Distribution network line fault determination method and device, equipment and medium

Abstract

The embodiment of the invention provides a distribution network line fault determination method and device, equipment and a medium. The method comprises the following steps: firstly, acquiring an operation state data set and a historical fault data set of a target distribution network line; then, on the basis of a feature selection algorithm, the dependency degree of the historical fault data set relative to the operation state data set is calculated; secondly, optimizing the objective function according to the dependency degree and a preset criterion, and determining a fault criterion subset; and finally, based on the fault criterion subset, determining the fault type of the target distribution network line. Through the method, the accuracy and applicability of fault judgment are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power system fault diagnosis, and in particular to a distribution network line fault determination method, device, equipment and medium. BACKGROUND

[0002] With the accelerated construction of new power systems, distribution network lines bear the key tasks of distributed power consumption and multi-element load access, and their safe and stable operation becomes a core link to ensure reliable energy supply. The plan clearly states that the efficiency of distribution network fault diagnosis needs to be improved through intelligent technology to reduce power outage time and economic losses. Against this background, the rapid and accurate judgment of distribution network line faults has become a problem to be solved.

[0003] In the prior art, the commonly used distribution network line fault determination method is usually a logical judgment method based on threshold comparison. Specifically, by setting fixed thresholds of electrical quantities such as current and voltage, fault alarm is triggered when real-time monitoring data exceeds the threshold.

[0004] However, the distribution network line fault determination method in the prior art has poor adaptability to fault diagnosis, resulting in misjudgment and missed judgment. SUMMARY

[0005] The embodiments of the present application provide a distribution network line fault determination method, device, equipment and medium to solve the problem of poor adaptability to fault diagnosis in the prior art, resulting in misjudgment and missed judgment.

[0006] In a first aspect, the embodiments of the present application provide a distribution network line fault determination method, comprising:

[0007] obtaining an operating state data set and a historical fault data set of a target distribution network line;

[0008] calculating the dependence of the historical fault data set on the operating state data set based on a feature selection algorithm;

[0009] determining a fault criterion subset according to the dependence and a preset criterion optimization target function;

[0010] determining the fault type of the target distribution network line based on the fault criterion subset.

[0011] In a possible implementation, the dependence of the historical fault data set on the operating state data set is calculated based on a feature selection algorithm, comprising:

[0012] for each historical fault data in the historical fault data set, the mutual information of the historical fault data with respect to each operating state data in the operating state data set is calculated respectively;

[0013] According to the mutual information, a normalized dependency of each of the historical fault data with respect to each of the operating state data is calculated respectively;

[0014] According to the normalized dependency of each of the historical fault data with respect to each of the operating state data and the number of the historical fault data, the dependency of the historical fault data set with respect to the operating state data set is calculated.

[0015] In a possible implementation, the determining the fault criterion subset according to the dependency and a preset criterion optimization objective function comprises:

[0016] Randomly selecting a plurality of the operating state data from the operating state data set as a feature subset;

[0017] Based on a particle swarm optimization algorithm and the preset criterion optimization objective function, iteratively calculating the feature subset and the number of features in the feature subset until the preset criterion optimization objective function converges, to obtain the fault criterion subset.

[0018] In a possible implementation, the determining the fault type of the target distribution network line based on the fault criterion subset comprises:

[0019] When the criterion feature in the fault criterion subset is three-phase current and three-phase voltage, determining that the fault type of the target distribution network line is a short-circuit fault;

[0020] When the criterion feature in the fault criterion subset is zero-sequence current and neutral point voltage, determining that the fault type of the target distribution network line is a single-phase grounding fault;

[0021] When the criterion feature in the fault criterion subset is contact temperature and vibration signal, determining that the fault type of the target distribution network line is a switch contact failure fault;

[0022] When the criterion feature in the fault criterion subset is switching time of the switch device, determining that the fault type of the target distribution network line is a switch failure to operate fault.

[0023] In a possible implementation, the obtaining the operating state data set of the target distribution network line comprises:

[0024] Obtaining electrical quantity data and mechanical feature data of the target distribution network line in a preset period, wherein the electrical quantity data comprises three-phase current, voltage effective value, zero-sequence current, neutral point voltage data, and the mechanical feature data comprises contact temperature, vibration signal and switching time data of the switch device;

[0025] The electrical quantity data and the mechanical characteristic data are sequentially subjected to time synchronization processing, abnormal value elimination processing and standardization processing to obtain the operation state data set.

[0026] In a possible implementation, acquiring the historical fault data set comprises:

[0027] From the historical fault records, characteristic data that has a change before and after the occurrence of a fault is acquired;

[0028] The characteristic data is determined as the historical fault data set;

[0029] The characteristic data comprises a three-phase current mutation quantity, a voltage sudden drop rate, a zero-sequence current increment, a neutral point voltage offset quantity and a switching action time deviation.

[0030] In a possible implementation, after the operation state data set and the historical fault data set of the target distribution network line are acquired, the method further comprises:

[0031] The operation state data set and the historical fault data set are subjected to timestamp alignment processing.

[0032] In a second aspect, an embodiment of the present application provides a distribution network line fault determination apparatus, comprising:

[0033] An acquisition module is configured to acquire an operation state data set and a historical fault data set of a target distribution network line;

[0034] A calculation module is configured to calculate a dependency of the historical fault data set relative to the operation state data set based on a feature selection algorithm;

[0035] A first determination module is configured to determine a fault criterion subset according to the dependency and a preset criterion optimization target function;

[0036] A second determination module is configured to determine a fault type of the target distribution network line based on the fault criterion subset.

[0037] In a possible implementation, the calculation module is specifically configured to:

[0038] For each historical fault data in the historical fault data set, mutual information of the historical fault data relative to each operation state data in the operation state data set is calculated respectively;

[0039] According to the mutual information, a standardized dependency of each historical fault data relative to each operation state data is calculated respectively;

[0040] The dependency of the historical fault data set on the operation state data set is calculated according to a normalized dependency of each historical fault data on each operation state data and a quantity of the historical fault data.

[0041] In a possible implementation, the first determining module is specifically configured to:

[0042] randomly selecting a plurality of operation state data from the operation state data set as a feature subset;

[0043] iteratively calculating the feature subset and a quantity of features in the feature subset based on a particle swarm optimization algorithm and the preset criterion optimization objective function until the preset criterion optimization objective function converges, to obtain the fault criterion subset.

[0044] In a possible implementation, the second determining module is specifically configured to:

[0045] when the criterion features in the fault criterion subset are three-phase currents and three-phase voltages, determining that a fault type of the target distribution network line is a short-circuit fault;

[0046] when the criterion features in the fault criterion subset are zero-sequence currents and neutral point voltages, determining that the fault type of the target distribution network line is a single-phase grounding fault;

[0047] when the criterion features in the fault criterion subset are contact temperatures and vibration signals, determining that the fault type of the target distribution network line is a switch contact failure fault;

[0048] when the criterion features in the fault criterion subset are switching-on and switching-off times of a switch device, determining that the fault type of the target distribution network line is a switch failure-to-operate fault.

[0049] In a possible implementation, the obtaining module is specifically configured to:

[0050] obtaining electrical quantity data and mechanical feature data of the target distribution network line in a preset period, wherein the electrical quantity data includes three-phase currents, voltage effective values, zero-sequence currents, neutral point voltage data, and the mechanical feature data includes contact temperatures, vibration signals and switching-on and switching-off times of a switch device;

[0051] sequentially performing time synchronization processing, outlier elimination processing and standardization processing on the electrical quantity data and the mechanical feature data, to obtain the operation state data set.

[0052] In a possible implementation, the obtaining module is specifically configured to:

[0053] From the historical fault record, obtain feature data with changes before and after the fault occurrence time;

[0054] Determine the feature data as the historical fault data set;

[0055] The feature data includes three-phase current mutation, voltage step-down rate, zero sequence current increment, neutral point voltage offset, and switch action time deviation.

[0056] In a possible implementation, the distribution network line fault determination apparatus further includes a processing module configured to:

[0057] Timestamp alignment processing is performed on the operating state data set and the historical fault data set.

[0058] In a third aspect, the embodiments of the present application provide an electronic device, comprising: a memory, a processor;

[0059] The memory stores computer execution instructions;

[0060] The processor executes the computer execution instructions stored in the memory, so that the processor executes the first aspect and / or various possible implementation manners of the first aspect.

[0061] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium, the computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by a processor to implement the first aspect and / or various possible implementation manners of the first aspect.

[0062] The distribution network line fault determination method, apparatus, device and medium provided by the embodiments of the present application first obtain the operating state data set and the historical fault data set of the target distribution network line, and construct a data basis for analysis. Then, based on a feature selection algorithm, the dependence of the historical fault data set on the operating state data set is calculated, so as to quantify the correlation between the features and the fault, and provide a basis for subsequent acquisition of a fault judgment subset. Then, according to the dependence and a preset criterion optimization target function, a high-value fault criterion subset is screened out to reduce redundant features and improve the model generalization ability. Finally, based on the fault criterion subset, the fault type of the target distribution network line is determined, which realizes accurate determination of the line fault type in this way, improves the accuracy and efficiency of fault diagnosis, and reduces misjudgment and missed judgment. BRIEF DESCRIPTION OF DRAWINGS

[0063] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present application and, together with the specification, serve to explain the principles of the application.

[0064] Figure 1Flowchart of the method for determining a distribution network line fault provided by an embodiment of the present application Figure 1 ;

[0065] Figure 2 Flowchart of the method for determining a distribution network line fault provided by an embodiment of the present application Figure 2 ;

[0066] Figure 3 Structural diagram of the device for determining a distribution network line fault provided by an embodiment of the present application

[0067] Figure 4 Structural diagram of the electronic device provided by an embodiment of the present application.

[0068] The specific embodiments of the present application have been shown in the above-described drawings, and will be described in more detail hereinafter. These drawings and the written description are not intended to restrict the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0069] The exemplary embodiments will be described in detail herein with reference to the attached drawings. In the following description, the same numbers are used to indicate the same or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not meant to represent all implementations consistent with the present application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the present application as detailed in the appended claims.

[0070] With the accelerated construction of new power systems, distribution network lines bear the key task of distributed power consumption and multi-element load access, and their safe and stable operation becomes the core link to ensure reliable energy supply. The plan clearly points out that the efficiency of distribution network fault diagnosis needs to be improved through intelligent technology to reduce power outage time and economic loss. In this context, the rapid and accurate judgment of distribution network line faults has become a problem to be solved.

[0071] In the prior art, the commonly used distribution network line fault diagnosis method is usually a logical judgment method based on threshold comparison. Specifically, a fixed threshold of electrical quantities such as current and voltage is set, and a fault alarm is triggered when the real-time monitoring data exceeds the threshold.

[0072] However, the prior art has significant defects. The use of static threshold or fixed feature set cannot adapt to feature drift caused by distribution network load fluctuation, equipment aging and environmental changes, and is prone to misjudgment and omission.

[0073] Based on this, the application provides a distribution network line fault determination method. In view of the fact that the existing power distribution network fault diagnosis method relies on static threshold and fixed feature set, and is difficult to cope with the feature drift caused by load fluctuation, equipment aging and external environment change in the operation environment of the distribution network, the inventors think of using statistical learning theory, using a feature selection algorithm (i.e. mutual information) to evaluate the dependence between each feature and the target variable, i.e. the dependence of the historical fault data set with respect to the operation state data set, dynamically mining the deep correlation between the historical fault data and the current operation state, and optimizing the fault criterion subset based on the dependence, thereby enhancing the robustness and generalization ability of the diagnosis model to feature changes. In this way, adaptive adjustment can be made according to the real-time changes of the operation state of the distribution network, thereby significantly improving the accuracy and real-time performance of fault diagnosis and reducing the misjudgment and missed judgment.

[0074] The technical solutions of the application and how the technical solutions solve the above technical problems will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes can not be described again in some embodiments. The embodiments of the application will be described below with reference to the drawings.

[0075] Figure 1 The flowchart of the distribution network line fault determination method provided by the embodiments of the application is shown in Figure 1 ; as shown in the figure, the method comprises: Figure 1

[0076] S101, obtaining the operation state data set and the historical fault data set of the target distribution network line.

[0077] It can be understood that by obtaining the operation state data set and the historical fault data set of the target distribution network line, the mapping basis between the input data (operation state data set) and the output data (historical fault data set) is explicitly constructed, thereby providing a data basis for subsequent feature selection and criterion extraction.

[0078] S102, calculating the dependence of the historical fault data set with respect to the operation state data set based on a feature selection algorithm.

[0079] In an implementable manner, first, for each historical fault data in the historical fault data set, the mutual information of the historical fault data with respect to each operation state data in the operation state data set is calculated; then, according to the mutual information, the standardized dependence of each historical fault data with respect to each operation state data is calculated; finally, according to the standardized dependence of each historical fault data with respect to each operation state data and the number of historical fault data, the dependence of the historical fault data set with respect to the operation state data set is calculated.

[0080] It should be noted that the calculation formula of mutual information is:​

[0081]

[0082] where C is the running state dataset; D is the historical fault dataset; is the historical fault dataset is the running state dataset is the mutual information of and is the marginal probability density of and is the joint probability density of and and are calculated using Gaussian kernel density estimation.

[0083] After that, the calculation formula of the normalized dependence is:

[0084]

[0085] where is the historical fault dataset is the running state dataset is the normalized dependence of is the mutual information of is the maximum value of the mutual information of all the features of the running state dataset to the historical fault dataset

[0086] Finally, the calculation formula of the dependence of the historical fault dataset to the running state dataset is:

[0087]

[0088] where is the historical fault dataset is the running state dataset is the normalized dependence of is the number of features in the output historical fault dataset.

[0089] It can be understood that by using the calculation methods of mutual information and normalized dependence, the correlation strength between the historical fault data and the running state data is systematically evaluated, and the importance quantification of the role of each input feature in fault judgment is realized. Not only the nonlinear dependence relationship between the input features and the fault features is revealed, but also the comparability between different features is ensured through normalization processing, which provides precise and interpretable data support for subsequent feature screening and criterion feature subset optimization, and significantly improves the effectiveness and generalization ability of the fault judgment model. ​​

[0090] S103, determining the fault criterion subset according to the dependence and the preset criterion optimization target function.

[0091] In an implementable manner, first, a plurality of operating state data are randomly selected from the operating state data set as a feature subset; then, the feature subset and the number of features in the feature subset are iteratively calculated based on the particle swarm optimization algorithm and the preset criterion optimization target function, until the preset criterion optimization target function converges, and the fault judgment subset is obtained.

[0092] It should be noted that the preset criterion optimization target function is constructed according to the maximization of the historical fault data set while minimizing the size of the feature subset, and the specific expression is:

[0093]

[0094] In the formula, is the feature subset, is the number of features in the feature subset; is a balance coefficient, which can be set to 0.4 in the embodiment of the application, is the dependence of the feature subset on the historical fault data set.

[0095] It should be understood that in the process of iteratively calculating the feature subset and the number of features in the feature subset based on the particle swarm optimization algorithm and the preset criterion optimization target function, first, population initialization is performed, assuming that the total number of features is N, and each "particle" represents a feature subset (a 0-1 vector with a length of N): wherein "1" represents selecting the feature, and "0" represents not selecting; initializing the particle swarm (such as 30 particles), randomly generating a binary vector and a velocity vector for each particle; then, evaluating the fitness (i.e. the value of the preset criterion optimization target function) of each particle to minimize the value of the preset criterion optimization target function; then, updating the velocity and position of each particle (wherein the updating formula of the velocity and the position is the conventional particle swarm velocity and position updating formula); finally, if the target function converges (such as the value is unchanged for a plurality of consecutive iterations) or reaches the maximum number of iterations, the process is stopped, and the final fault judgment subset is obtained.

[0096] It can be understood that in this way, the selection of too many redundant features or the neglect of key features is avoided, the computational complexity is reduced, and the speed and accuracy of fault judgment are improved.

[0097] S104, determining the fault type of the target distribution network line based on the fault criterion subset.

[0098] In one feasible method, when the criterion characteristics in the fault criterion subset are three-phase current and three-phase voltage, the fault type of the target distribution network line is determined to be a short-circuit fault; when the criterion characteristics in the fault criterion subset are zero-sequence current and neutral point voltage, the fault type of the target distribution network line is determined to be a single-phase grounding fault; when the criterion characteristics in the fault criterion subset are contact temperature and vibration signal, the fault type of the target distribution network line is determined to be a poor switch contact fault; when the criterion characteristics in the fault criterion subset are the opening and closing time of the switching device, the fault type of the target distribution network line is determined to be a switch refusal to operate fault.

[0099] As can be seen, this method achieves rapid and accurate identification of distribution network line fault types by precisely matching different fault types based on key features of a fault criterion subset. The efficient criterion features derived from feature selection optimization not only improve the accuracy and reliability of fault diagnosis, but also effectively reduce computational complexity, significantly enhancing the efficiency and intelligence of distribution network fault detection and location.

[0100] The distribution network line fault determination method provided in the embodiment of the present application first obtains the operating status dataset and historical fault dataset of the target distribution network line to construct a data foundation for analysis; then, based on the feature selection algorithm, the dependency of the historical fault dataset with respect to the operating status dataset is calculated, thereby quantifying the correlation between the features and the faults, and providing a basis for the subsequent acquisition of the fault judgment subset; then, the objective function is optimized according to the dependency and the preset criteria, and a high-value fault judgment subset is screened out to reduce redundant features and improve the generalization ability of the model; finally, based on the fault judgment subset, the fault type of the target distribution network line is determined. In this way, accurate judgment of the line fault type is achieved, the accuracy and efficiency of fault diagnosis are improved, and misjudgment and missed judgment are reduced.

[0101] Figure 2 Schematic diagram of the process of determining the distribution network line fault provided in the embodiment of the present application Figure 2 ,like Figure 1 As shown, this embodiment Figure 3 Based on the embodiment, how to obtain a data set is described in detail. The method includes:

[0102] S201. Obtain electrical quantity data and mechanical characteristic data of a target distribution network line in a preset period.

[0103] Among them, electrical quantity data includes three-phase current, voltage RMS, zero-sequence current, and neutral point voltage data; mechanical characteristic data includes contact temperature, vibration signal, and opening and closing time data of the switching device.

[0104] It should be noted that the three-phase current effective value is used to measure the current level of the three-phase load, which can be used to judge the load balance state and abnormal power consumption behavior; the voltage effective value is used to analyze the power supply voltage quality, to judge the voltage fluctuation or over / under voltage condition; the zero sequence current reflects whether there is a single-phase ground fault; the neutral point voltage data is used to measure the neutral point drift or imbalance in the power distribution system.

[0105] The contact temperature is used to monitor the risk of contact overheating, identify poor contact, aging and other problems; the vibration signal is used to analyze the mechanical action quality, and find out the hidden troubles of jamming or wear in advance; the opening and closing time data is used to detect the change of switch action performance.

[0106] S202, sequentially performing time synchronization processing, outlier rejection processing and standardization processing on the electrical quantity data and mechanical characteristic data to obtain a running state data set.

[0107] It should be understood that the data from different collection devices or different signal sources (such as electrical quantity sampling devices and mechanical vibration sensors) are time-synchronized, i.e. aligned on a unified time axis, to ensure the consistency of multi-source data in time, which can ensure that multi-type data can correctly correspond to the system state at the same time point, and prevent misjudgment caused by time mismatch; the outliers are rejected to reduce the interference of abnormal data on model training and fault diagnosis, and improve the stability and accuracy of diagnosis; the data is standardized, which can eliminate the dimension influence and enhance the feature comparability.

[0108] It should be noted that the way to obtain the historical fault data set includes:

[0109] First, from the historical fault record, the feature data with changes before and after the fault occurrence time is obtained; then, the feature data is determined as the historical fault data set.

[0110] The feature data includes three-phase current mutation, voltage step-down rate, zero sequence current increment, neutral point voltage offset and switch action time deviation.

[0111] It should be further noted that after obtaining the running state data set and the historical fault data set of the target distribution network line, the running state data set and the historical fault data set need to be aligned, specifically:

[0112] The running state data set and the historical fault data set are timestamped and aligned.

[0113] For example, assuming that the running state data set is C, as shown in Table 1, and the historical fault data set is D, as shown in Table 2, then the data set A obtained by aligning the running state data set and the historical fault data set is as follows:

[0114] A=(C、D)

[0115] It can be understood that, by aligning the running state data set and the historical fault data set, different sources and types of information can be better integrated, the correlation and complementarity between features can be enhanced, and a reliable foundation can be provided for subsequent feature extraction and model training.

[0116] Table 1 Running state data set C

[0117]

[0118] Table 2 Historical fault data set D

[0119]

[0120] Figure 3 A structural schematic diagram of a line fault determination device provided by an embodiment of the present application is shown in FIG. 1. As shown in FIG. 1, the device includes: Figure 4

[0121] An acquisition module 301 is configured to acquire a running state data set and a historical fault data set of a target distribution network line.

[0122] A calculation module 302 is configured to calculate a dependency of the historical fault data set relative to the running state data set based on a feature selection algorithm.

[0123] A first determination module 303 is configured to determine a fault criterion subset according to the dependency and a preset criterion optimization target function.

[0124] A second determination module 304 is configured to determine a fault type of the target distribution network line based on the fault criterion subset.

[0125] In a possible implementation, the calculation module 302 is specifically configured to:

[0126] For each historical fault data in the historical fault data set, mutual information of the historical fault data relative to each running state data in the running state data set is calculated respectively.

[0127] According to the mutual information, a standardized dependency of each historical fault data relative to each running state data is calculated respectively.

[0128] According to the standardized dependency of each historical fault data relative to each running state data and the number of historical fault data, the dependency of the historical fault data set relative to the running state data set is calculated.

[0129] In a possible implementation, the first determination module 303 is specifically configured to:

[0130] Randomly select a plurality of running state data from the running state data set as a feature subset.​

[0131] Based on the particle swarm optimization algorithm and the preset criterion optimization objective function, the feature subset and the number of features in the feature subset are iteratively calculated until the preset criterion optimization objective function converges, and a fault judgment subset is obtained.

[0132] In a possible implementation, the second determination module 304 is specifically configured to:

[0133] When the criterion features in the fault criterion subset are three-phase currents and three-phase voltages, it is determined that the fault type of the target distribution network line is a short-circuit fault;

[0134] When the criterion features in the fault criterion subset are zero-sequence currents and neutral point voltages, it is determined that the fault type of the target distribution network line is a single-phase grounding fault;

[0135] When the criterion features in the fault criterion subset are contact temperatures and vibration signals, it is determined that the fault type of the target distribution network line is a switch contact failure fault;

[0136] When the criterion features in the fault criterion subset are switching times of the switch device, it is determined that the fault type of the target distribution network line is a switch failure-to-operate fault.

[0137] In a possible implementation, the acquisition module 301 is specifically configured to:

[0138] The electrical quantity data and the mechanical feature data of the target distribution network line are acquired in a preset period; wherein the electrical quantity data includes three-phase currents, voltage effective values, zero-sequence currents, and neutral point voltage data, and the mechanical feature data includes contact temperatures, vibration signals, and switching times of the switch device;

[0139] The electrical quantity data and the mechanical feature data are sequentially subjected to time synchronization processing, outlier rejection processing, and standardization processing to obtain an operating state data set.

[0140] In a possible implementation, the acquisition module 301 is specifically configured to:

[0141] From the historical fault records, feature data that changes before and after the fault occurrence time is acquired;

[0142] The feature data is determined as a historical fault data set;

[0143] The feature data includes three-phase current mutation, voltage step-down rate, zero-sequence current increment, neutral point voltage offset, and switch action time deviation.

[0144] In a possible implementation, the distribution network line fault determination apparatus further includes a processing module configured to:

[0145] Timestamp alignment is performed on the operational status data set and the historical fault data set.

[0146] The network line fault determination apparatus provided by the embodiments of the present application can execute the method provided by the method embodiments, and has similar implementation principles and technical effects, which will not be described here again.

[0147] Figure 4 The structure schematic diagram of the electronic device provided by the embodiments of the present application is shown in FIG. 1. ​ As shown in FIG. 1, the electronic device 40 provided by the embodiments of the present application includes at least one processor 401 and a memory 402. Optionally, the device 40 further includes a communication component 403. The processor 401, the memory 402 and the communication component 403 are connected through a bus 404.

[0148] In the specific implementation process, the at least one processor 401 executes the computer execution instructions stored in the memory 402, so that the at least one processor 401 executes the above-mentioned method.

[0149] The specific implementation process of the processor 401 can refer to the method embodiments, which have similar implementation principles and technical effects, and will not be described here again.

[0150] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC) and the like. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor and the like. The steps of the method disclosed in the application can be directly embodied as the execution of the hardware processor, or executed by the combination of the hardware and software modules in the processor.

[0151] The memory can include a random access memory (RAM), and can also include a non-volatile memory (NVM), for example, at least one disk memory.

[0152] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, the bus in the drawings of the present application does not limit to only one bus or one type of bus.

[0153] The present application also provides a computer readable storage medium, which stores computer execution instructions, and when a processor executes the computer execution instructions, the above method is realized.

[0154] The above readable storage medium can be realized by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0155] An exemplary readable storage medium is coupled to the processor, so that the processor can read information from the readable storage medium, and can write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an Application Specific Integrated Circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in the device.

[0156] The division of units is only a logical function division, and in actual implementation, there can be another division mode, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0157] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on multiple network units. According to actual needs, part or all of the units can be selected to achieve the purpose of the present embodiment.

[0158] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0159] If the function is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the part of the present application that essentially contributes to the prior art or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various program code storage media.

[0160] Those skilled in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware. The aforementioned program can be stored in a computer readable storage medium. The program executes the steps of the above-mentioned method embodiments when executed; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, and various program code storage media.

[0161] Finally, it should be noted that those skilled in the art, after considering the specification and practicing the disclosed application, will easily think of other embodiments of the present application. The present application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include known or customary technical means in the art that are not disclosed in the present application, and is not limited to the precise structure described above and shown in the drawings, and various modifications and changes can be made without departing from the scope thereof. The scope of the present application is only limited by the appended claims.

Claims

1. A method for determining a distribution network line fault, characterized in that: include: Obtain the operating status dataset and historical fault dataset of the target distribution network line; Calculating the dependency of the historical fault data set on the operating status data set based on a feature selection algorithm; Optimizing the objective function according to the dependency and the preset criteria, and determining a fault criterion subset; Based on the fault criterion subset, a fault type of the target distribution network line is determined.

2. The method according to claim 1, characterized in that The calculating, based on a feature selection algorithm, the dependency of the historical fault data set on the operating status data set includes: For each historical fault data in the historical fault data set, respectively calculating the mutual information of the historical fault data with respect to each operating status data in the operating status data set; Calculating the normalized dependency of each of the historical fault data with respect to each of the operating status data according to the mutual information; The dependency of the historical fault data set on the operating status data set is calculated based on the standardized dependency of each historical fault data set on each operating status data set and the amount of the historical fault data set.

3. The method according to claim 1, characterized in that The step of optimizing the objective function according to the dependency and the preset criteria to determine the fault criterion subset includes: Randomly selecting a plurality of the operating status data from the operating status data set as a feature subset; Based on the particle swarm optimization algorithm and the preset criterion optimization objective function, the feature subset and the number of features in the feature subset are iteratively calculated until the preset criterion optimization objective function converges, thereby obtaining the fault judgment subset.

4. The method according to claim 1, wherein The determining the fault type of the target distribution network line based on the fault criterion subset includes: When the criterion features in the fault criterion subset are three-phase current and three-phase voltage, determining that the fault type of the target distribution network line is a short circuit fault; When the criterion features in the fault criterion subset are zero-sequence current and neutral point voltage, determining that the fault type of the target distribution network line is a single-phase grounding fault; When the criterion features in the fault criterion subset are contact temperature and vibration signal, determining that the fault type of the target distribution network line is a poor switch contact fault; When the criterion feature in the fault criterion subset is the opening and closing time of the switching device, it is determined that the fault type of the target distribution network line is a switch refusal fault.

5. The method according to claim 1, wherein The step of obtaining the target distribution network line operation status data set includes: Acquire electrical quantity data and mechanical characteristic data of the target distribution network line at a preset period; wherein the electrical quantity data includes three-phase current, voltage RMS, zero-sequence current, and neutral point voltage data; and the mechanical characteristic data includes contact temperature, vibration signal, and opening and closing time data of the switchgear; The electrical quantity data and the mechanical characteristic data are sequentially subjected to time synchronization processing, outlier elimination processing, and standardization processing to obtain the operating status data set.

6. The method according to claim 1, characterized in that Obtaining historical fault data sets includes: Obtain characteristic data that changes before and after the fault occurs from historical fault records; Determining the characteristic data as the historical fault data set; The characteristic data include three-phase current mutation, voltage sag rate, zero-sequence current increment, neutral point voltage offset and switch action time deviation.

7. The method according to claim 1, characterized in that After obtaining the operating status dataset and the historical fault dataset of the target distribution network line, the method further includes: Perform timestamp alignment processing on the operating status dataset and the historical fault dataset.

8. A distribution network line fault determination device, characterized in that: include: An acquisition module is used to obtain the operating status dataset and historical fault dataset of the target distribution network line; a calculation module, configured to calculate the dependency of the historical fault data set on the operating status data set based on a feature selection algorithm; A first determination module is configured to optimize an objective function according to the dependency and a preset criterion to determine a fault criterion subset; The second determination module is configured to determine the fault type of the target distribution network line based on the fault criterion subset.

9. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

Images