Power distribution network fault early warning method, device, equipment, readable storage medium and program product

Abstract

The application relates to a power distribution network fault early warning method, device, equipment, computer readable storage medium and computer program product. The method comprises the following steps: collecting and cross-transmitting real-time information of a power distribution network based on two sets of equipment to obtain two groups of real-time data corresponding to the two sets of equipment; extracting fault features of the power distribution network from the two groups of real-time data respectively to obtain first fault features and second fault features; inputting the first fault features into a preset analysis model; the analysis model is used for analyzing the first fault features and outputting corresponding first fault information; obtaining second fault information based on simulation analysis of the second fault features; determining the consistency degree of the first fault information and the second fault information; if the consistency degree reaches a preset standard, determining the fault information of the power distribution network and outputting a corresponding level of early warning signal. The method can realize the automation of power distribution network fault troubleshooting and improve the accuracy of power distribution network fault early warning.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric power, and in particular to a power distribution network fault early warning method, device, equipment, computer readable storage medium and computer program product. BACKGROUND

[0002] The power distribution network refers to a power network that accepts electric energy from a power transmission network or a regional power plant, and distributes the electric energy to various users through power distribution facilities or step by step according to voltage. The power distribution network is composed of overhead lines, cables, towers, distribution transformers, disconnectors, reactive power compensators and some auxiliary facilities.

[0003] For power distribution network faults, a periodic manual maintenance method is generally used to troubleshoot and handle. This method has low efficiency. Meanwhile, due to the diversification of power distribution network faults, the professional ability of the operating personnel is required to be high, and there is a difference in troubleshooting effect of the power distribution network faults due to different operating personnel. Therefore, how to improve the efficiency and accuracy of troubleshooting and handling of the power distribution network faults is a problem to be solved. SUMMARY

[0004] Therefore, it is necessary to provide a power distribution network fault early warning method, device, computer equipment, computer readable storage medium and computer program product to improve the efficiency and accuracy of troubleshooting of the power distribution network, in order to solve the above technical problems.

[0005] In a first aspect, the present application provides a power distribution network fault early warning method, comprising:

[0006] Based on the collection and cross-transmission of real-time information of the power distribution network by two sets of equipment, two groups of real-time data corresponding to the two sets of equipment are obtained;

[0007] Fault features of the power distribution network are extracted from the two groups of real-time data respectively, to obtain first fault features and second fault features. The fault features at least include one of the following: power parameter features, topology structure features, time series data features, fault signal features and data statistical features;

[0008] The first fault features are input into a preset analysis model. The analysis model is used to analyze the first fault features and output corresponding first fault information. The analysis model is obtained by training based on historical data of the power distribution network;

[0009] Based on the simulation analysis of the second fault features, second fault information is obtained;

[0010] The consistency degree of the first fault information and the second fault information is determined;

[0011] In the case where the consistency degree reaches a preset standard, the fault information of the power distribution network is determined and a corresponding level of early warning signal is output.

[0012] In one of the embodiments, the second fault information is obtained based on the simulation analysis on the second fault feature, and the second fault information includes:

[0013] According to the second fault feature, the corresponding feature point value and the feature overall mean value are determined;

[0014] The deviation degree of the feature point value compared with the feature overall mean value is determined;

[0015] According to the deviation degree, the second fault information is determined.

[0016] In one of the embodiments, the deviation degree of the feature point value compared with the feature overall mean value is determined, including:

[0017] According to the feature point value, the correlation coefficient of the second fault feature and the historical data is determined;

[0018] According to the feature point value, the historical data and the correlation coefficient, the deviation degree of the feature point value in the second fault feature compared with the feature overall mean value is determined.

[0019] In one of the embodiments, the power parameter feature is extracted in the following way:

[0020] The power original signal of the power distribution network is obtained;

[0021] At least one local extreme point of the original signal is determined;

[0022] The average value and the envelope value of adjacent local extreme points are determined;

[0023] According to the average value and the envelope value, the power parameter feature is determined.

[0024] In one of the embodiments, the method further includes:

[0025] According to the first fault feature, the preliminary analysis model is determined from a plurality of preset basic analysis models;

[0026] The fault type corresponding to the first fault feature is determined;

[0027] Based on the fault type and the corresponding simulation, the preliminary analysis model is optimized to obtain the analysis model.

[0028] In one of the embodiments, the real-time data includes: current, voltage, equipment and line temperature, environmental humidity, power usage, circuit switch state, transformer operating state in the circuit;

[0029] The method further includes: pre-processing the real-time data to improve data quality; the pre-processing includes at least one of the following: cleaning, removing abnormal data, filling missing values.

[0030] In a second aspect, the application further provides a power distribution network fault early warning device, which comprises:

[0031] a feature acquisition module, configured to obtain two sets of real-time data corresponding to the two sets of equipment based on the acquisition and cross-transmission of real-time information of the power distribution network by the two sets of equipment; extract fault features of the power distribution network from the two sets of real-time data respectively to obtain first fault features and second fault features; the fault features at least include one of the following: power parameter features, topological structure features, time series data features, fault signal features, and data statistical features;

[0032] a first analysis module, configured to input the first fault features into a preset analysis model; the analysis model is configured to analyze the first fault features and output corresponding first fault information; the analysis model is obtained through training based on historical data of the power distribution network;

[0033] a second analysis module, configured to obtain second fault information based on simulation analysis of the second fault features;

[0034] a fault early warning module, configured to determine the consistency degree of the first fault information and the second fault information; in the case that the consistency degree reaches a preset standard, determine the fault information of the power distribution network and output a corresponding level of early warning signal.

[0035] In a third aspect, the application further provides a power distribution network fault early warning device, comprising a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method in the first aspect when executing the computer program.

[0036] In a fourth aspect, the application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the method in the first aspect.

[0037] In a fifth aspect, the application further provides a computer program product, comprising a computer program, and the computer program is executed by a processor to implement the steps of the method in the first aspect.

[0038] The above-described distribution network fault early warning method, apparatus, device, computer-readable storage medium, and computer program product utilize two sets of equipment to collect and cross-transmit real-time distribution network information, generating two sets of real-time data. This allows for the use of these two sets of real-time data to provide distribution network fault early warnings, effectively preventing data anomalies from affecting the accuracy of distribution network fault early warnings. Fault characteristics are extracted from the real-time data to obtain a first fault characteristic and a second fault characteristic. The first fault characteristic is analyzed using an analytical model to obtain first fault information, and the second fault characteristic is simulated and analyzed to obtain second fault information. Finally, based on the consistency between the first and second fault information, the distribution network fault information is determined and a corresponding warning signal is output. In other words, the real-time distribution network data is analyzed using both analytical models and simulations. Based on the analysis results, a comprehensive determination is made as to whether a fault exists in the distribution network, as well as the specific fault conditions if a fault exists, and the corresponding distribution network fault information is provided. This automates the troubleshooting and processing of distribution network faults, making distribution network fault early warnings more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 1 is a flow chart of a method for early warning of a distribution network fault in one embodiment;

[0041] Figure 2 This is another flowchart of a method for early warning of a power distribution network failure in one embodiment;

[0042] Figure 3 1 is another flow chart of a method for early warning of a power distribution network fault in one embodiment;

[0043] Figure 4 Schematic diagram of the structure of a power distribution network fault warning system in one embodiment;

[0044] Figure 5 This is a structural block diagram of a distribution network fault early warning device in one embodiment;

[0045] Figure 6 FIG. 1 is a diagram showing the internal structure of a distribution network fault warning device in one embodiment. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0047] In one embodiment, as shown in Figure 1 A power distribution network fault early warning method is provided. The method is applied to a power distribution network early warning system. It should be understood that the method can also be applied to other systems, such as a power distribution network management system, a whole power grid management system, etc. The method can be applied to a terminal and a server, and the terminal and the server are preinstalled with the above system. The server can be a standalone physical server, a server cluster or a distributed system composed of multiple physical servers, a cloud server providing cloud computing services, or a system including a terminal and a server and implemented through the interaction of the terminal and the server. The method includes steps S101 to S105.

[0048] Step S101: Based on the collection and cross-transmission of real-time information of the power distribution network by two sets of equipment, two groups of real-time data corresponding to the two sets of equipment are obtained.

[0049] The equipment can include but is not limited to sensors, intelligent meters and other equipment. The two sets of equipment can operate independently of each other and alternately transmit data. Real-time data refers to data reflecting the real-time operation of the power distribution network.

[0050] Exemplarily, the collection and cross-transmission of real-time information of the power distribution network by two sets of equipment can obtain two groups of real-time data, thereby facilitating the subsequent use of the two groups of real-time data.

[0051] Step S102: Extracting the fault features of the power distribution network from the two groups of real-time data respectively to obtain first and second fault features; the fault features at least include one of the following: power parameter features, topology structure features, time series data features, fault signal features, and data statistical features.

[0052] The power parameter features refer to the features of parameters related to power, such as voltage, current, etc. The topology structure features refer to the features related to the topology structure of the power distribution network, such as the components of the power distribution network, such as overhead lines, cables, towers, distribution transformers, disconnectors, etc., and the relationship between the components. The time series data features refer to the features related to the time series data of the power distribution network. The fault signal features refer to the features related to the fault signals of the power distribution network. The data statistical features refer to the features of the relevant statistical data of the power distribution network.

[0053] Exemplarily, since two groups of real-time data are obtained, the fault features of the two groups of real-time data can be extracted to obtain the first fault feature and the second fault feature. For example, the first fault feature can be obtained by fusing the above-mentioned specific types of fault features, and the second fault feature can also be obtained in this way.

[0054] Step S103: inputting the first fault feature into a preset analysis model; the analysis model is used for analyzing the first fault feature and outputting corresponding first fault information; the analysis model is obtained by training based on historical data of the power distribution network.

[0055] The preset analysis model is an artificial intelligence model for power distribution network fault analysis set in advance. The historical data of the power distribution network are related data of the power distribution network in a past time range. The historical data are relative to the real-time data. Essentially, both of them are related data reflecting the operation of the power distribution network. The core difference lies in the time difference.

[0056] Exemplarily, the existing or self-defined artificial intelligence model can be trained in advance using the historical data of the power distribution network to obtain the analysis model. Of course, the analysis model can also be optimized. The optimization can be based on all types of fault features or based on a certain type or a few types of fault features. In addition, different types of analysis models can be trained according to different types of fault features, and then the corresponding type of analysis model can be selected according to the needs. Then, the analysis model can be used to analyze the first fault feature to obtain the first fault information. The first fault information can be indicative of the existence of a fault in the power distribution network and the specific fault information, or it can also be indicative of the non-existence of a fault in the power distribution network.

[0057] Step S104: obtaining the second fault information based on the simulation analysis of the second fault feature.

[0058] Exemplarily, the simulation analysis of the second fault feature obtained through the foregoing steps can be performed to analyze the related information about the fault of the power distribution network contained in the second fault feature to obtain the second fault information. The second fault information can be indicative of the existence of a fault in the power distribution network and the specific fault information, or it can also be indicative of the non-existence of a fault in the power distribution network.

[0059] Step S105: determining the consistency degree of the first fault information and the second fault information; in the case where the consistency degree reaches a preset standard, determining the fault information of the power distribution network and outputting a corresponding level of early warning signal.

[0060] Exemplarily, after obtaining the first fault information and the second fault information, the two can be compared to determine the consistency between the two, if the consistency reaches the preset standard, the fault information of the power distribution network can be determined and the corresponding level of early warning signal is output. For example, the consistency can include three levels of low, medium and high, and the corresponding preset standard can be required to reach medium or high. Further, for example, if the first fault information represents that the power distribution network does not exist fault, and the second fault information represents that the power distribution network exists fault, it can be considered that the consistency is low, and the consistency does not reach the preset standard. For another example, if the first fault information and the second fault information both represent that the power distribution network exists fault and the specific fault is in the power distribution transformer, it can be considered that the consistency is high and reaches the preset standard. For another example, if the first fault information and the second fault information both represent that the power distribution network exists fault but the respective specific faults are different, it can be considered that the consistency is medium and reaches the preset standard. Of course, the consistency can include two levels of inconsistency and consistency, and the preset standard can be required to be consistent.

[0061] In the embodiment, the real-time information of the power distribution network is collected and cross-transmitted by the two sets of equipment, two groups of real-time data are obtained, and the power distribution network fault early warning is performed by the two groups of real-time data, which can effectively prevent the data anomaly from affecting the accuracy of the power distribution network fault early warning. The fault features are extracted from the real-time data to obtain first fault features and second fault features. The first fault information is obtained by analyzing the first fault features by using the analysis model, and the second fault information is obtained by simulating and analyzing the second fault features. Finally, the fault information of the power distribution network is determined according to the consistency of the first fault information and the second fault information, and the corresponding level of early warning signal is output. That is, the real-time data of the power distribution network is analyzed from the aspects of the analysis model and the simulation, and according to the analysis result, whether the power distribution network exists fault and the specific fault condition when the fault exists are comprehensively determined, and the corresponding power distribution network is given. This realizes the automation of the power distribution network fault troubleshooting and makes the power distribution network fault early warning more accurate.

[0062] In one of the embodiments, as shown in FIG. 2, Figure 2 The "obtaining the second fault information based on the simulation and analysis of the second fault features" in the foregoing embodiment can include steps S201 to S203:

[0063] Step S201: determining the corresponding feature point value and the feature overall mean value according to the second fault features.

[0064] The fault features can include a plurality of feature points, and the corresponding feature point value is the value corresponding to a specific point in the second fault features; and the feature overall mean value is the mean value of the values corresponding to all feature points.

[0065] Exemplarily, the second fault feature can include different types of fault features, and thus the corresponding feature point value and the feature overall mean value can be determined for different types of fault features respectively. For example, for a temperature type of fault feature, the corresponding feature point value can be a feature value corresponding to a single point temperature, and the feature overall mean value can be a feature mean value corresponding to an overall temperature.

[0066] Step S202: determining a deviation degree of the feature point value compared with the feature overall mean value.

[0067] Exemplarily, the manner of determining the deviation degree can be implemented by using a range method, a standard deviation method, etc. Herein, no limitation is made.

[0068] Step S203: determining the second fault information according to the deviation degree.

[0069] Exemplarily, a deviation threshold value can be set, and if the value of the obtained deviation degree does not exceed the deviation threshold value, it can be considered that there is no fault, and otherwise, it can be considered that there is a fault.

[0070] In the embodiment, by determining the feature point value and the feature overall mean value corresponding to the second fault feature, and based on the deviation degree of the feature point value compared with the feature overall mean value, the second fault information is determined. This makes the obtained second fault information more accurately determine whether there is a fault in the power distribution network, and the corresponding fault information when there is a fault.

[0071] In one of the embodiments, the "determining the deviation degree of the feature point value compared with the feature overall mean value" in the foregoing embodiments can include: determining a correlation coefficient of the second fault feature and historical data according to the feature point value; and determining the deviation degree of the feature point value in the second fault feature compared with the feature overall mean value according to the feature point value, the historical data, and the correlation coefficient.

[0072] The correlation coefficient is a coefficient indicating the correlation degree of the second fault feature and the historical data.

[0073] Exemplarily, the correlation coefficient can be calculated by the following formula:

[0074] , wherein,

[0075] x represents the second fault feature;

[0076] represents the second fault feature mean value;

[0077] r represents the correlation coefficient;

[0078] y represents a certain data point in the historical data;

[0079] representing the mean value of a certain data point in the historical data of the power distribution network.

[0080] Exemplarily, the degree of deviation can be calculated by the following formula:

[0081] wherein,

[0082] Z represents the degree of deviation.

[0083] representing the standard deviation corresponding to x.

[0084] In this embodiment, the degree of deviation is determined by calculating the correlation coefficient and according to the feature point value, the historical data and the correlation coefficient, which can obtain a more accurate degree of deviation, thereby helping to obtain more accurate second fault information, and further helping to realize more accurate power distribution network fault warning.

[0085] In one of the embodiments, the power parameter features in the foregoing embodiments can be extracted by the method as shown in Figure 3 , and specifically include steps S301 to S304:

[0086] Step S301: obtaining the power original signal of the power distribution network.

[0087] The power original signal of the power distribution network, i.e. the power-related untreated signal of the power distribution network, for example, a voltage signal.

[0088] Step S302: determining at least one local extreme point of the original signal.

[0089] The local extreme point can be a point corresponding to a local maximum value and / or a local minimum value in the original signal.

[0090] Step S303: determining the average value and the envelope value of adjacent local extreme points.

[0091] Step S304: determining the power parameter features according to the average value and the envelope value.

[0092] A possible specific method for determining the power parameter features is given below:

[0093] determining all local extreme points n i of the original signal x(t) (i=1, 2, …, M); calculating the average value m i and the envelope value a i of all adjacent local extreme points, and the specific calculation formula is as follows:

[0094] , wherein, i=1, 2, …, M-1.

[0095] According to the average value m i and the envelope value a i , the power parameter feature can be obtained. Exemplarily, the average value m i and the envelope value a i can be compared with the historical data to obtain whether the data is faulty.

[0096] In the embodiment, by decomposing the power original signal to obtain the average value and the envelope value, a more accurate power parameter feature can be obtained, that is, the power parameter feature can more accurately reflect the actual operation of the power distribution network and is more representative, which helps to realize more accurate power distribution network fault warning.

[0097] In one of the embodiments, the power distribution network fault warning method in the foregoing embodiments can further include: determining a preliminary analysis model from a plurality of preset basic analysis models according to the first fault feature; determining a fault type corresponding to the first fault feature; and optimizing the preliminary analysis model based on the fault type and corresponding simulation analysis to obtain an analysis model.

[0098] Exemplarily, a plurality of basic analysis models can be preset, which can be existing or self-defined artificial intelligence models, and then a suitable basic analysis model is selected from the plurality of basic analysis models as the preliminary analysis model according to the first fault feature. The selection can be manual selection or automatic selection by setting selection conditions, for example, the selection can be made according to the calculation amount and specific calculation task type required by the first fault feature.

[0099] Exemplarily, after the preliminary analysis model is determined, the fault type corresponding to the first fault feature is determined, that is, the fault type to be analyzed by the model is determined, and then the preliminary analysis model can be optimized accordingly. For example, data corresponding to the fault type can be determined from the historical data of the power distribution network and used for simulation analysis, and then the simulation analysis result can be used to optimize the preliminary analysis model to obtain the analysis model.

[0100] In the embodiment, the preliminary analysis model is determined, and the preliminary analysis model is optimized from the perspective of the fault type to obtain the analysis model, which makes the analysis of the analysis model on the first fault feature more accurate, that is, more accurate first fault information is obtained.

[0101] In one of the embodiments, the real-time data in the foregoing embodiments can include: current, voltage, device and line temperature, environmental humidity, power usage, circuit switch state, transformer operating state in the circuit;

[0102] The power distribution network fault early warning method in the foregoing embodiments can further include: pre-processing the real-time data to improve data quality; the pre-processing includes at least one of the following: cleaning, removing abnormal data, and filling missing values.

[0103] In this embodiment, since the real-time data can include multiple types of currents, voltages, and the like in the circuit, this helps the real-time data to more comprehensively and accurately reflect the real situation of the power distribution network; since the real-time data is pre-processed by cleaning, removing abnormal data, filling missing values, and the like, this can improve the data quality, facilitate the subsequent processing of the real-time data, and also helps the real-time data to more comprehensively and accurately reflect the real situation of the power distribution network.

[0104] In one embodiment, as shown in FIG. 1, a power distribution network fault early warning system is provided, which includes a simulation data acquisition module, a data processing and analysis module, a fault feature extraction module, a pre-warning model construction module, a pre-warning module, and a data recording module. Specifically as follows: Figure 4 Regarding the simulation data acquisition module:

[0105] The module acquires the data of voltage, current, frequency, and power factor of each node of the power distribution network in real time through sensors and smart meter devices. The measurement devices used in the simulation data acquisition module are provided with two sets, and data transmission is performed through cross operation. The simulation data acquisition module includes a sensor module, a smart meter module, and a data acquisition device module. The sensor module is used to monitor the current, voltage, equipment and line temperature, and environmental humidity in the circuit. The smart meter module is used to monitor the use of electric energy, the switching state of the circuit, and the running state of the transformer. The data acquisition device module includes a data collector and a data transmitter. The data collector is responsible for collecting the data acquired by the sensor module and the smart meter module, and the data transmitter is responsible for transmitting the collected data to the data processing and analysis module. The data collected by each module in the simulation data acquisition module can better analyze the related problems in the power distribution network and improve the accuracy of the results. Specifically, the simulation data acquisition module collects data through various devices, and each type of device is provided with two sets. The two sets of devices are alternately operated to transmit data. By comparing the data measured by the two sets of devices, it can be determined whether the device is faulty, thereby preventing unnecessary emergency measures caused by device failure.

[0106] Regarding the data processing and analysis module:

[0107]

[0108] ​The module performs preprocessing operations such as cleaning, denoising, and correction on the collected data to improve data quality. Exemplarily, the data processing and analysis module can include a data cleaning module, a feature extraction module, a data analysis module, a fault diagnosis module, a prediction module, and a visualization module. Among them, the data cleaning module is responsible for cleaning the collected raw data, removing abnormal data, and filling missing values to ensure the quality and accuracy of the data; the feature extraction module extracts features reflecting the system state and characteristics from the data based on the preprocessing of the data cleaning module, so that the extracted data is representative, and the subsequent secondary processing result is more typical, improving the accuracy of the system in fault prediction; the data analysis module analyzes the data after feature extraction based on the data extracted by the feature extraction data module, identifies potential fault patterns, rules, and abnormal situations; the fault diagnosis module diagnoses and locates the fault based on the data analysis result of the data analysis module, identifies the fault type and location in the power distribution network; the prediction module performs fault prediction and trend prediction based on historical data and analysis results; the visualization module is responsible for presenting the results of data processing and analysis in a visual manner, thereby helping users understand the data and discover potential patterns. Through data preprocessing by the data processing and analysis module, the quality and effectiveness of the data are improved, and the interference of useless data is reduced. At the same time, the processed data is subjected to initial fault diagnosis, and the output is visualized.

[0109] Regarding the fault feature extraction module:

[0110] Based on the stored data, the fault feature extraction module extracts fault features using data mining and machine learning techniques, making the extracted fault features representative. The fault feature extraction module algorithm is as follows:

[0111] Suppose a set of monitoring data x1, x1...xn, calculate the mean μ and standard deviation σ as features.

[0112] The calculation formula of the mean is: ;

[0113] The calculation formula of the standard deviation is: ;

[0114] The fault feature extraction module includes a power parameter extraction module, a topology structure feature extraction module, a time sequence feature extraction module, a fault signal feature extraction module, a statistical feature extraction module, and a multi-modal feature fusion module. Among them, the power parameter extraction module is responsible for extracting features related to power parameters. A possible method for extracting features related to power parameters is as follows:

[0115] For any signal x(t), the decomposition process is as follows: determine all local extreme points ni (i=1,2,…,M);calculate the average value m of all adjacent local extreme points i and envelope value a i ;

[0116] , i=1,2,…,M-1 (1)

[0117] , i=1,2,…,M-1 (2)

[0118] The calculated average value m i and envelope value a i are compared with the historical data to determine whether there is a data fault.

[0119] The topology feature extraction module is responsible for extracting the topology features of the power distribution network; the time sequence feature extraction module is responsible for extracting the features of the time sequence data; the fault signal feature extraction module is responsible for extracting the features related to the fault signal; the statistical feature extraction module is responsible for extracting the statistical features of the data; and the multi-modal feature fusion module is responsible for fusing different types of features. The further extraction of the fault feature extraction module on various types of data makes the data more helpful for maintenance personnel, facilitating subsequent maintenance.

[0120] Regarding the early warning model construction module:

[0121] This module is used to establish an early warning model, compare and analyze the extracted fault features with historical data, and identify potential fault patterns. The early warning model construction module includes a model selection module, a model training module, a model evaluation module, a model optimization module, and a real-time monitoring module.

[0122] The model selection module selects a suitable prediction model based on the data extracted by the fault feature extraction module, and the development trend of the power distribution network under the data can be more intuitively perceived through the prediction model; the model training module is responsible for training the selected model using historical data, so that the model can accurately predict the possible future fault conditions; the model evaluation module is responsible for evaluating the performance of the trained model, verifying the effectiveness and reliability of the model; the model optimization module is responsible for optimizing and adjusting the parameters of the model according to the evaluation results, in order to improve the prediction performance and generalization ability of the model. The real-time monitoring module includes a data adjustment module, a secondary simulation module and a data comparison module; the data adjustment module is responsible for real-time monitoring of the power distribution network operation state and fault warning, timely updating the model and adjusting the warning strategy; the secondary simulation module is based on the prediction model selected by the model selection module, and combines another group of data for secondary simulation, thereby improving the accuracy of the results and preventing unnecessary emergency measures caused by equipment failure; the data comparison module compares the data provided by the model selection module based on the secondary simulation of the secondary simulation module, and the same result is obtained. The next step is performed.

[0123] Specifically, the early warning model construction module will first select a suitable prediction model in combination with the fault feature extraction module extracting data, and the development trend can be more intuitively observed through the prediction model, and technical support is provided for subsequent review. After selecting a suitable prediction model, the prediction model is trained, so that the prediction model can analyze the extracted data, and the model evaluation module will evaluate the performance of the prediction model, verify the effectiveness and reliability of the model, and finally the model optimization module optimizes and adjusts the parameters of the model to improve the prediction performance and generalization ability of the model. While optimizing and adjusting the parameters of the model, another group of data can be analyzed to obtain an analysis result, and the analysis result is compared with the analysis result obtained by using the prediction model. If the results are consistent, the next step is performed, and if the results are inconsistent, the simulation analysis of two new groups of data is performed again. If the results of the two new groups of data are the same as those of the previous two groups of data, there is a problem of equipment failure.

[0124] A possible specific method for analyzing another group of data is given below:

[0125] The mean value is calculated according to the following formula:

[0126] The variance is calculated according to the following formula:

[0127] Where x represents the fault feature of the power distribution network;

[0128] represents the mean value of the power grid fault feature;

[0129] representing the variance of the power distribution network fault feature;

[0130] The correlation coefficient between the power grid fault feature and the historical data is calculated according to the following formula:

[0131] wherein,

[0132] r represents the correlation coefficient;

[0133] y represents a data point in the historical data;

[0134] representing the mean of a certain data point in the power distribution network historical data.

[0135] The deviation degree of a certain specific value from the overall mean can be calculated by the following formula:

[0136] wherein, Z represents the deviation degree. The threshold range of Z can be set, and the value exceeding the threshold is a fault.

[0137] Regarding the early warning module: the module automatically triggers an early warning signal when the fault risk is detected based on the early warning model construction module, reminding the staff to take corresponding measures, and marking the data that is abnormal but not recognized as a fault pattern, and uploading it to manual processing. The early warning module includes an alarm module, an information matching module and a data output module. Among them, the alarm module releases the corresponding early warning signal according to the severity based on the model built by the early warning model construction module; the information matching module matches the most suitable maintenance personnel based on the early warning signal released by the alarm module combined with the fault information of the power distribution network; the data output module gives the maintenance personnel corresponding maintenance data, methods and real-time data based on the matching of the maintenance personnel by the information matching module.

[0138] Specifically, the early warning module will release different early warning signals according to the model results built by the early warning model construction module combined with the severity, and will also match the most suitable maintenance personnel according to the information and skills of the current on-duty personnel, so that the maintenance personnel can specialize in a certain technical field, reducing unnecessary waste of energy, and will also provide the maintenance personnel with corresponding maintenance data, schemes and real-time data, and record the actual operation mode of the maintenance personnel, filter useful information, for the next time. The scheme is provided.

[0139] Regarding the data recording module: this module records and stores the corresponding data after the staff completes the processing of the fault risk, and separately stores the marked data, which is convenient for the next time. The data recording module includes a data storage module, which is responsible for storing the collected historical data for subsequent analysis and processing.

[0140] In this embodiment, by establishing the fault feature extraction module, the fault feature extraction module can extract fault features based on the stored data, and the fault feature extraction module will select the corresponding feature extraction algorithm according to different types of faults, and determine the threshold of the fault feature, so that the extracted data is more representative, thereby facilitating the maintenance of the staff; by establishing the early warning model construction module, the extracted fault features are compared and analyzed with historical data to identify potential fault patterns, and the system will also perform data simulation analysis again according to real-time data. The same result of the two analyses will release a warning signal, and the type of the warning signal release is also associated with the severity of the simulation result, so that emergency measures can be started in time when an emergency occurs; by establishing the simulation data acquisition module, the related measuring devices used in the simulation data acquisition module are provided with two sets, which deliver data by cross operation, and the comparison of the data results of the two groups can effectively prevent the phenomenon of data anomaly caused by measuring device failure, improve the accuracy of the system in judging the related problems of the power distribution network, and reduce the error of manual measurement and improve the accuracy of the data through automatic measurement of the related measuring devices.

[0141] It should be understood that, although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or steps or stages in other steps.

[0142] Based on the same inventive concept, the embodiments of the present application also provide a power distribution network fault warning device for implementing the power distribution network fault warning method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more power distribution network fault warning device embodiments provided below can refer to the limitations of the power distribution network fault warning method in the above text, which will not be repeated here.

[0143] In one exemplary embodiment, as shown in Figure 5 A power distribution network fault warning device 500 is provided, comprising:

[0144] The feature acquisition module 501 is configured to obtain two sets of real-time data corresponding to the two sets of equipment based on the collection and cross-transmission of real-time information of the power distribution network by the two sets of equipment; extract fault features of the power distribution network from the two sets of real-time data respectively to obtain first fault features and second fault features; the fault features at least include one of the following: power parameter features, topology structure features, time series data features, fault signal features, and data statistical features;

[0145] The first analysis module 502 is configured to input the first fault features into a preset analysis model; the analysis model is configured to analyze the first fault features and output corresponding first fault information; the analysis model is obtained through training based on historical data of the power distribution network;

[0146] The second analysis module 503 is configured to obtain second fault information based on simulation analysis of the second fault features;

[0147] The fault warning module 504 is configured to determine the consistency degree of the first fault information and the second fault information; in the case where the consistency degree reaches a preset standard, determine the fault information of the power distribution network and output a corresponding level of warning signal.

[0148] In one of the embodiments, the second analysis module 503 is further configured to determine corresponding feature point values and feature overall mean values according to the second fault features; determine the deviation degree of the feature point values compared with the feature overall mean values; and determine the second fault information according to the deviation degree.

[0149] In one of the embodiments, the second analysis module 503 is further configured to determine the correlation coefficient of the second fault features and the historical data according to the feature point values; and determine the deviation degree of the feature point values in the second fault features compared with the feature overall mean values according to the feature point values, the historical data and the correlation coefficient.

[0150] In one of the embodiments, the feature acquisition module 501 is further configured to extract the power parameter features in the following manner: obtain power original signals of the power distribution network; determine at least one local extreme point of the original signals; determine the average value and the envelope value of adjacent local extreme points; and determine the power parameter features according to the average value and the envelope value.

[0151] In one of the embodiments, the first analysis module 502 is further configured to determine a preliminary analysis model from a plurality of preset basic analysis models according to the first fault features; determine the fault type corresponding to the first fault features; and optimize the preliminary analysis model based on the fault type and corresponding simulation simulation to obtain the analysis model.

[0152] In one of the embodiments, the feature acquisition module 501 is further configured to acquire real-time data including: current in the circuit, voltage, temperature of the device and the circuit, environmental humidity, usage of electric energy, switching state of the circuit, operating state of the transformer; and pre-process the real-time data to improve data quality; the pre-processing includes at least one of the following: cleaning, removing abnormal data, filling missing values.

[0153] The modules in the power distribution network fault early warning device described above can be implemented wholly or partially by software, hardware, or a combination thereof. The modules described above can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in a computer device in software form, so as to be called and executed by a processor to perform operations corresponding to the modules.

[0154] In one exemplary embodiment, a power distribution network fault early warning device is provided, which can be a terminal, and an internal structure diagram thereof can be as shown in FIG. Figure 6 The power distribution network fault early warning device includes a processor, a memory, an input / output interface, a communication interface, and an early warning signal unit. The processor, the memory, and the input / output interface are connected through a system bus, and the communication interface and the early warning signal unit are connected to the system bus through the input / output interface. The processor of the power distribution network fault early warning device is configured to provide computing and control capabilities. The memory of the power distribution network fault early warning device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The input / output interface of the power distribution network fault early warning device is configured to exchange information between the processor and external devices. The communication interface of the power distribution network fault early warning device is configured to perform wired or wireless communication with external terminals. The wireless communication can be achieved through WIFI, mobile cellular network, near field communication (NFC), or other technologies. The computer program is executed by the processor to implement a power distribution network fault early warning method. The early warning signal unit of the power distribution network fault early warning device is configured to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen.

[0155] Those skilled in the art can understand that Figure 6 The structure shown in FIG.

[0156] In an example embodiment, there is provided a power distribution network fault early warning device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps of the power distribution network fault early warning method in the above embodiments when executing the computer program.

[0157] In an example embodiment, there is provided a computer readable storage medium having stored thereon a computer program, the computer program implementing the steps of the power distribution network fault early warning method in the above embodiments when executed by a processor.

[0158] In an example embodiment, there is provided a computer program product comprising a computer program, the computer program implementing the steps of the power distribution network fault early warning method in the above embodiments when executed by a processor.

[0159] 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. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0160] The technical features of the above embodiments can be combined in any manner. To make the description concise, all possible combinations of the technical features in the above embodiments are not described, but as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present application.

[0161] The above-described embodiments are merely illustrative of several embodiments of the present application, which are described in more detail and in a specific manner, but should not be construed as limiting the scope of the patent of the present application. It should be noted that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A power distribution network fault early warning method, characterized in that, The method comprises: Based on the collection and cross-transmission of real-time information of the power distribution network by two sets of equipment, two groups of real-time data corresponding to the two sets of equipment are obtained; Respectively extracting fault features of the power distribution network from the two groups of real-time data, obtaining first fault features and second fault features; the fault features at least include one of the following: power parameter features, topology structure features, time series data features, fault signal features, data statistical features; Input the first fault features into a preset analysis model; the analysis model is used for analyzing the first fault features and outputting corresponding first fault information; the analysis model is obtained by training based on historical data of the power distribution network; Based on the simulation analysis of the second fault features, the second fault information is obtained; Determine the consistency degree of the first fault information and the second fault information; In the case where the consistency degree reaches a preset standard, the fault information of the power distribution network is determined and a corresponding level of early warning signal is outputted; The simulation analysis based on the second fault features to obtain the second fault information comprises: According to the second fault features, determine the corresponding feature point value and feature overall mean value; Determine the deviation degree of the feature point value compared with the feature overall mean value; According to the deviation degree, determine the second fault information.

2. The method of claim 1, wherein, The determination of the deviation degree of the feature point value compared with the feature overall mean value comprises: According to the feature point value, determine the correlation coefficient of the second fault features and the historical data; According to the feature point value, the historical data and the correlation coefficient, determine the deviation degree of the feature point value in the second fault features compared with the feature overall mean value.

3. The method of claim 1, wherein, The power parameter features are extracted in the following way: Obtain the power original signal of the power distribution network; Determine at least one local extreme point of the original signal; Determine the average value and envelope value of adjacent local extreme points; According to the average value and envelope value, determine the power parameter features.

4. The method of claim 1, wherein, The method further comprises: According to the first fault features, determine a preliminary analysis model from a plurality of preset basic analysis models; Determine the fault type corresponding to the first fault features; Based on the fault type and corresponding simulation, optimize the preliminary analysis model to obtain the analysis model.

5. The method of claim 1, wherein: The real-time data includes: current, voltage, equipment and line temperature, environmental humidity, power usage, circuit switch state, transformer operating state; The method further comprises: preprocessing the real-time data to improve data quality; the preprocessing includes at least one of the following: cleaning, removing abnormal data, filling missing values.

6. A power distribution network fault early warning device, characterized by, The device comprises: The feature acquisition module is configured to obtain two sets of real-time data corresponding to the two sets of equipment based on the collection and cross-transmission of real-time information of the power distribution network by the two sets of equipment; extract fault features of the power distribution network from the two sets of real-time data respectively to obtain first fault features and second fault features; the fault features at least include one of the following: power parameter features, topology structure features, time series data features, fault signal features, and data statistical features; The first analysis module is configured to input the first fault features into a preset analysis model; the analysis model is configured to analyze the first fault features and output corresponding first fault information; the analysis model is obtained by training based on historical data of the power distribution network; The second analysis module is configured to obtain second fault information based on simulation analysis of the second fault features; The fault warning module is configured to determine the consistency degree of the first fault information and the second fault information; in the case that the consistency degree reaches a preset standard, determine the fault information of the power distribution network and output a corresponding level of warning signal; The second analysis module is further configured to determine corresponding feature point values and feature overall mean values according to the second fault features; determine the deviation degree of the feature point values compared with the feature overall mean values; and determine the second fault information according to the deviation degree.

7. The apparatus of claim 6, wherein, The second analysis module is further configured to determine the correlation coefficient of the second fault features and the historical data according to the feature point values; and determine the deviation degree of the feature point values compared with the feature overall mean values in the second fault features according to the feature point values, the historical data, and the correlation coefficient.

8. A power distribution network fault warning device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the steps of the method of any one of claims 1 to 5.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 5.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 5.

Images