Power line fault monitoring method and device, electronic equipment and readable storage medium

Abstract

The invention provides a power line fault monitoring method and device, electronic equipment and a readable storage medium, and belongs to the technical field of line fault analysis, and the method comprises the steps: obtaining multiple types of monitoring signals of a target line; compensating each type of monitoring signals based on the target influence factors to obtain multiple types of target monitoring signals; wherein the target influence factors corresponding to each type of monitoring signals are different, and the target influence factors are at least one of a plurality of power influence factors corresponding to the target line; and performing fault monitoring on the target line based on the multiple types of target monitoring signals to obtain the state of the target line. According to the power line fault monitoring method and device, the electronic equipment and the readable storage medium provided by the invention, the accuracy and reliability of the line fault analysis and monitoring method can be improved.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of line fault analysis, and more specifically, relates to a method and device for monitoring power line faults, electronic equipment, and a readable storage medium. Background Art

[0002] With the rapid development of the power industry, the safe and stable operation of power lines has become extremely important. However, due to various reasons such as equipment aging, load overload, external interference, etc., power lines often have potential faults, which may lead to the paralysis of the power system or even accidents. In order to ensure the normal operation of the power system, it is very important to monitor the status of the power lines and promptly detect and eliminate potential faults. Therefore, an accurate and reliable line fault analysis and monitoring method is needed. Summary of the invention

[0003] The purpose of the present disclosure is to provide a power line fault monitoring method and device, electronic equipment, and readable storage medium to improve the accuracy and reliability of the line fault analysis and monitoring method.

[0004] A first aspect of an embodiment of the present disclosure provides a method for monitoring a power line fault, comprising: Obtain multiple types of monitoring signals of the target line; Each type of monitoring signal is compensated based on the target influencing factor to obtain multiple types of target monitoring signals; wherein each type of monitoring signal corresponds to a different target influencing factor, and the target influencing factor is at least one of the multiple power influencing factors corresponding to the target line; The target line is monitored for faults based on the multiple types of target monitoring signals to obtain a state of the target line.

[0005] A second aspect of the embodiments of the present disclosure provides a power line fault monitoring device, including: A signal acquisition module, used to acquire multiple types of monitoring signals of the target line; A signal compensation module, used to compensate each type of monitoring signal based on the target influencing factor to obtain multiple types of target monitoring signals; wherein each type of monitoring signal corresponds to a different target influencing factor, and the target influencing factor is at least one of the multiple power influencing factors corresponding to the target line; The line monitoring module is used to perform fault monitoring on the target line based on the multiple types of target monitoring signals to obtain the state of the target line.

[0006] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned power line fault monitoring method when executing the computer program.

[0007] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned power line fault monitoring method are implemented.

[0008] The power line fault monitoring method and device, electronic device, and readable storage medium provided by the embodiments of the present disclosure have the following beneficial effects: The present disclosure obtains multiple types of monitoring signals that can reflect the target line conditions from multiple angles, making the monitoring more comprehensive. Secondly, compensation for the target influencing factors of different monitoring signals can effectively eliminate the signal deviation caused by the target factors, greatly improving the accuracy and reliability of the monitoring signals. Accurate target monitoring signals can timely and accurately discover hidden faults in the line, accurately determine the type of fault, greatly reduce troubleshooting time and maintenance costs, effectively ensure the safe and stable operation of power lines, reduce the incidence of power outages caused by line faults, improve the continuity and reliability of power supply, and enhance the overall stability and operation efficiency of the power system. Therefore, the present disclosure can improve the accuracy and reliability of the target line fault analysis and monitoring method. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A schematic diagram of a flow chart of a method for monitoring a power line fault provided by an embodiment of the present disclosure; Figure 2 A structural block diagram of a power line fault monitoring device provided by an embodiment of the present disclosure; Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0011] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0012] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0013] Please refer to Figure 1 , Figure 1 A schematic diagram of a flow chart of a power line fault monitoring method provided in an embodiment of the present disclosure, the method comprising: S101: Acquire multiple types of monitoring signals of a target line.

[0014] In this embodiment, the target line is a power line selected for monitoring in the power system. The multiple types of monitoring signals are multiple types of signals that can reflect the operating status of the target line from different aspects. The multiple types of monitoring signals may include but are not limited to voltage signals, current signals and arc signals, which are used to evaluate the status of the target line.

[0015] The present disclosure can be used to analyze and judge the state of the target line by acquiring multiple types of monitoring signals of the target line. For example, the current signal reflects the load and short circuit conditions, the voltage signal reflects the power supply stability, the temperature signal indicates the risk of overload and heating, and the arc signal warns of arc faults. Exemplarily, the current signal can be obtained by a current transformer installed on the target line. For example, in an industrial power supply line, the current transformer converts the large current in the line into a small current signal that can be collected by the monitoring equipment according to a certain transformation ratio. Assuming that the current of the line is 500A when it is operating normally and the transformation ratio of the current transformer is 1000:1, the secondary current signal collected by the monitoring equipment is 0.5A. By real-time monitoring of the current signal, the load condition of the line can be understood. When the current suddenly increases to far beyond the normal range, it indicates that a short circuit fault has occurred in the line or a new high-power load has been connected.

[0016] S102: Compensating each type of monitoring signal based on the target influencing factor to obtain multiple types of target monitoring signals; wherein each type of monitoring signal corresponds to a different target influencing factor, and the target influencing factor is at least one of multiple power influencing factors corresponding to the target line.

[0017] In this embodiment, the target influencing factors are various factors that may interfere with the monitoring signal or cause the monitoring signal to deviate from the true value. The target influencing factors are closely related to the operating environment, the characteristics of the power line, and the peripheral equipment. The target influencing factors may include electromagnetic interference, ambient temperature, and ambient humidity. Different monitoring signals may be affected by different target influencing factors.

[0018] The multi-type target monitoring signals are various monitoring signals obtained after compensation processing for the corresponding target influencing factors, and are various monitoring signals that can more accurately reflect the actual operating status of the target line. The multi-type target monitoring signals are signals after removing or correcting the deviation caused by the target influencing factors on the basis of the original monitoring signals, and can be used for subsequent more accurate fault monitoring and analysis.

[0019] This embodiment finds out the target influencing factors that affect the accuracy of each type of monitoring signal acquired, and then uses appropriate compensation means to correct the original monitoring signal, and finally obtains multiple types of target monitoring signals after compensation optimization.

[0020] Exemplarily, the current signal is compensated, and considering that the target influencing factor is electromagnetic interference, the intensity, frequency and phase of the electromagnetic interference can be measured, and the compensation factor corresponding to the current signal is determined based on the neural network model, so as to correct the circuit signal. Among them, the compensation factor can be an amplitude compensation factor, a phase compensation factor, and a harmonic compensation factor.

[0021] S103: Perform fault monitoring on the target line based on multiple types of target monitoring signals to obtain the state of the target line.

[0022] In this embodiment, fault monitoring is to judge multiple types of monitoring signals of the target line through a fault analysis model to determine whether there is a fault on the target line and the type of the fault (ie, the state of the target line).

[0023] The state of the target line is the current operating condition of the target line, which can usually be divided into normal operation, potential faults, and faults that have occurred. For the case of a fault that has occurred, the specific characteristics of the fault can be further clarified.

[0024] The multiple types of target monitoring signals obtained after compensation processing in this embodiment can use specific fault analysis methods to monitor the operation of the target line and ultimately determine the state of the target line. For example, if the current signal is monitored to suddenly increase significantly and exceed the set threshold, and the voltage signal drops sharply, it indicates that a short circuit fault has occurred in the target line; if the current signal continues to be lower than the normal range, and the voltage signal is high, there is a circuit breaker or a serious lack of load.

[0025] From the above, it can be concluded that the acquisition of multiple types of monitoring signals by the present disclosure can reflect the target line conditions from multiple angles, making the monitoring more comprehensive. Secondly, compensation for the target influencing factors of different monitoring signals can effectively eliminate the signal deviation caused by the target factors, greatly improving the accuracy and reliability of the monitoring signals. Accurate target monitoring signals can timely and accurately detect hidden faults in the line, accurately determine the type of fault, greatly reduce troubleshooting time and maintenance costs, effectively ensure the safe and stable operation of power lines, reduce the incidence of power outages caused by line faults, improve the continuity and reliability of power supply, and enhance the overall stability and operation efficiency of the power system. Therefore, the present disclosure can improve the accuracy and reliability of the target line fault analysis and monitoring method.

[0026] In one embodiment of the present disclosure, each type of monitoring signal is compensated based on the target influencing factor to obtain multiple types of target monitoring signals, including: Determine the target influencing factors corresponding to each type of monitoring signal; Determine a signal compensation model corresponding to each type of monitoring signal based on the target influencing factors corresponding to the type of monitoring signal; Based on the signal compensation model corresponding to each type of monitoring signal, the monitoring signal of this type is compensated to obtain multiple types of target monitoring signals.

[0027] In this embodiment, determining the target influencing factors corresponding to each type of monitoring signal includes: Determine the location of each type of monitoring signal in the target line; The target influencing factors corresponding to each type of monitoring signal are determined based on the position of the monitoring signal in the target line.

[0028] Among them, the target influencing factors may be ambient temperature, ambient humidity and electromagnetic interference.

[0029] If each type of monitoring signal is in the first position in the target line, the target influencing factor corresponding to the type of monitoring signal is that the influence of ambient temperature is greater than the influence of electromagnetic interference, and the influence of electromagnetic interference is greater than the influence of ambient humidity; If each type of monitoring signal is at the second position in the target line, the target influencing factor corresponding to the type of monitoring signal is that the influence of environmental humidity is greater than the influence of electromagnetic interference, and the influence of electromagnetic interference is greater than the influence of environmental temperature; If each type of monitoring signal is at the third position in the target line, the target influencing factor corresponding to the monitoring signal is that the electromagnetic interference influence is greater than the ambient temperature influence and also greater than the ambient humidity influence; wherein the ambient temperature and ambient humidity are both relatively stable; The first position, the second position and the third position are different from each other. The first position may be a scene with high temperature, dryness and certain electromagnetic interference, the second position may be a scene with high humidity and certain electromagnetic interference, and the third position may be a scene close to a strong electromagnetic field source and with relatively stable ambient temperature and humidity.

[0030] The signal compensation model is a mathematical model or algorithm framework constructed based on the relationship between the target influencing factors and the monitoring signal. Its purpose is to correct the deviation of the monitoring signal caused by the target influencing factors through specific calculation and processing methods, so that the compensated signal can be closer to the actual line operation status.

[0031] Based on the target influencing factors corresponding to each type of monitoring signal, a signal compensation model corresponding to the type of monitoring signal is determined, including: Determine, based on each type of monitoring signal, a comprehensive loss function corresponding to the type of monitoring signal; A signal compensation model corresponding to this type of monitoring signal is constructed based on the comprehensive loss function.

[0032] Based on each type of monitoring signal, a comprehensive loss function corresponding to the type of monitoring signal is determined, including: Determine the predicted value of each type of monitoring signal based on the monitoring signal; each type of monitoring signal is a monitoring signal under the target influencing factor; Determining an ideal value of each type of monitoring signal based on the type of monitoring signal; Determine a comprehensive loss function corresponding to the monitoring signal of this type based on the predicted value of the monitoring signal of this type and the ideal value of the monitoring signal of this type; Among them, the target influencing factors are ambient temperature, ambient humidity and electromagnetic interference.

[0033] The comprehensive loss function is a weighted calculation of the first loss function, the second loss function, the third loss function, and the fourth loss function: The first loss function for:

[0034] in, represents the sample size, Indicates The predicted value of each type of monitoring signal, Indicates Standard value for each type of monitoring signal; The second loss function for:

[0035] in, represents the temperature weight, Represents the square of the second norm of the ambient temperature value; The third loss function for:

[0036] in, represents the humidity weight, Represents the square of the second norm of the ambient humidity value; The fourth loss function for:

[0037] in, represents the electromagnetic interference weight, The square of the second norm of the electromagnetic interference value; Comprehensive loss function for:

[0038]

[0039] in, , and It can be adjusted dynamically according to actual conditions.

[0040] According to the determined target influencing factors, select or construct a suitable signal compensation model. Using the selected or constructed signal compensation model, input the original monitoring signal into it, and after calculation and correction processing by the model, obtain the target monitoring signal after removing or reducing the interference of the target influencing factors. These signals can more accurately reflect the actual operating status of the target line.

[0041] Take a city 10kV distribution line as an example: Determine the target influencing factors of the current signal: There are some factories around the line. When large motors and other equipment in the factories start and stop, electromagnetic interference will be generated, so electromagnetic interference is the main target influencing factor of the current signal; Determine the signal compensation model: For electromagnetic interference, build a dynamic compensation model based on historical electromagnetic interference data and real-time monitoring data to predict and correct the current signal according to the electromagnetic interference change trend.

[0042] Compensation is performed to obtain a target monitoring signal: the collected original current signal is input into a dynamic compensation model to correct the deviation caused by load fluctuations to obtain a target monitoring current signal.

[0043] From the above, it can be concluded that this embodiment can construct a signal compensation model in a targeted manner by determining the target influencing factors corresponding to each type of monitoring signal, so that the signal compensation is more in line with the actual situation; the signal compensation model is determined by a comprehensive loss function, and the relationship between ambient temperature, ambient humidity and electromagnetic interference and the monitoring signal is fully considered, so as to effectively correct the deviations caused by these factors and improve the accuracy of the monitoring signal.

[0044] In one embodiment of the present disclosure, the signal compensation model corresponding to each type of monitoring signal is determined based on a simulation data set corresponding to the type of monitoring signal.

[0045] In this embodiment, each type of monitoring signal can be different types of information collection quantities used to reflect the operation status of the line, such as current signals, voltage signals, power signals, etc. For example, the current signal can reflect the load size and changes of the line, and the voltage signal reflects the power supply level and stability of the line.

[0046] The simulation data set is a series of data sets related to each type of monitoring signal generated by simulating different operating conditions, environmental factors, and possible fault conditions. The simulation data set does not come from actual real-time line monitoring, but is an artificially created representative data set used to build and train the signal compensation model so that the signal compensation model can learn how to correctly compensate the monitoring signal under various circumstances.

[0047] This embodiment first obtains a large amount of simulation data by simulating multiple scenarios that may affect the monitoring signal, and constructs a simulation data set corresponding to each type of monitoring signal; then the signal compensation model is determined using the simulation data set corresponding to the type of monitoring signal.

[0048] Take the construction of a compensation model for voltage monitoring signals as an example: First, identify factors that affect the voltage monitoring signal, such as electromagnetic interference.

[0049] Then, the simulation data is generated. Electromagnetic interference simulation: Consider the impact of electromagnetic interference of different strengths and frequencies on the voltage monitoring signal.

[0050] Afterwards, the voltage monitoring signal data obtained in the above-mentioned various simulation situations are combined to form a simulation data set corresponding to the voltage monitoring signal.

[0051] Finally, the voltage signal compensation model is constructed using the simulated data set corresponding to the voltage monitoring signal. For example, a neural network model is used, and the original voltage value in the simulated data set is used as the input layer node. After the hidden layer feature extraction and conversion (the number of hidden layer nodes and activation function are determined according to the actual situation, such as using 10 hidden layer nodes and ReLU activation function), the compensated voltage value is output in the output layer. Through the training of a large amount of simulated data, the weights and biases of the neural network are continuously adjusted, so that the model can learn how to accurately compensate the voltage monitoring signal under different electromagnetic interference conditions. The neural network model obtained after training is the signal compensation model corresponding to the voltage monitoring signal. When the voltage signal is actually monitored, it is input into the model to obtain the compensated voltage signal, thereby improving the accuracy and reliability of voltage monitoring.

[0052] It can be concluded from the above that this embodiment can cover a wider range of situations, including some extreme or special situations that rarely occur in practice but may have a significant impact on the monitoring signal, making the model more versatile and adaptable, and able to better cope with various complex actual operating environments.

[0053] In one embodiment of the present disclosure, the power line fault monitoring method further includes: Simulating each type of monitoring signal in the first state as a first monitoring signal set; simulating each type of monitoring signal in the second state as a second monitoring signal set; Determine a simulation data set corresponding to each type of monitoring signal according to a first monitoring signal set corresponding to each type of monitoring signal and a second monitoring signal set corresponding to each type of monitoring signal; The second state is an ideal state of the first state.

[0054] In this embodiment, the first state is the state of the power line during actual operation when it is affected by various complex environmental factors, equipment operating conditions, potential interference, etc. Considering that it is difficult to determine the standard monitoring signal corresponding to the historical monitoring signal, the target influencing factors of each type of monitoring signal are simulated to determine the simulated data set corresponding to each type of monitoring signal.

[0055] The target monitoring factors may include, but are not limited to, changes in ambient temperature, fluctuations in ambient humidity, the presence of electromagnetic interference, etc., which may make the monitoring signals complex and diverse and may deviate from the ideal value. For example, if the ambient temperature around the simulated line rises and there are large electrical equipment nearby that frequently starts and stops to generate electromagnetic interference, the state of the monitored current, voltage and other signals at this time is the first state.

[0056] The first monitoring signal set is obtained by simulating various monitoring signals (such as current signals and voltage signals) when the power line is in the first state. The data in the first monitoring signal set reflects the changes of various monitoring signals in the simulation under the actual complex operating environment, and is an important basic data source for the subsequent construction of simulation data sets and determination of compensation models.

[0057] The second state is an ideal operating state relative to the first state, that is, the state of the power line when it is not or rarely interfered by the above-mentioned adverse factors. In this state, the ambient temperature and humidity remain stable and appropriate, and there is no electromagnetic interference. At this time, each type of monitoring signal can accurately reflect the true operating parameters of the power line, and there is no deviation or error caused by external interference. For example, in a laboratory environment, the temperature and humidity are artificially controlled to be constant, and external electromagnetic interference is shielded. At this time, the simulated monitoring signal state is the second state.

[0058] The second monitoring signal set corresponds to the second state, and is a data set generated by simulating each type of monitoring signal when the simulated power line is in the ideal second state. The above data represents the "standard" value or "real" value of each type of monitoring signal under ideal conditions, which is in sharp contrast to the first monitoring signal set and is used for comparative analysis and determination of the compensation amount or compensation rule in the compensation model.

[0059] The simulation data set is a data set composed of the first monitoring signal set and the second monitoring signal set corresponding to each type of monitoring signal, which integrates the monitoring signal data under the simulated actual complex state and the ideal state, and provides a comprehensive data basis for the subsequent determination of the signal compensation model corresponding to each type of monitoring signal. Through the analysis and processing of the simulation data set, this embodiment can find out the change rules and differences of the monitoring signal from the simulated actual state to the ideal state, thereby constructing a compensation model that can effectively correct the deviation of the monitoring signal.

[0060] Take the construction of a simulated data set for current monitoring signals as an example: First, simulate the current monitoring signal in the first state. Assume that there is a 10kV distribution line and consider the following actual situation: Impact of electromagnetic interference: Simulate the impact of 50Hz-1kHz electromagnetic interference generated by nearby high-voltage equipment on the current transformer. Assume that electromagnetic interference will change the magnetic permeability of the current transformer, resulting in deviation in the measured current. According to the relationship model between electromagnetic interference intensity and magnetic permeability change (derived through experiments or theoretical derivation), calculate the change in current measurement value under different electromagnetic interference intensities, and add these data to the current monitoring signal data in the first state.

[0061] The first monitoring signal set is obtained through the above simulation, for example, including 1000 current monitoring signal values ​​at different times and under different temperatures, loads and electromagnetic interference conditions.

[0062] Then simulate the current monitoring signal in the second state. In the laboratory environment, set the ambient temperature to 25°C, the humidity to 50%, shield the external electromagnetic interference, and set the line load to 500kW. At this time, the current value calculated according to Ohm's law is the current value in the ideal state. Simulate and generate 1000 such current values ​​as the second monitoring signal set.

[0063] Finally, the first monitoring signal set and the second monitoring signal set are combined to form a simulation data set corresponding to the current monitoring signal. The above simulation data set contains current monitoring signal data under various complex situations and ideal conditions in simulated actual operation. By analyzing it, such as calculating the difference distribution and change trend between the first monitoring signal set and the second monitoring signal set, it can provide a basis for constructing a compensation model for the current monitoring signal, such as determining the relationship model between the compensation factor and factors such as temperature and electromagnetic interference, so as to achieve accurate compensation for the actual monitoring current signal.

[0064] From the above, it can be concluded that this embodiment constructs a simulated data set by simulating the first state and the second state, which can comprehensively cover the actual and ideal conditions of line operation, help to accurately determine the signal compensation model, effectively correct the monitoring signal deviation caused by factors such as ambient temperature, humidity, and electromagnetic interference, and greatly improve the monitoring accuracy.

[0065] In one embodiment of the present disclosure, the signal compensation model corresponding to each type of monitoring signal is determined according to a simulation data set corresponding to each type of monitoring signal, and includes: Determine a compensation factor corresponding to each type of monitoring signal according to a first monitoring signal set corresponding to the type of monitoring signal and a second monitoring signal set corresponding to the type of monitoring signal; The first model is trained based on the first monitoring signal set corresponding to each type of monitoring signal and the compensation factor corresponding to the type of monitoring signal to obtain a signal compensation model corresponding to the type of monitoring signal.

[0066] In this embodiment, the compensation factor is a coefficient or parameter combination used to correct the deviation of the monitoring signal, which reflects the change relationship from the first monitoring signal set (monitoring signals under actual conditions) to the second monitoring signal set (monitoring signals under ideal conditions). By quantifying the above relationship, the actual monitoring signal can be adjusted according to the compensation factor in the subsequent signal compensation process to make it closer to the signal value under the ideal condition.

[0067] The first model is the initial model framework for constructing the signal compensation model, which can be various mathematical models or machine learning models, such as linear regression models, neural network models, etc., with some parameters to be determined (such as slope and intercept in linear regression, weight and bias in neural network). By using the first monitoring signal set and compensation factor of each type of monitoring signal for training, these parameters are continuously adjusted to finally obtain a signal compensation model that can accurately compensate the monitoring signal.

[0068] This embodiment calculates the compensation factor by comparing the data difference between the same type of monitoring signal in the first state (actual complex state) and the second state (ideal state). For example, for the voltage monitoring signal, each voltage value in the first monitoring signal set is compared and analyzed with the corresponding ideal voltage value in the second monitoring signal set. A simple proportional calculation (such as dividing the actual voltage value by the ideal voltage value to obtain the compensation factor) or a more complex statistical analysis method (such as determining the compensation factor based on data distribution characteristics) can be used to obtain a compensation factor sequence or functional relationship applicable to this type of voltage monitoring signal.

[0069] At the same time, the first monitoring signal set is used as input data, and the corresponding compensation factor is used as the output target, and the above data is used to train the first model. During the training process, the first model continuously adjusts its own parameters so that its processing results for the first monitoring signal set are as close as possible to the correction value indicated by the compensation factor. For example, if a linear regression model is used as the first model, the training process is to continuously adjust the slope and intercept of the straight line so that when the monitoring signal in the first monitoring signal set is input, the output correction value is consistent with the compensation factor. After multiple iterative training, the optimized model obtained is the signal compensation model corresponding to this type of monitoring signal, and the model can effectively compensate and correct such signals actually monitored.

[0070] From the above, it can be concluded that this embodiment determines the compensation factor and trains the model by accurately comparing the first monitoring signal set and the second monitoring signal set, which can deeply explore the rules of how the monitoring signals are affected by factors such as ambient temperature and electromagnetic interference; and can effectively correct the signal deviations caused by various types of interference, greatly improving the accuracy and reliability of the monitoring signals.

[0071] In one embodiment of the present disclosure, fault monitoring is performed on a target line based on multiple types of target monitoring signals to obtain the state of the target line, including: Multiple types of target monitoring signals are input into a target fault analysis model for fault monitoring to determine the state of a target line; wherein the target fault analysis model is a fault analysis model for determining a line based on multiple types of analog monitoring signals and line state information corresponding to the multiple types of analog monitoring signals.

[0072] In one embodiment of the present disclosure, the power line fault monitoring method further includes: using the multiple types of simulated monitoring signals as inputs to the second model; Taking the line status information corresponding to the multiple types of analog monitoring signals as the output of the second model; The second model is trained to obtain a fault analysis model of the line.

[0073] In this embodiment, the target fault analysis model is a model used to judge the state of the power line (whether there is a fault, the type and degree of the fault, etc.) based on multiple types of monitoring signals. It is trained and constructed based on a large amount of simulation data and corresponding line state information, and can analyze and process the target monitoring signals actually monitored, so as to draw conclusions about the operating state of the target line.

[0074] Multiple types of simulated monitoring signals can be generated by simulating the multiple types of monitoring signal data generated by power lines under various operating conditions, fault scenarios and environmental factors, such as simulating the changes in current and voltage signals under different degrees of short-circuit faults, or various signals during normal operation under different ambient temperatures, humidity, and electromagnetic interference. The above simulated signals are used to build and train fault analysis models so that they can learn the relationship between different signal features and line status.

[0075] Line status information is information describing the operating status of power lines, including normal operation, various faults (such as short circuit, open circuit, overload, ground fault, etc.) and specific characteristics of faults (such as fault type, fault severity, etc.). It corresponds to multiple types of analog monitoring signals and is used as the output target of model training, so that the model can learn how to accurately judge the status information of the line based on the input analog monitoring signals.

[0076] The second model is the initial model framework for constructing the target fault analysis model, which can be a neural network model, a support vector machine model, etc. in the machine learning model, with some parameters and structures to be determined. It is trained by using multiple types of simulated monitoring signals as input and the line status information corresponding to the multiple types of simulated monitoring signals as output, and continuously optimizing the model parameters and structure, and finally obtaining the target fault analysis model that can accurately perform fault analysis.

[0077] Input multiple types of target monitoring signals into the target fault analysis model for fault monitoring and determine the state of the target line: In actual power line fault monitoring, first obtain multiple types of target monitoring signals after a series of previous processing (such as signal compensation, etc.), and then input these signals into the pre-trained target fault analysis model. The model analyzes and calculates the input target monitoring signals based on the relationship logic between the signal and the line state learned internally, and thus draws a conclusion on whether the target line is currently in normal operation or a certain fault state (as well as detailed information about the fault).

[0078] In the process of constructing the fault analysis model, the multiple types of monitoring signal data generated by simulation are input into the second model, and the known line status information corresponding to the above simulation signal is used as the expected output of the model. Then the second model is trained using the above data. During the training process, the second model continuously adjusts its own parameters (such as weights and biases in the neural network) or optimizes its own structure (such as branching rules in the decision tree model) to improve the model's fit to the relationship between the input simulation monitoring signal and the output line status information. After sufficient training, the optimized model obtained is a line fault analysis model that can be used for actual line fault analysis.

[0079] Take the construction of a power line fault analysis model based on neural network as an example: First, multiple types of monitoring signals are simulated.

[0080] Then, determine the line status information corresponding to each type of analog monitoring signal. For the analog signal of normal operation, mark it as "normal" state; for the analog signal of short circuit fault, mark it as "short circuit fault, high fault severity" and other detailed information; for the analog signal of open circuit fault, also mark the corresponding severity and other information.

[0081] Next, a neural network is selected as the second model. Its structure includes an input layer (the number of nodes corresponds to the types of multiple monitoring signals, such as 3 nodes for current, voltage, temperature, etc.), a hidden layer (assuming that 2 hidden layers are set, the first hidden layer has 5 nodes, the second hidden layer has 3 nodes, and ReLU is used as the activation function) and an output layer (the number of nodes is determined according to the type of line status information that needs to be judged. For example, if three states, normal, short circuit and open circuit, are judged, 3 nodes are set, and the Softmax function is used for classification output).

[0082] Finally, during the training process, the error between the model output and the actual line status information is calculated based on the loss function, and then the weights and biases of the neural network are adjusted through the back propagation algorithm to continuously optimize the model. After thousands of training iterations, a trained line fault analysis model is obtained.

[0083] In actual power line fault monitoring, multiple types of target monitoring signals (such as actual monitored current, voltage, and temperature signals) collected in real time and processed after compensation are input into the trained fault analysis model. The model can then analyze and determine whether the target line is in normal operation or has some kind of fault, and provide relevant information about the fault, such as the fault type and possible fault location, thereby achieving fault monitoring of power lines.

[0084] From the above, it can be concluded that this embodiment can enable the model to accurately grasp the complex relationship between signals and faults by using multiple types of simulated monitoring signals and corresponding line status information to train the model. Inputting multiple types of target monitoring signals into the model for fault monitoring can quickly and accurately determine the target line status and effectively identify various fault types such as short circuit, open circuit, overload and their details.

[0085] Corresponding to the power line fault monitoring method of the above embodiment, Figure 2 This is a structural block diagram of a power line fault monitoring device provided by an embodiment of the present disclosure. For ease of description, only the parts related to the embodiment of the present disclosure are shown. Figure 2 The power line fault monitoring device 20 includes: a signal acquisition module 21, a signal compensation module 22 and a line monitoring module 23.

[0086] Among them, the signal acquisition module is used to obtain multiple types of monitoring signals of the target line; A signal compensation module, used to compensate each type of monitoring signal based on the target influencing factor to obtain multiple types of target monitoring signals; wherein each type of monitoring signal corresponds to a different target influencing factor, and the target influencing factor is at least one of multiple power influencing factors corresponding to the target line; The line monitoring module is used to perform fault monitoring on the target line based on multiple types of target monitoring signals to obtain the status of the target line.

[0087] In one embodiment of the present disclosure, the signal compensation module is specifically used to: Determine the target influencing factors corresponding to each type of monitoring signal; Determine a signal compensation model corresponding to each type of monitoring signal based on the target influencing factors corresponding to the type of monitoring signal; Based on the signal compensation model corresponding to each type of monitoring signal, the monitoring signal of this type is compensated to obtain multiple types of target monitoring signals.

[0088] In one embodiment of the present disclosure, the signal compensation model corresponding to each type of monitoring signal is determined based on a simulation data set corresponding to the type of monitoring signal.

[0089] In one embodiment of the present disclosure, the power line fault monitoring device 20 further includes: a signal simulation module; A signal simulation module, used for simulating each type of monitoring signal in a first state as a first monitoring signal set; simulating each type of monitoring signal in the second state as a second monitoring signal set; Determine a simulation data set corresponding to each type of monitoring signal according to a first monitoring signal set corresponding to each type of monitoring signal and a second monitoring signal set corresponding to each type of monitoring signal; The second state is an ideal state of the first state.

[0090] In one embodiment of the present disclosure, the power line fault monitoring device 20 further includes: a first training module; A first training module, used to determine a compensation factor corresponding to each type of monitoring signal according to a first monitoring signal set corresponding to the type of monitoring signal and a second monitoring signal set corresponding to the type of monitoring signal; The first model is trained based on the first monitoring signal set corresponding to each type of monitoring signal and the compensation factor corresponding to the type of monitoring signal to obtain a signal compensation model corresponding to the type of monitoring signal.

[0091] In one embodiment of the present disclosure, a line monitoring module is specifically used to input multiple types of target monitoring signals into a target fault analysis model for fault monitoring to determine the state of a target line; wherein the target fault analysis model is a fault analysis model for determining a line based on multiple types of analog monitoring signals and line state information corresponding to the multiple types of analog monitoring signals.

[0092] In one embodiment of the present disclosure, the power line fault monitoring device 20 further includes: a second training module; A second training module, used for taking multiple types of simulated monitoring signals as inputs of a second model; Taking the line status information corresponding to the multiple types of analog monitoring signals as the output of the second model; The second model is trained to obtain a fault analysis model of the line.

[0093] See also Figure 3 , Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 3 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above-mentioned device embodiments, such as Figure 2 The functions of modules 21 to 23 are shown.

[0094] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0095] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0096] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0097] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the power line fault monitoring method provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device described in the embodiments of the present disclosure, which will not be repeated here.

[0098] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0099] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0100] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0101] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0102] In the several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0103] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present disclosure.

[0104] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0105] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for monitoring power line faults, characterized in that: include: Obtain multiple types of monitoring signals of the target line; Each type of monitoring signal is compensated based on the target influencing factor to obtain multiple types of target monitoring signals; wherein each type of monitoring signal corresponds to a different target influencing factor, and the target influencing factor is at least one of the multiple power influencing factors corresponding to the target line; The target line is monitored for faults based on the multiple types of target monitoring signals to obtain a state of the target line.

2. The power line fault monitoring method according to claim 1, characterized in that: The method of compensating each type of monitoring signal based on the target influencing factors to obtain multiple types of target monitoring signals includes: Determine the target influencing factors corresponding to each type of monitoring signal; Determine a signal compensation model corresponding to each type of monitoring signal based on the target influencing factors corresponding to the type of monitoring signal; Each type of monitoring signal is compensated based on a signal compensation model corresponding to that type of monitoring signal to obtain the multiple types of target monitoring signals.

3. The power line fault monitoring method according to claim 2, characterized in that: The signal compensation model corresponding to each type of monitoring signal is determined according to the simulation data set corresponding to the type of monitoring signal.

4. The power line fault monitoring method according to claim 3, characterized in that: Also includes: Simulating each type of monitoring signal in the first state as a first monitoring signal set; simulating each type of monitoring signal in the second state as a second monitoring signal set; Determine a simulation data set corresponding to each type of monitoring signal according to a first monitoring signal set corresponding to each type of monitoring signal and a second monitoring signal set corresponding to each type of monitoring signal; The second state is an ideal state of the first state.

5. The power line fault monitoring method according to claim 4, characterized in that: The signal compensation model corresponding to each type of monitoring signal is determined according to the simulation data set corresponding to each type of monitoring signal, and includes: Determine a compensation factor corresponding to each type of monitoring signal according to a first monitoring signal set corresponding to the type of monitoring signal and a second monitoring signal set corresponding to the type of monitoring signal; The first model is trained based on the first monitoring signal set corresponding to each type of monitoring signal and the compensation factor corresponding to the type of monitoring signal to obtain a signal compensation model corresponding to the type of monitoring signal.

6. The power line fault monitoring method according to claim 1, characterized in that: The performing fault monitoring on the target line based on the multiple types of target monitoring signals to obtain the state of the target line includes: The multiple types of target monitoring signals are input into a target fault analysis model for fault monitoring to determine the state of the target line; wherein the target fault analysis model is a fault analysis model for determining the line based on multiple types of analog monitoring signals and line state information corresponding to the multiple types of analog monitoring signals.

7. The power line fault monitoring method according to claim 6, characterized in that: Also includes: Using the multiple types of simulated monitoring signals as inputs of a second model; Using the line status information corresponding to the multiple types of analog monitoring signals as the output of the second model; The second model is trained to obtain a fault analysis model of the line.

8. A power line fault monitoring device, characterized in that: include: A signal acquisition module, used to acquire multiple types of monitoring signals of the target line; A signal compensation module, used to compensate each type of monitoring signal based on the target influencing factor to obtain multiple types of target monitoring signals; wherein each type of monitoring signal corresponds to a different target influencing factor, and the target influencing factor is at least one of the multiple power influencing factors corresponding to the target line; The line monitoring module is used to perform fault monitoring on the target line based on the multiple types of target monitoring signals to obtain the state of the target line.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images