A method and system for operation and maintenance of transmission lines based on fault location and prediction

Abstract

This invention discloses a method and system for transmission line operation and maintenance based on fault location and prediction, belonging to the field of transmission line operation and maintenance technology. It includes collecting real-time and historical operating data of cables in the transmission line, and constructing a deep learning model based on Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM); using the deep learning model to analyze the real-time operating data and locate the fault point; predicting the future operating state of the transmission line based on the deep learning model and determining whether an early warning is triggered; formulating a transmission line maintenance plan based on the fault point and the future operating state of the transmission line, and optimizing the deep learning model based on real-time data. This invention effectively reduces fault investigation time and the impact of faults on the system by constructing a deep learning model; it takes measures before potential problems occur, improving the reliability and maintainability of transmission lines and reducing maintenance costs.

Description

Technical Field

[0001] This invention relates to the field of power transmission line operation and maintenance technology, and in particular to a power transmission line operation and maintenance method and system based on fault location and prediction. Background Technology

[0002] With the rapid development and expansion of power systems, the operation and maintenance of transmission lines has become increasingly complex, and traditional transmission line operation and maintenance methods are no longer efficient and timely enough. In the field of power system operation and maintenance, various advanced monitoring and analysis technologies have emerged, providing new possibilities for improving the level of line operation and maintenance. These technologies include, but are not limited to, Internet of Things (IoT) technology, data mining, and artificial intelligence. Among them, deep learning, as an important branch of artificial intelligence, has shown outstanding performance in processing complex power system data. The rise of deep learning has brought revolutionary changes to power system operation and maintenance. Various deep learning models, with their superior capabilities in image processing and time series analysis, have become powerful tools for power system data processing. These models can extract complex features from large amounts of real-time operating data, more accurately capture the changing trends of line operating status, and provide strong support for fault location and prediction.

[0003] However, despite the significant achievements brought about by the introduction of advanced monitoring and analysis technologies, existing power system operation and maintenance methods still face a series of problems. First, methods relying on periodic inspections and post-event maintenance risk missing potential faults, resulting in insufficient monitoring of line safety. Second, traditional methods are inefficient when processing large amounts of operational data and struggle to make timely decisions under high real-time requirements. These problems severely restrict the overall efficiency of power system operation and maintenance. Therefore, with the development of power systems, the problems faced by traditional operation and maintenance methods urgently require advanced solutions to bring an innovative and efficient solution to transmission line operation and maintenance. Summary of the Invention

[0004] In view of the problems that existing technologies for the operation and maintenance of transmission lines are not comprehensive enough in terms of fault detection, which may lead to the risk of missing potential faults, and are inefficient in processing large amounts of operational data and making timely decisions, this invention is proposed.

[0005] Therefore, the problem to be solved by this invention is how to provide a method for analyzing real-time operating data, accurately locating fault points, predicting future operating status, and reducing accident risks.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, embodiments of the present invention provide a transmission line operation and maintenance method based on fault location and prediction, which includes collecting real-time and historical operating data of cables in the transmission line, and constructing a deep learning model based on a convolutional neural network (CNN) and a long short-term memory network (LSTM); using the deep learning model to analyze the real-time operating data and locate the fault point; predicting the future operating state of the transmission line based on the deep learning model and determining whether an early warning is triggered; formulating a transmission line maintenance plan based on the fault point and the future operating state of the transmission line, and optimizing the deep learning model based on real-time data.

[0008] As a preferred embodiment of the transmission line operation and maintenance method based on fault location and prediction described in this invention, the real-time operation data includes the current, voltage, and temperature of the cables in the transmission line; the historical operation data includes data of the cables in the transmission line under normal operating conditions and data of the cables in the transmission line under different types of fault conditions; the construction of the deep learning model includes the following steps: using a convolutional neural network (CNN) for spatial feature extraction, using a long short-term memory network (LSTM) for time series modeling; labeling the historical operation data with status; and using the labeled historical operation data for supervised learning and optimizing the model parameters.

[0009] As a preferred embodiment of the transmission line operation and maintenance method based on fault location and prediction described in this invention, the calculation formula of the deep learning model is as follows:

[0010]

[0011] Where F(x,t) represents the output feature of the deep learning model; x represents the input data; t represents the system runtime; K represents the number of convolutional kernels; α represents the decay factor in time series modeling; σ represents the sigmoid function; W k b represents the weight parameters of the k-th convolutional kernel. k U is the bias parameter of the k-th convolution kernel; tanh is the hyperbolic tangent function; U k h represents the weight parameters of the k-th LSTM unit. t-1 τ represents the hidden state in the previous time step in the LSTM; τ is the integral variable over time.

[0012] As a preferred embodiment of the transmission line operation and maintenance method based on fault location and prediction described in this invention, the fault location includes the following steps: real-time monitoring of relevant data of the transmission line and learning the normal operation status using a deep learning model; detecting abnormal operation status of the transmission line and comparing and classifying the abnormal data with known fault modes; and determining the location of the fault point using a fast fault location algorithm based on fault classification information and the topology of the transmission line.

[0013] As a preferred embodiment of the transmission line operation and maintenance method based on fault location and prediction described in this invention, the calculation formula for detecting abnormal operating states of the transmission line is as follows:

[0014]

[0015] Among them, P fault (t) represents the probability of a fault occurring in the transmission line at time t; λ is a parameter controlling the slope of the activation function; if the probability of a fault occurs P fault If (t) is greater than the first threshold, then the transmission line is determined to be faulty; if the probability of fault occurrence P fault If (t) is not greater than the first threshold, the transmission line is determined to be operating normally; the calculation formula for the normal operating state is as follows:

[0016]

[0017] Among them, F normal (t) represents the abstract characteristics of the normal operating state of the transmission line at time t; the formula for calculating the location of the fault point is as follows:

[0018]

[0019] Among them, L fault (t) represents the location of the fault at time t; β is the influence factor of weighted historical data in the loss function; F normal (τ) represents the abstract characteristics of the normal operating state of the transmission line at time τ; argmin is the parameter value that makes the function reach its minimum value.

[0020] As a preferred embodiment of the transmission line operation and maintenance method based on fault location and prediction described in this invention, the method of predicting the future operating status of the transmission line includes the following steps: using a deep learning model to analyze the trends of historical data and current data to predict the future line status; classifying the types of faults that occur; determining the fault occurrence time window based on the predicted future line status and sending early warning information in advance.

[0021] As a preferred embodiment of the transmission line operation and maintenance method based on fault location and prediction described in this invention, the calculation formula for predicting the future state of the line is as follows:

[0022]

[0023] in, W represents the predicted future state of the line at time t. prediction The weighting parameters are used for prediction; the calculation formula for the fault occurrence time window is as follows:

[0024]

[0025] Among them, P fault-time (t) represents the probability of a fault occurring within a time window at time t; if the probability of a fault occurring within a time window is P... fault-time If (t) is not greater than the second threshold, the predicted state is determined to be normal, and no warning is triggered; if the probability P of the fault occurrence time window is less than the second threshold, the predicted state is determined to be normal, and no warning is triggered. fault-time (t) If the fault occurrence time window probability is between the second and third thresholds, then the fault occurrence time window probability is recalculated and the relevant information is recorded; if the fault occurrence time window probability P fault-time If (t) is greater than the third threshold, an alert will be triggered and the maintenance personnel will be notified.

[0026] Secondly, to further address the safety issues existing in the operation and maintenance of transmission lines, this invention provides a transmission line operation and maintenance system based on fault location and prediction, comprising: a model building module for collecting real-time and historical operation data of the transmission line and constructing a deep learning model based on spatial features and time series; a fault location module for using the deep learning model to detect whether a fault has occurred in the transmission line and locate the fault point; a prediction module for predicting the future operating state of the transmission line and triggering an early warning based on the future fault occurrence time; and an operation and maintenance module for formulating a transmission line maintenance plan based on the detected fault point location and the predicted future operating state.

[0027] Thirdly, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the computer program, when executed by the processor, implements any step of the transmission line operation and maintenance method based on fault location and prediction as described in the first aspect of the present invention.

[0028] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the transmission line operation and maintenance method based on fault location and prediction as described in the first aspect of the present invention.

[0029] The beneficial effects of this invention are as follows: By utilizing Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM) to construct a deep learning model, this invention achieves intelligent monitoring and learning of transmission lines, improving the ability to perceive changes in operating status; by utilizing rapid fault location, it effectively reduces fault investigation time, reduces the impact of faults on the system, and enhances the fault response capability of transmission lines; based on the advance prediction of future operating status, the system can take measures before potential problems occur, thereby improving the reliability and maintainability of transmission lines and reducing maintenance costs. Attached Figure Description

[0030] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0031] Figure 1 This is a flowchart illustrating the implementation of the present invention in Example 1.

[0032] Figure 2 This is a diagram of the early warning triggering strategy in Example 1. Detailed Implementation

[0033] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0034] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0035] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation 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 a single or selective embodiment that is mutually exclusive with other embodiments.

[0036] Example 1

[0037] Reference Figure 1 and Figure 2 This is the first embodiment of the present invention, which provides a transmission line operation and maintenance method based on fault location and prediction, including the following steps:

[0038] S1: Collect real-time and historical operating data of cables in power transmission lines, and build a deep learning model based on convolutional neural network (CNN) and long short-term memory network (LSTM).

[0039] Preferred, such as Figure 1The diagram illustrates the implementation process of this invention. By collecting real-time and historical operating data of cables in transmission lines, a deep learning model is constructed using a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) network to analyze the real-time cable data. If a fault is detected in the transmission line, the fault point is located. If no fault is detected, the future state of the transmission line is directly predicted. After predicting the location of the future fault, the fault occurrence time window is confirmed, and it is determined whether to issue an early warning. Finally, a transmission line maintenance plan is formulated based on the early warning result and the confirmed current fault location, and the model parameters are dynamically adjusted according to real-time data.

[0040] Preferably, the real-time operating data includes the current, voltage, and temperature of the cables in the transmission line.

[0041] Preferably, the historical operating data includes data on cables in the transmission line under normal operating conditions and data on cables in the transmission line under different types of fault conditions.

[0042] Furthermore, constructing a deep learning model includes the following steps: using a convolutional neural network (CNN) for spatial feature extraction and using a long short-term memory network (LSTM) for time series modeling.

[0043] Historical operating data is labeled with status, including labels for normal and abnormal states. The specific formulas for current, voltage, and temperature are as follows:

[0044]

[0045] Where D(t) is the integrated data of current, voltage and temperature; I(τ) is the current data; V(τ) is the voltage data; T(τ) is the temperature data; and τ is the integral variable of time.

[0046] Supervised learning is performed using labeled historical operational data, and the model parameters are optimized to enable the model to accurately predict the operational status of the line. The formula for calculating the complex loss function of supervised learning is as follows:

[0047]

[0048] in, The complex loss function for supervised learning; t is the system runtime; β is the weighted historical data factor in the loss function; N is the number of samples in the loss function; y i The output of a deep learning model; This is the actual value.

[0049] Specifically, the calculation formula for deep learning models is as follows:

[0050]

[0051] Where F(x, t) represents the output feature of the deep learning model, containing spatial and temporal information; x represents the input data; t represents the system runtime; K represents the number of convolutional kernels, indicating the number of convolutional kernels used in the spatial feature extraction process; α represents the decay factor in time series modeling; σ represents the sigmoid function; W k b represents the weight parameters of the k-th convolutional kernel. k U is the bias parameter of the k-th convolution kernel; tanh is the hyperbolic tangent function used to introduce nonlinearity; U k Here, h represents the weight matrix in a Long Short-Term Memory (LSTM) network, indicating the weight parameters of the k-th LSTM unit. t-1 τ represents the hidden state in the previous time step in the LSTM; τ is the integral variable over time.

[0052] Specifically, by combining convolutional neural networks (CNNs) and long short-term memory networks (LSTMs), it is possible to simultaneously learn the spatial and temporal characteristics of transmission lines, comprehensively describe the line status, and lay the foundation for fault diagnosis and prediction.

[0053] S2: Utilize deep learning models to analyze real-time operational data and locate fault points.

[0054] Specifically, locating the fault point includes the following steps: real-time monitoring of relevant data of the transmission line and using deep learning models to learn the normal operating status.

[0055] It detects abnormal operating conditions of transmission lines and compares and classifies abnormal data with known fault modes, including short circuit, open circuit, and partial discharge.

[0056] Based on fault classification information and the topology of transmission lines, a fast fault location algorithm is used to determine the location of the fault point.

[0057] Specifically, the calculation formula for detecting abnormal operating conditions of transmission lines is as follows:

[0058]

[0059] Among them, P fault (t) represents the probability of a fault occurring in the transmission line at time t; λ is a parameter controlling the slope of the activation function.

[0060] Furthermore, if the probability of failure P fault If (t) is greater than the first threshold, then the transmission line is determined to be faulty.

[0061] If the probability of failure occurs is P fault If (t) is not greater than the first threshold, the transmission line is determined to be operating normally.

[0062] Specifically, the calculation formula for normal operation is as follows:

[0063]

[0064] Among them, F normal (t) is an abstract feature of the normal operating state of the transmission line at time t.

[0065] Furthermore, the formula for calculating the location of the fault is as follows:

[0066]

[0067] Among them, L fault (t) represents the location of the fault at time t; β is the influence factor of weighted historical data in the loss function; F normal (τ) represents the abstract characteristics of the normal operating state of the transmission line at time τ; argmin is the parameter value that makes the function reach its minimum value.

[0068] Specifically, by utilizing a fast fault location algorithm combined with the transmission line topology, the location of the fault point can be located efficiently and accurately, improving fault handling efficiency, providing a basis for fault disposal decisions, shortening line restoration time, and reducing economic losses.

[0069] S3: Predict the future operating status of transmission lines based on deep learning models and determine whether to trigger an early warning.

[0070] Specifically, predicting the future operating status of transmission lines involves the following steps: using deep learning models to analyze trends in historical and current data to predict the future status of the lines.

[0071] The types of failures that occur are categorized.

[0072] Based on predictions of future line conditions, the time window for fault occurrence is determined, and early warning information is sent in advance.

[0073] Furthermore, the formula for predicting future line conditions is as follows:

[0074]

[0075] in, W represents the predicted future state of the line at time t. prediction These are the weight parameters for prediction.

[0076] Furthermore, the formula for calculating the fault occurrence time window is as follows:

[0077]

[0078] Among them, P fault-time(t) represents the probability of the fault occurring within the time window at time t.

[0079] Specifically, such as Figure 2 The diagram shows the early warning triggering strategy of this invention. If the probability P of the fault occurrence time window is... fault-time If (t) is not greater than the second threshold, the predicted state is determined to be normal and no warning is triggered.

[0080] If the probability of the fault occurring within the time window is P fault-time (t) If the fault occurs between the second and third thresholds, the probability of the fault occurrence time window is recalculated and the relevant information is recorded.

[0081] If the probability of the fault occurring within the time window is P fault-time If (t) is greater than the third threshold, an alert will be triggered and the maintenance personnel will be notified.

[0082] Specifically, by collecting a large amount of transmission line data under normal operation and known fault scenarios, the first, second, and third thresholds in the initial early warning triggering strategy are set. During iterative training, the specific values ​​of the thresholds are adjusted according to the results and actual needs, and finally the optimal first, second, and third thresholds are obtained, which can cover fault scenarios to the greatest extent and avoid misjudging normal fluctuations.

[0083] Specifically, by analyzing historical trends and current data, it is possible to predict the future operating status of the lines, detect potential faults in advance, and trigger early warnings based on the prediction results. This provides maintenance personnel with sufficient preparation time to implement preventive maintenance, avoid the escalation of faults, and reduce the impact of faults.

[0084] S4: Develop a transmission line maintenance plan based on the fault point and the future operating status of the transmission line, and optimize the deep learning model based on real-time data.

[0085] Developing a transmission line maintenance plan includes the following steps: Based on the detected fault location and specific line structure, develop a fault handling plan, including line switching, equipment replacement, or equipment repair.

[0086] Preventive maintenance plans are developed based on forecasts of future operating conditions. These plans include regular inspections, equipment replacement, and performance optimization to ensure that lines are maintained before failures occur, thus reducing potential impacts.

[0087] Establish an adaptive update mechanism to dynamically adjust model parameters based on new real-time data, improve prediction accuracy, and ensure that the model can adapt to changes in line conditions and new fault modes.

[0088] This embodiment also provides a transmission line operation and maintenance system based on fault location and prediction, including: a model building module, used to collect real-time and historical operation data of the transmission line, and build a deep learning model based on spatial features and time series; a fault location module, used to use the deep learning model to detect whether a fault has occurred in the transmission line and locate the fault point; a prediction module, used to predict the future operating state of the transmission line and trigger an early warning based on the future fault occurrence time; and an operation and maintenance module, used to formulate a transmission line maintenance plan based on the detected fault point location and the predicted future operating state.

[0089] This embodiment also provides a computer device applicable to a transmission line operation and maintenance method based on fault location and prediction, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the transmission line operation and maintenance method based on fault location and prediction proposed in the above embodiment.

[0090] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0091] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements a transmission line operation and maintenance method based on fault location and prediction as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0092] In summary, this invention utilizes a deep learning model constructed using Convolutional Neural Networks (CNN) and Long Short-Term Memory Networks (LSTM) to achieve intelligent monitoring and learning of transmission lines, thereby improving the ability to perceive changes in operating status. Rapid fault location effectively reduces fault investigation time, minimizes the impact of faults on the system, and enhances the fault response capability of transmission lines. Furthermore, advance prediction of future operating status enables the system to take measures before potential problems occur, thereby improving the reliability and maintainability of transmission lines and reducing maintenance costs.

[0093] Example 2

[0094] Referring to Tables 1 to 4, this is the second embodiment of the present invention. The difference between this embodiment and the first embodiment is that, in order to verify its beneficial effects, operational data and related descriptions of the present invention in a real environment are provided.

[0095] Table 1 shows the operating data of cables in power transmission lines collected in a real environment by the present invention, including the current, voltage and temperature of the cables in the power transmission lines, which provides a data basis for subsequent fault detection and prediction of future operating status.

[0096] Table 1. Operational Data of Transmission Lines

[0097] sample Current (kA) Voltage (kV) Temperature (°C) 1 0.12 220 75 2 0.13 230 78 3 0.11 225 72 ... ... ... ... n 0.12 215 80

[0098] Based on the transmission line operation data provided in the table above, a deep learning model is used to analyze the data and determine whether a fault has occurred in the current transmission line. As shown in Table 2, the probability of fault occurrence calculated by our invention is used to predict possible fault states. Compared with the existing technology, our invention improves the accuracy of fault detection and speeds up the troubleshooting of transmission line faults.

[0099] Table 2 Fault Probability Data Table

[0100] sample Failure probability 1 0.04 2 0.10 3 0.03 ... ... n 0.08

[0101] Tables 3 and 4 show the prediction of the future operating status of transmission lines and the determination of whether an early warning will be triggered according to the present invention.

[0102] Table 3. Forecast of Future Operating Status of Transmission Lines

[0103] sample Predicted state Fault location 1 normal none 2 abnormal Node B 3 normal none ... ... ... n abnormal Node C

[0104] Table 4. Fault Occurrence Time Window Probability and Early Warning Data

[0105] sample Fault occurrence time window probability Warning triggered 1 0.03 No trigger 2 0.10 Triggering an alert 3 0.02 No trigger ... ... ... n 0.08 Record information and recalculate

[0106] As can be seen from the table above, our invention performs excellently in predicting line status and locating fault points, and is more reliable and accurate than traditional methods. At the same time, the established early warning mechanism can detect potential faults in advance, and has stronger real-time performance and predictability.

[0107] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A transmission line operation and maintenance method based on fault location and prediction, characterized in that: include: Real-time and historical operating data of cables in power transmission lines are collected, and deep learning models are built based on convolutional neural networks (CNN) and long short-term memory networks (LSTM). The deep learning model is used to analyze real-time operating data and locate fault points; Based on the deep learning model, predict the future operating status of the transmission line and determine whether to trigger an early warning. Based on the fault points and the future operating status of the transmission lines, a maintenance plan for the transmission lines is formulated, and the deep learning model is optimized based on real-time data. The real-time operating data includes the current, voltage, and temperature of the cables in the transmission line; The historical operating data includes data on cables in transmission lines under normal operating conditions and data on cables in transmission lines under different types of fault conditions; The construction of the deep learning model includes the following steps: Spatial feature extraction is performed using a convolutional neural network (CNN), and time series modeling is performed using a long short-term memory network (LSTM). Status annotations are added to historical operational data; Supervised learning and model parameter optimization are performed using labeled historical runtime data; The calculation formula for the deep learning model is as follows: Where F(x,t) represents the output feature of the deep learning model; x represents the input data; t represents the system runtime; K represents the number of convolutional kernels; α represents the decay factor in time series modeling; σ represents the sigmoid function; W k b represents the weight parameters of the k-th convolutional kernel. k U is the bias parameter of the k-th convolution kernel; tanh is the hyperbolic tangent function; U k h represents the weight parameters of the k-th LSTM unit. t-1 τ represents the hidden state in the previous time step in the LSTM; τ is the integral variable over time. Locating the fault point includes the following steps: Real-time monitoring of relevant data of power transmission lines and use deep learning models to learn the normal operating status; Detect abnormal operating conditions of transmission lines and compare and classify abnormal data with known fault modes; Based on fault classification information and the topology of transmission lines, a fast fault location algorithm is used to determine the location of the fault point.

2. The transmission line operation and maintenance method based on fault location and prediction as described in claim 1, characterized in that: The calculation formula for detecting abnormal operating conditions of transmission lines is as follows: Among them, P fault (t) represents the probability of a fault occurring in the transmission line at time t; λ is a parameter controlling the slope of the activation function; If the probability of failure occurs is P fault If (t) is greater than the first threshold, then the transmission line is determined to be faulty; If the probability of failure occurs is P fault If (t) is not greater than the first threshold, the transmission line is determined to be operating normally; The formula for calculating the normal operating state is as follows: Among them, F normal (t) represents the abstract characteristics of the normal operating state of the transmission line at time t; The formula for calculating the location of the fault point is as follows: Among them, L fault (t) represents the location of the fault at time t; β is the influence factor of weighted historical data in the loss function; F normal (τ) represents the abstract characteristics of the normal operating state of the transmission line at time τ; argmin is the parameter value that makes the function reach its minimum value.

3. The transmission line operation and maintenance method based on fault location and prediction as described in claim 2, characterized in that: The prediction of the future operating status of the transmission line includes the following steps: Utilize deep learning models to analyze trends in historical and current data to predict future line conditions; Classify the types of failures that occur; Based on predictions of future line conditions, the time window for fault occurrence is determined, and early warning information is sent in advance.

4. The transmission line operation and maintenance method based on fault location and prediction as described in claim 3, characterized in that: The formula for predicting future line conditions is as follows: in, W represents the predicted future state of the line at time t. prediction These are the weight parameters for prediction; The formula for calculating the fault occurrence time window is as follows: Among them, P fault-time (t) represents the probability of the fault occurring within the time window at time t; If the probability of the fault occurring within the time window is P fault-time If (t) is not greater than the second threshold, the predicted state is determined to be normal and no warning is triggered; If the probability of the fault occurring within the time window is P fault-time (t) If the fault occurs between the second and third thresholds, the probability of the fault occurrence time window is recalculated and the relevant information is recorded. If the probability of the fault occurring within the time window is P fault-time If (t) is greater than the third threshold, an alert will be triggered and the maintenance personnel will be notified.

5. A transmission line operation and maintenance system based on fault location and prediction, based on the transmission line operation and maintenance method based on fault location and prediction as described in any one of claims 1 to 4, characterized in that: include, The model building module is used to collect real-time and historical operating data of transmission lines and build deep learning models based on spatial features and time series. The fault location module is used to detect whether a fault has occurred in the transmission line and to locate the fault point using a deep learning model. The prediction module is used to predict the future operating status of transmission lines and trigger early warnings based on the future occurrence time of faults; The operation and maintenance module is used to formulate transmission line maintenance plans based on the detected fault locations and predicted future operating conditions.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the transmission line operation and maintenance method based on fault location and prediction as described in any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the transmission line operation and maintenance method based on fault location and prediction as described in any one of claims 1 to 4.

Images