Distribution network area fault diagnosis method, device, equipment and medium

Abstract

The invention discloses a distribution network area fault diagnosis method, device, equipment and medium, and relates to the field of distribution network fault diagnosis, and the main points of the technical scheme are that the method comprises the steps: obtaining the electrical quantity of each element when a fault occurs in a distribution network area, and the switching value of a relay protection device associated with each element; performing wavelet transformation on the electrical quantity by adopting a wavelet function to obtain wavelet transformation results of each element before and after the fault occurs; calculating the relative fault degree of the electrical quantity of each element through a wavelet transformation result; according to the switching values, constructing a Bayesian network of action information of the relay protection device associated with the elements, assigning values to nodes of the Bayesian network based on the action information, and calculating the fault probability of each element based on the assigned Bayesian network; calculating a switching value relative fault degree based on the probability; and fusing the electrical quantity relative fault degree and the switching quantity relative fault degree to obtain a fusion fault probability of each element, and diagnosing a fault element in each element of the distribution network area according to the fusion fault probability.

Description

Technical Field

[0001] The present application relates to the field of distribution network fault diagnosis, and more specifically, to a distribution network substation fault diagnosis method, device, equipment and medium. Background Art

[0002] As the scale of the power grid gradually expands and the number of power distribution equipment continues to increase, power distribution substation faults occur repeatedly. At present, the emergency repair of sporadic distribution substations or user faults is mainly passive fault repair. Customers in the faulty substation call 95598 to report the problem and generate a repair work order, which is then transferred to the municipal power supply service command center and finally handled by the grassroots team. According to investigations and statistics, half of the time for emergency repair of sporadic distribution substations or user faults is currently spent on customer reporting and fault analysis. The fault response is not timely, which seriously affects the customer's electricity experience.

[0003] Traditional fault identification methods mainly rely on manual analysis and on-site verification to check item by item, with low accuracy. When conducting fault analysis, it is necessary to use various real-time and non-real-time information data provided by multi-source information systems to conduct comprehensive analysis based on multi-source information. When a fault occurs in a sporadic distribution network area or user, the main electrical quantities and switch quantity information near the fault point will change abnormally. The switch quantity information mainly refers to the action information of circuit breakers, disconnectors, etc., and the electrical quantity information refers to some electrical data such as node voltage and branch current of the distribution network.

[0004] At present, fault diagnosis methods can be divided into three categories: based on switch quantity, based on electrical quantity and based on non-fault key information. Among them, the method based on switch quantity is affected by the misoperation and false alarm of protection and circuit breaker action information, and the collected information is of low integrity, making it difficult to obtain accurate positioning results; the method based on electrical quantity uses information such as measured impedance and traveling wave characteristics after the fault, which is highly accurate, but requires more measurement points, especially when there are many distribution line branches, it is difficult to eliminate pseudo fault points; the method based on non-fault key information mostly uses user complaint information, which helps to identify the fault level in the distribution network topology when other fault information is missing, but the user complaint information is non-scheduled fault information after the fault, and the stability and timeliness are not high.

[0005] It can be seen that the current fault diagnosis using a single data source may lead to errors in fault diagnosis due to incomplete or distorted information in the data source. Summary of the invention

[0006] The present application provides a distribution network substation fault diagnosis method, device, equipment and medium to solve the problem of fault diagnosis errors caused by incomplete or distorted information when using a single data source for fault diagnosis.

[0007] In a first aspect of the present application, a distribution network area fault diagnosis method is provided, the method comprising:

[0008] Obtain the electrical quantity of each component when a fault occurs in the distribution network area;

[0009] The wavelet function is used to perform wavelet transform on the electrical quantity, and the first wavelet transform result of each component before the fault occurs and the second wavelet transform result after the fault occurs are obtained;

[0010] According to the first wavelet transform result and the second wavelet transform result, the relative fault degree of the electrical quantity of each component is calculated;

[0011] Obtain the switching value of the relay protection device associated with each component after a fault occurs in the distribution network area;

[0012] According to the switching quantity, a Bayesian network of the action information of the relay protection device associated with the component is constructed, and the nodes of the Bayesian network are assigned values ​​based on the action information of the relay protection device. The probability of failure of each component is calculated based on the assigned Bayesian network; the action information refers to the actual state value and expected state value of the action of the relay protection device;

[0013] The relative fault degree of the switch quantity of the relay protection device is calculated based on the probability of each component failing;

[0014] The relative fault degree of electrical quantity and the relative fault degree of switch quantity are integrated to obtain the integrated fault probability of each component. The faulty components in the distribution network substation are diagnosed according to the integrated fault probability of each component.

[0015] In one implementation, the relative fault degree of the electrical quantity of each component is calculated according to the first wavelet transform result and the second wavelet transform result, including:

[0016] Select the maximum value and the minimum value of the first wavelet transform result and the second wavelet transform result respectively;

[0017] Calculate the amplitude change of the electrical quantity of each component before and after the fault based on the maximum and minimum values;

[0018] The amplitude variation degree is annotated in combination with the first credibility to obtain the relative fault degree of the electrical quantity of each component.

[0019] In one implementation, the first credibility refers to the credibility of a result of fault diagnosis of a component based on a regularized orthogonal matching pursuit compressed sensing reconstruction algorithm.

[0020] In one implementation, the expression for calculating the probability of failure of each component is:

[0021] Among them, w iis the weight of each node to the root node; P(y) is the prior probability of a component failure; P(z i |y) wi When the weighted event y occurs, z i The posterior probability of occurrence, i represents the i-th element.

[0022] In one implementation, the relative fault degree of the switch quantity of the relay protection device is calculated based on the probability of failure of each component. Specifically, the probability of failure of each component is annotated in combination with the second credibility to obtain the relative fault degree of the switch quantity of the relay protection device.

[0023] In one implementation, the second credibility refers to the credibility of a fault diagnosis result of a relay protection device based on a regularized orthogonal matching pursuit compressed sensing reconstruction algorithm.

[0024] In one implementation, the relative fault degree of electrical quantity and the relative fault degree of switch quantity are integrated to obtain the integrated fault probability of each component, including:

[0025] Converting the relative fault degree of the electrical quantity into a first probability distribution function, and converting the relative fault degree of the switch quantity into a second probability distribution function;

[0026] Calculating a normalization coefficient according to the first probability distribution function and the second probability distribution function;

[0027] The fusion failure probability of each component is calculated according to the normalization coefficient, the first probability distribution function and the second probability distribution function.

[0028] In a second aspect of the present application, a distribution network area fault diagnosis device is provided, the device comprising:

[0029] The first acquisition module is used to obtain the electrical quantity of each component when a fault occurs in the distribution network area;

[0030] The first processing module is used to perform wavelet transform on the electrical quantity using a wavelet function to obtain a first wavelet transform result of each component before a fault occurs, and a second wavelet transform result after the fault occurs;

[0031] A first calculation module is used to calculate the relative fault degree of the electrical quantity of each component according to the first wavelet transformation result and the second wavelet transformation result;

[0032] The second acquisition module is used to obtain the switching value of the relay protection device associated with each component after a fault occurs in the distribution network substation;

[0033] The second processing module is used to construct a Bayesian network of the action information of the relay protection device associated with the component according to the switching quantity, and assign values ​​to the nodes of the Bayesian network based on the action information of the relay protection device, and calculate the probability of failure of each component based on the assigned Bayesian network; wherein the action information refers to the actual state value and the expected state value of the action of the relay protection device;

[0034] A second calculation module is used to calculate the relative fault degree of the switch quantity of the relay protection device based on the probability of each component failing;

[0035] The probability fusion module is used to fuse the relative fault degree of electrical quantities and the relative fault degree of switch quantities to obtain the fused fault probability of each component, and diagnose the faulty components in the components of the distribution network according to the fused fault probability of each component.

[0036] The third aspect of the present application provides an electronic device, which includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of a distribution network substation fault diagnosis method provided in the first aspect of the present application are implemented.

[0037] The third aspect of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of a distribution network substation fault diagnosis method provided in the first aspect of the present application are implemented.

[0038] Compared with the prior art, this application has the following beneficial effects:

[0039] In a distribution network substation fault diagnosis method provided in an embodiment of the present application, for the electrical quantity of the component and the switch quantity of the relay protection, wavelet transform and Bayesian network are used to perform fault feature analysis, respectively, to obtain the relative fault degree of the electrical quantity of each component and the relative fault degree of the switch quantity of the relay protection device associated with the component, respectively, and the relative fault degree of the electrical quantity and the relative fault degree of the switch quantity are integrated to determine the fusion fault probability of each component, and then the component corresponding to the maximum value of the fusion fault probability of each component is determined as the fault component. Since each data information reflects different fault characteristics of the power system fault, compared with the fault diagnosis algorithm of a single data source, the present application comprehensively utilizes the electrical quantity and switch quantity that characterize the fault state of the distribution network to make up for the fault diagnosis error caused by incomplete or distorted information when using a single data source for fault diagnosis, so that the redundancy of the collected data can be fully utilized to correct the influence of erroneous data and improve the accuracy of fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings described herein are used to provide a further understanding of the embodiments of the present application, constitute a part of the present application, and do not constitute a limitation on the embodiments of the present application. In the drawings:

[0041] Figure 1 A schematic diagram of a flow chart of a distribution network area fault diagnosis method provided in an embodiment of the present application;

[0042] Figure 2 A local schematic diagram of an abnormal area in a distribution network area provided in an embodiment of the present application;

[0043] Figure 3 A result diagram of the fused failure probability of each component in the abnormal area of ​​the distribution network provided in the embodiment of the present application;

[0044] Figure 4 A functional block diagram of a distribution network area fault diagnosis device provided in an embodiment of the present application;

[0045] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with examples and drawings. The illustrative implementation scheme of the present application and its description are only used to explain the present application and are not intended to limit the present application.

[0047] It should be noted that the terms "include" or "may include" used in various embodiments of the present application indicate the presence of the function, operation or element applied for, and do not limit the addition of one or more functions, operations or elements. In addition, as used in various embodiments of the present application, the terms "include", "have" and their cognates are only intended to indicate specific features, numbers, steps, operations, elements, components or a combination of the foregoing items, and should not be understood as first excluding the presence of one or more other features, numbers, steps, operations, elements, components or a combination of the foregoing items or the possibility of adding one or more features, numbers, steps, operations, elements, components or a combination of the foregoing items.

[0048] It should be understood that terms such as "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly indicate the number of technical features indicated. Therefore, features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0049] At present, fault diagnosis methods can be divided into three categories: based on switch quantity, based on electrical quantity and based on non-fault key information. Among them, the method based on switch quantity is affected by the misoperation and false alarm of protection and circuit breaker action information, and the collected information is of low integrity, making it difficult to obtain accurate positioning results; the method based on electrical quantity uses information such as measured impedance and traveling wave characteristics after the fault, which is highly accurate, but requires more measurement points, especially when there are many distribution line branches, it is difficult to eliminate pseudo fault points; the method based on non-fault key information mostly uses user complaint information, which helps to identify the fault level in the distribution network topology when other fault information is missing, but the user complaint information is non-scheduled fault information after the fault, and the stability and timeliness are not high.

[0050] It can be seen that the current fault diagnosis using a single data source may lead to errors in fault diagnosis due to incomplete or distorted information in the data source.

[0051] To this end, the embodiment of the present application provides a distribution network substation fault diagnosis method. For the electrical quantity of the component and the switch quantity of the relay protection, the wavelet transform and the Bayesian network are used to perform fault feature analysis, respectively, and the relative fault degree of the electrical quantity of each component and the relative fault degree of the switch quantity of the relay protection device associated with the component are obtained. The relative fault degree of the electrical quantity and the relative fault degree of the switch quantity are integrated to determine the fusion fault probability of each component, and then the component corresponding to the maximum value of the fusion fault probability of each component is determined as the fault component. Since each data information reflects different fault characteristics of the power system fault, compared with the fault diagnosis algorithm of a single data source, the present application comprehensively utilizes the electrical quantity and switch quantity that characterize the fault state of the distribution network to make up for the fault diagnosis error caused by incomplete or distorted information when using a single data source for fault diagnosis, so that the redundancy of the collected data can be fully utilized to correct the influence of erroneous data and improve the accuracy of fault diagnosis.

[0052] The following is a detailed description of the diagnostic method provided in the embodiment of the present application in conjunction with the accompanying drawings. Figure 1 , Figure 1 A schematic diagram of a flow chart of a distribution network area fault diagnosis method provided in an embodiment of the present application, such as Figure 1 As shown, the method includes:

[0053] S101, obtaining the electrical quantity of each component when a fault occurs in the distribution network substation.

[0054] In this embodiment, the electrical quantity refers to some electrical data such as node voltage and branch current of the power distribution network.

[0055] S102, using a wavelet function to perform wavelet transform on the electrical quantity, to obtain a first wavelet transform result of each component before the fault occurs, and a second wavelet transform result after the fault occurs.

[0056] In this embodiment, after a fault occurs in a sporadic distribution network area, the transient electrical components generated can be described by the wavelet analysis method. After the transient components of the electrical quantity are transformed by the wavelet function, they can be analyzed and verified from the time domain and frequency domain dimensions respectively. For the fault line, the change in the current amplitude of the line is much greater than the change in the current amplitude of the non-fault line. Therefore, this embodiment uses the wavelet fault quantification to quantify the degree of change in the amplitude of the electrical quantity before and after the component fault.

[0057] Assume that when a fault occurs, the fault signal obtained by the i-th (i=1, 2, ..., n) element is x i , and obtain the wavelet transform result B of multi-resolution analysis i1 , B i2 , B i3 , …, B il , where l represents the number of sampling points of the signal. Wavelet transform technology is used to extract the fault time B i1 , B i2 , B i3 , …, B ik is the wavelet transform result corresponding to the signal before the fault, that is, the first wavelet transform result. ik+1 , B ik+2 , B ik+3 , …, B ik+l It is the wavelet transform result corresponding to the signal after the fault, that is, the second wavelet transform result.

[0058] S103, calculating the relative fault degree of the electrical quantity of each component according to the first wavelet transform result and the second wavelet transform result.

[0059] In this embodiment, the relative fault degree of the electrical quantity of each component is calculated based on the first wavelet transform result and the second wavelet transform result, including: selecting the maximum value and the minimum value of the first wavelet transform result and the second wavelet transform result respectively; calculating the amplitude change degree of the electrical quantity of each component before and after the fault based on the maximum value and the minimum value; and annotating the amplitude change degree in combination with the first credibility to obtain the relative fault degree of the electrical quantity of each component.

[0060] Specifically, the calculation formula for selecting the maximum and minimum values ​​is as follows: Let F ik =max{B i1 ,B i2 ,B i3 ,…,B ik}; F il =max{B ik+1 ,B ik+2 ,B ik+3 ,…,B ik+l}.

[0061] The calculation formula for calculating the amplitude change of the electrical quantity of each component before and after the fault is: Among them, V i is the amplitude change degree of the signal before and after the fault.

[0062] Then V i (i=1, 2,) is processed as follows: In the formula, e i It is called the wavelet fault degree of the i-th component after the fault occurs, which represents the magnitude of the wavelet fault degree of the i-th component.

[0063] Combined with the credibility, the electrical quantities are standardized to obtain the relative fault degree m of the electrical quantity of the i-th component. e_i for

[0064] In the formula, α e is the credibility of the result of fault diagnosis of the component based on the Regularized Orthogonal Matching Pursuit (ROMP) compressed sensing reconstruction algorithm, that is, the first credibility. Specifically, the value of the first credibility is 0.9.

[0065] Among them, the compressed sensing algorithm can collect less data and "decompress" a large amount of information from it, discover the characteristics of the signal, and achieve the effect of restoring the original signal. Here it is used to restore the fault information of each component. The ROMP algorithm is a compressed sensing algorithm. This method can converge quickly with a small amount of calculation.

[0066] S104, obtaining the switching value of the relay protection device associated with each component after a fault occurs in the distribution network substation.

[0067] In this embodiment, the switch quantity mainly refers to the action information of the circuit breaker, disconnector and the like.

[0068] S105, based on the switching quantity, construct a Bayesian network of the action information of the relay protection device associated with the component, and assign values ​​to the nodes of the Bayesian network based on the action information of the relay protection device, and calculate the probability of failure of each component based on the assigned Bayesian network; wherein the action information refers to the actual state value and expected state value of the action of the relay protection device.

[0069] In this embodiment, after a fault occurs in a scattered distribution network area or user, resulting in abnormal electrical quantity, the relay protection device associated with the faulty component is activated, and then the corresponding circuit breaker is tripped to cut off the faulty component from the power grid. According to the logic of the relay protection device action, the actual state and expected state value of each component that is judged to be abnormal in electrical quantity are considered to construct a Bayesian network, and then the probability of failure of each component is calculated.

[0070] Therefore, depending on whether the relay protection device is activated or not, the corresponding node in the Bayesian network is assigned a value of 0 or 1. In view of the fact that the protection and circuit breaker itself have the situation of refusal to operate or malfunction, the weights of the nodes in the Bayesian network are first modified. In addition, considering the action status information of the automatic reclosing device of the circuit breaker, the Bayesian formula of each node is obtained as follows:

[0071] Among them, w i is the weight of each node to the root node; P(y) is the prior probability of a component failure; P(z i |y) wi When the weighted event y occurs, z i The posterior probability of occurrence, i represents the i-th element.

[0072] S106, calculating the relative fault degree of the switch quantity of the relay protection device based on the probability of each component failing.

[0073] In this embodiment, after determining the probability of each component failure, the component failure probability p calculated based on the protection and circuit breaker action information is combined with the second credibility. i After standardization, the relative fault degree m of the switching quantity of the i-th protection and circuit breaker element is obtained. s_i for Among them, α s It is the credibility of the fault diagnosis results of the relay protection device based on the Regularized Orthogonal Matching Pursuit (ROMP) compressed sensing reconstruction algorithm, that is, the second credibility.

[0074] S107, integrating the relative fault degree of the electrical quantity and the relative fault degree of the switch quantity to obtain the integrated fault probability of each component, and diagnosing the faulty component among the components in the distribution network substation according to the integrated fault probability of each component.

[0075] In this embodiment, first, the DS evidence theory is explained, that is, the basic probability distribution based on different evidences on the same recognition framework is used to calculate the combined probability distribution using the synthesis rule, thereby combining several independent evidence bodies, and finally giving a reasonable judgment after comprehensive analysis of the information.

[0076] The relative fault degree of electrical quantity and the relative fault degree of switch quantity are integrated to obtain the integrated fault probability of each component, including: converting the relative fault degree of electrical quantity into a first probability distribution function, converting the relative fault degree of switch quantity into a second probability distribution function; calculating a normalization coefficient according to the first probability distribution function and the second probability distribution function; calculating the integrated fault probability of each component according to the normalization coefficient, the first probability distribution function and the second probability distribution function.

[0077] Specifically, in order to achieve a comprehensive characterization of fault characteristics, the DS evidence theory is used to fuse two independent pieces of evidence, switch quantity and electrical quantity, to finally determine the faulty component. e_i 、m s_i The basic probability distribution function M is converted into two diagnostic methods: switch quantity and electrical quantity. e (i) M s (i), namely the first probability distribution function and the second probability distribution function. Then substitute them into the following formula to obtain the normalization coefficient K: The larger the K value is, the smaller the conflict between the two evidence bodies is.

[0078] Finally, substitute the K value and the basic probability distribution function into the following formula to obtain the fused failure probability M of each component: i ,The component with the highest fusion failure probability is finally confirmed as the faulty component.

[0079] Among them, the fusion failure probability M of each component is calculated i The calculation formula is:

[0080] This embodiment also selects a 10kV public transformer area for analysis, and constructs the network topology of the public transformer area based on the relationship between the components and the corresponding protection and circuit breakers, such as Figure 2 As shown, Figure 2 The relative fault degree of electrical quantity and the relative fault degree of switch quantity of each component inside the abnormal area are calculated to calculate the fusion fault probability. The results are as follows Figure 3 As shown in the figure, it can be seen from the data that the device L 1-2 The probability of fusion failure is the highest, and it is determined to be the fault point. After on-site verification by the staff, the device is a user switch, and the incoming line pile head is burned. It can be seen that the fault point diagnosed by the diagnostic method provided by this application is consistent with the on-site location, which verifies the accuracy of the method proposed in this application.

[0081] Please refer to Figure 4 , Figure 4 A schematic diagram of a distribution network fault diagnosis device provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, the device comprises:

[0082] The first acquisition module 410 is used to acquire the electrical quantity of each component when a fault occurs in the distribution network substation;

[0083] The first processing module 420 is used to perform wavelet transformation on the electrical quantity using a wavelet function to obtain a first wavelet transformation result of each component before a fault occurs, and a second wavelet transformation result after the fault occurs;

[0084] A first calculation module 430 is used to calculate the relative fault degree of the electrical quantity of each component according to the first wavelet transformation result and the second wavelet transformation result;

[0085] The second acquisition module 440 is used to obtain the switching value of the relay protection device associated with each component after a fault occurs in the distribution network substation;

[0086] The second processing module 450 is used to construct a Bayesian network of the action information of the relay protection device associated with the component according to the switching quantity, and assign values ​​to the nodes of the Bayesian network based on the action information of the relay protection device, and calculate the probability of failure of each component based on the assigned Bayesian network; wherein the action information refers to the actual state value and the expected state value of the action of the relay protection device;

[0087] A second calculation module 460 is used to calculate the relative fault degree of the switch value of the relay protection device based on the probability of each component failing;

[0088] The probability fusion module 470 is used to fuse the relative fault degree of the electrical quantity and the relative fault degree of the switch quantity to obtain the fused fault probability of each component, and diagnose the faulty components in the components of the distribution network according to the fused fault probability of each component.

[0089] It should be noted that the implementation of each module of a distribution network substation fault diagnosis device provided in an embodiment of the present application is consistent with the implementation method of a distribution network substation fault diagnosis method described above, and therefore, it will not be repeated here.

[0090] Correspondingly, the device uses wavelet transform and Bayesian network to analyze the fault characteristics of the electrical quantity of the component and the switching quantity of the relay protection, respectively, to obtain the relative fault degree of the electrical quantity of each component and the relative fault degree of the switching quantity of the relay protection device associated with the component, and fuses the relative fault degree of the electrical quantity and the relative fault degree of the switching quantity to determine the fusion fault probability of each component, and then the component corresponding to the maximum value of the fusion fault probability of each component is determined as the faulty component. Since each data information reflects different fault characteristics of the power system fault, compared with the fault diagnosis algorithm of a single data source, the present application comprehensively utilizes the electrical quantity and the switching quantity that characterize the fault state of the distribution network to make up for the fault diagnosis error caused by incomplete or distorted information when using a single data source for fault diagnosis, so that the redundancy of the collected data can be fully utilized to correct the influence of erroneous data and improve the accuracy of fault diagnosis.

[0091] Please refer to Figure 5 , Figure 5A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device 500 includes a processor 510, a memory 520, a communication interface 530, and at least one communication bus for connecting the processor 510, the memory 520, and the communication interface 530. The memory 520 includes, but is not limited to, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (PROM), or a portable CD-ROM, and the memory 420 is used for related instructions and data.

[0092] The communication interface 530 is used to receive and send data. The processor 510 can be one or more CPUs. When the processor 510 is a CPU, the CPU can be a single-core CPU or a multi-core CPU. The processor 410 in the electronic device 500 is used to read one or more programs 421 stored in the memory 420, and perform the following operations: obtain the electrical quantity of each component when a fault occurs in the distribution network substation; use a wavelet function to perform a wavelet transform on the electrical quantity to obtain the first wavelet transform result of each component before the fault occurs, and the second wavelet transform result after the fault occurs; calculate the relative fault degree of the electrical quantity of each component based on the first wavelet transform result and the second wavelet transform result; obtain the switching quantity of the relay protection device associated with each component after a fault occurs in the distribution network substation; and construct a corresponding fault relationship based on the switching quantity. A Bayesian network of the action information of the relay protection device associated with the component is constructed, and the nodes of the Bayesian network are assigned values ​​based on the action information of the relay protection device, and the probability of failure of each component is calculated based on the assigned Bayesian network; the action information refers to the actual state value and the expected state value of the relay protection device action; the relative fault degree of the switching quantity of the relay protection device is calculated based on the probability of failure of each component; the relative fault degree of the electrical quantity and the relative fault degree of the switching quantity are integrated to obtain the integrated fault probability of each component, and the faulty components in the components of the distribution network substation are diagnosed according to the integrated fault probability of each component.

[0093] It should be noted that the specific implementation of each operation can be Figure 1 The corresponding description of the method embodiment shown, the electronic device 500 can be used to execute a distribution network substation fault diagnosis method of the above method embodiment of the present application, which will not be described in detail here.

[0094] In the embodiments of the present disclosure, a computer-readable storage medium is also provided, and the computer-readable storage medium is a memory device in a computer device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in a computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by a processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of a distribution network area fault diagnosis method in the above embodiment. Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0095] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of the present application in detail. It should be understood that the above description is only the specific implementation method of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A method for diagnosing faults in a distribution network area, characterized in that the method include: Obtain the electrical quantity of each component when a fault occurs in the distribution network area; The wavelet function is used to perform wavelet transform on the electrical quantity, and the first wavelet transform result of each component before the fault occurs and the second wavelet transform result after the fault occurs are obtained; According to the first wavelet transform result and the second wavelet transform result, the relative fault degree of the electrical quantity of each component is calculated; Obtain the switching value of the relay protection device associated with each component after a fault occurs in the distribution network area; According to the switching quantity, a Bayesian network of the action information of the relay protection device associated with the component is constructed, and the nodes of the Bayesian network are assigned values ​​based on the action information of the relay protection device. The probability of failure of each component is calculated based on the assigned Bayesian network; the action information refers to the actual state value and expected state value of the action of the relay protection device; The relative fault degree of the switch quantity of the relay protection device is calculated based on the probability of each component failing; The relative fault degree of electrical quantity and the relative fault degree of switch quantity are integrated to obtain the integrated fault probability of each component. The faulty components in the distribution network substation are diagnosed according to the integrated fault probability of each component.

2. The method according to claim 1, characterized in that According to the first wavelet transform result and the second wavelet transform result, the relative fault degree of the electrical quantity of each component is calculated, including: Select the maximum value and the minimum value of the first wavelet transform result and the second wavelet transform result respectively; Calculate the amplitude change of the electrical quantity of each component before and after the fault based on the maximum and minimum values; The amplitude variation degree is annotated in combination with the first credibility to obtain the relative fault degree of the electrical quantity of each component.

3. The method according to claim 2, characterized in that The first credibility refers to the credibility of the result of fault diagnosis of the component based on the regularized orthogonal matching pursuit compressed sensing reconstruction algorithm.

4. The method according to claim 1, characterized in that: The expression for calculating the probability of failure of each component is: Among them, w i is the weight of each node to the root node; P(y) is the prior probability of a component failure; P(z i |y) wi When the weighted event y occurs, z i The posterior probability of occurrence, i represents the i-th element.

5. The method according to claim 1, characterized in that The relative fault degree of the switch quantity of the relay protection device is calculated based on the probability of each component failing, specifically: the probability of each component failing is annotated in combination with the second credibility to obtain the relative fault degree of the switch quantity of the relay protection device.

6. The method according to claim 5, characterized in that The second credibility refers to the credibility of the fault diagnosis result of the relay protection device based on the regularized orthogonal matching pursuit compressed sensing reconstruction algorithm.

7. The method according to claim 1, characterized in that By integrating the relative fault degree of electrical quantity and the relative fault degree of switch quantity, the integrated fault probability of each component is obtained, including: Converting the relative fault degree of the electrical quantity into a first probability distribution function, and converting the relative fault degree of the switch quantity into a second probability distribution function; Calculating a normalization coefficient according to the first probability distribution function and the second probability distribution function; The fusion failure probability of each component is calculated according to the normalization coefficient, the first probability distribution function and the second probability distribution function.

8. A distribution network area fault diagnosis device, characterized in that: The device includes: The first acquisition module is used to obtain the electrical quantity of each component when a fault occurs in the distribution network area; The first processing module is used to perform wavelet transform on the electrical quantity using a wavelet function to obtain a first wavelet transform result of each component before a fault occurs, and a second wavelet transform result after the fault occurs; A first calculation module is used to calculate the relative fault degree of the electrical quantity of each component according to the first wavelet transformation result and the second wavelet transformation result; The second acquisition module is used to obtain the switching value of the relay protection device associated with each component after a fault occurs in the distribution network substation; The second processing module is used to construct a Bayesian network of the action information of the relay protection device associated with the component according to the switching quantity, and assign values ​​to the nodes of the Bayesian network based on the action information of the relay protection device, and calculate the probability of failure of each component based on the assigned Bayesian network; wherein the action information refers to the actual state value and the expected state value of the action of the relay protection device; A second calculation module is used to calculate the relative fault degree of the switch quantity of the relay protection device based on the probability of each component failing; The probability fusion module is used to fuse the relative fault degree of electrical quantities and the relative fault degree of switch quantities to obtain the fused fault probability of each component, and diagnose the faulty components in the components of the distribution network according to the fused fault probability of each component.

9. An electronic device, characterized in that: The electronic device includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of a distribution network substation fault diagnosis method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of a distribution network substation fault diagnosis method according to any one of claims 1 to 7 are implemented.

Images