Fault diagnosis method and device for power distribution network, equipment and storage medium

Abstract

The invention discloses a fault diagnosis method and device for a power distribution network, equipment and a storage medium. The method comprises the following steps: determining a suspected node according to electrical operation data of each node in the power distribution network; based on the doubt node, screening out the structure data of the doubt node from the structure data of each node in the power distribution network, and determining an initial fault node according to the structure data of the doubt node and the electrical operation data; performing feature extraction on the electrical operation data of the initial fault node by using a preset time window to obtain electrical feature data of the initial fault node, and determining the fault time of the initial fault node according to the electrical feature data; screening the electrical operation data through the fault time to obtain first electrical operation data, and determining a target fault node by using the first electrical operation data and preset target power; and determining a fault diagnosis result of the power distribution network according to the target fault node. Through the technical scheme of the embodiment of the invention, the power distribution network fault diagnosis efficiency and accuracy can be improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the technical field of power distribution networks, and in particular to a fault diagnosis method, apparatus, device and storage medium for a power distribution network. Background Art

[0002] With the vigorous development of the power industry, the distribution network, as the key end of the power system, shoulders the important task of providing stable and reliable power supply to users. Its safe and stable operation is directly related to the continuity and quality of power supply. Therefore, effective fault diagnosis of the distribution network has become an indispensable part of ensuring its stable operation.

[0003] At present, the fault diagnosis method of distribution network mainly relies on manual experience analysis. However, this method is not only inefficient but also difficult to guarantee accuracy.

[0004] Therefore, it is urgent to propose a new method to solve the above problems. Summary of the invention

[0005] The present invention provides a distribution network fault diagnosis method, device, equipment and storage medium, which can improve the efficiency and accuracy of distribution network fault diagnosis.

[0006] In a first aspect, an embodiment of the present invention provides a method for diagnosing a fault in a distribution network, comprising:

[0007] Determine the nodes in question based on the electrical operation data of each node in the distribution network;

[0008] Based on the doubtful node, the structural data of the doubtful node is screened out from the structural data of each node in the distribution network, and an initial fault node is determined according to the structural data of the doubtful node and the electrical operation data;

[0009] Extracting features of the electrical operation data of the initial fault node using a preset time window to obtain electrical feature data of the initial fault node, and determining the fault time of the initial fault node according to the electrical feature data;

[0010] Filtering the electrical operation data according to the fault time to obtain first electrical operation data, and determining a target fault node using the first electrical operation data and a preset target power;

[0011] A fault diagnosis result of the distribution network is determined according to the target fault node.

[0012] The technical solution of the present invention determines the doubtful node according to the electrical operation data of each node in the distribution network, which saves the time for determining the initial fault node later, thereby improving the efficiency of the entire fault detection process. Afterwards, the structural data of the doubtful node is screened out from the structural data of each node in the distribution network based on the doubtful node, and the initial fault node is determined according to the structural data and electrical operation data of the doubtful node, effectively narrowing the scope of fault investigation, thereby improving the efficiency of fault detection. Then, the electrical operation data of the initial fault node is feature extracted using a preset time window to obtain the electrical characteristic data of the initial fault node, and the fault time of the initial fault node is determined according to the electrical characteristic data, thereby improving the accuracy of the determined fault time. Subsequently, the electrical operation data is screened by the fault time to obtain the first electrical operation data, focusing on the key information of the fault occurrence period and avoiding the interference of irrelevant data. The target fault node is determined using the first electrical operation data and the preset target power, which can more accurately judge the actual impact of the fault on the electrical operation parameters and improve the accuracy of fault diagnosis. Finally, the fault diagnosis result of the distribution network is determined according to the target fault node, which can quickly and accurately determine the fault diagnosis result of the distribution network, provide valuable fault information for the staff, thereby ensuring the reliable operation of the distribution network and enhancing user satisfaction. Therefore, the technical solution of the present invention solves the problem of low efficiency and difficulty in ensuring accuracy caused by relying on manual experience analysis in the prior art.

[0013] In a second aspect, an embodiment of the present invention further provides a fault diagnosis device for a distribution network, the device comprising:

[0014] A first node determination module is used to determine the doubtful node according to the electrical operation data of each node in the distribution network;

[0015] A second node determination module, configured to filter out the structural data of the doubtful node from the structural data of each node in the distribution network based on the doubtful node, and determine the initial fault node according to the structural data of the doubtful node and the electrical operation data;

[0016] A time determination module, used to extract features from the electrical operation data of the initial fault node using a preset time window to obtain electrical feature data of the initial fault node, and determine the fault time of the initial fault node according to the electrical feature data;

[0017] a third node determination module, configured to filter the electrical operation data by the fault time to obtain first electrical operation data, and determine a target fault node by using the first electrical operation data and a preset target power;

[0018] A fault diagnosis module is used to determine a fault diagnosis result of the distribution network according to the target fault node.

[0019] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0020] at least one processor; and a memory communicatively coupled to the at least one processor;

[0021] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can implement any distribution network fault diagnosis method described in the first aspect.

[0022] In a fourth aspect, an embodiment of the present invention further provides a storage medium including computer executable instructions,

[0023] The computer executable instructions, when executed by a computer processor, implement any of the distribution network fault diagnosis methods described in the first aspect.

[0024] It should be noted that the above-mentioned computer instructions may be stored in whole or in part on a computer-readable storage medium. The computer-readable storage medium may be packaged together with the processor of the fault diagnosis device of the distribution network, or may be packaged separately from the processor of the fault diagnosis device of the distribution network, and this application does not limit this.

[0025] The description of the second, third and fourth aspects in this application can refer to the detailed description of the first aspect; and the beneficial effects of the description of the second, third and fourth aspects can refer to the beneficial effect analysis of the first aspect, which will not be repeated here.

[0026] In this application, the name of the above-mentioned distribution network fault diagnosis device does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear with other names. As long as the functions of each device or functional module are similar to those of this application, they fall within the scope of the claims of this application and their equivalent technologies.

[0027] These and other aspects of the present application will become more apparent from the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0029] Figure 1 A flow chart of a method for diagnosing a fault in a distribution network provided by an embodiment of the present invention;

[0030] Figure 2 A flowchart of another method for diagnosing a fault in a distribution network provided by an embodiment of the present invention;

[0031] Figure 3 A schematic diagram of the structure of a fault diagnosis device for a distribution network provided by an embodiment of the present invention;

[0032] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0034] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0035] The terms "first" and "second" and the like in the specification and drawings of this application are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.

[0036] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0037] It should be mentioned before discussing exemplary embodiments in more detail that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe various operations (or steps) as sequential processes, many operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of various operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to methods, functions, procedures, subroutines, subprograms, etc. In addition, the embodiments in the present invention and the features in the embodiments can be combined with each other without conflict.

[0038] It should be noted that, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0039] In the description of the present application, unless otherwise specified, “plurality” means two or more.

[0040] Figure 1 The present invention provides a flowchart of a method for diagnosing a fault in a distribution network. The present invention is applicable to situations where a fault diagnosis of a distribution network is required. The method can be performed by a fault diagnosis device for a distribution network. The fault diagnosis device for a distribution network can be implemented in hardware or software. The device can be integrated into an electronic device, such as a computer, and the present invention does not limit this. Figure 1 As shown, the specific steps include:

[0041] Step 110: Determine the suspicious nodes according to the electrical operation data of each node in the distribution network.

[0042] Specifically, the distribution network refers to a power grid that receives electrical energy from the transmission network or regional power plants and distributes it locally or step by step according to voltage to various types of users through distribution facilities. A node refers to a connection point in the power network, for example, a node can be a substation, distribution transformer, switchgear, or user access point. Electrical operation data refers to various electrical parameter data generated by each node in the distribution network during operation, for example, electrical operation data can be voltage, current, and power. A questionable node refers to a node that is preliminarily judged to have problems based on electrical operation data.

[0043] In a specific implementation, the electrical operation data of each node can be first obtained from the monitoring system of the distribution network, and then the obtained data can be preprocessed (such as filtering noise and filling in missing values) to improve the data quality. Then, it is determined whether the electrical operation data of each node after preprocessing is within the preset electrical data operation range. For each node, if the electrical operation data of the node is within the preset electrical data operation range, the node is determined to be a normal node. If the electrical operation data of the node is not within the preset electrical data operation range, the node is determined to be a questionable node. For example: the distribution network includes 2 nodes, namely node A and node B, the electrical operation data is a voltage value, the preset electrical data operation range is 9.5 kilovolts (kV)-10.5kV, the electrical operation data of node A at time t1 is 10.2kV, and the electrical operation data of node B is 11.3kV, then the questionable node is node B. For example: the distribution network contains 2 nodes, namely node C and node D. The electrical operation data are voltage values ​​and current values. The preset electrical data operation range is 9.5 kilovolts (kV)-10.5kV and 5 amperes (A)-10A. At time t1, the electrical operation data of node C is 10.2kV and 5A, and the electrical operation data of node D is 11.3kV and 8A. The node in question is node D.

[0044] In this embodiment, the questionable nodes are determined according to the electrical operation data of each node in the distribution network, which saves the time for subsequent determination of the initial fault node, thereby improving the efficiency of the entire fault detection process.

[0045] Step 120: Filter out structural data of the doubtful node from structural data of each node in the distribution network based on the doubtful node, and determine the initial fault node according to the structural data and electrical operation data of the doubtful node.

[0046] Specifically, structural data refers to information about the physical structure and connection relationship of each node in the distribution network. For example, structural data includes the type of line connected to the node (such as overhead line or cable), line length, conductor model, connected equipment type (transformer, switch, etc.) and its parameters (such as impedance). The initial fault node refers to the node that may have a fault that is initially determined based on the structural data and electrical operation data of the suspected node.

[0047] In a specific implementation, after determining the doubtful node, the structural data of each node in the distribution network can be obtained from the management system of the distribution network, and then the relevant structural data of these nodes can be screened out from the structural data of the distribution network according to the doubtful node obtained above, so as to obtain the structural data of the doubtful node. Then, the adjacent nodes of the doubtful node are determined according to the structural data of the doubtful node, and then for each doubtful node, it is determined whether the adjacent nodes of the doubtful node are all doubtful nodes. If the adjacent nodes of the doubtful node are all doubtful nodes, the doubtful node is determined to be the initial fault node. If the adjacent nodes of the doubtful node are not all doubtful nodes, it is determined that the doubtful node is not the initial fault node.

[0048] In this embodiment, using topology data to screen suspicious nodes can effectively narrow the scope of fault investigation, thereby improving fault detection efficiency.

[0049] Step 130 : extracting features from the electrical operation data of the initial fault node using a preset time window to obtain electrical feature data of the initial fault node, and determining the fault time of the initial fault node according to the electrical feature data.

[0050] Specifically, the preset time window refers to the time period for feature extraction set in advance according to actual conditions or needs. Electrical feature data refers to representative or critical feature information extracted from the electrical operation data of the initial fault node. Fault time refers to the specific time when the initial fault node fails, determined based on the electrical feature data.

[0051] In a specific implementation, the electrical operation data of the initial fault node within a preset time window can be obtained from the monitoring system of the distribution network, and then the mean of the electrical operation data within the preset time window can be calculated to obtain the electrical characteristic data of the initial fault node. For example, if the electrical operation data is voltage, all voltage values ​​of the initial fault node within the preset time window can be averaged to obtain the average voltage value within the time window, that is, the electrical characteristic data of the initial fault node.

[0052] The failure time of the initial fault node is then determined based on the electrical characteristic data. Specifically, the difference between the electrical operation data and the electrical characteristic data (mean) at each moment in the preset time window can be calculated to obtain the electrical difference at each moment. The moment when the electrical difference is greater than the preset electrical difference is then determined as the failure time of the initial fault node.

[0053] In this embodiment, through the above steps, the accuracy of the determined fault time is improved.

[0054] Step 140: Filter the electrical operation data by fault time to obtain first electrical operation data, and determine a target fault node using the first electrical operation data and a preset target power.

[0055] Specifically, the first electrical operation data refers to the electrical operation data related to the fault screened out by the fault time. The preset target power refers to the expected power set in advance according to the actual situation or demand. The target fault node refers to the node that is finally determined to have a fault.

[0056] In a specific implementation, the power of each node corresponding to the fault time can be filtered out from the electrical operation data according to the fault time to obtain the first electrical operation data, and then the power deviation of the fault time is calculated based on the first electrical operation data and the preset target power of each node, and then the fault time with a power deviation greater than the second preset power threshold is determined as the target fault time, and finally the initial fault node corresponding to the target fault time is determined as the target fault node.

[0057] In this embodiment, the first electrical operation data filtered out based on the fault time accurately focuses on the key information of the fault occurrence period and avoids interference from irrelevant data. The first electrical operation data is then compared with the preset target power for analysis, thereby improving the accuracy of fault diagnosis.

[0058] Step 150: Determine a fault diagnosis result of the distribution network according to the target fault node.

[0059] Specifically, the fault diagnosis result refers to the final judgment on the fault condition of the distribution network. For example, the fault diagnosis result includes whether a fault occurs or not.

[0060] In a specific implementation, the fault diagnosis result of the distribution network can be determined based on whether the target fault node exists. Specifically, if the number of target fault nodes is not 0 (that is, there are target fault nodes), the fault diagnosis result of the distribution network is determined to be a fault. At this time, the determined target fault node and the fault time of the target fault node can be sent to the terminal of the staff to help the staff quickly locate the fault point and start emergency repair work in time, thereby reducing the inconvenience and economic losses caused to the production and life of users. If the number of target fault nodes is 0 (that is, there are no target fault nodes), the fault diagnosis result of the distribution network is determined to be no fault. At this time, the fault diagnosis result of no fault can be sent to the terminal of the staff to help the staff eliminate potential fault hidden dangers and troubleshoot directions, avoid wasting unnecessary time and energy on inspections in fault-free areas, thereby improving the operation and maintenance management level and operation efficiency of the entire distribution network.

[0061] In this embodiment, the fault diagnosis result of the distribution network is determined according to the target fault node, which can quickly and accurately determine the fault diagnosis result of the distribution network, provide valuable fault information to the staff, thereby ensuring the reliable operation of the distribution network and enhancing user satisfaction.

[0062] In the embodiment of the present invention, the doubtful node is determined according to the electrical operation data of each node in the distribution network, which saves the time for determining the initial fault node later, thereby improving the efficiency of the entire fault detection process. Afterwards, the structural data of the doubtful node is screened out from the structural data of each node in the distribution network based on the doubtful node, and the initial fault node is determined according to the structural data and electrical operation data of the doubtful node, effectively narrowing the scope of fault investigation, thereby improving the efficiency of fault detection. Then, the electrical operation data of the initial fault node is feature extracted using a preset time window to obtain the electrical characteristic data of the initial fault node, and the fault time of the initial fault node is determined according to the electrical characteristic data, thereby improving the accuracy of the determined fault time. Subsequently, the electrical operation data is screened by the fault time to obtain the first electrical operation data, focusing on the key information of the fault occurrence period and avoiding the interference of irrelevant data. The target fault node is determined using the first electrical operation data and the preset target power, which can more accurately judge the actual impact of the fault on the electrical operation parameters and improve the accuracy of fault diagnosis. Finally, the fault diagnosis result of the distribution network is determined according to the target fault node, which can quickly and accurately determine the fault diagnosis result of the distribution network, provide valuable fault information for the staff, thereby ensuring the reliable operation of the distribution network and enhancing user satisfaction. Therefore, the technical solution of the present invention solves the problem of low efficiency and difficulty in ensuring accuracy caused by relying on manual experience analysis in the prior art.

[0063] Figure 2 A flowchart of another method for diagnosing a fault in a distribution network provided by an embodiment of the present invention is provided. This embodiment is specific based on the above embodiment. In this embodiment, the method may further include:

[0064] Step 210: Calculate the calculation power of each node according to the voltage and current of each node, and obtain the total power of the distribution network according to the power of each node.

[0065] Specifically, electrical operation data includes voltage, current and power. Calculated power refers to the power calculated based on voltage and current. Total power refers to the sum of the power of all nodes in the distribution network.

[0066] In a specific implementation, the voltage, current and power of each node at different times can be obtained from the monitoring system of the distribution network. Then, for each node, the voltage mean of the node is calculated based on its voltage value at each time. According to the same method, the current mean of the node is calculated from the current value at each time, and then the power mean of the node is determined according to the power value at each time. Subsequently, the voltage mean of the node is multiplied by the current mean to obtain the calculated power of the node. After the calculated power of all nodes is obtained, the sum of the power mean of each node is further calculated to obtain the total power of the distribution network.

[0067] In this embodiment, through the above steps, a data basis is provided for subsequently determining the fault weight of each node.

[0068] Step 211: determine the fault weight of each node based on the calculated power, power and total power of each node.

[0069] Specifically, the failure weight refers to an indicator used to measure the probability of failure of each node.

[0070] In the specific implementation, for each node, the power average of the node can be first determined as the power of the node, and then the fault weight of the node can be determined according to the calculated power, power and total power of the node. The specific calculation formula is as follows: fault weight of the node = |calculated power of the node - power of the node| / total power.

[0071] In this embodiment, by determining the fault weight of each node, the accuracy of subsequently determining the doubtful nodes is greatly improved, so that the entire fault diagnosis process can locate potential fault points more efficiently and accurately, laying a solid foundation for ensuring the stable operation of the distribution network, reducing the waste of time and resources caused by inaccurate fault troubleshooting, and enhancing the reliability and scientificity of distribution network fault diagnosis and processing.

[0072] Step 212: Determine nodes with fault weights greater than zero as questionable nodes.

[0073] In a specific implementation, after obtaining the fault weight of each node, the nodes with a fault weight greater than zero can be determined as questionable nodes.

[0074] It should be noted that if there is no node with a fault weight greater than zero, it can be directly determined that there is no target fault node.

[0075] Step 213: Filter out the structural data of the doubtful node from the structural data of each node in the distribution network based on the doubtful node, and determine the initial fault node according to the structural data and electrical operation data of the doubtful node.

[0076] Furthermore, the initial fault node is determined based on the structural data and electrical operation data of the questionable node, including: determining the adjacent nodes of the questionable node based on the structural data of the questionable node, and filtering out the impedance between the adjacent nodes and the questionable node from the structural data of the questionable node based on the adjacent nodes and the questionable node to obtain the adjacent impedance; determining the flow power of the questionable node based on the adjacent impedance, the power of the questionable node and the power of the adjacent nodes; and determining the questionable node whose flow power is greater than a first preset power threshold as the initial fault node.

[0077] Specifically, the adjacent nodes of the suspected node refer to other nodes directly connected to the suspected node. The adjacent impedance refers to the impedance value between the suspected node and its adjacent nodes. The flow power refers to the power determined based on the adjacent impedance, the power of the suspected node and the power of the adjacent nodes, which is used to determine the initial fault node. The first preset power threshold refers to the power threshold set in advance according to actual conditions or needs.

[0078] In a specific implementation, after obtaining the doubtful node, the adjacent node of the doubtful node can be determined based on the structural data of the doubtful node, and the impedance between the adjacent node and the doubtful node can be screened out from the structural data of the doubtful node based on the adjacent node and the doubtful node to obtain the adjacent impedance. Then, the power flow power of the doubtful node is calculated based on the adjacent impedance, the power of the doubtful node and the power of the adjacent node. The specific calculation formula is as follows:

[0079]

[0080] Among them, P flow represents the power flow, P represents the power of the node in question, and P j represents the power of the jth adjacent node, Z ij represents the adjacent impedance, and n represents the total number of adjacent nodes.

[0081] Then, after the power flow power of each doubtful node is obtained, the doubtful node whose power flow power is greater than the first preset power threshold may be determined as an initial fault node.

[0082] In this embodiment, through the above steps, not only the accuracy of determining the initial faulty node is improved, but also unnecessary calculations on a large number of irrelevant nodes are avoided, thereby significantly improving the overall efficiency of fault diagnosis.

[0083] Step 214: determine the voltage characteristic value of the initial fault node at each moment according to the preset first time window and the voltage of the initial fault node at each moment, and determine the current characteristic value of the initial fault node at each moment according to the preset second time window and the current of the initial fault node at each moment.

[0084] Specifically, the preset time window includes a preset first time window and a preset second time window. The preset first time window refers to a time window set in advance according to actual conditions or needs. The preset second time window refers to another time window set in advance according to actual conditions or needs. The preset first time window is smaller than the preset second time window. The electrical characteristic data includes a current characteristic value and a voltage characteristic value. The voltage characteristic value refers to a value that can characterize the voltage change characteristics determined based on the preset first time window and the voltage of the initial fault node at each moment. The current characteristic value refers to a value that can characterize the current change characteristics determined based on the preset second time window and the current of the initial fault node at each moment.

[0085] In a specific implementation, after the initial fault node is determined, the voltage characteristic value of the initial fault node at each moment can be calculated according to the preset first time window and the voltage of the initial fault node at each moment. The specific calculation formula is as follows:

[0086]

[0087] Among them, V e (t i ) represents the voltage characteristic value at the i-th moment, T s represents the preset first time window, V(t i ) represents the voltage value at the i-th moment.

[0088] At the same time, the current characteristic value of the initial fault node at each moment can be calculated according to the preset second time window and the current of the initial fault node at each moment. The specific calculation formula is as follows:

[0089]

[0090] Among them, I e (t i ) represents the current characteristic value at the i-th moment, T l represents the preset second time window, I(t i ) represents the current value at the i-th moment.

[0091] In this embodiment, through the above steps, the voltage and current at multiple moments are comprehensively considered, rather than relying solely on the observation value at a single moment, which effectively avoids the impact of data randomness on the analysis results, and can more accurately capture the changing trend of voltage and current over time, thereby improving the accuracy of the subsequent determined fault time.

[0092] Step 215: Determine the voltage deviation of the initial fault node at each moment according to the voltage of the initial fault node at each moment and the corresponding voltage characteristic value, and determine the current deviation of the initial fault node at each moment according to the current of the initial fault node at each moment and the corresponding current characteristic value.

[0093] Specifically, voltage deviation refers to the difference between the actual voltage of the initial fault node and the corresponding voltage characteristic value, which is one of the important judgment bases for determining the fault time. Current deviation refers to the difference between the actual current of the initial fault node and the corresponding current characteristic value, which is one of the important judgment bases for determining the fault time.

[0094] In a specific implementation, after obtaining the voltage characteristic value and current characteristic value of the initial fault node at each moment, the voltage deviation of the initial fault node at each moment can be determined according to the voltage of the initial fault node at each moment and the corresponding voltage characteristic value. The specific calculation formula is as follows:

[0095] ΔV fault (t i )=|V e (t i )-V(t i )|

[0096] Where, ΔV fault (t i ) represents the voltage deviation at the i-th moment.

[0097] At the same time, the current deviation of the initial fault node at each moment can be determined according to the current of the initial fault node at each moment and the corresponding current characteristic value. The specific calculation formula is as follows:

[0098] ΔI fault (t i )=|I e (t i )-I(t i )|

[0099] Among them, ΔI fault (t i ) represents the current deviation at the i-th moment.

[0100] In this embodiment, through the above steps, the degree to which the electrical parameters of the initial fault node deviate from the normal state can be accurately quantified, thereby improving the accuracy of the subsequent determined fault time.

[0101] Step 216: Determine the time when the voltage deviation is greater than the preset voltage threshold and the current deviation is greater than the preset current threshold as the fault time of the initial fault node.

[0102] Specifically, the preset voltage threshold refers to a threshold set in advance according to actual conditions or requirements for determining whether the voltage deviation exceeds the standard. The preset current threshold refers to a threshold set in advance according to actual conditions or requirements for determining whether the current deviation exceeds the standard.

[0103] In a specific implementation, after obtaining the current deviation and current deviation of the initial fault node at each moment, the moment when the voltage deviation is greater than a preset voltage threshold and the current deviation is greater than a preset current threshold can be determined as the fault time of the initial fault node.

[0104] It should be noted that if there is no moment when the voltage deviation is greater than the preset voltage threshold and the current deviation is greater than the preset current threshold, it can be directly determined that there is no target fault node.

[0105] In this embodiment, through the above steps, the accuracy of the determined fault time is improved.

[0106] Step 217: Filter the electrical operation data by fault time to obtain first electrical operation data, and determine the target fault node by using the first electrical operation data and the preset target power.

[0107] Furthermore, step 217 may specifically include: filtering out the power of each node corresponding to the fault time from the electrical operation data according to the fault time to obtain the first electrical operation data; calculating the power deviation of the fault time based on the first electrical operation data and the preset target power of each node; determining the fault time with a power deviation greater than a second preset power threshold as the target fault time, and determining the initial fault node corresponding to the target fault time as the target fault node.

[0108] Specifically, the power deviation refers to the degree of power deviation determined according to the actual power and the preset target power. The second preset power threshold refers to a power threshold set in advance according to actual conditions or requirements for determining the target failure time.

[0109] In a specific implementation, the power of each node corresponding to the fault time can be firstly filtered out from the electrical operation data according to the fault time to obtain the first electrical operation data, and then the power deviation of the fault time is calculated based on the first electrical operation data and the preset target power of each node. The specific calculation formula is as follows:

[0110]

[0111] Among them, ΔP fault (t i ) represents the power deviation at the i-th moment, N represents the total number of nodes, P a (t i ) represents the power of the ath node at the i-th moment, P a-expected (t i ) represents the preset target power of the a-th node at the i-th moment.

[0112] Then, the fault time when the power deviation is greater than the second preset power threshold can be determined as the target fault time, and the initial fault node corresponding to the target fault time can be determined as the target fault node. In addition, if there is no fault time when the power deviation is greater than the second preset power threshold, the number of target fault nodes can be determined to be zero, that is, there is no target fault node.

[0113] In this embodiment, through the above steps, the accuracy of determining the target fault node is improved.

[0114] Step 218: Determine the fault diagnosis result of the distribution network according to the target fault node.

[0115] Step 219: Determine whether the fault diagnosis result is that a fault has occurred.

[0116] If a fault occurs, execute step 221 ; if no fault occurs, execute step 220 .

[0117] In a specific implementation, after obtaining the fault diagnosis result, it can be determined whether the fault diagnosis result is a fault. If a fault occurs, the target fault node and the structure data of the distribution network are input into a pre-trained distribution network fault type model to obtain the fault type of the distribution network; if a fault does not occur, the fault diagnosis result is determined to be no fault.

[0118] Step 220: Determine that the fault diagnosis result is that no fault has occurred.

[0119] In a specific implementation, after determining that the fault diagnosis result is not a fault, it can be determined that the fault diagnosis result is not a fault. At this time, the fault diagnosis result of no fault can be sent to the staff's terminal to avoid the staff wasting unnecessary time and energy on inspections in fault-free areas.

[0120] Step 221: Input the target fault node and the structural data of the distribution network into a pre-trained distribution network fault type model to obtain the fault type of the distribution network.

[0121] Specifically, the pre-trained distribution network fault type model refers to a model obtained after training based on historical electrical operation data of each distribution network and corresponding structural data, and the fault type of the distribution network can be determined based on the target fault node and the structural data of the distribution network.

[0122] In the specific implementation, after obtaining the target fault node, the target fault node and the structural data of the distribution network can be input into the pre-trained distribution network fault type model to obtain the fault type of the distribution network (such as short circuit fault, open circuit fault, ground fault or overload fault). Then the obtained distribution network fault type can be sent to the terminal of the staff to provide highly targeted guidance to the staff during the fault handling process, so that the staff can clearly know the specific type of the fault, and then be able to choose the appropriate processing method and tool in a targeted manner, avoiding blind troubleshooting and invalid operations, thereby improving the efficiency and accuracy of fault handling.

[0123] Furthermore, the training process of the distribution network fault type model includes: obtaining the historical electrical operation data and corresponding structural data of each distribution network; performing data enhancement processing on the historical electrical operation data of each distribution network to obtain the historical enhanced electrical operation data of each distribution network, and performing multi-dimensional feature extraction on the historical electrical operation data and the historical enhanced electrical operation data of each distribution network to obtain the historical electrical feature data of multiple dimensions of each distribution network; using the historical electrical operation data, structural data, historical enhanced electrical operation data and historical electrical feature data of multiple dimensions of each distribution network to train the self-supervised model, and calculate the loss function; optimizing the model based on the back propagation algorithm until the preset optimization conditions are met to obtain the distribution network fault type model.

[0124] Specifically, data enhancement refers to a data processing technology that can expand the amount of data through some specific methods (such as adding noise, changing the time series order of data, scaling or translating data, etc.) to generate more diverse data samples. Historical enhanced electrical operation data refers to historical electrical operation data after data enhancement processing. Historical electrical feature data in multiple dimensions refers to data obtained by extracting features of historical electrical operation data and historical enhanced electrical operation data in multiple dimensions (such as time dimension and space dimension). A self-supervised model refers to a machine learning model that learns by automatically generating supervisory signals from data. The loss function includes a transformation invariance loss function and a cross entropy loss function. The transformation invariance loss function refers to a special loss function. In this embodiment, it is mainly used to measure the difference between historical electrical operation data and historical enhanced electrical operation data after data enhancement in multiple dimensions, and train the model by minimizing this difference, so that it is robust to data changes, that is, the model can maintain a stable output when facing data changes (such as changes in the data enhancement process), learn the essential characteristics of the data, and not be disturbed by the surface changes of the data. The transformation invariance loss function includes the square norm of the difference between the historical electrical operation data and the historical enhanced electrical operation data in multiple dimensions, that is, by calculating the square norm of the difference between the historical electrical operation data and the historical enhanced electrical operation data in different dimensions, the degree of change of the data after the enhancement processing is measured. For example: the transformation invariance loss function can be Among them, L1 represents the transformation invariance loss function, M represents the number of samples, and T1(x i ) represents the i-th historical electrical operation data, T2(x i ) represents the historical enhanced electrical operation data corresponding to the i-th historical electrical operation data, represents the historical electrical characteristic data obtained after feature extraction of the i-th historical electrical operation data in one dimension, represents the historical electrical feature data obtained after feature extraction of the historical enhanced electrical operation data corresponding to the i-th historical electrical operation data in one dimension, represents the historical electrical characteristic data obtained after feature extraction of the i-th historical electrical operation data in another dimension, represents the historical electrical characteristic data obtained after feature extraction of the historical enhanced electrical operation data corresponding to the i-th historical electrical operation data in another dimension, represents the historical electrical characteristic data obtained after feature extraction of the i-th historical electrical operation data in another dimension, represents the historical electrical feature data obtained after feature extraction of the historical enhanced electrical operation data corresponding to the i-th historical electrical operation data in another dimension, λ1, λ2, and λ3 represent the weight coefficients in different dimensions respectively. The cross entropy loss function includes the negative log-likelihood between the pseudo-label probability distribution and the predicted probability distribution.

[0125] In the specific implementation, the historical electrical operation data and the corresponding structural data of each distribution network are first obtained, and then the historical electrical operation data of each distribution network is subjected to data enhancement processing (such as translation and scaling) to obtain the historical enhanced electrical operation data of each distribution network. Then, a neural network (such as a convolutional neural network or a back propagation neural network) can be used to perform multi-dimensional feature extraction on the historical electrical operation data and historical enhanced electrical operation data of each distribution network to obtain the historical electrical feature data of multiple dimensions of each distribution network. After that, a pre-set pseudo-label generation strategy can be used to generate pseudo-labels for the historical electrical operation data of each distribution network and its corresponding structural data. For example, the pseudo-label generation strategy can be expressed by the following formula: Among them, P pse (t) represents the pseudo fault label at time t, V i (t) and I i (t) is the voltage and current of the ith node at time t, P total (t) is the total power of the distribution network at time t, α i is the weight coefficient of each node.

[0126] After completing the above steps, the historical electrical operation data, structural data, historical enhanced electrical operation data and historical electrical feature data of multiple dimensions of each distribution network can be used to train the self-supervised model in combination with the pre-generated pseudo labels, and the loss function is calculated during the training process until the loss function converges. After that, the model can be optimized based on the back propagation algorithm (such as the gradient descent method) until the preset optimization conditions are met (such as the number of iterations reaches the preset number) to obtain the distribution network fault type model.

[0127] In this embodiment, through the above steps, the distribution network fault type model can be used to obtain the fault type of the distribution network according to the target fault node and the structural data of the distribution network.

[0128] Therefore, the technical solution of the present invention calculates the calculated power of each node according to the voltage and current of each node, and obtains the total power of the distribution network according to the power of each node, and determines the fault weight of each node based on the calculated power, power and total power of each node, which greatly improves the accuracy of determining the doubtful node later, so that the entire fault diagnosis process can locate the potential fault point more efficiently and accurately. Then, the node with a fault weight greater than zero is determined as the doubtful node. Based on the doubtful node, the structural data of the doubtful node is screened out from the structural data of each node in the distribution network, and the initial fault node is determined according to the structural data and electrical operation data of the doubtful node, which effectively narrows the scope of fault investigation, thereby improving the fault detection efficiency. Then, according to the preset first time window and the voltage of the initial fault node at each moment, the voltage characteristic value of the initial fault node at each moment is determined, and according to the preset second time window and the current of the initial fault node at each moment, the current characteristic value of the initial fault node at each moment is determined, which effectively avoids the influence of data contingency on the analysis result, and then can more accurately capture the trend of voltage and current changes over time, thereby improving the accuracy of the subsequent determined fault time. The voltage deviation of the initial fault node at each moment is determined according to the voltage of the initial fault node at each moment and the corresponding voltage characteristic value, and the current deviation of the initial fault node at each moment is determined according to the current of the initial fault node at each moment and the corresponding current characteristic value, and the degree of deviation of the electrical parameters of the initial fault node from the normal state is accurately quantified. Then, the moment when the voltage deviation is greater than the preset voltage threshold and the current deviation is greater than the preset current threshold is determined as the fault time of the initial fault node, thereby improving the accuracy of the determined fault time. Subsequently, the electrical operation data is screened by the fault time to obtain the first electrical operation data, focusing on the key information of the fault occurrence period and avoiding the interference of irrelevant data. The target fault node is determined by the first electrical operation data and the preset target power, which can more accurately judge the actual impact of the fault on the electrical operation parameters and improve the accuracy of fault diagnosis. After that, the fault diagnosis result of the distribution network is determined according to the target fault node, which can quickly and accurately determine the fault diagnosis result of the distribution network, provide valuable fault information for the staff, thereby ensuring the reliable operation of the distribution network and enhancing the user's satisfaction. Then determine whether the fault diagnosis result is a fault. If a fault occurs, the target fault node and the structural data of the distribution network are input into the pre-trained distribution network fault type model to obtain the fault type of the distribution network. At this time, the fault type of the distribution network can be sent to the staff's terminal to provide highly targeted guidance to the staff during the fault handling process, so that the staff can clearly know the specific type of the fault, and then be able to choose the appropriate processing methods and tools in a targeted manner, avoiding blind troubleshooting and invalid operations, thereby improving the efficiency and accuracy of fault handling.If no fault occurs, the fault diagnosis result is determined to be no fault, and the fault diagnosis result of no fault can be sent to the terminal of the staff, so as to avoid the staff from wasting unnecessary time and energy on inspection in the fault-free area. Therefore, the technical solution of the present invention solves the problem of low efficiency and difficulty in ensuring accuracy caused by relying on manual experience analysis in the prior art.

[0129] Figure 3 A structural schematic diagram of a distribution network fault diagnosis device provided in an embodiment of the present invention, the device and the distribution network fault diagnosis method of the above-mentioned embodiments belong to the same inventive concept, and the details not fully described in the embodiment of the distribution network fault diagnosis device can refer to the embodiment of the above-mentioned distribution network fault diagnosis method.

[0130] like Figure 3 As shown, the device comprises:

[0131] A first node determination module 310, configured to determine a doubtful node based on electrical operation data of each node in the distribution network;

[0132] A second node determination module 320, configured to filter out the structural data of the doubtful node from the structural data of each node in the distribution network based on the doubtful node, and determine the initial fault node according to the structural data of the doubtful node and the electrical operation data;

[0133] A time determination module 330 is used to extract features from the electrical operation data of the initial fault node using a preset time window to obtain electrical feature data of the initial fault node, and determine the fault time of the initial fault node according to the electrical feature data;

[0134] A third node determination module 340 is used to filter the electrical operation data according to the fault time to obtain first electrical operation data, and determine a target fault node using the first electrical operation data and a preset target power;

[0135] The fault diagnosis module 350 is used to determine the fault diagnosis result of the distribution network according to the target fault node.

[0136] Based on the above embodiment, the electrical operation data includes voltage, current and power, and the first node determination module 310 is specifically used for:

[0137] Calculating the calculated power of each node according to the voltage and current of each node, and obtaining the total power of the distribution network according to the power of each node;

[0138] Determine a fault weight of each node based on the calculation power, power and total power of each node;

[0139] The node whose fault weight is greater than zero is determined as the suspicious node.

[0140] Based on the above embodiment, the second node determination module 320 determines the initial fault node according to the structural data of the doubtful node and the electrical operation data, including:

[0141] Determine an adjacent node of the questionable node according to the structural data of the questionable node, and filter out an impedance between the adjacent node and the questionable node from the structural data of the questionable node based on the adjacent node and the questionable node to obtain an adjacent impedance;

[0142] Determining the power flow power of the node in question according to the adjacent impedance, the power of the node in question and the power of the adjacent nodes;

[0143] The questionable node whose power flow power is greater than a first preset power threshold is determined as the initial fault node.

[0144] On the basis of the above embodiment, the preset time window includes a preset first time window and a preset second time window, the preset first time window is smaller than the preset second time window, the electrical characteristic data includes a current characteristic value and a voltage characteristic value, and the time determination module 330 is specifically used for:

[0145] Determine the voltage characteristic value of the initial fault node at each moment according to the preset first time window and the voltage of the initial fault node at each moment, and determine the current characteristic value of the initial fault node at each moment according to the preset second time window and the current of the initial fault node at each moment;

[0146] Determine the voltage deviation of the initial fault node at each moment according to the voltage of the initial fault node at each moment and the corresponding voltage characteristic value, and determine the current deviation of the initial fault node at each moment according to the current of the initial fault node at each moment and the corresponding current characteristic value;

[0147] The moment when the voltage deviation is greater than a preset voltage threshold and the current deviation is greater than a preset current threshold is determined as the fault time of the initial fault node.

[0148] On the basis of the above embodiment, the third node determination module 340 is specifically used to: filter out the power of each node corresponding to the fault time from the electrical operation data according to the fault time, and obtain the first electrical operation data;

[0149] Calculating the power deviation of the fault time based on the first electrical operation data and the preset target power of each node;

[0150] The fault time at which the power deviation is greater than a second preset power threshold is determined as the target fault time, and the initial fault node corresponding to the target fault time is determined as the target fault node.

[0151] Based on the above embodiment, the device further includes:

[0152] A fault type determination module is used to input the target fault node and the structural data of the distribution network into a pre-trained distribution network fault type model to obtain the fault type of the distribution network after determining the fault diagnosis result of the distribution network according to the target fault node and determining that the fault diagnosis result is a fault.

[0153] Based on the above embodiment, the training process of the distribution network fault type model includes:

[0154] Obtain historical electrical operation data and corresponding structural data of each distribution network;

[0155] Performing data enhancement processing on the historical electrical operation data of each distribution network to obtain the historical enhanced electrical operation data of each distribution network, performing multi-dimensional feature extraction on the historical electrical operation data and the historical enhanced electrical operation data of each distribution network to obtain the multi-dimensional historical electrical feature data of each distribution network;

[0156] The self-supervised model is trained using the historical electrical operation data, structural data, historical enhanced electrical operation data and historical electrical feature data of multiple dimensions of each distribution network, and a loss function is calculated, wherein the loss function includes a transformation invariance loss function and a cross entropy loss function, the transformation invariance loss function includes the square norm of the difference between the historical electrical operation data and the historical enhanced electrical operation data in multiple dimensions, and the cross entropy loss function includes the negative log-likelihood between the pseudo-label probability distribution and the predicted probability distribution;

[0157] The model is optimized based on the back propagation algorithm until the preset optimization conditions are met to obtain the distribution network fault type model.

[0158] The fault diagnosis device for a distribution network provided in an embodiment of the present invention can execute the fault diagnosis method for a distribution network provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0159] It is worth noting that in the embodiment of the above-mentioned distribution network fault diagnosis device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0160] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 4 A block diagram of an exemplary electronic device 4 suitable for implementing embodiments of the present invention is shown. Figure 4 The electronic device 4 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0161] like Figure 4 As shown, the electronic device 4 is in the form of a general purpose computing electronic device. The components of the electronic device 4 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

[0162] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0163] The electronic device 4 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 4, including volatile and non-volatile media, removable and non-removable media.

[0164] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 4 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 not shown, usually called a "hard drive"). Although Figure 4 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0165] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0166] The electronic device 4 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), one or more devices that enable a user to interact with the electronic device 4, and / or any device that enables the electronic device 4 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 4 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. Figure 4 As shown, the network adapter 20 communicates with other modules of the electronic device 4 via the bus 18. It should be understood that although Figure 4 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 4, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0167] The processing unit 16 executes various functional applications and page displays by running the program stored in the system memory 28, for example, implementing the fault diagnosis method of the distribution network provided in the embodiment of the present invention, the method comprising:

[0168] Determine the nodes in question based on the electrical operation data of each node in the distribution network;

[0169] Based on the doubtful node, the structural data of the doubtful node is screened out from the structural data of each node in the distribution network, and an initial fault node is determined according to the structural data of the doubtful node and the electrical operation data;

[0170] Extracting features of the electrical operation data of the initial fault node using a preset time window to obtain electrical feature data of the initial fault node, and determining the fault time of the initial fault node according to the electrical feature data;

[0171] Filtering the electrical operation data according to the fault time to obtain first electrical operation data, and determining a target fault node using the first electrical operation data and a preset target power;

[0172] A fault diagnosis result of the distribution network is determined according to the target fault node.

[0173] Of course, those skilled in the art can understand that the processor can also implement the technical solution of the fault diagnosis method for the distribution network provided by any embodiment of the present invention.

[0174] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, for example, a fault diagnosis method for a distribution network provided in an embodiment of the present invention is implemented. The method includes:

[0175] Determine the nodes in question based on the electrical operation data of each node in the distribution network;

[0176] Based on the doubtful node, the structural data of the doubtful node is screened out from the structural data of each node in the distribution network, and an initial fault node is determined according to the structural data of the doubtful node and the electrical operation data;

[0177] Extracting features of the electrical operation data of the initial fault node using a preset time window to obtain electrical feature data of the initial fault node, and determining the fault time of the initial fault node according to the electrical feature data;

[0178] Filtering the electrical operation data according to the fault time to obtain first electrical operation data, and determining a target fault node using the first electrical operation data and a preset target power;

[0179] A fault diagnosis result of the distribution network is determined according to the target fault node.

[0180] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0181] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0182] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0183] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0184] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0185] In addition, the acquisition, storage, use, and processing of data in the technical solution of the present invention are in compliance with the relevant provisions of national laws and regulations.

[0186] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A fault diagnosis method for a distribution network, characterized in that: The method comprises: Determine the nodes in question based on the electrical operation data of each node in the distribution network; Based on the doubtful node, the structural data of the doubtful node is screened out from the structural data of each node in the distribution network, and an initial fault node is determined according to the structural data of the doubtful node and the electrical operation data; Extracting features of the electrical operation data of the initial fault node using a preset time window to obtain electrical feature data of the initial fault node, and determining the fault time of the initial fault node according to the electrical feature data; Filtering the electrical operation data according to the fault time to obtain first electrical operation data, and determining a target fault node using the first electrical operation data and a preset target power; A fault diagnosis result of the distribution network is determined according to the target fault node.

2. The fault diagnosis method for a distribution network according to claim 1, characterized in that: The electrical operation data includes voltage, current and power. Determining the suspicious node according to the electrical operation data of each node in the distribution network includes: Calculating the calculated power of each node according to the voltage and current of each node, and obtaining the total power of the distribution network according to the power of each node; Determine a fault weight of each node based on the calculation power, power and total power of each node; The node whose fault weight is greater than zero is determined as the suspicious node.

3. The fault diagnosis method for distribution network according to claim 2, characterized in that: Determining an initial fault node according to the structural data of the questionable node and the electrical operation data includes: Determine an adjacent node of the questionable node according to the structural data of the questionable node, and filter out an impedance between the adjacent node and the questionable node from the structural data of the questionable node based on the adjacent node and the questionable node to obtain an adjacent impedance; Determining the power flow power of the node in question according to the adjacent impedance, the power of the node in question and the power of the adjacent nodes; The questionable node whose power flow power is greater than a first preset power threshold is determined as the initial fault node.

4. The fault diagnosis method for a distribution network according to claim 2, characterized in that: The preset time window includes a preset first time window and a preset second time window, the preset first time window is smaller than the preset second time window, the electrical characteristic data includes a current characteristic value and a voltage characteristic value, and the electrical operation data of the initial fault node is feature extracted by using the preset time window to obtain the electrical characteristic data of the initial fault node, and the fault time of the initial fault node is determined according to the electrical characteristic data, including: Determine the voltage characteristic value of the initial fault node at each moment according to the preset first time window and the voltage of the initial fault node at each moment, and determine the current characteristic value of the initial fault node at each moment according to the preset second time window and the current of the initial fault node at each moment; Determine the voltage deviation of the initial fault node at each moment according to the voltage of the initial fault node at each moment and the corresponding voltage characteristic value, and determine the current deviation of the initial fault node at each moment according to the current of the initial fault node at each moment and the corresponding current characteristic value; The moment when the voltage deviation is greater than a preset voltage threshold and the current deviation is greater than a preset current threshold is determined as the fault time of the initial fault node.

5. The fault diagnosis method for distribution network according to claim 2, characterized in that: The electrical operation data is screened by the fault time to obtain first electrical operation data, and a target fault node is determined by using the first electrical operation data and a preset target power, including: Filtering the power of each node corresponding to the fault time from the electrical operation data according to the fault time to obtain the first electrical operation data; Calculating the power deviation of the fault time based on the first electrical operation data and the preset target power of each node; The fault time at which the power deviation is greater than a second preset power threshold is determined as the target fault time, and the initial fault node corresponding to the target fault time is determined as the target fault node.

6. The fault diagnosis method for a distribution network according to claim 1, characterized in that: After determining the fault diagnosis result of the distribution network according to the target fault node, the method further includes: When it is determined that the fault diagnosis result is that a fault has occurred, the target fault node and the structural data of the distribution network are input into a pre-trained distribution network fault type model to obtain the fault type of the distribution network.

7. The fault diagnosis method for a power distribution network according to claim 6, characterized in that: The training process of the distribution network fault type model includes: Obtain historical electrical operation data and corresponding structural data of each distribution network; Performing data enhancement processing on the historical electrical operation data of each distribution network to obtain the historical enhanced electrical operation data of each distribution network, performing multi-dimensional feature extraction on the historical electrical operation data and the historical enhanced electrical operation data of each distribution network to obtain the multi-dimensional historical electrical feature data of each distribution network; The self-supervised model is trained using the historical electrical operation data, structural data, historical enhanced electrical operation data and historical electrical feature data of multiple dimensions of each distribution network, and a loss function is calculated, wherein the loss function includes a transformation invariance loss function and a cross entropy loss function, the transformation invariance loss function includes the square norm of the difference between the historical electrical operation data and the historical enhanced electrical operation data in multiple dimensions, and the cross entropy loss function includes the negative log-likelihood between the pseudo-label probability distribution and the predicted probability distribution; The model is optimized based on the back propagation algorithm until the preset optimization conditions are met to obtain the distribution network fault type model.

8. A fault diagnosis device for a distribution network, characterized in that: The device comprises: A first node determination module is used to determine the doubtful node according to the electrical operation data of each node in the distribution network; A second node determination module, configured to filter out the structural data of the doubtful node from the structural data of each node in the distribution network based on the doubtful node, and determine the initial fault node according to the structural data of the doubtful node and the electrical operation data; A time determination module, used to extract features from the electrical operation data of the initial fault node using a preset time window to obtain electrical feature data of the initial fault node, and determine the fault time of the initial fault node according to the electrical feature data; a third node determination module, configured to filter the electrical operation data by the fault time to obtain first electrical operation data, and determine a target fault node by using the first electrical operation data and a preset target power; A fault diagnosis module is used to determine a fault diagnosis result of the distribution network according to the target fault node.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the fault diagnosis method for the distribution network described in any one of claims 1-7.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions, when executed by a computer processor, implement the fault diagnosis method for a distribution network as described in any one of claims 1 to 7.

Images