Fault positioning method, system and equipment based on low-voltage distribution network topology identification, and medium

Abstract

The invention relates to the technical field of power system automation control, in particular to a fault positioning method, system and device based on low-voltage distribution network topology recognition and a medium. The method comprises the following steps: firstly, extracting a current characteristic data set according to current data acquired from a low-voltage distribution area; dividing the current feature data set into a current feature data training set and a current feature data test set, and calling a random forest algorithm to construct a low-voltage distribution network topology identification model to obtain a topology identification result; and finally, according to the current characteristic data test set and the topology identification result, obtaining the relationship between the user side and the distribution transformer side, thereby realizing the rapid identification of the relationship between the user side and the distribution transformer side, positioning the low-voltage distribution network line fault, and improving the identification accuracy and the fault removal efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of power system automation control, and in particular to a fault location method, system, equipment and medium based on low-voltage distribution network topology identification. Background Art

[0002] As people's quality of life and consumption level are gradually improving, the demand for electricity from all walks of life and residents is constantly increasing, and new requirements are also put forward for the quality, safety and stability of electric energy. As a bridge between the transmission network and users, the distribution network's fault location and fault handling capabilities also need to reach a new level to ensure the power supply quality and reliability of the distribution network. The safe and stable operation of the distribution network is not only related to the vital interests of the majority of users, but also has great social and economic significance.

[0003] However, the current online recognition accuracy of household-transformer relationships in low-voltage distribution networks is low, which is not conducive to the rapid troubleshooting of faults and seriously affects work efficiency. Summary of the invention

[0004] Aiming at the problem that the online recognition accuracy of the relationship between users and transformers in a low-voltage distribution network is low in the existing fault location method, which is not conducive to the rapid elimination of faults and seriously affects the work efficiency, the present invention proposes a fault location method, system, equipment and medium based on the topology identification of a low-voltage distribution network; the method first extracts a current characteristic data set according to the current data obtained from the low-voltage distribution station area; then the current characteristic data set is divided into a current characteristic data training set and a current characteristic data test set, and a random forest algorithm is called to construct a low-voltage distribution network topology identification model to obtain a topology identification result; finally, according to the current characteristic data test set and the topology identification result, the relationship between the user side and the distribution transformer side is obtained, the rapid identification of the relationship between the user side and the distribution transformer side is realized, the low-voltage distribution network line fault is located, and the identification accuracy and the fault elimination efficiency are improved.

[0005] The specific implementation contents of the present invention are as follows:

[0006] A fault location method based on low voltage distribution network topology identification specifically comprises the following steps:

[0007] Step S1: extracting current data features based on current data acquired from the low-voltage distribution station area to obtain a current feature data set;

[0008] Step S2: dividing the current characteristic data set into a current characteristic data training set and a current characteristic data test set, calling the random forest algorithm according to the current characteristic data training set, constructing a low-voltage distribution network topology recognition model, and obtaining a topology recognition result;

[0009] Step S3: According to the current characteristic data test set and the topology recognition result, the relationship between the user side and the distribution transformer side is obtained, and the low-voltage distribution network line fault is located.

[0010] In order to better implement the present invention, further, the step S1 specifically includes the following steps:

[0011] Step S11: acquiring current data from the low voltage distribution station area and preprocessing; Step S12: segmenting the preprocessed current data according to the set time;

[0012] Step S13: extracting current data features from the segmented current data according to the set feature index;

[0013] Step S14: Generate a current characteristic data set according to the current data characteristics.

[0014] In order to better implement the present invention, further, the current data includes distribution transformer side current data and user side current data.

[0015] In order to better implement the present invention, further, the step S12 specifically includes the following steps:

[0016] Step S121: according to the set time, the current data of the distribution transformer side and the current data of the user side at the same time are taken as a group of current data objects;

[0017] Step S122: segment the current data object in an equidistant segmentation manner.

[0018] In order to better implement the present invention, further, the step S13 specifically includes the following steps:

[0019] Step S131: according to the set characteristic index, calling the current data object after the sliding time window sliding segmentation;

[0020] Step S132: Obtain the correlation coefficient of the sliding time window according to the data in the sliding time window of the user-side time series, the data in the sliding time window of the distribution transformer-side time series, the average value of the user-side time series in the sliding time window, the average value of the distribution transformer-side time series in the sliding time window, and the set sliding time window length;

[0021] Step S133: obtaining a correlation coefficient sequence according to the correlation coefficient of the sliding time window and the length of the segmented current data object sequence;

[0022] Step S134: according to the set interval, correlation coefficient sequence, and current data characteristics.

[0023] In order to better implement the present invention, further, the step S14 specifically includes the following steps:

[0024] Step S141: Calculate the coefficient of variation according to the segmented current sequence and the current sequence length;

[0025] Step S142: Calculate bucket entropy according to the segmented current sequence, the set interval bucket, the length of the segmented current sequence, and the set number of buckets;

[0026] Step S143: According to the current data characteristics, combined with the coefficient of variation, bucket entropy, and the set threshold, the segmented current time series data with large current fluctuations are screened, the current feature vector is constructed, and the current feature data set is generated.

[0027] In order to better implement the present invention, further, the step S2 specifically includes the following steps:

[0028] Step S21: dividing the current characteristic data set into a current characteristic data training set and a current characteristic data test set;

[0029] Step S22: calling the random forest algorithm to randomly extract a certain number of data with replacement from the current feature training data set as samples, to obtain multiple current feature training sample subsets;

[0030] Step S23: randomly selecting n features from multiple training sample subsets as attribute sets corresponding to decision tree classification, and constructing a decision tree;

[0031] Step S24: randomly selecting the best variable and split point from the n characteristic variables to obtain the first node;

[0032] Step S25: dividing the first node into a second node and a third node according to the selected optimal variables and split points;

[0033] Step S26: Repeat steps S23 to S25 to construct a random forest;

[0034] Step S27: constructing a low voltage distribution network topology recognition model according to the constructed random forest;

[0035] Step S28: inputting the current characteristic vector into the low voltage distribution network topology identification model to obtain a topology identification result.

[0036] Based on the above-mentioned fault location method based on low-voltage distribution network topology identification, in order to better realize the present invention, further, a fault location system based on low-voltage distribution network topology identification is proposed, which is used to execute the above-mentioned fault location method based on low-voltage distribution network topology identification; comprising a collection unit, an identification unit, and a positioning unit;

[0037] The acquisition unit is used to acquire current data from the low-voltage distribution station area, extract current data features, and obtain a current feature data set;

[0038] The identification unit is used to divide the current characteristic data set into a current characteristic data training set and a current characteristic data test set, call the random forest algorithm according to the current characteristic data training set, build a low-voltage distribution network topology identification model, and obtain a topology identification result;

[0039] The positioning unit is used to obtain the relationship between the user side and the distribution transformer side according to the current characteristic data test set and the topology recognition result; and locate the low-voltage distribution network line fault according to the relationship between the user side and the distribution transformer side.

[0040] Based on the above-proposed fault location method based on low-voltage distribution network topology identification, in order to better realize the present invention, further, an electronic device is proposed, including a memory and a processor; a computer program is stored on the memory; when the computer program is executed on the processor, the above-proposed fault location method based on low-voltage distribution network topology identification is implemented.

[0041] Based on the above-proposed fault location method based on low-voltage distribution network topology identification, in order to better realize the present invention, further, a computer-readable storage medium is proposed, on which computer instructions are stored; when the computer instructions are executed on the above-mentioned electronic device, the above-mentioned fault location method based on low-voltage distribution network topology identification is implemented.

[0042] The present invention has the following beneficial effects:

[0043] (1) The present invention extracts the current data features after segmentation, thereby reducing the amount of calculation and improving the efficiency of recognition. The current features are screened by set characteristic indicators to form a final current data feature data set, laying the foundation for the subsequent establishment of topological relationships.

[0044] (2) The present invention uses the user-side current data and the distribution transformer-side current data as samples, and uses the distribution transformer-side current data and the user-side current data at the same time as a group of current data objects to identify the relationship between the user and the distribution transformer, and to quickly and accurately identify the topological relationship, thereby further improving the fault location accuracy and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A schematic flow chart of a fault location method based on low-voltage distribution network topology identification provided by the present invention.

[0046] Figure 2 A schematic diagram of the random forest algorithm flow chart provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. It should be understood that the described embodiments are only part of the embodiments of the present invention, not all of the embodiments, and therefore should not be regarded as limiting the scope of protection. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technical personnel in this field without making creative work are within the scope of protection of the present invention.

[0048] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "disposed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0049] Embodiment 1:

[0050] This embodiment proposes a fault location method based on low-voltage distribution network topology identification, which specifically includes the following steps:

[0051] Step S1: extracting current data features based on current data acquired from the low-voltage distribution station area to obtain a current feature data set;

[0052] Furthermore, the step S1 specifically includes the following steps:

[0053] Step S11: acquiring current data from the low-voltage distribution station area and preprocessing the current data, wherein the current data includes current data on the distribution transformer side and current data on the user side.

[0054] Step S12: segment the pre-processed current data according to the set time.

[0055] Furthermore, the step S12 specifically includes the following steps:

[0056] Step S121: according to the set time, the current data of the distribution transformer side and the current data of the user side at the same time are taken as a group of current data objects;

[0057] Step S122: segment the current data object in an equidistant segmentation manner.

[0058] Step S13: extracting current data features from the segmented current data according to the set feature index.

[0059] Furthermore, the step S13 specifically includes the following steps:

[0060] Step S131: according to the set characteristic index, calling the current data object after the sliding time window sliding segmentation;

[0061] Step S132: Obtain the correlation coefficient of the sliding time window according to the data in the sliding time window of the user-side time series, the data in the sliding time window of the distribution transformer-side time series, the average value of the user-side time series in the sliding time window, the average value of the distribution transformer-side time series in the sliding time window, and the set sliding time window length;

[0062] Step S133: obtaining a correlation coefficient sequence according to the correlation coefficient of the sliding time window and the length of the segmented current data object sequence;

[0063] Step S134: according to the set interval, correlation coefficient sequence, and current data characteristics.

[0064] Step S14: Generate a current characteristic data set according to the current data characteristics.

[0065] Furthermore, the step S14 specifically includes the following steps:

[0066] Step S141: Calculate the coefficient of variation according to the segmented current sequence and the current sequence length;

[0067] Step S142: Calculate bucket entropy according to the segmented current sequence, the set interval bucket, the length of the segmented current sequence, and the set number of buckets;

[0068] Step S143: According to the current data characteristics, combined with the coefficient of variation, bucket entropy, and the set threshold, the segmented current time series data with large current fluctuations are screened, the current feature vector is constructed, and the current feature data set is generated.

[0069] Step S2: Divide the current characteristic data set into a current characteristic data training set and a current characteristic data test set, call the random forest algorithm according to the current characteristic data training set, build a low-voltage distribution network topology recognition model, and obtain a topology recognition result.

[0070] Furthermore, the step S2 specifically includes the following steps:

[0071] Step S21: dividing the current characteristic data set into a current characteristic data training set and a current characteristic data test set;

[0072] Step S22: calling the random forest algorithm to randomly extract a certain number of data with replacement from the current feature training data set as samples, to obtain multiple current feature training sample subsets;

[0073] Step S23: randomly selecting n features from multiple training sample subsets as attribute sets corresponding to decision tree classification, and constructing a decision tree;

[0074] Step S24: randomly selecting the best variable and split point from the n characteristic variables to obtain the first node;

[0075] Step S25: dividing the first node into a second node and a third node according to the selected optimal variables and split points;

[0076] Step S26: Repeat steps S23 to S25 to construct a random forest;

[0077] Step S27: constructing a low voltage distribution network topology recognition model according to the constructed random forest;

[0078] Step S28: inputting the current characteristic vector into the low voltage distribution network topology identification model to obtain a topology identification result.

[0079] Step S3: According to the current characteristic data test set and the topology recognition result, the relationship between the user side and the distribution transformer side is obtained, and the low-voltage distribution network line fault is located.

[0080] Working principle: This embodiment first extracts a current characteristic data set based on the current data obtained from the low-voltage distribution station area; then divides the current characteristic data set into a current characteristic data training set and a current characteristic data test set, calls the random forest algorithm to build a low-voltage distribution network topology recognition model, and obtains a topology recognition result; finally, according to the current characteristic data test set and the topology recognition result, the relationship between the user side and the distribution transformer side is obtained, and the relationship between the user side and the distribution transformer side is quickly recognized. The current data features are extracted after segmentation, which reduces the amount of calculation and improves the recognition efficiency. The current features are screened by the set characteristic indicators to form the final current data characteristic data set, which lays the foundation for the subsequent establishment of the topological relationship; and by taking the user side current data and the distribution transformer side current data as samples, and taking the distribution transformer side current data and the user side current data at the same time as a group of current data objects, the relationship between the user and the distribution transformer is recognized, and the topological relationship is quickly and accurately recognized, which further improves the fault location accuracy and efficiency.

[0081] Embodiment 2:

[0082] This embodiment is based on the above embodiment 1. Figure 1 , Figure 2 As shown, a detailed description is given by taking the collection of user meter current data and distribution meter current data as an example.

[0083] Step S1: according to the user meter current data and distribution meter current data obtained from the low-voltage distribution station area, the current data features are extracted to obtain a current feature data set; this embodiment aligns all current sequences according to the start time so that the time and length of all current sequences are consistent, and filters them to remove the influence of noise, segments the preprocessed data, sets a sliding time window when calculating the correlation coefficient, extracts the segmented current features, filters the data, and forms a feature vector set, which specifically includes the following steps.

[0084] Step S11: obtaining user meter current data and distribution meter current data from the low-voltage distribution station area and pre-processing;

[0085] Step S12: according to the set time, the current data of the distribution meter and the current data of the user meter at the same time are taken as a group of current data objects; and the current data objects are segmented in an equidistant manner.

[0086] Step S13: according to the set characteristic index, calling the current data object after the sliding time window sliding segmentation;

[0087] According to the data in the sliding time window of the user-side time series, the data in the sliding time window of the distribution transformer-side time series, the average value of the user-side time series in the sliding time window, the average value of the distribution transformer-side time series in the sliding time window, and the set sliding time window length, the correlation coefficient ρ of the sliding time window is obtained;

[0088]

[0089] Among them, X m,i is the i-th data in the m-th sliding time window of the user's meter time series; ρ m is the correlation coefficient of the mth sliding time window, Y m,i is the ith data in the mth sliding time window of the distribution meter time series; μ Xm is the average value of the user meter time series in the mth sliding time window; μ Ym is the average value of the user's electric meter time series in the mth sliding time window; n is the set sliding time window length;

[0090] According to the correlation coefficient of the sliding time window and the length of the segmented current data object sequence, a correlation coefficient sequence is obtained;

[0091] S=(ρ1,ρ2,…,ρ e )

[0092] Wherein, S is the correlation coefficient sequence obtained by calculating the local correlation coefficient.

[0093] Step S14: Calculate the coefficient of variation β according to the segmented current sequence and the current sequence length;

[0094]

[0095] Where b is the length of the current sequence, X is the segmented current sequence, β is the coefficient of variation, μ X Average value of the segmented current series.

[0096] Calculate the bucket entropy B according to the segmented current sequence, the set interval bucket, the length of the segmented current sequence, and the set number of buckets E (X);

[0097]

[0098] Where X is the segment current sequence, p k is the probability that the value of the segmented current sequence X falls into the kth bucket, maxK is the number of buckets, and l(X) is the length of the segmented current sequence X.

[0099] According to the characteristics of current data, combined with the coefficient of variation, bucket entropy, and set threshold, the segmented current time series data with large current fluctuations are screened, the current feature vector is constructed, and the current feature data set is generated.

[0100] Step S2: Divide the current characteristic data set into a current characteristic data training set and a current characteristic data test set, call the random forest algorithm according to the current characteristic data training set, build a low-voltage distribution network topology recognition model, and obtain a topology recognition result.

[0101] During training, the number of decision trees is an important parameter and has a great influence on the classification accuracy of the model. In this embodiment, the number of decision trees is gradually changed to construct the final random forest. Figure 2 As shown, step S2 specifically includes the following steps:

[0102] Step S21: dividing the current characteristic data set into a current characteristic data training set and a current characteristic data test set;

[0103] Step S22: calling the random forest algorithm to randomly extract a certain number of data with replacement from the current feature training data set as samples, to obtain multiple current feature training sample subsets;

[0104] Step S23: randomly selecting n features from multiple training sample subsets as attribute sets corresponding to decision tree classification, and constructing a decision tree;

[0105] Step S24: randomly selecting the best variable and split point from the n characteristic variables to obtain the first node;

[0106] Step S25: dividing the first node into a second node and a third node according to the selected optimal variables and split points;

[0107] Step S26: Repeat steps S23 to S25 to construct a random forest;

[0108] Step S27: constructing a low voltage distribution network topology recognition model according to the constructed random forest;

[0109] Step S28: inputting the current characteristic vector into the low voltage distribution network topology identification model to obtain a topology identification result.

[0110] The low-voltage distribution network topology recognition model constructed in this embodiment is capable of identifying high-dimensional features and directly generating topology results by inputting a feature vector set.

[0111] Step S3: According to the current characteristic data test set and the topology recognition result, the relationship between the user side and the distribution transformer side is obtained, and the low-voltage distribution network line fault is located.

[0112] By simulating this embodiment, the relationship between the user's electricity meter and the distribution meter can be quickly and accurately identified, the identification time is shortened, and the fault is quickly located.

[0113] The other parts of this embodiment are the same as those of the above-mentioned embodiment 1, and thus will not be described in detail.

[0114] Embodiment 3:

[0115] Based on any one of the above-mentioned embodiments 1-2, this embodiment proposes a fault location system based on low-voltage distribution network topology identification, which is used to execute the above-mentioned fault location method based on low-voltage distribution network topology identification; it includes a collection unit, an identification unit, and a positioning unit;

[0116] The acquisition unit is used to acquire current data from the low-voltage distribution station area, extract current data features, and obtain a current feature data set;

[0117] The identification unit is used to divide the current characteristic data set into a current characteristic data training set and a current characteristic data test set, call the random forest algorithm according to the current characteristic data training set, build a low-voltage distribution network topology identification model, and obtain a topology identification result;

[0118] The positioning unit is used to obtain the relationship between the user side and the distribution transformer side according to the current characteristic data test set and the topology recognition result; and locate the low-voltage distribution network line fault according to the relationship between the user side and the distribution transformer side.

[0119] This embodiment also proposes an electronic device, including a memory and a processor; a computer program is stored on the memory; when the computer program is executed on the processor, the above-mentioned fault location method based on low-voltage distribution network topology identification is implemented.

[0120] This embodiment further proposes a computer-readable storage medium, on which computer instructions are stored; when the computer instructions are executed on the above-mentioned electronic device, the above-mentioned fault location method based on low-voltage distribution network topology identification is implemented.

[0121] The other parts of this embodiment are the same as any one of the above-mentioned embodiments 1-2, so they will not be repeated here.

[0122] The processor involved in the embodiments of the present application may be a chip. For example, it may be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on chip (SoC), a central processor unit (CPU), a network processor (NP), a digital signal processor (DSP), a microcontroller unit (MCU), a programmable logic device (PLD), or other integrated chips.

[0123] The memory involved in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0124] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0125] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0126] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0127] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0128] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one device or distributed on multiple devices. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0129] In addition, each functional module in each embodiment of the present application may be integrated into one device, or each module may exist physically separately, or two or more modules may be integrated into one device.

[0130] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loading and executing computer program instructions on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or may contain one or more servers, data centers and other data storage devices that can be integrated with a medium. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).

[0131] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A fault location method based on low voltage distribution network topology identification, characterized in that: The specific steps include: Step S1: extracting current data features based on current data acquired from the low-voltage distribution station area to obtain a current feature data set; Step S2: dividing the current characteristic data set into a current characteristic data training set and a current characteristic data test set, calling the random forest algorithm according to the current characteristic data training set, constructing a low-voltage distribution network topology recognition model, and obtaining a topology recognition result; Step S3: According to the current characteristic data test set and the topology recognition result, the relationship between the user side and the distribution transformer side is obtained, and the low-voltage distribution network line fault is located.

2. A fault location method based on low voltage distribution network topology identification according to claim 1, characterized in that: The step S1 specifically includes the following steps: Step S11: acquiring current data from the low voltage distribution station area and preprocessing; Step S12: segmenting the preprocessed current data according to the set time; Step S13: extracting current data features from the segmented current data according to the set feature index; Step S14: Generate a current characteristic data set according to the current data characteristics.

3. A fault location method based on low voltage distribution network topology identification according to claim 2, characterized in that: The current data includes distribution transformer side current data and user side current data.

4. A fault location method based on low voltage distribution network topology identification according to claim 3, characterized in that: The step S12 specifically includes the following steps: Step S121: according to the set time, the current data of the distribution transformer side and the current data of the user side at the same time are taken as a group of current data objects; Step S122: segment the current data object in an equidistant segmentation manner.

5. A fault location method based on low voltage distribution network topology identification according to claim 4, characterized in that: The step S13 specifically includes the following steps: Step S131: according to the set characteristic index, calling the current data object after the sliding time window sliding segmentation; Step S132: Obtain the correlation coefficient of the sliding time window according to the data in the sliding time window of the user-side time series, the data in the sliding time window of the distribution transformer-side time series, the average value of the user-side time series in the sliding time window, the average value of the distribution transformer-side time series in the sliding time window, and the set sliding time window length; Step S133: obtaining a correlation coefficient sequence according to the correlation coefficient of the sliding time window and the length of the segmented current data object sequence; Step S134: according to the set interval, correlation coefficient sequence, and current data characteristics.

6. A fault location method based on low voltage distribution network topology identification according to claim 5, characterized in that: The step S14 specifically includes the following steps: Step S141: Calculate the coefficient of variation according to the segmented current sequence and the current sequence length; Step S142: Calculate bucket entropy according to the segmented current sequence, the set interval bucket, the length of the segmented current sequence, and the set number of buckets; Step S143: According to the current data characteristics, combined with the coefficient of variation, bucket entropy, and the set threshold, the segmented current time series data with large current fluctuations are screened, the current feature vector is constructed, and the current feature data set is generated.

7. A fault location method based on low voltage distribution network topology identification according to claim 6, characterized in that: The step S2 specifically includes the following steps: Step S21: dividing the current characteristic data set into a current characteristic data training set and a current characteristic data test set; Step S22: calling the random forest algorithm to randomly extract a certain number of data with replacement from the current feature training data set as samples, to obtain multiple current feature training sample subsets; Step S23: randomly selecting n features from multiple training sample subsets as attribute sets corresponding to decision tree classification, and constructing a decision tree; Step S24: randomly selecting the best variable and split point from the n characteristic variables to obtain the first node; Step S25: dividing the first node into a second node and a third node according to the selected optimal variables and split points; Step S26: Repeat steps S23 to S25 to construct a random forest; Step S27: constructing a low voltage distribution network topology recognition model according to the constructed random forest; Step S28: inputting the current characteristic vector into the low voltage distribution network topology identification model to obtain a topology identification result.

8. A fault location system based on low-voltage distribution network topology identification, used to execute the fault location method based on low-voltage distribution network topology identification as claimed in claim 1; characterized in that It includes a collection unit, an identification unit, and a positioning unit; The acquisition unit is used to acquire current data from the low-voltage distribution station area, extract current data features, and obtain a current feature data set; The identification unit is used to divide the current characteristic data set into a current characteristic data training set and a current characteristic data test set, call the random forest algorithm according to the current characteristic data training set, build a low-voltage distribution network topology identification model, and obtain a topology identification result; The positioning unit is used to obtain the relationship between the user side and the distribution transformer side according to the current characteristic data test set and the topology recognition result; and locate the low-voltage distribution network line fault according to the relationship between the user side and the distribution transformer side.

9. An electronic device, characterized in that: It comprises a memory and a processor; a computer program is stored in the memory; when the computer program is executed on the processor, the fault location method based on low-voltage distribution network topology identification as described in any one of claims 1-7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions; when the computer instructions are executed on the electronic device as described in claim 9, the fault location method based on low-voltage distribution network topology identification as described in any one of claims 1-7 is implemented.

Images