Intelligent Network-Based Low-Voltage Power Grid Residual Current Monitoring and Early Warning System and Method

Abstract

The residual current monitoring and early warning system and method for low-voltage power grids based on intelligent networks belong to the field of safety monitoring. The method includes installing residual current sensors to monitor current changes and performing intelligent analysis on current fluctuations; establishing a machine learning model based on historical data to train the normal fluctuation characteristics of residual current; using a time series anomaly detection algorithm to judge sudden changes in current and regularly optimizing the model with new data; dividing the residual current fluctuations into levels, and when the current deviation reaches the threshold, the system automatically issues corresponding-level notifications according to the early warning level, automatically judging the location of the fault node through the geographical location of the sensor and the network topology structure, and combining the power grid topology data to judge the fault section; after the early warning is triggered, the system conducts statistical analysis on abnormal current data, and according to the real-time current data and the fault probability, the system automatically optimizes the acquisition frequency and the early warning threshold. The present invention significantly improves the safety and response speed of the power grid through monitoring and intelligent early warning.

Description

Technical Field

[0001] The present invention belongs to the field of safety monitoring, and more specifically, particularly relates to a residual current monitoring and early warning system and method for low-voltage power grids based on an intelligent network. Background Art

[0002] In a low-voltage power grid, with the increase in the number of monitoring devices and sensors, the amount of residual current data collected in real time is extremely large. Especially in the high-frequency acquisition mode, the pressure of data storage, transmission, and calculation increases significantly, which may lead to system delays and affect the real-time nature of early warnings. The centralized data processing method is difficult to efficiently process all data during high-fault periods, easily causing network congestion and affecting the operation efficiency of the system. The reasons for abnormal current fluctuations in the power grid are diverse, such as electrical appliance aging, load fluctuations, environmental factors, etc., which easily lead to false alarms and missed alarms. When the current intelligent early warning system performs abnormal detection, it may not be able to effectively distinguish minor fluctuations from real faults, resulting in frequent false alarms or ignoring potential risks. Different fault types (such as short circuits, leakage, etc.) exhibit similar residual current characteristics, and conventional algorithms are difficult to accurately distinguish, affecting the accuracy of fault determination.

[0003] The operating environment of a low-voltage power grid is complex and changeable, and traditional fixed-threshold monitoring and standardized algorithm models are often difficult to adapt to changes in different regions, loads, and environmental conditions. For example, current fluctuations under bad weather may be similar to those of equipment failures, and existing algorithms have poor adaptability and stability in extreme cases. Due to the large differences in the operating characteristics of different power grid regions, standardized algorithms are difficult to take into account all situations and lack targeted fault analysis, resulting in uneven early warning effects. The distribution range of low-voltage power grids is wide, especially in remote or complex terrain areas, and real-time data transmission may encounter problems such as network delays and signal attenuation, affecting the immediacy of early warnings. The delay in data transmission may cause fault information not to be transmitted to the operation and maintenance center in a timely manner, increasing the difficulty of hidden danger identification and affecting the rapid response to emergency faults. Summary of the Invention

[0004] In view of the above or existing problems of the residual current monitoring and early warning system and method for low-voltage power grids based on an intelligent network, the present invention is proposed.

[0005] To solve the above technical problems, the present invention provides the following technical solutions:

[0006] An embodiment of the present invention provides a residual current monitoring and early warning method for a low-voltage power grid based on an intelligent network, including: installing a residual current sensor to monitor current changes and performing intelligent analysis on current fluctuations;

[0007] Build a machine learning model based on historical data to train the normal fluctuation characteristics of residual current, including: build an LSTM model based on historical data, and train the normal fluctuation characteristics of residual current through multi-dimensional feature extraction and feature engineering of current time series data. Feature engineering includes time domain, frequency domain and environmental factors; combine the LSTM model deep learning algorithm to identify the normal current mode, and continuously update the model during system operation;

[0008] Through the time series anomaly detection algorithm, judge the sudden change of current, set a threshold according to the normal fluctuation range in historical data. If an abnormal fluctuation of current exceeding the threshold is detected, immediately generate a warning signal, and regularly optimize the model with new data to improve the recognition rate of abnormal current in different scenarios;

[0009] Divide the residual current fluctuation into levels. When the current deviation reaches the threshold, the system automatically sends corresponding level notifications according to the warning level, automatically judge the location of the fault node through the geographical location of the sensor and the network topology structure, and combine the power grid topology data to judge the fault section;

[0010] After the warning is triggered, the system statistically analyzes the abnormal current data and automatically generates a report. According to the real-time current data and the fault probability, the system automatically optimizes the acquisition frequency and the warning threshold.

[0011] As a preferred scheme of the method for monitoring and warning residual current in a low-voltage power grid based on an intelligent network according to the present invention, wherein: the steps of the LSTM model deep learning algorithm are:

[0012] Initialize the LSTM network, set the number of hidden layers L and the number of hidden units H, and adjust the network weights through the backpropagation algorithm:

[0013]

[0014] where η is the learning rate, is the gradient of the loss function with respect to the weight, and continue to iterate until the validation set error converges.

[0015] As a preferred scheme of the method for monitoring and warning residual current in a low-voltage power grid based on an intelligent network according to the present invention, wherein: through the time series anomaly detection algorithm, judge the sudden change of current. If an abnormal fluctuation exceeding the set threshold is detected, immediately generate a warning signal, and regularly optimize the model with new data to improve the recognition rate of abnormal current in different scenarios, including:

[0016] Set a dynamic threshold A according to the normal fluctuation range in historical data to judge whether there is an abnormal fluctuation. Assume that in the normal situation, the mean value of current fluctuation is μ and the standard deviation is σ, and set the threshold A as:

[0017]

[0018] Among them, k is an adjustment parameter. When the current fluctuation value exceeds A, it can be determined as abnormal.

[0019] Assume that the actual value of the current at time t is x t , and the predicted value is x t1 ;

[0020] The residual calculation formula is:

[0021]

[0022] If the residual e t exceeds the threshold A, that is: ∣e t ∣ > A, then it is determined as abnormal fluctuation and a warning signal is generated;

[0023] Continuously obtain current data from the monitoring device, including normal and abnormal current fluctuation records. The data covers various device operation modes, environmental conditions, and load levels. Mark the new data into two categories: normal and abnormal. For known abnormal situations, manual annotation or external fault detection records are used as references.

[0024] As a preferred solution of the low-voltage power grid residual current monitoring and warning method based on the intelligent network described in the present invention, among them: divide the residual current fluctuation into levels. When the current deviation reaches the threshold, the system automatically issues corresponding-level notifications according to the warning level, including:

[0025] According to historical data analysis and scenario setting, divide the current fluctuation into multiple levels including normal, slightly abnormal, moderately abnormal, and severely abnormal. Each level defines different threshold ranges, representing different degrees of risk;

[0026] If the current deviation is within the range of ±1σ of the average value μ, it is normal fluctuation;

[0027] If the current deviation is between ±1σ and ±2σ of the average value μ, it indicates a slight fluctuation and is slightly abnormal;

[0028] If the current deviation is between ±2σ and ±3σ of the average value μ, it is moderately abnormal;

[0029] If the current deviation exceeds ±3σ of the average value μ, there is a serious safety hazard and it is severely abnormal;

[0030] Among them, σ is the standard deviation;

[0031] When the current fluctuation value exceeds the threshold of each level, the system automatically judges the risk level of the current fluctuation.

[0032] As a preferred solution of the method for monitoring and warning of residual current in a low-voltage power grid based on an intelligent network according to the present invention, wherein: based on the geographical location of the sensors and the network topology, the position of the fault node is automatically judged, and the fault section is judged in combination with the power grid topology data, including:

[0033] After detecting an anomaly, the system locates the fault node by using the geographical location of the sensors and the network topology through the following steps:

[0034] Combined with the topology model, the system searches for the sensors that trigger the anomaly signal and their adjacent nodes, and preliminarily determines the source location of the anomaly; based on the geographical coordinates and node relationships, the system identifies the location of the sensor with the most concentrated anomaly signal and determines the fault node;

[0035] After determining the fault node, the system uses the topology model to check the adjacent power lines and branch paths to judge whether the fault propagates along the power line. Whether the fault propagates along the power line depends on the current fluctuation on the adjacent line, the propagation characteristics of the fault waveform along the time axis, and the physical characteristics of the power line. The propagation model is based on the following formula:

[0036]

[0037] Wherein, I (u,v) is the real-time current value of line (u, v), is the normal current value of line (u, v);

[0038] If ΔI (u,v) > Threshold, it means that the fault has propagated to this line.

[0039] As a preferred solution of the method for monitoring and warning of residual current in a low-voltage power grid based on an intelligent network according to the present invention, wherein: after the warning is triggered, the system statistically analyzes the abnormal current data and automatically generates a report. According to the real-time current data and the fault probability, the system automatically optimizes the acquisition frequency and the warning threshold, including:

[0040] Perform multi-dimensional statistics on the abnormal data, including: calculating the amplitude of the current deviation from the normal value to judge the severity of the anomaly; analyzing the frequency of abnormal fluctuations occurring within a unit time to evaluate the stability of the area or equipment; recording the duration of a single abnormal fluctuation to identify the difference between short-term fluctuations and continuous anomalies;

[0041] Identify potential patterns of abnormal data through machine learning and data mining techniques, and analyze the relationship between specific fault types and specific current fluctuation characteristics;

[0042] Based on historical data and real-time abnormal data, the system calculates the occurrence probability of the fault. After the warning is triggered, the system analyzes whether it is a high-risk period or a node with a high fault probability;

[0043] Evaluate whether the current time is a high-risk period according to the time period when historical faults occurred, and define the fault frequency function:

[0044]

[0045] where N t is the number of faults within the time period t, and T is the total length of time;

[0046] If the current f(t) > threshold, it is determined as a high-risk period;

[0047] Analyze the fault risk of the current device or area through the fault probability model:

[0048] ;

[0049] If P(fault|Ft) > threshold, the system determines it as a high fault probability node;

[0050] If the system determines that the current is in a high fault probability stage, the acquisition frequency is automatically increased; if the power grid is in a stable state, the system reduces the acquisition frequency.

[0051] A low-voltage power grid residual current monitoring and early warning system based on an intelligent network, including: a current monitoring module for installing a residual current sensor to monitor current changes and perform intelligent analysis on current fluctuations;

[0052] A fluctuation feature training module for establishing a machine learning model based on historical data and training the normal fluctuation features of residual current, including: establishing an LSTM model based on historical data, training the normal fluctuation features of residual current through multi-dimensional feature extraction and feature engineering of current time series data, and feature engineering includes time domain, frequency domain and environmental factors; combining the LSTM model deep learning algorithm to identify the normal current mode and continuously update the model during system operation;

[0053] A detection and judgment module for judging the sudden change of current through a time series anomaly detection algorithm, setting a threshold according to the normal fluctuation range in historical data, and immediately generating a warning signal if an abnormal fluctuation exceeding the set threshold is detected, and regularly optimizing the model with new data to improve the recognition rate of abnormal current in different scenarios;

[0054] A fault early warning module for classifying the residual current fluctuations, and when the current deviation reaches the threshold, the system automatically sends corresponding level notifications according to the warning level, automatically determines the location of the fault node through the geographical location of the sensor and the network topology structure, and combines the power grid topology data to judge the fault section;

[0055] An optimization analysis module, which is used to perform statistical analysis on abnormal current data by the system after the warning is triggered, automatically generate reports, and automatically optimize the acquisition frequency and warning threshold according to real-time current data and failure probability.

[0056] A computing device, the computing device comprising:

[0057] At least one processor, a memory, and an input / output unit;

[0058] Wherein, the memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the steps of the method for monitoring and warning residual current in a low-voltage power grid based on an intelligent network.

[0059] A computer-readable storage medium, which includes instructions that, when running on a computer, cause the computer to execute the steps of the method for monitoring and warning residual current in a low-voltage power grid based on an intelligent network.

[0060] The beneficial effects of the present invention are as follows: Through real-time monitoring and intelligent warning, the system of the present invention can quickly identify abnormal residual current fluctuations, send warning signals in a timely manner, help operation and maintenance personnel discover and locate potential faults in advance, significantly improve the safety and response speed of the power grid, and reduce the accident risk. The present invention adopts advanced algorithms such as machine learning and time series analysis. Through in-depth learning and anomaly detection of historical data, it can accurately identify the difference between normal fluctuations and faults, reducing the possibility of false alarms and missed alarms. Especially in a complex power grid environment, the system can adapt to different loads and environmental conditions to achieve more reliable fault determination. Description of the Drawings

[0061] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for description in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0062] Figure 1 It is a flowchart of a method for monitoring and warning residual current in a low-voltage power grid based on an intelligent network provided by an embodiment of the present invention.

[0063] Figure 2 It is a schematic structural diagram of a system for monitoring and warning residual current in a low-voltage power grid based on an intelligent network provided by an embodiment of the present invention.

[0064] Figure 3 It schematically shows a schematic structural diagram of a medium of an embodiment of the present invention.

[0065] Figure 4Schematically shows a schematic structural diagram of a computing device according to an embodiment of the present invention.

[0066] In the drawings, the same or corresponding reference numerals indicate the same or corresponding parts. Detailed implementation manners

[0067] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will describe the detailed implementation manners of the present invention in conjunction with the drawings of the specification.

[0068] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0069] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it an individual or alternative embodiment that is mutually exclusive with other embodiments.

[0070] Embodiment 1

[0071] The following refers to Figure 1 , Figure 1 is a flowchart of a method for monitoring and warning residual current in a low-voltage power grid based on an intelligent network provided by an embodiment of the present invention. It should be noted that the implementation manner of the present invention can be applied to any applicable scenario.

[0072] Figure 1 The flow of the method for monitoring and warning residual current in a low-voltage power grid based on an intelligent network provided by an embodiment of the present invention shown in

[0073] S1: Establish a machine learning model based on historical data to train the normal fluctuation characteristics of the residual current.

[0074] Preferably, an LSTM model is established based on historical data. By extracting multi-dimensional features and performing feature engineering on current time-series data, such as time domain, frequency domain, and environmental factors, the normal fluctuation characteristics of the residual current are trained. The normal current pattern is identified by combining the deep learning algorithm of the LSTM model, and the model is continuously updated during the operation of the system;

[0075] Initialize the LSTM network, set the number of hidden layers L and the number of hidden units H, and adjust the network weights through the backpropagation algorithm:

[0076]

[0077] where η is the learning rate, is the gradient of the loss function with respect to the weights; continue the iteration until the validation set error converges.

[0078] Furthermore, calculate the average current and standard deviation within a time window, record the central tendency of its fluctuations, perform Fourier transform or wavelet transform on the current data to extract its frequency domain features. For example, analyze the frequency distribution through discrete Fourier transform (DFT) to observe whether there are specific frequency components in the current fluctuations to judge the fault mode; introduce environmental factors (such as temperature, humidity, etc.) as additional features of the current fluctuations. If the current is significantly affected by environmental factors, adding these feature variables to the LSTM model helps the model accurately identify the normal mode.

[0079] Use a multi-layer LSTM structure. The input is multi-dimensional time series features, including the time domain features, frequency domain features of the current, and environmental factor features. The shape of the model input is a three-dimensional tensor (number of samples, number of time steps, number of features). For example, if each sample contains 60 time steps and each step contains 10 features, the input is (number of samples, 60, 10); use historical data to train the LSTM model, set appropriate loss functions and optimization algorithms, and through multiple iterations, identify the normal operating rules of the current. Each batch of training data allows the model to learn the short-term and long-term dependencies in the time series data, so as to better capture the normal fluctuation features.

[0080] S2: Through the time series anomaly detection algorithm, judge the sudden change of the current. If an abnormal fluctuation exceeding the set threshold is detected, immediately generate a warning signal, and regularly optimize the model with new data to improve the model's recognition rate of abnormal current under different scenarios.

[0081] Preferably, set a dynamic threshold A according to the normal fluctuation range in the historical data to judge whether there is an abnormal fluctuation. Assume that under normal circumstances, the mean of the current fluctuation is μ and the standard deviation is σ, and set the threshold A as:

[0082]

[0083] where k is an adjustment parameter. When the current fluctuation value exceeds A, it can be determined as abnormal;

[0084] Assume that the actual value of the current at time t is x t , and the predicted value is x t1 ;

[0085] The residual calculation formula is:

[0086]

[0087] If the residual e t exceeds the threshold T, that is: |e tIf ∣>T, it is determined as an abnormal fluctuation and a warning signal is generated;

[0088] Continuously obtain current data from the monitoring device, including records of normal and abnormal current fluctuations. The data covers various device operation modes, environmental conditions, and load levels. Mark the new data into two categories: normal and abnormal. For known abnormal situations, manual annotation or external fault detection records are used as references.

[0089] Furthermore, assume that the mean value of normal current fluctuations μ = 5A and the standard deviation σ = 0.5 A.

[0090] Adopt the dynamic threshold formula , for example, set k = 3, then T = 5 + 3 ⋅ 0.5 = 6.5A. That is to say, when the real-time current fluctuation exceeds 6.5A, the system will regard it as abnormal;

[0091] A smaller k value is sensitive to small fluctuations, while a larger k value will only trigger a warning when there are large fluctuations. During the test phase, the value of k is usually adjusted repeatedly through actual operation data and expert opinions to find the optimal value suitable for the grid stability requirements; The system collects the current value x at the current time t from the sensor t , as the input data;

[0092] Assume that at a certain moment t, the actual current value x t = 6.8A, use the prediction model to calculate the predicted value x t1 ,

[0093] Through the LSTM model or another time series prediction model, the system predicts the current value x at time t t1 , that is, the expected value of the current under normal circumstances. Assume that at this time the model predicted value x t1 = 5.9 A, the system calculates the residual e at the current time t t , the formula is: e t = x t - x t1 , substituting the data gives et = 6.8 - 5.9 = 0.9A;

[0094] When ∣e t ∣>T, that is, 0.9>6.5 does not hold, so it does not exceed the threshold. At this time, the system will not generate a warning; If during subsequent monitoring, it is found that ∣e t ∣ is greater than T, then the system determines it as an abnormal fluctuation and immediately issues a warning signal.

[0095] S3: Classify the remaining current fluctuations. When the current deviation reaches the threshold, the system automatically sends notifications at the corresponding warning levels according to the warning levels. Through the geographical location of the sensor and the network topology structure, the position of the fault node is automatically judged, and the fault section is judged in combination with the grid topology data.

[0096] Preferably, according to historical data analysis and scenario setting, the current fluctuation is divided into multiple levels such as normal, slightly abnormal, moderately abnormal, and severely abnormal, and different threshold ranges are defined for each level, representing different degrees of risk;

[0097] If the current deviation is within the range of ±1σ of the average value μ, it is a normal fluctuation;

[0098] If the current deviation is between ±1σ and ±2σ of the average value μ, it indicates a slight fluctuation and is slightly abnormal;

[0099] If the current deviation is between ±2σ and ±3σ of the average value μ, it is moderately abnormal;

[0100] If the current deviation exceeds ±3σ of the average value μ, there is a serious potential safety hazard and it is severely abnormal;

[0101] When the current fluctuation value exceeds the threshold of each level, the system automatically determines the risk level of the current fluctuation.

[0102] Preferably, after detecting an abnormality, the system uses the geographical location and network topology of the sensor to locate the faulty node through the following steps:

[0103] Combined with the topology model, the system searches for the sensor that triggers the abnormal signal and its neighboring nodes, and preliminarily determines the source location of the abnormality; based on the geographical coordinates and node relationships, it identifies the location of the sensor where the abnormal signal is most concentrated and determines the faulty node;

[0104] After determining the faulty node, the system uses the topology model to check the adjacent power lines and branch paths to determine whether the fault propagates along the power line. Whether the fault propagates along the power line depends on the current fluctuation on the neighboring line, the propagation characteristics of the fault waveform along the time axis, and the physical characteristics of the power line. The propagation model is based on the following formula:

[0105]

[0106] where, I (u,v) is the real-time current value of the line (u, v), is the normal current value of the line (u, v);

[0107] If ΔI (u,v) > Threshold, it means that the fault has propagated to this line.

[0108] Furthermore, assume that xt = 6.2 A, and the deviation from the average value μ = 5 A is ∣xt - μ∣ = 1.2 A;

[0109] According to the deviation range, the current fluctuation is classified into the corresponding level:

[0110] If the current value is between [4.5, 5.5] A, it belongs to normal fluctuation and does not trigger an alarm;

[0111] If the current value is between [4, 4.5) A or (5.5, 6] A, it is determined as a minor anomaly;

[0112] If the current value is between [3.5, 4) A or (6, 6.5] A, it is determined as a moderate anomaly;

[0113] If the current value is less than 3.5 A or greater than 6.5 A, it is determined as a severe anomaly;

[0114] In this example, the current value x t = 6.2 A is between (6, 6.5] A, so the system determines that the current fluctuation is "moderate anomaly".

[0115] S4: After the alarm is triggered, the system statistically analyzes the abnormal current data and automatically generates a report. According to the real-time current data and the failure probability, the system automatically optimizes the acquisition frequency and the alarm threshold.

[0116] Preferably, multi-dimensional statistics are performed on the abnormal data, including: calculating the amplitude of the current deviation from the normal value to judge the severity of the anomaly; analyzing the frequency of abnormal fluctuations occurring within a unit time to evaluate the stability of this area or equipment; recording the duration of a single abnormal fluctuation to identify the difference between short-term fluctuations and continuous anomalies;

[0117] Identifying potential patterns of abnormal data through machine learning and data mining techniques, such as the relationship between specific fault types and specific current fluctuation characteristics;

[0118] Based on historical data and real-time abnormal data, the system calculates the occurrence probability of a fault. After the alarm is triggered, the system analyzes whether it is a high-risk period or a high-fault-probability node;

[0119] According to the time period when historical faults occurred, evaluate whether the current time is a high-risk period, and define the fault frequency function:

[0120]

[0121] where N t is the number of faults within the time period t, and T is the total time length;

[0122] If the current f(t) > threshold, it is determined as a high-risk period;

[0123] Analyze the fault risk of the current equipment or area through the fault probability model:

[0124] ;

[0125] If P(failure|Ft) > threshold, the system determines it as a node with a high failure probability;

[0126] If the system determines that it is currently in a stage of high failure probability, it automatically increases the acquisition frequency; if the power grid is in a stable state, the system decreases the acquisition frequency.

[0127] Furthermore, the system sets a time window (e.g., 1 hour) to count the number of abnormal fluctuations occurring within this time period. For example, if there are 10 current abnormal fluctuations within 1 hour, it indicates that there may be instability in this area or device; by analyzing the abnormal frequency, the system determines whether this area or device is in a high-frequency abnormal state; if the abnormal frequency is higher than the set threshold, the system determines that this area or device needs further investigation or maintenance;

[0128] Whenever an abnormal fluctuation is detected, the system starts to record its duration, from the moment when the abnormality starts to the moment when it returns to normal. For example, if a certain abnormality lasts for 5 seconds, the system will record this value to distinguish between short-term abnormalities and persistent abnormalities;

[0129] If the duration of the abnormal fluctuation is lower than the set threshold (such as 3 seconds), it is a short-term fluctuation; if it exceeds the threshold, it is a persistent abnormality; a persistent abnormality indicates that there may be a potential fault in the device, and the system can increase the monitoring level of this device and generate an additional warning;

[0130] The system extracts features from the abnormal data, including multi-dimensional information such as deviation amplitude, duration, and abnormal frequency, to construct an abnormal feature vector. For example, an abnormal feature vector may include: deviation amplitude = 2.5 A, duration = 5 seconds, frequency = 10 times / hour.

[0131] After introducing the method of the exemplary embodiment of the present invention, next, refer to Figure 2 A low-voltage power grid residual current monitoring and warning device based on an intelligent network according to an exemplary embodiment of the present invention is described. The device includes:

[0132] A current monitoring module for installing a residual current sensor to monitor current changes and perform intelligent analysis on current fluctuations;

[0133] A fluctuation feature training module for establishing a machine learning model based on historical data to train the normal fluctuation features of the residual current, including: establishing an LSTM model based on historical data, training the normal fluctuation features of the residual current through multi-dimensional feature extraction and feature engineering of current time series data, and the feature engineering includes time domain, frequency domain, and environmental factors; combining the LSTM model deep learning algorithm to identify the normal current pattern and continuously update the model during the operation of the system;

[0134] The detection and judgment module is used to judge the sudden change of current through the time series anomaly detection algorithm, set a threshold according to the normal fluctuation range in the historical data, generate a warning signal immediately if an abnormal fluctuation exceeding the set threshold is detected, and optimize the model regularly using new data to improve the recognition rate of abnormal current in different scenarios;

[0135] The fault warning module is used to classify the residual current fluctuation levels. When the current deviation reaches the threshold, the system automatically issues corresponding level notifications according to the warning levels, automatically determines the location of the fault node through the geographical location of the sensor and the network topology structure, and determines the fault section in combination with the power grid topology data;

[0136] The optimization and analysis module is used to, after the warning is triggered, the system statistically analyzes the abnormal current data and automatically generates a report. According to the real-time current data and the fault probability, the system automatically optimizes the acquisition frequency and the warning threshold.

[0137] After introducing the methods and devices of the exemplary embodiments of the present invention, next, refer to Figure 3 For the computer-readable storage medium of the exemplary embodiments of the present invention, please refer to Figure 3 , which shows that the computer-readable storage medium is an optical disc 30, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it will implement the steps recorded in the above method embodiments. For example, install a residual current sensor to monitor the current change and perform intelligent analysis on the current fluctuation; establish a machine learning model based on historical data to train the normal fluctuation characteristics of the residual current; judge the sudden change of current through the time series anomaly detection algorithm. If an abnormal fluctuation exceeding the set threshold is detected, generate a warning signal immediately, and optimize the model regularly using new data to improve the recognition rate of abnormal current in different scenarios;

[0138] Classify the residual current fluctuation levels. When the current deviation reaches the threshold, the system automatically issues corresponding level notifications according to the warning levels, automatically determines the location of the fault node through the geographical location of the sensor and the network topology structure, and determines the fault section in combination with the power grid topology data; after the warning is triggered, the system statistically analyzes the abnormal current data and automatically generates a report. According to the real-time current data and the fault probability, the system automatically optimizes the acquisition frequency and the warning threshold; the specific implementation manners of each step will not be repeated here.

[0139] It should be noted that examples of the computer-readable storage medium may further include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or other optical and magnetic storage media, which will not be elaborated here one by one.

[0140] After introducing the methods, apparatuses, and media of the exemplary embodiments of the present invention, next, reference is made to Figure 4 a computing device for monitoring and warning of residual current in a low-voltage power grid based on an intelligent network according to an exemplary embodiment of the present invention.

[0141] Figure 4 FIG. shows a block diagram of an exemplary computing device 40 suitable for implementing the embodiments of the present invention. The computing device 40 may be a computer system or a server. Figure 4 The shown computing device 40 is merely an example and should not impose any limitation on the functions and usage scope of the embodiments of the present invention.

[0142] As Figure 4 shown, the components of the computing device 40 may include, but are not limited to: one or more processors or processing units 401, a system memory 402, and a bus 403 connecting different system components (including the system memory 402 and the processing unit 401).

[0143] The computing device 40 typically includes a variety of computer system-readable media. These media can be any available media accessible by the computing device 40, including volatile and non-volatile media, removable and non-removable media.

[0144] The system memory 402 may include computer system-readable media in the form of volatile memory, such as random access memory (RAM) 4021 and / or cache memory 4022. The computing device 40 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, ROM 4023 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 not shown in the figure, usually referred to as a "hard disk drive"). Although not shown in Figure 4As shown, a disk drive for reading and writing to a removable non-volatile disk (such as a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM, or other optical medium) can be provided. In these cases, each drive can be connected to the bus 403 through one or more data medium interfaces. The system memory 402 may include at least one program product having a set (such as at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0145] A program / utility 4025 having a set (at least one) of program modules 4024 can be stored, for example, in the system memory 402, and such program modules 4024 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment. The program modules 4024 generally perform the functions and / or methods in the embodiments described in the present invention.

[0146] The computing device 40 can also communicate with one or more external devices 404 (such as a keyboard, a pointing device, a display, etc.). Such communication can be carried out through an input / output (I / O) interface 405. And, the computing device 40 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 406. As Figure 4 shown, the network adapter 406 communicates with other modules (such as the processing unit 401, etc.) of the computing device 40 through the bus 403. It should be understood that although Figure 4 not shown in the figure, other hardware and / or software modules can be used in combination with the computing device 40.

[0147] The processing unit 401 executes various functional applications and data processing by running programs stored in the system memory 402. For example, it installs residual current sensors to monitor current changes and performs intelligent analysis on current fluctuations; establishes a machine learning model based on historical data to train the normal fluctuation characteristics of residual current; uses a time series anomaly detection algorithm to judge sudden changes in current. If abnormal fluctuations exceeding the set threshold are detected, it immediately generates a warning signal, regularly optimizes the model with new data to improve the recognition rate of abnormal current in different scenarios; classifies the residual current fluctuations. When the current deviation reaches the threshold, the system automatically issues corresponding-level notifications according to the warning level, automatically determines the location of the fault node based on the geographical location of the sensor and the network topology, and combines the power grid topology data to judge the fault section; after the warning is triggered, the system statistically analyzes the abnormal current data and automatically generates a report. According to the real-time current data and the fault probability, the system automatically optimizes the acquisition frequency and the warning threshold. The specific implementation methods of each step will not be repeated here. It should be noted that although several units / modules or sub-units / sub-modules of the synchronous escape wiring device based on multi-commodity flow are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present invention, the features and functions of two or more units / modules described above can be embodied in one unit / modules. Conversely, the features and functions of one unit / modules described above can be further divided and embodied by multiple units / modules.

[0148] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments and will not be repeated here.

[0149] In several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical functional division, and there may be other division methods in actual implementation. Also, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some communication interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0150] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0151] In addition, in each embodiment of the present invention, each functional unit may be integrated in a processing unit, may exist separately as individual physical units, or two or more units may be integrated in one unit.

[0152] If the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0153] Finally, it should be noted that: the above-mentioned embodiments are only specific implementation manners of the present invention, used to illustrate the technical solutions of the present invention, rather than limiting them. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: any person skilled in the art within the technical scope disclosed by the present invention can still modify the technical solutions recorded in the foregoing embodiments, or can easily think of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes, or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

[0154] In addition, although the operations of the method of the present invention are described in a specific order in the drawings, this does not require or imply that these operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution.

Claims

1. A low voltage power grid residual current monitoring and early warning method based on intelligent network, characterized in that: include: Install residual current sensors to monitor current changes and perform intelligent analysis of current fluctuations; Establish a machine learning model based on historical data to train the normal fluctuation characteristics of residual current, including: establish an LSTM model based on historical data, train the normal fluctuation characteristics of residual current by extracting multi-dimensional features of current time series data and feature engineering, the feature engineering includes time domain, frequency domain and environmental factors; combine the LSTM model deep learning algorithm to identify the normal current mode, and continuously update the model during system operation; Through the time series anomaly detection algorithm, sudden changes in current are judged, and thresholds are set according to the normal fluctuation range in historical data. If abnormal fluctuations in current exceeding the threshold are detected, an early warning signal is immediately generated. New data is regularly used to optimize the model to improve the model's recognition rate of abnormal current in different scenarios; The residual current fluctuation is divided into levels. When the current deviation reaches the threshold, the system automatically issues a notification of the corresponding level according to the warning level. The location of the fault node is automatically determined through the geographical location of the sensor and the network topology structure, and the fault section is determined in combination with the grid topology data. After the warning is triggered, the system performs statistical analysis on the abnormal current data and automatically generates reports. Based on the real-time current data and fault probability, the system automatically optimizes the collection frequency and warning threshold.

2. The low-voltage power grid residual current monitoring and early warning method based on intelligent network as claimed in claim 1 is characterized in that: The steps of the LSTM model deep learning algorithm are: Initialize the LSTM network, set the number of hidden layers L and the number of hidden units H, and adjust the network weights through the back propagation algorithm: Where η is the learning rate, It is the gradient of the loss function with respect to the weights, and the iteration continues until the validation set error converges.

3. The low-voltage power grid residual current monitoring and early warning method based on intelligent network as claimed in claim 1 is characterized in that: The above-mentioned timing anomaly detection algorithm is used to judge the sudden change of current. If an abnormal fluctuation exceeding the set threshold is detected, an early warning signal is immediately generated. New data is regularly used to optimize the model to improve the model's recognition rate of abnormal current in different scenarios, including: A dynamic threshold A is set according to the normal fluctuation range in the historical data to determine whether there is abnormal fluctuation. Assuming that under normal circumstances, the mean value of the current fluctuation is μ and the standard deviation is σ, the threshold A is set as: Among them, k is an adjustment parameter. When the current fluctuation value exceeds A, it can be judged as abnormal; Assume that the actual value of the current at time t is x t , the predicted value is x t1 ; The residual calculation formula is: If the residual e t Exceeding the threshold A, that is: |e t ∣>A, it is judged as abnormal fluctuation and a warning signal is generated; Continuously obtain current data from monitoring equipment, including normal and abnormal current fluctuation records. The data covers various equipment operating modes, environmental conditions and load levels. New data are marked as normal or abnormal. For known abnormal situations, manual annotation or external fault detection records are used as reference.

4. The low-voltage power grid residual current monitoring and early warning method based on intelligent network as claimed in claim 1 is characterized in that: The residual current fluctuation is divided into levels. When the current deviation reaches a threshold, the system automatically issues a notification of the corresponding level according to the warning level, including: Based on historical data analysis and scenario settings, current fluctuations are divided into multiple levels, including normal, slightly abnormal, moderately abnormal, and severely abnormal. Each level defines a different threshold range, representing different degrees of risk; If the current deviation is within ±1σ of the average value μ, it is a normal fluctuation; If the current deviation is between ±1σ and ±2σ of the average value μ, it indicates a slight fluctuation and is a slight abnormality; If the current deviation is between ±2σ and ±3σ of the mean value μ, it is considered moderately abnormal; If the current deviation exceeds ±3σ of the average value μ, there is a serious safety hazard and it is a serious abnormality; Where σ is the standard deviation; When the current fluctuation value exceeds the threshold of each level, the system automatically determines the risk level of the current fluctuation.

5. The low-voltage power grid residual current monitoring and early warning method based on intelligent network as claimed in claim 1 is characterized in that: The method of automatically determining the location of the faulty node by using the geographical location of the sensor and the network topology structure, and determining the faulty section in combination with the grid topology data, includes: After detecting an anomaly, the system uses the sensor's geographic location and network topology to locate the faulty node through the following steps: Combined with the topological model, the system searches for the sensor that triggers the abnormal signal and its neighboring nodes to preliminarily determine the source of the abnormality. Based on the geographic coordinates and node relationships, the system identifies the sensor location where the abnormal signal is most concentrated and determines the faulty node. After determining the fault node, the system uses the topological model to check the adjacent power lines and branch paths to determine whether the fault propagates along the power line. The fault propagation along the power line depends on the current fluctuations on the adjacent lines, the propagation characteristics of the fault waveform along the time axis, and the physical characteristics of the power line. The propagation model is based on the following formula: Among them, I (u,v) is the real-time current value of the line (u, v), is the normal current value of the line (u, v); If ΔI (u,v) >Threshold, indicating that the fault has propagated to the line.

6. The low-voltage power grid residual current monitoring and early warning method based on intelligent network as claimed in claim 1 is characterized in that: After the warning is triggered, the system performs statistical analysis on the abnormal current data and automatically generates reports. According to the real-time current data and the probability of failure, the system automatically optimizes the acquisition frequency and the warning threshold, including: Perform multi-dimensional statistics on abnormal data, including: calculating the magnitude of the current deviation from the normal value to determine the severity of the abnormality; analyzing the frequency of abnormal fluctuations per unit time to evaluate the stability of the area or equipment; recording the duration of a single abnormal fluctuation to identify the difference between short-term fluctuations and continuous abnormalities; Identify potential patterns in abnormal data through machine learning and data mining techniques, and analyze the relationship between specific fault types and specific current fluctuation characteristics; Based on historical data and real-time abnormal data, the system calculates the probability of failure. When an early warning is triggered, the system analyzes whether it is a high-risk period or a high-failure probability node; According to the time periods when historical failures occurred, evaluate whether the current time is a high-risk period and define the failure frequency function: Among them, N t is the number of failures in time period t, and T is the total length of time; If the current f(t)>threshold, it is determined to be a high-risk period; Analyze the failure risk of current equipment or areas through the failure probability model: ； If P(fault|Ft)>threshold, the system determines it as a high failure probability node; If the system determines that it is currently in a high failure probability stage, it will automatically increase the collection frequency; if the power grid is in a stable state, the system will reduce the collection frequency.

7. A low voltage power grid residual current monitoring and early warning system based on intelligent network, characterized in that: include: Current monitoring module, used to install residual current sensors to monitor current changes and perform intelligent analysis of current fluctuations; The fluctuation feature training module is used to establish a machine learning model based on historical data and train the normal fluctuation features of the residual current, including: establishing an LSTM model based on historical data, training the normal fluctuation features of the residual current by extracting multi-dimensional features of the current time series data and feature engineering, the feature engineering includes time domain, frequency domain and environmental factors; combining the LSTM model deep learning algorithm to identify the normal current mode, and continuously updating the model during system operation; The detection and judgment module is used to judge the sudden change of current through the time series anomaly detection algorithm, set the threshold according to the normal fluctuation range in the historical data, and immediately generate a warning signal if an abnormal fluctuation exceeding the set threshold is detected. The model is optimized regularly with new data to improve the model's recognition rate of abnormal current in different scenarios; The fault warning module is used to classify the residual current fluctuation. When the current deviation reaches the threshold, the system automatically issues a notification of the corresponding level according to the warning level. The location of the fault node is automatically determined through the sensor's geographical location and network topology, and the fault section is determined in combination with the grid topology data. The optimization analysis module is used to perform statistical analysis on abnormal current data and automatically generate reports after the early warning is triggered. According to the real-time current data and fault probability, the system automatically optimizes the collection frequency and early warning threshold.

8. A computing device, comprising: at least one processor, memory, and input-output unit; The memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the steps of the low-voltage power grid residual current monitoring and early warning method based on an intelligent network as described in any one of claims 1 to 6.

9. A computer-readable storage medium comprising instructions, which, when executed on a computer, enables the computer to execute the steps of the low-voltage power grid residual current monitoring and early warning method based on an intelligent network as described in any one of claims 1 to 6.

Images