FTU-based fault location method for distribution network

Abstract

The present invention relates to a distribution network fault location method based on FTU, comprising the following steps: collecting electrical signals of the distribution network through FTU to obtain electrical collection signals, and digitally processing the electrical collection signals to obtain electrical parameters; mapping the electrical parameters to a preset electrical parameter-time coordinate system, and plotting a curve of the electrical parameters on the electrical parameter-time coordinate system to obtain a visualization curve; monitoring whether the visualization curve on the electrical parameter-time coordinate system has an abnormal phenomenon, and if the visualization curve has an abnormal phenomenon, marking an abnormal area corresponding to the abnormal phenomenon to obtain a visualization marking curve; obtaining the time of an abnormal point based on the abnormal phenomenon on the visualization marking curve, and obtaining the distribution network fault location based on the time of the abnormal point and the propagation speed of the electrical collection signal; and solving the technical problem that it is difficult to accurately and quickly determine the fault location under a complex network structure.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network, and in particular to a distribution network fault locating method, device, equipment and storage medium based on FTU. Background Art

[0002] In the traditional distribution network fault location process, manual inspections and manual data recording are usually used to detect and locate faults. This method is not only time-consuming and labor-intensive, but also inefficient, especially in complex network structures. It is difficult to accurately and quickly determine the fault location. With the development of smart grids, the application of feeder terminal units (FTUs) has become increasingly popular. It can collect electrical signals in real time in the distribution network and transmit them remotely, providing a basis for the automated management of the distribution network.

[0003] However, the data collected by existing FTUs often require professional technicians to analyze and interpret, and it is difficult for non-professionals to directly understand the meaning of these data, which limits the efficiency of fault location. In addition, due to the complexity of the distribution network, it is difficult to accurately determine the location of the fault by relying solely on a single electrical parameter (such as voltage or current), especially when multiple faults occur at the same time, and it is easy to make misjudgments based on experience alone. Summary of the invention

[0004] The main purpose of the present invention is to provide a distribution network fault location method, device, equipment and storage medium based on FTU, which solves the technical problem that it is difficult to accurately and quickly determine the fault location under a complex network structure.

[0005] To achieve the above object, the present invention provides a distribution network fault location method based on FTU, comprising the following steps:

[0006] The FTU collects electrical signals from the distribution network to obtain electrical collection signals, and digitally processes the electrical collection signals to obtain electrical parameters; wherein the electrical parameters are voltage parameters, current parameters, or power parameters;

[0007] The electrical parameter is mapped to a preset electrical parameter-time coordinate system, and a curve is drawn for the electrical parameter on the electrical parameter-time coordinate system to obtain a visualization curve; wherein the electrical parameter-time coordinate system includes an abscissa and a ordinate, the ordinate of the visualization curve represents the value of the electrical parameter, and the abscissa represents the time from the electrical parameter to FTU;

[0008] Monitor whether the visualized curve on the electrical parameter-time coordinate system has any abnormal phenomenon. If the visualized curve has any abnormal phenomenon, mark the abnormal area corresponding to the abnormal phenomenon to obtain a visualized marked curve; wherein the abnormal phenomenon includes a mutation point, a jump point, an oscillation point, a drift point and missing data;

[0009] The time of the abnormal point is obtained based on the abnormal phenomenon on the visual marking curve, and the distribution network fault location is obtained based on the time of the abnormal point and the propagation speed of the electrical acquisition signal.

[0010] Furthermore, the electrical signal of the distribution network is collected by the FTU to obtain the electrical collection signal, and the electrical collection signal is digitally processed to obtain electrical parameters, including:

[0011] Collecting electrical signals from the distribution network through the FTU to obtain preliminary collected signals;

[0012] Performing low-pass filtering on the preliminary collected signal to obtain a low-pass filtered signal;

[0013] Performing bandpass filtering on the low-pass filtered signal to obtain a bandpass filtered signal;

[0014] Amplifying the bandpass filtered signal to obtain an amplified signal; and using the amplified signal as an electrical acquisition signal;

[0015] The amplified signal is digitally converted by a preset analog-to-digital converter to obtain electrical parameters.

[0016] Further, mapping the electrical parameters to a preset electrical parameter-time coordinate system, and plotting the electrical parameters on the electrical parameter-time coordinate system to obtain a visualized curve, including:

[0017] Sorting the electrical parameters in time series to obtain time series electrical parameters;

[0018] Mapping the timing electrical parameters to a preset electrical parameter-time coordinate system;

[0019] Using a linear interpolation technique, plotting a curve of the electrical parameter on the electrical parameter-time coordinate system to obtain an electrical curve;

[0020] The electrical curve is fitted to obtain a visualization curve.

[0021] Further, monitoring whether the visualization curve on the electrical parameter-time coordinate system has abnormal phenomena, and if the visualization curve has abnormal phenomena, marking the abnormal area corresponding to the abnormal phenomena to obtain a visualization marked curve, including:

[0022] Performing abnormal phenomenon monitoring on the visualized curve on the electrical parameter-time coordinate system to obtain abnormal phenomenon monitoring results;

[0023] If the abnormal phenomenon monitoring result is that the visualization curve has an abnormal phenomenon, the area corresponding to the abnormal phenomenon is isolated to obtain an isolated area; wherein the abnormal phenomenon includes a mutation point, a jump point, an oscillation point, a drift point and missing data;

[0024] The isolation area is specially marked to obtain a dotted line marked area; wherein the special mark includes a circle for the isolation area and arrow marks at both ends of the isolation area;

[0025] The dotted line marked area is translated onto the visualization curve to obtain a visualization marked curve.

[0026] Furthermore, abnormal phenomenon monitoring is performed on the visualized curve on the electrical parameter-time coordinate system to obtain abnormal phenomenon monitoring results, including:

[0027] Input the visualized curve on the electrical parameter-time coordinate system into the trained monitoring algorithm; wherein the monitoring algorithm includes the MDFFM multi-dimensional feature fusion module, the SPP_SF module, the dynamic snake convolution module and the multi-task supervision module, and the SPP_SF module includes the SPP module and the efficient pooling layer SoftPool;

[0028] Perform feature extraction on the visualization curve through the MDFFM multi-dimensional feature fusion module to obtain extracted features;

[0029] Capturing subtle features of the extracted features through a dynamic snake-shaped convolution module to obtain subtle captured features, and fusing the subtle captured features to obtain multi-scale fused features;

[0030] Performing feature enhancement on the multi-scale fusion feature through the SPP_SF module to obtain enhanced features;

[0031] The enhanced features are monitored for abnormal phenomena through a multi-task supervision module to obtain abnormal phenomenon monitoring results.

[0032] Furthermore, the isolation area is specially marked to obtain a dotted line marked area, including:

[0033] Identify the starting point and the end point of the isolation area, and determine the corresponding coordinates of the starting point and the end point; wherein the coordinates include the starting point coordinates and the end point coordinates;

[0034] Determine the center point based on the starting point coordinates and the end point coordinates, and use the distance from the center point to the starting point or the end point as the radius;

[0035] Obtaining a marked circle based on the center point and the radius;

[0036] The isolation area is specially marked based on the marking circle to obtain a dotted line marked area; wherein the dotted line marked area is the isolation area covered by the marking circle.

[0037] Further, the time of the abnormal point is obtained based on the abnormal phenomenon on the visual marking curve, and the distribution network fault location is obtained based on the time of the abnormal point and the propagation speed of the electrical acquisition signal, including:

[0038] Marking the abnormal phenomena on the visual marking curve respectively to obtain the time of the corresponding abnormal point;

[0039] Taking the starting point and the end point as abnormal points, and taking the starting point coordinates and the end point coordinates as abnormal point coordinates;

[0040] A tangent line is drawn through the abnormal point to obtain the slope of the abnormal point.

[0041] Using a differential equation, constructing an outlier curve based on the coordinates of the outlier and the slope of the outlier;

[0042] An abnormal trend prediction is performed on the abnormal point curve to obtain an abnormal trend prediction result. If the abnormal trend prediction is not within the preset prediction range, the distribution network fault location is obtained according to the time of the abnormal point and the propagation speed of the electrical acquisition signal.

[0043] The present invention also provides a distribution network fault location device based on FTU, comprising:

[0044] A collection module, used for collecting electrical signals from the distribution network through the FTU to obtain electrical collection signals, and digitally processing the electrical collection signals to obtain electrical parameters; wherein the electrical parameters are voltage parameters, current parameters or power parameters;

[0045] A drawing module, used for mapping the electrical parameters to a preset electrical parameter-time coordinate system, and drawing a curve of the electrical parameters on the electrical parameter-time coordinate system to obtain a visualization curve; wherein the electrical parameter-time coordinate system includes an abscissa and a ordinate, the ordinate of the visualization curve represents the value of the electrical parameter, and the abscissa represents the time from the electrical parameter to the FTU;

[0046] A monitoring module is used to monitor whether there is any abnormal phenomenon in the visualization curve on the electrical parameter-time coordinate system. If there is any abnormal phenomenon in the visualization curve, the abnormal area corresponding to the abnormal phenomenon is marked to obtain a visualization marked curve; wherein the abnormal phenomenon includes a mutation point, a jump point, an oscillation point, a drift point and missing data;

[0047] The positioning module is used to obtain the time of the abnormal point based on the abnormal phenomenon on the visual marking curve, and to obtain the distribution network fault location based on the time of the abnormal point and the propagation speed of the electrical acquisition signal.

[0048] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0049] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned methods are implemented.

[0050] The FTU-based distribution network fault location method provided by the present invention comprises the following steps: collecting electrical signals of the distribution network through the FTU to obtain electrical collection signals, and digitally processing the electrical collection signals to obtain electrical parameters; mapping the electrical parameters to a preset electrical parameter-time coordinate system, and drawing a curve of the electrical parameters on the electrical parameter-time coordinate system to obtain a visualization curve; monitoring whether the visualization curve on the electrical parameter-time coordinate system has abnormal phenomena, and if the visualization curve has abnormal phenomena, marking the abnormal area corresponding to the abnormal phenomena to obtain a visualization marking curve; obtaining the time of the abnormal point based on the abnormal phenomenon on the visualization marking curve, and obtaining the distribution network fault location based on the time of the abnormal point and the propagation speed of the electrical collection signal; through the above technical solution, the technical problem that it is difficult to accurately and quickly determine the fault location under a complex network structure is solved, and timely and accurate positioning and troubleshooting are achieved, which helps to maintain stable operation of the power grid and improve the power supply quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a schematic diagram of the steps of a distribution network fault location method based on FTU in one embodiment of the present invention;

[0052] Figure 2 is a structural block diagram of a distribution network fault location device based on FTU in one embodiment of the present invention;

[0053] Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0054] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0056] like Figure 1 As shown, Figure 1 It is a schematic diagram of the steps of a distribution network fault location method based on FTU in one embodiment of the present invention;

[0057] In one embodiment of the present invention, a method for locating a distribution network fault based on an FTU is provided, comprising the following steps:

[0058] Step S1, collect electrical signals from the distribution network through FTU to obtain electrical collection signals, and digitally process the electrical collection signals to obtain electrical parameters; wherein the electrical parameters are voltage parameters, current parameters, or power parameters.

[0059] Specifically, in this technical solution, it is first necessary to collect electrical signals from the distribution network through FTU (feeder terminal unit). The specific steps are as follows: Electrical signal collection: FTU: The feeder terminal unit is an intelligent device installed on the distribution line, which is used to monitor the status of the line in real time. Distribution network: refers to the network in the power system that is responsible for distributing electricity from the substation to the end user. Electrical signal collection: FTU will continuously monitor the electrical signals in the distribution network, which include but are not limited to voltage, current and power.

[0060] Electrically collected signals: Electrically collected signals refer to the raw electrical signal data collected by the FTU from the distribution network, which may be in the form of analog signals.

[0061] Digital processing: In order to facilitate subsequent data processing and analysis, these analog signals need to be converted into digital signals. This process usually involves analog-to-digital conversion (A / D conversion), which is the process of converting analog signals into digital signals.

[0062] Electrical parameters: After digital processing, the FTU converts the acquired electrical signals into specific numerical parameters, which can be voltage parameters, current parameters or power parameters, etc.

[0063] In summary, this step mainly refers to using FTU to collect electrical signals from the distribution network and converting these signals into digital electrical parameters through analog-to-digital conversion and other means for further analysis and processing. The advantage of this approach is that the electrical signals can be more easily read and processed by the computer system, thereby providing the necessary data support for subsequent fault detection and location.

[0064] Step S2, mapping the electrical parameters to a preset electrical parameter-time coordinate system, and plotting the electrical parameters on the electrical parameter-time coordinate system to obtain a visualization curve; wherein the electrical parameter-time coordinate system includes a horizontal coordinate and a vertical coordinate, the vertical coordinate of the visualization curve represents the value of the electrical parameter, and the horizontal coordinate represents the time from the electrical parameter to FTU.

[0065] Specifically, the following is an explanation of the technical solution for this step. Electrical parameters are mapped to a preset electrical parameter-time coordinate system: In this step, the electrical parameters previously collected and digitized by FTU must first be mapped to a preset electrical parameter-time coordinate system. This coordinate system has two axes: the horizontal axis and the vertical axis. Electrical parameter-time coordinate system: This is a two-dimensional coordinate system, in which the vertical axis represents the value of the electrical parameter, and the horizontal axis represents the time from the electrical parameter to the FTU, that is, the time point of data collection.

[0066] Curve drawing and visualization: Curve drawing: Next, we draw a curve on the coordinate system according to the corresponding collection time points of these electrical parameters. The purpose of this is to intuitively show the changing trend of electrical parameters over time. Visualization curve: Through curve drawing, we can get a visualization curve that can clearly show the changes of electrical parameters over time. This curve helps engineers and technicians quickly understand the operating status of the electrical system and can more easily identify any abnormal behavior. In summary, the main purpose of this step is to visualize the collected electrical parameters using the electrical parameter-time coordinate system. By drawing the visualization curve, we can clearly see the changes of electrical parameters over time, which is very helpful for monitoring the health of the distribution network and detecting problems early. Such a visualization method makes data analysis more intuitive and efficient.

[0067] Step S3, monitor whether there is any abnormal phenomenon in the visualization curve on the electrical parameter-time coordinate system. If there is any abnormal phenomenon in the visualization curve, mark the abnormal area corresponding to the abnormal phenomenon to obtain a visualization marked curve; wherein the abnormal phenomenon includes mutation points, jump points, oscillation points, drift points and missing data.

[0068] Specifically, the following is an explanation of the technical solution for this step, monitoring the visualized curve on the electrical parameter-time coordinate system: In this step, it is necessary to monitor the visualized curve that has been drawn on the electrical parameter-time coordinate system. The ordinate of this coordinate system represents the value of the electrical parameter, and the abscissa represents the time from the electrical parameter to the FTU, that is, the time point of data collection. The goal of monitoring is to check whether there are any abnormalities in the visualized curve. Abnormal phenomena may refer to electrical parameter values ​​that are beyond the normal range, sudden changes, or trends that do not meet expectations.

[0069] Mark abnormal areas:

[0070] If abnormal phenomena are found in the visualization curve during the monitoring process, the next step is to mark the areas corresponding to these abnormal phenomena. This means that on the electrical parameter-time coordinate system, we will specially mark those data points or time periods that show abnormal behavior so that we can quickly locate the problem in subsequent analysis. Get a visual marking curve: After marking the abnormal phenomena, we will get a visual marking curve with special markings. These markings can help technicians quickly identify which parts need further investigation and processing. The visual marking curve not only shows the changes of electrical parameters over time, but also highlights the key points or time periods that need attention, which is very useful for fault diagnosis and maintenance work. In summary, the main purpose of this step is to detect any possible abnormal phenomena by monitoring the visualization curve on the electrical parameter-time coordinate system, and mark these abnormal areas, and finally get a visual marking curve. Such marking helps to quickly locate the problem, so that timely measures can be taken to solve the problem and ensure the stable operation of the power system. In addition, the abnormal phenomena include mutation points, jump points, oscillation points, drift points and missing data.

[0071] Step S4, obtaining the time of the abnormal point based on the abnormal phenomenon on the visual marking curve, and obtaining the distribution network fault location based on the time of the abnormal point and the propagation speed of the electrical acquisition signal.

[0072] Specifically, the following is an explanation of the technical solution for this step, based on the abnormal phenomenon on the visual marking curve, the time of the abnormal point is obtained: In this step, the first thing to pay attention to is the visual marking curve that has been previously monitored and marked with abnormal phenomena on the electrical parameter-time coordinate system. All abnormal phenomena marked on this curve will be analyzed to determine the specific time point when each abnormal phenomenon occurs. These time points are called the time of the abnormal point. The distribution network fault location is obtained based on the time of the abnormal point and the propagation speed of the electrical acquisition signal: Next, the approximate location of the fault can be calculated using the time of the abnormal point and the known propagation speed of the electrical acquisition signal. The propagation speed of the electrical acquisition signal refers to the speed at which the signal propagates from one point to another in the distribution network, which can usually be estimated by physical properties such as wire material, length and other factors. Since the time of occurrence of the abnormal point can be regarded as the time point when the fault occurs, combined with the propagation speed of the signal, we can reversely infer the distance between the fault point and a reference point. In this way, the location of the fault can be roughly determined. In summary, the main goal of this step is: First, based on the mark on the visual marking curve, determine the specific time point when each abnormal phenomenon occurs (i.e., the time of the abnormal point). Secondly, the approximate location of the fault is calculated by using the time of the abnormal point and the known propagation speed of the electrical acquisition signal, thereby locating the distribution network fault. Such a technical solution can help power system operation and maintenance personnel respond to fault events quickly, improve the accuracy and efficiency of fault location, and thus reduce power outage time and maintenance costs.

[0073] In a specific embodiment, the electrical signal of the distribution network is collected by the FTU to obtain the electrical collection signal, and the electrical collection signal is digitally processed to obtain electrical parameters, including:

[0074] Collecting electrical signals from the distribution network through the FTU to obtain preliminary collected signals;

[0075] Performing low-pass filtering on the preliminary collected signal to obtain a low-pass filtered signal;

[0076] Performing bandpass filtering on the low-pass filtered signal to obtain a bandpass filtered signal;

[0077] Amplifying the bandpass filtered signal to obtain an amplified signal; and using the amplified signal as an electrical acquisition signal;

[0078] The amplified signal is digitally converted by a preset analog-to-digital converter to obtain electrical parameters.

[0079] Specifically, the following is an explanation of the technical solution for this step, wherein the FTU collects electrical signals from the distribution network to obtain a preliminary collected signal: In this step, the FTU (feeder terminal unit) collects electrical signals from the distribution network to obtain preliminary electrical signals. These signals are usually analog signals and may contain various frequency components. The preliminary collected signal is low-pass filtered to obtain a low-pass filtered signal: In order to remove high-frequency noise and retain useful low-frequency signals, the preliminary collected signal is fed into a low-pass filter. The function of the low-pass filter is to allow signals below a specific cutoff frequency to pass, while signals above this frequency are weakened or removed. The signal obtained after such processing is called a low-pass filtered signal. The low-pass filtered signal is band-pass filtered to obtain a band-pass filtered signal: The signal after low-pass filtering needs to be further processed to retain signals within a specific frequency range of interest. At this time, a band-pass filter is used, which allows signals within a specific frequency range to pass, while weakening or removing signals of other frequencies. The signal obtained after such processing is called a band-pass filtered signal. The bandpass filtered signal is amplified to obtain an amplified signal; and the amplified signal is used as an electrical acquisition signal: In order to ensure that the signal is strong enough for subsequent processing and conversion, the bandpass filtered signal will be sent to the amplifier for amplification. The amplified signal is called the amplified signal, and it is used as an electrical acquisition signal for subsequent processing. The amplified signal is digitized by a preset analog-to-digital converter to obtain electrical parameters: The last step is to convert the analog signal into a digital signal so that the computer system can process it. This step is completed by an analog-to-digital converter (ADC). The analog-to-digital converter converts the amplified signal into a digital signal, which represents the numerical value of the electrical parameter, which can be voltage, current or power. In summary, the main purpose of this step is to collect electrical signals in the distribution network through the FTU, and remove noise and retain useful signal components through a series of signal processing techniques (low-pass filtering, bandpass filtering and signal amplification), and finally convert the analog signal into a digital signal through analog-to-digital conversion to obtain electrical parameters that can be used for further analysis and processing. Such a processing flow helps to improve the quality of the signal, thereby improving the accuracy of fault detection and location.

[0080] In a specific embodiment, the electrical parameter is mapped to a preset electrical parameter-time coordinate system, and a curve is plotted for the electrical parameter on the electrical parameter-time coordinate system to obtain a visualized curve, including:

[0081] Sorting the electrical parameters in time series to obtain time series electrical parameters;

[0082] Mapping the timing electrical parameters to a preset electrical parameter-time coordinate system;

[0083] Using a linear interpolation technique, plotting a curve of the electrical parameter on the electrical parameter-time coordinate system to obtain an electrical curve;

[0084] The electrical curve is fitted to obtain a visualization curve.

[0085] Specifically, the following is an explanation of the technical solution for this step, which is to sort the electrical parameters in time series to obtain time series electrical parameters: In this step, the collected electrical parameters need to be sorted in time order. This ensures the time continuity and logical consistency of the data, which is convenient for subsequent analysis and display. The sorted data is called time series electrical parameters. Map the time series electrical parameters to a preset electrical parameter-time coordinate system: Next, the sorted time series electrical parameters need to be mapped to a preset coordinate system. This coordinate system uses time as the horizontal axis (X axis) and electrical parameters as the vertical axis (Y axis). This is done to intuitively show the trend of electrical parameters changing over time. Using linear interpolation technology, the electrical parameters on the electrical parameter-time coordinate system are plotted to obtain an electrical curve: In order to make the change trend of electrical parameters smoother, linear interpolation technology can be used to connect the points between electrical parameters and time. Linear interpolation is a simple method to estimate unknown data points by drawing a straight line between two known data points. After such processing, one or a series of line segments connecting the data points can be obtained on the coordinate system to form an electrical curve. Fitting the electrical curve to obtain a visualization curve: The last step is to fit the drawn electrical curve. Fitting refers to finding a best-matching curve through mathematical methods, which can well reflect the overall trend of electrical parameters changing over time. The fitting process may use more complex algorithms, such as polynomial regression or other statistical models, to ensure that the curve is consistent with the original data and has good smoothness. The final curve is the visualization curve, which can more clearly show the changing pattern of electrical parameters. In summary, the main purpose of this step is to obtain one or a series of visualization curves that can intuitively show the trend of electrical parameters changing over time by sorting the electrical parameters in time and drawing curves on a preset coordinate system, and by fitting these curves. This process not only helps to visualize the data, but also helps technicians quickly identify abnormal situations or patterns, so as to take corresponding measures in time.

[0086] In a specific embodiment, monitoring whether the visualized curve on the electrical parameter-time coordinate system has an abnormal phenomenon, and if the visualized curve has an abnormal phenomenon, marking the abnormal area corresponding to the abnormal phenomenon to obtain a visualized marked curve, including:

[0087] Performing abnormal phenomenon monitoring on the visualized curve on the electrical parameter-time coordinate system to obtain abnormal phenomenon monitoring results;

[0088] If the abnormal phenomenon monitoring result is that the visualization curve has an abnormal phenomenon, the area corresponding to the abnormal phenomenon is isolated to obtain an isolated area; wherein the abnormal phenomenon includes a mutation point, a jump point, an oscillation point, a drift point and missing data;

[0089] The isolation area is specially marked to obtain a dotted line marked area; wherein the special mark includes a circle for the isolation area and arrow marks at both ends of the isolation area;

[0090] The dotted line marked area is translated onto the visualization curve to obtain a visualization marked curve.

[0091] Specifically, the following is an explanation of the technical solution for this step, monitoring the visual curve on the electrical parameter-time coordinate system for abnormal phenomena to obtain abnormal phenomenon monitoring results: In this step, we need to monitor the previously obtained visual curve to find out whether there are any abnormal phenomena. Abnormal phenomenon monitoring usually uses statistical methods or machine learning algorithms to automatically detect points or intervals that deviate from normal behavior. The monitoring results will tell us whether there are abnormal phenomena and their types. If the abnormal phenomenon monitoring result is that there is an abnormal phenomenon in the visual curve, the area corresponding to the abnormal phenomenon is isolated to obtain an isolated area: If the monitoring result shows that there is indeed an abnormal phenomenon, then the area corresponding to these abnormal phenomena needs to be isolated next. This means separating abnormal data points or intervals from normal curves for further analysis. Abnormal phenomena may include but are not limited to mutation points, jump points, oscillation points, drift points and missing data. The isolated area is specially marked to obtain a dotted line marked area: For the isolated area, it needs to be specially marked for easy identification. Special marking can include drawing a circle around the isolated area or adding arrow marks at both ends of the isolated area. These marks can be in the form of dotted lines to distinguish them from normal curves, and can also clearly indicate which parts are abnormal. The dotted marked area is translated to the visual curve to obtain a visual marked curve: The last step is to reposition the isolated area with special marks onto the original visual curve. Doing so can make the entire curve chart more intuitive, and users can see at a glance which parts have abnormalities. After such processing, we get a marked visual curve, which can be used to easily view and analyze abnormal points in the data. In summary, this process is mainly to identify and highlight anomalies in the visual curve. Through monitoring, isolation, marking and reintegration, it can effectively assist engineers or analysts to quickly locate the problem and then take appropriate measures to solve the problem. This method can not only improve the efficiency of data analysis, but also help to better understand the potential problems behind the data.

[0092] In a specific embodiment, abnormal phenomenon monitoring is performed on the visualized curve on the electrical parameter-time coordinate system to obtain abnormal phenomenon monitoring results, including:

[0093] Input the visualized curve on the electrical parameter-time coordinate system into the trained monitoring algorithm; wherein the monitoring algorithm includes the MDFFM multi-dimensional feature fusion module, the SPP_SF module, the dynamic snake convolution module and the multi-task supervision module, and the SPP_SF module includes the SPP module and the efficient pooling layer SoftPool;

[0094] Perform feature extraction on the visualization curve through the MDFFM multi-dimensional feature fusion module to obtain extracted features;

[0095] Capturing subtle features of the extracted features through a dynamic snake-shaped convolution module to obtain subtle captured features, and fusing the subtle captured features to obtain multi-scale fused features;

[0096] Performing feature enhancement on the multi-scale fusion feature through the SPP_SF module to obtain enhanced features;

[0097] The enhanced features are monitored for abnormal phenomena through a multi-task supervision module to obtain abnormal phenomenon monitoring results.

[0098] Specifically, in order to realize the abnormal phenomenon monitoring of the visualization curve on the electrical parameter-time coordinate system, the whole process can be completed by a series of trained monitoring algorithms. First, the visualization curve on the electrical parameter-time coordinate system is input into a trained monitoring algorithm. The structure of this monitoring algorithm is very complex and powerful, mainly including several key modules, namely, the MDFFM multi-dimensional feature fusion module, the SPP_SF module, the dynamic snake convolution module and the multi-task supervision module. Among them, the SPP_SF module itself is composed of the SPP module and the efficient pooling layer SoftPool. After the visualization curve is input, it is first processed by the MDFFM multi-dimensional feature fusion module. The main function of this module is to extract features from the visualization curve. The so-called feature extraction refers to extracting the most valuable information for subsequent analysis and monitoring from the original data. In this process, the MDFFM multi-dimensional feature fusion module can process data of multiple dimensions at the same time, so that the extracted features are more comprehensive and accurate. The quality of the extracted features directly affects the effectiveness of the subsequent steps. Therefore, the MDFFM module plays a vital role in the entire monitoring algorithm. Then, the extracted features are input into the dynamic snake convolution module. The design of this module is inspired by the traditional convolutional neural network (CNN), but it is also innovative, especially in capturing subtle features. The dynamic snake convolution module can capture subtle feature changes, even tiny details that are easily overlooked by traditional methods, through the bionic snake path scanning mechanism. These subtle capture features are an important basis for abnormal phenomenon monitoring, because many abnormal phenomena are very weak in the early stages and are difficult to detect through rough feature detection. Therefore, the dynamic snake convolution module lays a solid foundation for subsequent abnormality detection through precise subtle capture. In addition, this module also has the function of fusing subtle capture features to finally obtain multi-scale fusion features. This step not only improves the recognition ability of features, but also enhances the sensitivity of the model to abnormal phenomena of different scales. Subsequently, the multi-scale fusion features are input into the SPP_SF module for feature enhancement. The SPP_SF module combines the advantages of the SPP (spatial pyramid pooling) module and the efficient pooling layer SoftPool, and further enhances the features through multi-level spatial information integration and efficient pooling operations. This enhancement not only improves the resolution of the features, but also increases the stability and consistency of the features at different spatial scales. After feature enhancement, the feature signal becomes more obvious and prominent, which makes subsequent anomaly monitoring more accurate. The SPP module processes feature information hierarchically through its unique spatial pyramid structure, ensuring that feature information at different levels can be fully utilized, while the efficient pooling operation of SoftPool ensures that important information is not lost during the feature enhancement process and improves the computational efficiency of the model.Finally, the enhanced features are input into the multi-task supervision module for abnormal phenomenon monitoring. The design of the multi-task supervision module takes into account the various tasks and goals that may be involved in the abnormal monitoring process. Through the parallel or serial multi-task processing mechanism, the module can detect multiple types of abnormal phenomena at the same time. In practical applications, this means that the multi-task supervision module can not only detect a specific abnormal phenomenon, but also integrate multiple possible abnormal types to provide a comprehensive monitoring result. In addition, the multi-task supervision module can provide more accurate and reliable abnormal phenomenon monitoring results through in-depth analysis of the enhanced features. The multi-task capability of this module makes the entire monitoring system more flexible and adaptable when dealing with complex and changeable electrical parameters, thereby greatly improving the accuracy of abnormal monitoring. Through the collaborative work of these modules, the monitoring results of the abnormal phenomenon are finally obtained. This result can not only indicate the time and type of the abnormality, but also give a specific feature description of the abnormal phenomenon, which provides an important basis for subsequent analysis and processing. The whole process reflects the close cooperation and mutual complementation between the various modules, and each module plays a unique and important role in achieving the monitoring goal. Such a design not only makes the monitoring algorithm powerful, but also ensures the efficiency and reliability of abnormal phenomenon monitoring of electrical parameters in practical applications.

[0099] In a specific embodiment, the isolation area is specially marked to obtain a dotted line marked area, including:

[0100] Identify the starting point and the end point of the isolation area, and determine the corresponding coordinates of the starting point and the end point; wherein the coordinates include the starting point coordinates and the end point coordinates;

[0101] Determine the center point based on the starting point coordinates and the end point coordinates, and use the distance from the center point to the starting point or the end point as the radius;

[0102] Obtaining a marked circle based on the center point and the radius;

[0103] The isolation area is specially marked based on the marking circle to obtain a dotted line marked area; wherein the dotted line marked area is the isolation area covered by the marking circle.

[0104] Specifically, the process of specially marking the isolation area to obtain the dotted line marked area is an important part of the distribution network fault location method. This process first requires identifying the starting point and the end point of the isolation area, and determining the corresponding coordinates of the two points, that is, the starting point coordinates and the end point coordinates. The purpose of this step is to clarify the specific location range of the fault and ensure that the subsequent marking work can accurately reflect the information of the fault area. For example, in the application scenario of distribution network fault location, when the system detects an abnormal change in the voltage or current parameters of a certain section of the line, the system will automatically identify the starting position and the end position of the abnormal change, that is, the starting point and the end point of the isolation area. These location information will be converted into specific coordinate values ​​for subsequent marking operations. After determining the starting point coordinates and the end point coordinates, the next step is to determine the center point based on these two coordinate points, and use the distance from the center point to the starting point or the end point as the radius. The center point here refers to the midpoint of the line connecting the starting point and the end point, and the radius refers to the distance from the midpoint to any end point. The purpose of this operation is to construct a circular mark that can completely cover the isolation area to ensure that all potential problems in the fault area can be marked. Taking the fault location of the distribution network as an example, when the system determines the coordinates of the two endpoints of the fault area, it will calculate the midpoint position of the two points, and then measure the distance from the midpoint to one of the endpoints, which is the radius. After having the center point and the radius, the next step is to obtain a marking circle based on the center point and the radius. The function of this marking circle is to specially mark the isolation area so that the fault area can be clearly distinguished from the layout of the entire distribution network, which is convenient for technicians to quickly identify and process. In actual operation, when the system calculates a circle that can cover the fault area, it will draw such a circle on the monitoring interface of the distribution network to specially mark the area. This marking method is not only intuitive, but also can effectively avoid information confusion caused by overly complex marking. Finally, the isolation area is specially marked based on the marking circle to obtain a dotted marking area, wherein the dotted marking area is the isolation area covered by the marking circle. The dotted marking area here refers to a marking circle presented in the form of a dotted line, which can not only clearly define the scope of the isolation area, but also because of the use of a dotted line style, the entire graphic looks more concise and clear, and easy to distinguish. Continuing with the application scenario of fault location in the distribution network mentioned above, when the system draws a marking circle covering the fault area in the monitoring interface, it will set the circle to a dotted line form, which will not affect the display of other normal line information, and allow maintenance personnel to identify the location of the fault at a glance. In summary, the process of special marking of the isolation area to obtain the dotted line marking area is a comprehensive technical means that integrates coordinate determination, center point and radius calculation, marking circle generation, and special marking in dotted form.This process can not only effectively highlight the areas that need to be focused on, but also ensure the accuracy of information transmission, which is of great significance for improving the operation and maintenance efficiency of the power system and ensuring the safe and stable operation of the power grid. Through this method, the maintenance team can accurately locate the location of the fault at the first time, so as to quickly take measures to repair it, reduce the power outage time, and ensure the power demand of users.

[0105] In a specific embodiment, obtaining the time of the abnormal point based on the abnormal phenomenon on the visual marking curve, and obtaining the distribution network fault location based on the time of the abnormal point and the propagation speed of the electrical acquisition signal, includes:

[0106] Marking the abnormal phenomena on the visual marking curve respectively to obtain the time of the corresponding abnormal point;

[0107] Taking the starting point and the end point as abnormal points, and taking the starting point coordinates and the end point coordinates as abnormal point coordinates;

[0108] Draw a tangent line of the visual marking curve through the abnormal point to obtain the slope of the abnormal point;

[0109] Using a differential equation, constructing an outlier curve based on the coordinates of the outlier and the slope of the outlier;

[0110] An abnormal trend prediction is performed on the abnormal point curve to obtain an abnormal trend prediction result. If the abnormal trend prediction is not within the preset prediction range, the distribution network fault location is obtained according to the time of the abnormal point and the propagation speed of the electrical acquisition signal.

[0111] Specifically, the process of obtaining the time of the abnormal point based on the abnormal phenomenon on the visual marking curve, and obtaining the distribution network fault location based on the time of the abnormal point and the propagation speed of the electrical acquisition signal is a technical solution for realizing accurate fault location by comprehensively using data analysis and mathematical modeling methods. This process first requires time marking the abnormal phenomenon on the visual marking curve to obtain the time of the corresponding abnormal point. This means that when abnormal changes in the voltage or current parameters in the distribution network are monitored, the system will automatically record the specific time when these abnormal changes occur. For example, in the application scenario of distribution network fault location, when the system detects abnormal phenomena such as sudden changes, jumps, oscillations or drifts in the voltage or current parameters of a certain section of the line, the time points of these abnormal phenomena will be immediately recorded, and these time points are the time of the abnormal points. Next, the starting point and the end point are also regarded as abnormal points, and their corresponding starting point coordinates and end point coordinates are used as the coordinates of the abnormal point. This operation is to ensure that the boundaries of the fault area can be accurately marked, so as to provide accurate data support for subsequent fault location. For example, in the above-mentioned distribution network fault location case, when the system identifies the starting and ending positions of the fault area, these two positions will also be marked as abnormal points, and their coordinate information will be recorded. The advantage of this is that the fault area can be fully covered to prevent any important fault information from being missed. Then, a tangent line is made to the visual marking curve through the abnormal point to obtain the slope of the abnormal point. The calculation of the slope is very important for understanding the nature and change trend of the abnormal phenomenon. By making a tangent line to the visual marking curve at the abnormal point, the rate of change of the electrical parameters near the point can be obtained. In the actual application of distribution network fault location, after the system calculates the slope at the abnormal point, the size and direction of the slope can be further analyzed to determine the severity and development trend of the fault. For example, if the slope of a certain abnormal point is very large, it means that the electrical parameters near the point change very drastically, and there may be a serious short circuit or other fault. Next, a differential equation is used to construct an abnormal point curve based on the coordinates of the abnormal point and the slope of the abnormal point. This process involves the technology of mathematical modeling, the purpose of which is to more accurately describe the change law of electrical parameters near the abnormal point. By constructing an abnormal point curve, the development process of the abnormal phenomenon can be more intuitively displayed, helping technicians better understand the nature of the fault. For example, in the application of distribution network fault location, when the system constructs an abnormal point curve based on the coordinates and slope of the abnormal point, the type and possible cause of the fault can be judged by observing the shape and trend of the curve. Finally, the abnormal trend of the abnormal point curve is predicted to obtain the abnormal trend prediction result. This prediction process aims to evaluate the possibility of fault development trend in the future, so as to take corresponding preventive measures in advance.If the result of the abnormal trend prediction exceeds the preset prediction range, it means that the fault situation may further deteriorate. At this time, it is necessary to determine the specific location of the fault based on the time of the abnormal point and the propagation speed of the electrical acquisition signal. In the actual operation of distribution network fault location, when the system predicts that the abnormal trend of a certain fault point exceeds the normal range, the fault location program will be started immediately. By calculating the relationship between the time of the abnormal point and the signal propagation speed, the location of the fault can be quickly locked. For example, assuming that it takes 10 milliseconds for the fault signal of a certain line to propagate from the starting point to the end point, and the time difference of the abnormal point recorded by the system is 5 milliseconds, then the specific location of the fault point from the starting point can be calculated based on this time difference and the known signal propagation speed. In summary, this series of steps not only covers the complete process from the identification of abnormal phenomena to the determination of the abnormal point time, to the construction of the abnormal point curve and the prediction of the abnormal trend, and finally to the fault location, but also fully reflects the important role of technical means in the operation and maintenance of the power system. Through this method, not only can the power grid faults be discovered and handled in a timely manner, but also the safety and stability of the power system can be effectively improved, and the continuity and reliability of power supply can be ensured. The application of this method not only improves the efficiency of fault handling, but also reduces the power outage time and economic losses caused by faults, providing strong technical support for the efficient operation of the power system.

[0112] The above describes the distribution network fault location method based on FTU in the embodiment of the present invention. The following describes the distribution network fault location device based on FTU in the embodiment of the present invention. Figure 2 In one embodiment of the present invention, a distribution network fault location device based on FTU includes:

[0113] The acquisition module 21 is used to acquire electrical signals from the distribution network through the FTU to obtain electrical acquisition signals, and to digitally process the electrical acquisition signals to obtain electrical parameters; wherein the electrical parameters are voltage parameters, current parameters or power parameters;

[0114] A drawing module 22 is used to map the electrical parameters to a preset electrical parameter-time coordinate system, and to draw a curve of the electrical parameters on the electrical parameter-time coordinate system to obtain a visualization curve; wherein the electrical parameter-time coordinate system includes an abscissa and a ordinate, the ordinate of the visualization curve represents the value of the electrical parameter, and the abscissa represents the time from the electrical parameter to the FTU;

[0115] The monitoring module 23 is used to monitor whether there is any abnormal phenomenon in the visualization curve on the electrical parameter-time coordinate system. If there is any abnormal phenomenon in the visualization curve, the abnormal area corresponding to the abnormal phenomenon is marked to obtain a visualization marked curve; wherein the abnormal phenomenon includes a mutation point, a jump point, an oscillation point, a drift point and missing data;

[0116] The positioning module 24 is used to obtain the time of the abnormal point based on the abnormal phenomenon on the visual marking curve, and obtain the distribution network fault location based on the time of the abnormal point and the propagation speed of the electrical acquisition signal.

[0117] In this embodiment, for the specific implementation of each unit in the above system embodiment, please refer to the above method embodiment, which will not be repeated here.

[0118] Reference Figure 3 The present invention also provides a computer device in an embodiment, wherein the internal structure of the computer device can be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0119] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0120] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0121] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0122] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0123] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A distribution network fault location method based on FTU, characterized in that: The following steps are involved: The FTU collects electrical signals from the distribution network to obtain electrical collection signals, and digitally processes the electrical collection signals to obtain electrical parameters; wherein the electrical parameters are voltage parameters, current parameters, or power parameters; The electrical parameter is mapped to a preset electrical parameter-time coordinate system, and a curve is drawn for the electrical parameter on the electrical parameter-time coordinate system to obtain a visualization curve; wherein the electrical parameter-time coordinate system includes an abscissa and a ordinate, the ordinate of the visualization curve represents the value of the electrical parameter, and the abscissa represents the time from the electrical parameter to FTU; Monitor whether the visualized curve on the electrical parameter-time coordinate system has any abnormal phenomenon. If the visualized curve has any abnormal phenomenon, mark the abnormal area corresponding to the abnormal phenomenon to obtain a visualized marked curve; wherein the abnormal phenomenon includes a mutation point, a jump point, an oscillation point, a drift point and missing data; The time of the abnormal point is obtained based on the abnormal phenomenon on the visual marking curve, and the distribution network fault location is obtained based on the time of the abnormal point and the propagation speed of the electrical acquisition signal; Monitoring whether the visualization curve on the electrical parameter-time coordinate system has abnormal phenomena, and if the visualization curve has abnormal phenomena, marking the abnormal area corresponding to the abnormal phenomena to obtain a visualization marking curve, including: Performing abnormal phenomenon monitoring on the visualized curve on the electrical parameter-time coordinate system to obtain abnormal phenomenon monitoring results; If the abnormal phenomenon monitoring result is that the visualization curve has an abnormal phenomenon, isolating the area corresponding to the abnormal phenomenon to obtain an isolated area; The isolation area is specially marked to obtain a dotted line marked area; wherein the special mark includes a circle for the isolation area and arrow marks at both ends of the isolation area; The dotted line marked area is translated onto the visualization curve to obtain a visualization marked curve; Perform abnormal phenomenon monitoring on the visualized curve on the electrical parameter-time coordinate system to obtain abnormal phenomenon monitoring results, including: Input the visualized curve on the electrical parameter-time coordinate system into the trained monitoring algorithm; wherein the monitoring algorithm includes the MDFFM multi-dimensional feature fusion module, the SPP_SF module, the dynamic snake convolution module and the multi-task supervision module, and the SPP_SF module includes the SPP module and the efficient pooling layer SoftPool; Perform feature extraction on the visualization curve through the MDFFM multi-dimensional feature fusion module to obtain extracted features; Capturing subtle features of the extracted features through a dynamic snake-shaped convolution module to obtain subtle captured features, and fusing the subtle captured features to obtain multi-scale fused features; Performing feature enhancement on the multi-scale fusion feature through the SPP_SF module to obtain enhanced features; Performing abnormal phenomenon monitoring on the enhanced features through a multi-task supervision module to obtain abnormal phenomenon monitoring results; The isolation area is specially marked to obtain a dotted line marked area, including: Identify the starting point and the end point of the isolation area, and determine the corresponding coordinates of the starting point and the end point; wherein the coordinates include the starting point coordinates and the end point coordinates; Determine the center point based on the starting point coordinates and the end point coordinates, and use the distance from the center point to the starting point or the end point as the radius; Obtaining a marked circle based on the center point and the radius; Based on the marking circle, the isolation area is specially marked to obtain a dotted line marked area; wherein the dotted line marked area is the isolation area covered by the marking circle; The time of the abnormal point is obtained based on the abnormal phenomenon on the visual marking curve, and the distribution network fault location is obtained based on the time of the abnormal point and the propagation speed of the electrical acquisition signal, including: Marking the abnormal phenomena on the visual marking curve respectively to obtain the time of the corresponding abnormal point; Taking the starting point and the end point as abnormal points, and taking the starting point coordinates and the end point coordinates as abnormal point coordinates; A tangent line is drawn through the abnormal point to obtain the slope of the abnormal point. Using a differential equation, constructing an outlier curve based on the coordinates of the outlier and the slope of the outlier; An abnormal trend prediction is performed on the abnormal point curve to obtain an abnormal trend prediction result. If the abnormal trend prediction is not within the preset prediction range, the distribution network fault location is obtained according to the time of the abnormal point and the propagation speed of the electrical acquisition signal.

2. The distribution network fault location method based on FTU according to claim 1 is characterized in that: The electrical signal of the distribution network is collected by the FTU to obtain the electrical collection signal, and the electrical collection signal is digitally processed to obtain electrical parameters, including: Collecting electrical signals from the distribution network through the FTU to obtain preliminary collected signals; Performing low-pass filtering on the preliminary collected signal to obtain a low-pass filtered signal; Performing bandpass filtering on the low-pass filtered signal to obtain a bandpass filtered signal; Amplifying the bandpass filtered signal to obtain an amplified signal; and using the amplified signal as an electrical acquisition signal; The amplified signal is digitally converted by a preset analog-to-digital converter to obtain electrical parameters.

3. The distribution network fault location method based on FTU according to claim 1 is characterized in that: Mapping the electrical parameters to a preset electrical parameter-time coordinate system, and plotting a curve of the electrical parameters on the electrical parameter-time coordinate system to obtain a visualized curve, including: Sorting the electrical parameters in time series to obtain time series electrical parameters; Mapping the timing electrical parameters to a preset electrical parameter-time coordinate system; Using a linear interpolation technique, plotting a curve of the electrical parameter on the electrical parameter-time coordinate system to obtain an electrical curve; The electrical curve is fitted to obtain a visualization curve.

4. A distribution network fault location device based on FTU, characterized in that: include: A collection module, used for collecting electrical signals from the distribution network through the FTU to obtain electrical collection signals, and digitally processing the electrical collection signals to obtain electrical parameters; wherein the electrical parameters are voltage parameters, current parameters or power parameters; A drawing module, used for mapping the electrical parameters to a preset electrical parameter-time coordinate system, and drawing a curve of the electrical parameters on the electrical parameter-time coordinate system to obtain a visualization curve; wherein the electrical parameter-time coordinate system includes an abscissa and a ordinate, the ordinate of the visualization curve represents the value of the electrical parameter, and the abscissa represents the time from the electrical parameter to the FTU; A monitoring module is used to monitor whether there is any abnormal phenomenon in the visualization curve on the electrical parameter-time coordinate system. If there is any abnormal phenomenon in the visualization curve, the abnormal area corresponding to the abnormal phenomenon is marked to obtain a visualization marked curve; wherein the abnormal phenomenon includes a mutation point, a jump point, an oscillation point, a drift point and missing data; A positioning module, used to obtain the time of the abnormal point based on the abnormal phenomenon on the visual marking curve, and obtain the distribution network fault location based on the time of the abnormal point and the propagation speed of the electrical acquisition signal; Monitoring whether the visualization curve on the electrical parameter-time coordinate system has abnormal phenomena, and if the visualization curve has abnormal phenomena, marking the abnormal area corresponding to the abnormal phenomena to obtain a visualization marking curve, including: Performing abnormal phenomenon monitoring on the visualized curve on the electrical parameter-time coordinate system to obtain abnormal phenomenon monitoring results; If the abnormal phenomenon monitoring result is that the visualization curve has an abnormal phenomenon, isolating the area corresponding to the abnormal phenomenon to obtain an isolated area; The isolation area is specially marked to obtain a dotted line marked area; wherein the special mark includes a circle for the isolation area and arrow marks at both ends of the isolation area; The dotted line marked area is translated onto the visualization curve to obtain a visualization marked curve; Perform abnormal phenomenon monitoring on the visualized curve on the electrical parameter-time coordinate system to obtain abnormal phenomenon monitoring results, including: Input the visualized curve on the electrical parameter-time coordinate system into the trained monitoring algorithm; wherein the monitoring algorithm includes the MDFFM multi-dimensional feature fusion module, the SPP_SF module, the dynamic snake convolution module and the multi-task supervision module, and the SPP_SF module includes the SPP module and the efficient pooling layer SoftPool; Perform feature extraction on the visualization curve through the MDFFM multi-dimensional feature fusion module to obtain extracted features; Capturing subtle features of the extracted features through a dynamic snake-shaped convolution module to obtain subtle captured features, and fusing the subtle captured features to obtain multi-scale fused features; Performing feature enhancement on the multi-scale fusion feature through the SPP_SF module to obtain enhanced features; Performing abnormal phenomenon monitoring on the enhanced features through a multi-task supervision module to obtain abnormal phenomenon monitoring results; The isolation area is specially marked to obtain a dotted line marked area, including: Identify the starting point and the end point of the isolation area, and determine the corresponding coordinates of the starting point and the end point; wherein the coordinates include the starting point coordinates and the end point coordinates; Determine the center point based on the starting point coordinates and the end point coordinates, and use the distance from the center point to the starting point or the end point as the radius; Obtaining a marked circle based on the center point and the radius; Based on the marking circle, the isolation area is specially marked to obtain a dotted line marked area; wherein the dotted line marked area is the isolation area covered by the marking circle; The time of the abnormal point is obtained based on the abnormal phenomenon on the visual marking curve, and the distribution network fault location is obtained based on the time of the abnormal point and the propagation speed of the electrical acquisition signal, including: Marking the abnormal phenomena on the visual marking curve respectively to obtain the time of the corresponding abnormal point; Taking the starting point and the end point as abnormal points, and taking the starting point coordinates and the end point coordinates as abnormal point coordinates; A tangent line is drawn through the abnormal point to obtain the slope of the abnormal point. Using a differential equation, constructing an outlier curve based on the coordinates of the outlier and the slope of the outlier; An abnormal trend prediction is performed on the abnormal point curve to obtain an abnormal trend prediction result. If the abnormal trend prediction is not within the preset prediction range, the distribution network fault location is obtained according to the time of the abnormal point and the propagation speed of the electrical acquisition signal.

5. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images