t)<r2, it means that the system has an abnormality at time t.

[0049] The steps of the fault area location process based on PMU data correlation analysis are as follows:

[0050] (1) Collect PMU measurement data, take electrical nodes as units, extract the three-phase voltage amplitude (or three-phase voltage and three-phase current amplitude) of each PMU, and generate the state data matrix D p(i) ;

[0051] (2) According to the given signal-to-noise ratio ρ(i), construct the factor matrix D of the yth influencing factor of node i e(i,y) , augmented matrix X A(i,y) and reference augmented matrix X ARef(i,y) ;

[0052] (3) Determine the length and width of the timing sliding time window, from X A(i,y) Get the real-time sliding time window matrix X at time t A(i,y) (t), and for X A(i,y) (t) Perform unified standardization processing according to the following formula;

[0053]

[0054] In the formula, x d,y Indicates the value of the yth influencing factor of the i-th electrical node, and the length and width of the real-time sliding window are Nw ×T w , i=1,2,...,N w ,j=1,2,...,T w ,μ(x i ) and σ(x i ) are x i The mean and standard deviation of μ(x i )=0,σ(x i )=1;

[0055] (4) The augmented matrix X at time t is calculated as follows: A(i,y) The average spectral radius of (t) Similarly, we can obtain the reference augmented matrix X ARef(i,y) The average spectral radius of (t)

[0056]

[0057]

[0058]

[0059] Where Z is a random matrix X with L non-Hermitian features l The product of (l=1,2,...L), X u,l ∈C N×N is a random matrix X l The singular value equivalent matrix of u is the singular value equivalent matrix of X, λ i are all eigenvalues ​​of X;

[0060] (5) The difference d in the average spectral radius of the yth influencing factor of node i at time t is calculated as follows: MSR(i,y) (t) and the average spectral radius integral S MSR(i,y) (t);

[0061]

[0062]

[0063] (6) Repeat steps (3) to (5) to calculate the difference d between the average spectral radius of each node and each influencing factor at each time in real time MSR ( i,y) (t) and the average spectral radius integral S MSR ( i,y )(t);

[0064] (7) Draw a trend chart of the difference in average spectral radius and compare the d of each node at each time.MSR ( i,y )(t) and d MSR ( i ) ,0 ,like It indicates that the influencing factor y in node i affects the disturbance at that moment, otherwise it indicates that the node is not the location that causes the system disturbance;

[0065] (8) For all satisfying d MSR ( i,y )(t)>d MSR ( i ) ,0 The average spectral radius integral S of the nodes MSR ( i )(t) Sort from small to large, S MSR ( i) The larger (t) is, the more important the corresponding influencing factor is in the system disturbance within the sampling time of the real-time sliding time window, and the more likely the corresponding electrical node is to be the fault area.

[0066] Embodiment 2:

[0067] See also Figure 1 As shown, the power system fault rapid diagnosis system based on artificial intelligence includes:

[0068] The status monitoring module is responsible for collecting real-time data of the power system to ensure the accuracy and real-time nature of the data. The status monitoring module monitors the data measured by the detection equipment in real time, and transmits it together with the collected inherent data of the power system to the data management module. At the same time, it uses historical fault data to focus on locations prone to faults and displays real-time status parameters on the terminal interface.

[0069] The acquired monitoring data is used to generate a status parameter trend chart of each device, and the data management module processes the data to display it to the staff in a visual manner. At the same time, the status monitoring module will send alarms and prompt information based on the analysis results of the fault diagnosis module.

[0070] The data management module is responsible for receiving and storing real-time data and fusing the data. The data management module transmits the acquired power system data through the data interface and uses multi-threaded parallelism to realize the parallel operation of data reception, splitting, sorting and storage to reduce the impact of time delay caused by splitting and sorting on data integrity and stability. After receiving the analysis results of the fault diagnosis module, the OWA operator is used to fuse the two diagnostic information, integrate it with the data in the fault time window, and then send it to the decision response module through the data interface.

[0071] The decision response module is used to provide fault handling suggestions or automatically execute preset emergency measures based on fault information. The decision response module uses data mining technology to analyze the analysis results of the fault diagnosis module as the core, combined with the data within the fault time window, to determine the handling suggestions that meet the current fault type and provide them to the staff through the communication interface, and automatically execute emergency measures to achieve rapid response.

[0072] The system configuration module is responsible for managing and setting various parameters and options of the system to ensure that the system runs as expected. The system configuration module uses the LabSQL toolkit to implement each module's access to the database using Microsoft ADO technology and SQL language, providing staff with an easy-to-use interface and automatically generating fault diagnosis reports. Staff can modify the system configuration information to adjust, add or delete preset emergency measures.

[0073] The fault diagnosis module is used to analyze real-time data to extract fault information and determine the time and location of the fault. Based on the real-time monitoring data, the fault diagnosis module determines the fault time based on the MSR indicator and locates the fault area based on the PMU data correlation analysis to obtain the actual fault time and fault area, classify the detected anomalies, and determine the impact range of the fault.

[0074] From the above, it can be seen that the present invention analyzes and integrates the various data obtained from the power system, and then uses the data to calculate to determine the fault time and fault location respectively, and uses the OWA-based fusion to integrate the two types of diagnostic information into one, so that different diagnostic information can be effectively combined and the specific situation of the fault can be diagnosed in advance. After that, the data of the area where the fault is located is used for mining, and appropriate response suggestions are provided to the staff, and emergency measures are automatically executed, which can reduce the impact of the fault on the power system and avoid the expansion of the scope of the power system fault.

[0075] Embodiment 3:

[0076] An embodiment of the present invention also provides an electric power device, which includes a terminal device and multiple node devices; wherein the terminal device includes a memory and a processor; the memory is connected to the processor and is used to store programs; the processor is used to implement the fault rapid diagnosis system as described above by running the program stored in the memory.

[0077] The embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the processor implements the above-mentioned rapid fault diagnosis system, and can achieve the same technical effect, which will not be described here to avoid repetition. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0078] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0079] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, 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 device to generate a program, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A way to specify functions in one or more boxes.

[0080] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0081] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0082] In the drawings of the embodiments disclosed in the present invention, only the structures involved in the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other.

[0083] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0084] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. Rapid fault diagnosis system for power system based on artificial intelligence, including: The state monitoring module, fault diagnosis module, data management module, decision response module and system configuration module are characterized in that the state monitoring module is responsible for collecting real-time data of the power system to ensure the accuracy and real-time nature of the data; the fault diagnosis module is used to analyze the real-time data to extract fault information therefrom and determine the time and location of the fault; the data management module is responsible for receiving and storing real-time data and performing information fusion on the data; the decision response module is used to provide fault handling suggestions or automatically execute preset emergency measures based on the fault information; and the system configuration module is responsible for managing and setting various parameters and options of the system to ensure that the system operates as expected.

2. The artificial intelligence-based rapid fault diagnosis system for electric power systems according to claim 1 is characterized in that: The data management module transmits the acquired power system data through the data interface, and uses multi-threaded parallelism to achieve parallel operation of data reception, splitting, sorting and storage to reduce the impact of time delays caused by splitting and sorting on data integrity and stability.

3. The artificial intelligence-based rapid fault diagnosis system for electric power systems according to claim 2 is characterized in that: The fault diagnosis module obtains the actual fault time and fault area based on the real-time monitoring data by determining the fault time based on the MSR indicator and locating the fault area based on the PMU data correlation analysis, classifies the detected anomalies, and determines the impact range of the fault.

4. The artificial intelligence-based rapid fault diagnosis system for electric power systems according to claim 3 is characterized in that: The status monitoring module monitors the data measured by the detection equipment in real time, and transmits it together with the collected inherent data of the power system to the data management module. At the same time, it uses historical fault data to focus on the locations prone to faults, and displays the real-time status parameters on the terminal interface.

5. The artificial intelligence-based rapid fault diagnosis system for electric power systems according to claim 4 is characterized in that: The status monitoring module uses the acquired monitoring data to generate a status parameter trend chart of each device, and combines the data management module to process the data in a visual manner to display it to the staff. At the same time, the status monitoring module will send alarm and prompt information based on the analysis results of the fault diagnosis module.

6. The artificial intelligence-based rapid fault diagnosis system for electric power systems according to claim 5 is characterized in that: After receiving the analysis result of the fault diagnosis module, the data management module uses the OWA operator to fuse the two types of diagnostic information, integrates it with the data in the fault time window, and then sends it to the decision response module through the data interface.

7. The artificial intelligence-based rapid fault diagnosis system for electric power systems according to claim 6 is characterized in that: The decision response module uses data mining technology to analyze the analysis results of the fault diagnosis module as the core, combines the data within the fault time window for analysis, determines the processing suggestions that meet the current fault type, and provides them to the staff through the communication interface, automatically executing emergency measures to achieve rapid response.

8. The artificial intelligence-based rapid fault diagnosis system for electric power systems according to claim 7 is characterized in that: The system configuration module uses the LabSQL toolkit to implement the access of each module to the database using Microsoft ADO technology and SQL language, providing an easy-to-operate interface for staff and automatically generating fault diagnosis reports. Staff can modify the system configuration information to adjust, add or delete preset emergency measures.

9. An electric power device, characterized in that: The power device includes a terminal device and multiple node devices; wherein the terminal device includes a memory and a processor; the memory is connected to the processor and is used to store programs; the processor is used to implement the fault rapid diagnosis system as described in claims 1-8 by running the program stored in the memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the rapid fault diagnosis system according to claims 1-8.

Images