Line safety online monitoring method and device for power supply system

Abstract

The invention discloses a line safety online monitoring method and device for a power supply system, and relates to the technical field of power system monitoring, and the method comprises the steps: S1, data collection: employing a plurality of sensors installed on a power supply line, and collecting all operation parameters of the line in real time; s2, data transmission: transmitting the acquired data to a data processing center in real time through wireless communication; s3, data preprocessing: the data processing center preprocesses the received data; s4, constructing a multi-source data fusion control model based on the neural network; s5, performing fault feature analysis on the line and positioning a fault position; s6, carrying out graded early warning on faults generated in the line, and pushing early warning information at the same time; according to the method, multiple sensors are deployed to collect the multi-source data, and the control model based on the neural network is constructed to perform fusion analysis on the data, so that the safety state of the line can be comprehensively and accurately evaluated.

Description

Technical Field

[0001] This application relates to the field of power system monitoring technology, and more specifically, to a method and apparatus for online monitoring of line safety in a power supply system. Background Technology

[0002] In modern power systems, the safe and stable operation of power supply lines is crucial. However, existing methods for monitoring the safety of power supply lines have many shortcomings. For example, traditional monitoring methods often only monitor a single parameter, failing to comprehensively reflect the actual safety status of the line; and the data processing and analysis methods are relatively simple, making it difficult to accurately predict potential line faults. Furthermore, even when line anomalies are detected, traditional methods suffer from insufficient accuracy and slow response in fault location, failing to provide timely and accurate fault location and effective early warning, thus prolonging fault repair time and affecting power supply reliability.

[0003] Therefore, there is an urgent need for a method that can comprehensively consider multiple factors, accurately monitor the safety status of power supply lines, quickly locate faults, and effectively provide early warning and handling. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, this application provides a method and apparatus for online monitoring of line safety in a power supply system to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, this application provides the following technical solution: a method for online monitoring of line safety in a power supply system, the method comprising:

[0006] S1. Data Acquisition: Using multiple sensors installed on the power supply line, various operating parameters of the line are collected in real time. The sensors are distributed in different locations on the line to comprehensively monitor the line, and also collect environmental humidity and wind speed.

[0007] S2. Data transmission: The collected data is transmitted to the data processing center in real time via wireless communication;

[0008] S3. Data Preprocessing: The data processing center preprocesses the received data;

[0009] S4. Construct a multi-source data fusion control model based on neural networks, and use the multi-source data fusion control model to evaluate the safety status of the line;

[0010] S5. Perform fault characteristic analysis on the line and locate the fault location;

[0011] S6. Implement graded early warning for faults occurring in the line, and push the early warning information.

[0012] Furthermore, the multiple sensors in S1 include a current sensor, a voltage sensor, a temperature sensor, a humidity sensor, a vibration sensor, and a sag sensor, and the various operating parameters include current, voltage, temperature, humidity, vibration, and sag.

[0013] Furthermore, in S2, data transmission adopts 5G and LoRa dual-mode communication, converting electrical signals into digital signals and transmitting them to the data processing center;

[0014] 5G is used for real-time data transmission with a bandwidth of ≥10Mbps, while LoRa is used for low-power status monitoring. During data transmission, an adaptive compression transmission model and an anti-interference transmission protocol are employed. The adaptive compression transmission model uses wavelet packet transform to achieve layered data compression, dynamically adjusting the compression ratio through information entropy. ,in, For the original data entropy, To determine the entropy of the compressed data, lossless compression is used for fault transient data and lossy compression is used for ordinary data, with a compression ratio of 3:1 to 10:1 between lossless and lossy compression.

[0015] The anti-interference transmission protocol is specifically an OFDM-based wireless transmission protocol that employs channel estimation and equalization techniques, achieving a bit error rate of... The following is the formula for calculating the bit error rate (BER): ,in, is the Gaussian tail function, SNR is the signal-to-noise ratio, and M is the modulation order.

[0016] Furthermore, in the data preprocessing of S3, median filtering is used to eliminate random impulse interference, wavelet transform is used to decompose the signal to remove white noise, while retaining the effective features in the data and identifying and correcting abnormal data.

[0017] The current data were obtained after denoising and correction. Voltage data Temperature data and ambient humidity data For current data Voltage data Temperature data and ambient humidity data Normalization is performed using the following formula: ,in, This represents the data obtained after denoising and correction. This represents the minimum value of this type of data. This represents the maximum value of this type of data. The normalized data is processed by normalizing data from different ranges to the same scale.

[0018] Furthermore, in S4, a multi-source data fusion control model based on a neural network is constructed, and the multi-source data fusion control model includes an input layer, several hidden layers, and an output layer:

[0019] Input layer: Receives normalized data, i.e., normalized current data. Voltage normalized data Temperature normalized data Humidity normalized data and wind speed normalized data The input layer has n nodes, corresponding to n input data;

[0020] Hidden layer: 1 The number of nodes in the layer is , , Let be the number of hidden layers. The weight matrix from the input layer to the first hidden layer is: The bias vector is Hidden layer layer to the first The weight matrix of the layer is The bias vector is Hidden layer Layer output The calculation formula is: ,in, For input layer data, The activation function is the ReLU function. ;

[0021] Output layer: The output of the output layer is the line safety status assessment value. The calculation formula is: ,in, Let be the activation function of the output layer, and its value range is . , The closer to 1, the better the line's safety status; the closer to 0, the greater the probability of a line fault.

[0022] During model training, the loss function Loss is defined using the mean squared error as the loss function, and the formula is as follows: ,in, This represents the actual safety status value of the line. Let n be the predicted value of the model and n be the number of samples. The loss function is minimized using the stochastic gradient descent algorithm to determine the model's weight matrix. and bias vector The optimal value;

[0023] In online monitoring, the preprocessed data is input into the trained control model to obtain the line safety status assessment value. ,when Below the set safety threshold When necessary, an early warning signal is issued and a fault location strategy is activated.

[0024] Furthermore, in step S5, a fault feature database is first established, which stores the data change characteristics of current, voltage, temperature, etc., corresponding to different types of faults. When the system detects a line abnormality, it immediately... The currently collected multi-source data is compared with the fault feature database to analyze the types of faults that have occurred.

[0025] when At that time, a fault location strategy is executed. The fault location strategy is as follows: the power supply line is divided into multiple monitoring areas, the sensor data in each area is centrally processed, and the area location algorithm is combined with the traveling wave location principle and current and voltage change analysis.

[0026] The propagation speed of a traveling wave in a transmission line is v. When a fault traveling wave signal is detected, the time difference between the reception of the traveling wave signal at different monitoring points is recorded. Suppose there are two monitoring points A and B. Point A receives the traveling wave signal first, and point B receives the traveling wave signal later. The distance between points A and B is . The formula for calculating the distance x from the fault point to point A is: By observing the sudden changes in current and voltage in different regions, the fault range can be narrowed down, and the specific area where the fault is located can be determined.

[0027] After identifying the fault area, the high-precision data from sensors within the area are used to accurately calculate the fault location using the least squares method, specifically:

[0028] Suppose there are k sensors in the area, and their coordinates are as follows: , ,..., The fault characteristic parameters detected by each sensor are as follows: Establish fault location The relationship model between the parameters detected by each sensor is solved using the least squares method to minimize the objective function F. The value, the objective function F is: ,in Based on the functional relationship established according to the fault characteristics, the precise location coordinates of the fault are obtained by solving this equation. .

[0029] Furthermore, in step S6, the warning is divided into three levels based on the severity and scope of the fault, specifically:

[0030] A Level 1 warning indicates that a fault has caused a partial power outage or minor equipment damage. The system will notify maintenance personnel via SMS and email, and display the fault location in yellow on the monitoring platform.

[0031] A Level 2 warning indicates that a fault has caused a large-scale power outage or moderate equipment damage. In addition to SMS and email notifications, the system will also remind maintenance personnel by phone and display the fault location in orange on the monitoring platform.

[0032] A Level 3 warning indicates that a fault has caused a large-scale power outage or serious equipment damage. The system immediately activates the emergency response mechanism, notifies all relevant personnel through various means such as broadcasting, SMS and telephone, and displays the fault location in red on the monitoring platform, while automatically cutting off the power supply to the fault area.

[0033] While issuing the warning, detailed information on the fault location, fault type, and scope of impact will be pushed to relevant departments and personnel.

[0034] Furthermore, an online monitoring device for line safety in a power supply system includes:

[0035] The data acquisition module uses multiple sensors installed on the power supply line to collect various operating parameters of the line in real time, and the sensors are distributed in different locations on the line to comprehensively monitor the line.

[0036] The data transmission module is used to transmit the collected data to the data processing center in real time via wireless communication;

[0037] The data preprocessing module is used by the data processing center to preprocess the received data;

[0038] The multi-source data fusion control model construction module is used to build a neural network-based multi-source data fusion control model, and to evaluate the safety status of the line through the multi-source data fusion control model;

[0039] The fault analysis and location module is used to analyze the fault characteristics of the line and locate the fault location.

[0040] The early warning module is used to provide graded early warnings for faults occurring in the line and to push the early warning information.

[0041] Furthermore, a terminal device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of a method for online monitoring of line safety.

[0042] Furthermore, a computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of a method for online monitoring of line safety in a power supply system.

[0043] The technical effects and advantages of this application are as follows:

[0044] Compared with existing technologies, this online monitoring method and device for power supply system line safety, by deploying multiple sensors to collect multi-source data and constructing a control model based on neural networks to fuse and analyze the data, can comprehensively and accurately assess the safety status of the line.

[0045] Normalization ensures data comparability, and the introduction of loss functions and optimization algorithms enables the model to be continuously optimized, improving monitoring accuracy. On this basis, the newly added fault location module uses a combination of multiple algorithms to quickly and accurately locate the fault location. The improved early warning mechanism realizes hierarchical early warning and information push, effectively shortening fault handling time and reducing the losses caused by faults.

[0046] The fault location module employs a regional location algorithm that combines fault feature analysis, traveling wave location principle with current and voltage change analysis, and least squares method for precise location. The combination of these algorithms enables the rapid and accurate determination of the fault location, overcoming the problems of insufficient fault location accuracy and slow response in traditional methods, thus saving time for fault repair.

[0047] A tiered early warning mechanism was established, which classifies faults into three levels based on their severity and scope of impact. Different early warning methods and handling measures are adopted, and information is pushed out and maintenance is tracked simultaneously. This achieves timely and targeted fault warnings, effectively shortens fault handling time, reduces power outage losses and equipment damage caused by faults, and ensures power supply reliability. Attached Figure Description

[0048] Figure 1 This is a flowchart illustrating the method of this application;

[0049] Figure 2 This is a schematic diagram of the structure of an online monitoring device for line safety in a power supply system according to this application. Detailed Implementation

[0050] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0051] Example 1

[0052] As attached Figure 1 The method shown is an online monitoring method for line safety in a power supply system, the method comprising:

[0053] S1. Data Acquisition: Using multiple sensors installed on the power supply line, various operating parameters of the line are collected in real time. The sensors are distributed in different locations on the line to comprehensively monitor the line, and also collect environmental humidity and wind speed.

[0054] S1 contains multiple sensors including a current sensor, a voltage sensor, a temperature sensor, a humidity sensor, a vibration sensor, and a sag sensor, and its various operating parameters include current, voltage, temperature, humidity, vibration, and sag.

[0055] S2. Data transmission: The collected data is transmitted to the data processing center in real time via wireless communication;

[0056] Data transmission in S2 uses 5G and LoRa dual-mode communication, converting electrical signals into digital signals before transmitting them to the data processing center;

[0057] 5G is used for real-time data transmission with a bandwidth of ≥10Mbps, while LoRa is used for low-power status monitoring. During data transmission, an adaptive compression transmission model and an anti-interference transmission protocol are employed. The adaptive compression transmission model uses wavelet packet transform to achieve layered data compression, dynamically adjusting the compression ratio through information entropy. ,in, For the original data entropy, To determine the entropy of the compressed data, lossless compression is used for fault transient data and lossy compression is used for ordinary data, with a compression ratio of 3:1 to 10:1 between lossless and lossy compression.

[0058] The anti-interference transmission protocol is specifically an OFDM-based wireless transmission protocol that employs channel estimation and equalization techniques, achieving a bit error rate of... The following is the formula for calculating the bit error rate (BER): ,in, is the Gaussian tail function, SNR is the signal-to-noise ratio, and M is the modulation order;

[0059] S3. Data Preprocessing: The data processing center preprocesses the received data;

[0060] In S3, random impulse interference is eliminated through median filtering and white noise is removed by decomposing the signal through wavelet transform, while retaining the effective features in the data and identifying and correcting abnormal data.

[0061] The current data were obtained after denoising and correction. Voltage data Temperature data and ambient humidity data For current data Voltage data Temperature data and ambient humidity data Normalization is performed using the following formula: ,in, This represents the data obtained after denoising and correction. This represents the minimum value of this type of data. This represents the maximum value of this type of data. For normalized data, normalization processing is used to unify data from different ranges to the same scale;

[0062] S4. Construct a multi-source data fusion control model based on neural networks, and use the multi-source data fusion control model to evaluate the safety status of the line;

[0063] In S4, a multi-source data fusion control model based on a neural network is constructed. The multi-source data fusion control model includes an input layer, several hidden layers, and an output layer.

[0064] Input layer: Receives normalized data, i.e., normalized current data. Voltage normalized data Temperature normalized data Humidity normalized data and wind speed normalized data The input layer has n nodes, corresponding to n input data;

[0065] Hidden layer: 1 The number of nodes in the layer is , , Let be the number of hidden layers. The weight matrix from the input layer to the first hidden layer is: The bias vector is Hidden layer layer to the first The weight matrix of the layer is The bias vector is Hidden layer Layer output The calculation formula is: ,in, For input layer data, The activation function is the ReLU function. ;

[0066] Output layer: The output of the output layer is the line safety status assessment value. The calculation formula is: ,in, Let be the activation function of the output layer, and its value range is . , The closer to 1, the better the line's safety status; the closer to 0, the greater the probability of a line fault.

[0067] During model training, the loss function Loss is defined using the mean squared error as the loss function, and the formula is as follows: ,in, This represents the actual safety status value of the line. Let n be the predicted value of the model and n be the number of samples. The loss function is minimized using the stochastic gradient descent algorithm to determine the model's weight matrix. and bias vector The optimal value;

[0068] In online monitoring, the preprocessed data is input into the trained control model to obtain the line safety status assessment value. ,when Below the set safety threshold When necessary, an early warning signal is issued and a fault location strategy is activated;

[0069] S5. Perform fault characteristic analysis on the line and locate the fault location;

[0070] S5 first establishes a fault characteristic database, which stores the data change characteristics of current, voltage, temperature, etc., corresponding to different types of faults. When the system detects a line abnormality, it immediately... The currently collected multi-source data is compared with the fault feature database to analyze the types of faults that have occurred.

[0071] when At that time, a fault location strategy is executed. The fault location strategy is as follows: the power supply line is divided into multiple monitoring areas, the sensor data in each area is centrally processed, and the area location algorithm is combined with the traveling wave location principle and current and voltage change analysis.

[0072] The propagation speed of a traveling wave in a transmission line is v. When a fault traveling wave signal is detected, the time difference between the reception of the traveling wave signal at different monitoring points is recorded. Suppose there are two monitoring points A and B. Point A receives the traveling wave signal first, and point B receives the traveling wave signal later. The distance between points A and B is . The formula for calculating the distance x from the fault point to point A is: By observing the sudden changes in current and voltage in different regions, the fault range can be narrowed down, and the specific area where the fault is located can be determined.

[0073] After identifying the fault area, the high-precision data from sensors within the area are used to accurately calculate the fault location using the least squares method, specifically:

[0074] Suppose there are k sensors in the area, and their coordinates are as follows: , ,..., The fault characteristic parameters detected by each sensor are as follows: Establish fault location The relationship model between the parameters detected by each sensor is solved using the least squares method to minimize the objective function F. The value, the objective function F is: ,in Based on the functional relationship established according to the fault characteristics, the precise location coordinates of the fault are obtained by solving this equation. ;

[0075] S6. Implement graded early warning for faults occurring in the line, and push the early warning information.

[0076] In S6, warnings are divided into three levels based on the severity and scope of the fault, as follows:

[0077] A Level 1 warning indicates that a fault has caused a partial power outage or minor equipment damage. The system will notify maintenance personnel via SMS and email, and display the fault location in yellow on the monitoring platform.

[0078] A Level 2 warning indicates that a fault has caused a large-scale power outage or moderate equipment damage. In addition to SMS and email notifications, the system will also remind maintenance personnel by phone and display the fault location in orange on the monitoring platform.

[0079] A Level 3 warning indicates that a fault has caused a large-scale power outage or serious equipment damage. The system immediately activates the emergency response mechanism, notifies all relevant personnel through various means such as broadcasting, SMS and telephone, and displays the fault location in red on the monitoring platform, while automatically cutting off the power supply to the fault area.

[0080] While issuing the warning, detailed information on the fault location, fault type, and scope of impact will be pushed to relevant departments and personnel.

[0081] Example 2

[0082] like Figure 2 As shown, an online monitoring device for line safety in a power supply system includes:

[0083] The data acquisition module uses multiple sensors installed on the power supply line to collect various operating parameters of the line in real time, and the sensors are distributed in different locations on the line to comprehensively monitor the line.

[0084] The data transmission module is used to transmit the collected data to the data processing center in real time via wireless communication;

[0085] The data preprocessing module is used by the data processing center to preprocess the received data;

[0086] The multi-source data fusion control model construction module is used to build a neural network-based multi-source data fusion control model, and to evaluate the safety status of the line through the multi-source data fusion control model;

[0087] The fault analysis and location module is used to analyze the fault characteristics of the line and locate the fault location.

[0088] The early warning module is used to provide graded early warnings for faults occurring in the line and to push the early warning information.

[0089] Example 3

[0090] A terminal device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of a method for online monitoring of line safety.

[0091] Example 3

[0092] A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the steps of a method for online monitoring of line safety in a power supply system are implemented.

[0093] In the above embodiments, the central processing unit / microprocessor / main control chip, etc., may include, but are not limited to, one or more processors or microprocessors.

[0094] Storage media may include, but are not limited to, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, and computer storage media (such as hard disks, floppy disks, solid-state drives, removable disks, CD-ROMs, DVD-ROMs, Blu-ray discs, etc.).

[0095] The central processing unit / microprocessor / main control chip, etc., can communicate with external devices via I / O bus through wired or wireless networks (not shown).

[0096] The storage medium may also store at least one computer-executable instruction for performing the steps of various functions and / or methods in the embodiments described herein when run by a central processing unit / microprocessor / main control chip, etc.

[0097] In one embodiment, the at least one computer-executable instruction may also be compiled into or comprise a software product, wherein one or more computer-executable instructions are executed by a processor to perform the steps of the various functions and / or methods in the embodiments described herein.

[0098] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0099] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0100] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0101] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for executing all or part of the steps of the methods of the various embodiments of this invention through a computer device (which may be a personal computer, server, or network device, etc.). The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0102] Finally: The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for online monitoring of line safety in a power supply system, characterized in that, The method includes: S1. Data Acquisition: Using multiple sensors installed on the power supply line, various operating parameters of the line are collected in real time. The sensors are distributed in different locations on the line to comprehensively monitor the line, and also collect environmental humidity and wind speed. S2. Data transmission: The collected data is transmitted to the data processing center in real time via wireless communication; S3. Data Preprocessing: The data processing center preprocesses the received data; S4. Construct a multi-source data fusion control model based on neural networks, and use the multi-source data fusion control model to evaluate the safety status of the line; S5. Perform fault characteristic analysis on the line and locate the fault location; S6. Implement graded early warning for faults occurring in the line, and push the early warning information.

2. The method for online monitoring of line safety in a power supply system according to claim 1, characterized in that: The multiple sensors in S1 include a current sensor, a voltage sensor, a temperature sensor, a humidity sensor, a vibration sensor, and a sag sensor, and the various operating parameters include current, voltage, temperature, humidity, vibration, and sag.

3. The online monitoring method for line safety of a power supply system according to claim 2, characterized in that: In S2, data transmission adopts 5G and LoRa dual-mode communication, converting electrical signals into digital signals and transmitting them to the data processing center. 5G is used for real-time data transmission with a bandwidth of ≥10Mbps, while LoRa is used for low-power status monitoring. During data transmission, an adaptive compression transmission model and an anti-interference transmission protocol are employed. The adaptive compression transmission model uses wavelet packet transform to achieve layered data compression, dynamically adjusting the compression ratio through information entropy. ,in, For the original data entropy, To determine the entropy of the compressed data, lossless compression is used for fault transient data and lossy compression is used for ordinary data, with a compression ratio of 3:1 to 10:1 between lossless and lossy compression. The anti-interference transmission protocol is specifically an OFDM-based wireless transmission protocol that employs channel estimation and equalization techniques, achieving a bit error rate of... The following is the formula for calculating the bit error rate (BER): ,in, is the Gaussian tail function, SNR is the signal-to-noise ratio, and M is the modulation order.

4. The method for online monitoring of line safety in a power supply system according to claim 1, characterized in that: In the data preprocessing described in S3, random impulse interference is eliminated by median filtering, white noise is removed by wavelet transform decomposition of the signal, and effective features in the data are preserved, while abnormal data is identified and corrected. The current data were obtained after denoising and correction. Voltage data Temperature data and ambient humidity data For current data Voltage data Temperature data and ambient humidity data Normalization is performed using the following formula: ,in, This represents the data obtained after denoising and correction. This represents the minimum value of this type of data. This represents the maximum value of this type of data. The normalized data is processed by normalizing data from different ranges to the same scale.

5. The online monitoring method for line safety of a power supply system according to claim 4, characterized in that: In S4, a multi-source data fusion control model based on a neural network is constructed, and the multi-source data fusion control model includes an input layer, several hidden layers, and an output layer: Input layer: Receives normalized data, i.e., normalized current data. Voltage normalized data Temperature normalized data Humidity normalized data and wind speed normalized data The input layer has n nodes, corresponding to n input data; Hidden layer: 1 The number of nodes in the layer is , , Let be the number of hidden layers. The weight matrix from the input layer to the first hidden layer is: The bias vector is Hidden layer layer to the first The weight matrix of the layer is The bias vector is Hidden layer Layer output The calculation formula is: ,in, For input layer data, The activation function is the ReLU function. ; Output layer: The output of the output layer is the line safety status assessment value. The calculation formula is: ,in, Let be the activation function of the output layer, and its value range is . , The closer to 1, the better the line's safety status; the closer to 0, the greater the probability of a line fault. During model training, the loss function Loss is defined using the mean squared error as the loss function, and the formula is as follows: ,in, This represents the actual safety status value of the line. Let n be the predicted value of the model and n be the number of samples. The loss function is minimized using the stochastic gradient descent algorithm to determine the model's weight matrix. and bias vector The optimal value; In online monitoring, the preprocessed data is input into the trained control model to obtain the line safety status assessment value. ,when Below the set safety threshold When necessary, an early warning signal is issued and a fault location strategy is activated.

6. The method for online monitoring of line safety in a power supply system according to claim 1, characterized in that: In step S5, a fault characteristic database is first established, which stores the data change characteristics of current, voltage, temperature, etc., corresponding to different types of faults. When the system detects a line abnormality, it immediately... The currently collected multi-source data is compared with the fault feature database to analyze the types of faults that have occurred. when At that time, a fault location strategy is executed. The fault location strategy is as follows: the power supply line is divided into multiple monitoring areas, the sensor data in each area is centrally processed, and the area location algorithm is combined with the traveling wave location principle and current and voltage change analysis. The propagation speed of a traveling wave in a transmission line is v. When a fault traveling wave signal is detected, the time difference between the reception of the traveling wave signal at different monitoring points is recorded. Suppose there are two monitoring points A and B. Point A receives the traveling wave signal first, and point B receives the traveling wave signal later. The distance between points A and B is . The formula for calculating the distance x from the fault point to point A is: By observing the sudden changes in current and voltage in different regions, the fault range can be narrowed down, and the specific area where the fault is located can be determined. After identifying the fault area, the high-precision data from sensors within the area are used to accurately calculate the fault location using the least squares method, specifically: Suppose there are k sensors in the area, and their coordinates are as follows: , ,..., The fault characteristic parameters detected by each sensor are as follows: Establish fault location The relationship model between the parameters detected by each sensor is solved using the least squares method to minimize the objective function F. The value, the objective function F is: ,in Based on the functional relationship established according to the fault characteristics, the precise location coordinates of the fault are obtained by solving this equation. .

7. The method for online monitoring of line safety in a power supply system according to claim 1, characterized in that: In S6, the early warning is divided into three levels according to the severity and scope of the fault, as follows: A Level 1 warning indicates that a fault has caused a partial power outage or minor equipment damage. The system will notify maintenance personnel via SMS and email, and display the fault location in yellow on the monitoring platform. A Level 2 warning indicates that a fault has caused a large-scale power outage or moderate equipment damage. In addition to SMS and email notifications, the system will also remind maintenance personnel by phone and display the fault location in orange on the monitoring platform. A Level 3 warning indicates that a fault has caused a large-scale power outage or serious equipment damage. The system immediately activates the emergency response mechanism, notifies all relevant personnel through various means such as broadcasting, SMS and telephone, and displays the fault location in red on the monitoring platform, while automatically cutting off the power supply to the fault area. While issuing the warning, detailed information on the fault location, fault type, and scope of impact will be pushed to relevant departments and personnel.

8. An online monitoring device for line safety in a power supply system, characterized in that, include: The data acquisition module uses multiple sensors installed on the power supply line to collect various operating parameters of the line in real time, and the sensors are distributed in different locations on the line to comprehensively monitor the line. The data transmission module is used to transmit the collected data to the data processing center in real time via wireless communication; The data preprocessing module is used by the data processing center to preprocess the received data; The multi-source data fusion control model construction module is used to build a neural network-based multi-source data fusion control model, and to evaluate the safety status of the line through the multi-source data fusion control model; The fault analysis and location module is used to analyze the fault characteristics of the line and locate the fault location. The early warning module is used to provide graded early warnings for faults occurring in the line and to push the early warning information.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements the steps of the online monitoring method for line safety of the power supply system as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the online monitoring method for line safety of a power supply system as described in any one of claims 1 to 7.

Images