Power transmission line risk assessment method and device, medium and electronic equipment

Abstract

The invention relates to a power transmission line risk assessment method and device, a medium and electronic equipment, and the method comprises the steps: obtaining the real-time data of a power transmission line at a key position, and enabling the real-time data to comprise real-time wind power data, real-time image data and real-time power data; determining a risk coefficient corresponding to each piece of real-time data, wherein the risk coefficient is used for representing the influence degree of each piece of real-time data on the safe operation of the power transmission line; determining a risk index of the power transmission line according to the risk coefficient; the method can achieve the comprehensive evaluation of the operation risk of the power transmission line, greatly improves the accuracy, efficiency and reliability of the risk detection and evaluation of the power transmission line, and better guarantees the safe operation of the power transmission line.

Description

Technical Field

[0001] The present disclosure relates to the field of power supply transmission technology, and in particular to a transmission line risk assessment method, device, medium and electronic equipment. Background Art

[0002] Transmission line risk refers to various uncertain events or conditions that may be encountered during the operation of transmission lines, which may cause line failures, power outages or damage, thus affecting the reliability and safety of power transmission. Existing transmission line monitoring and risk assessment methods have some common problems and challenges, such as incomplete collection of transmission line operation data, collection errors or low frequency, and incomplete analysis results due to the difficulty in effectively integrating different types of collected data. These problems have an adverse impact on the accuracy and timeliness of transmission line risk monitoring and the overall risk management effect. Summary of the invention

[0003] The purpose of the present disclosure is to provide a transmission line risk assessment method, device, medium and electronic equipment to solve the problems existing in the above-mentioned background technology.

[0004] In order to achieve the above-mentioned object, the present disclosure provides a first aspect of a transmission line risk assessment method, the method comprising: Acquire real-time data of transmission lines at key locations, including real-time wind data, real-time image data, and real-time power data; Determine a risk factor corresponding to each item of the real-time data, wherein the risk factor is used to characterize the degree of influence of each item of the real-time data on the safe operation of the transmission line; A risk index of the transmission line is determined according to the risk coefficient.

[0005] Optionally, the risk factor includes a wind influence coefficient, the real-time wind data includes a real-time wind speed, and the real-time wind speed is obtained by a wind speed sensor; the wind influence coefficient is determined according to the following steps: According to the real-time wind speed detected by the wind speed sensor, the real-time wind pressure is calculated according to the following formula (1): (1), In formula (1), Expressed as real-time wind pressure, Expressed as air density, Expressed as real-time wind speed; According to the real-time wind pressure, the wind load is calculated according to the following formula (2): (2), In formula (2), Expressed as wind load, Expressed as the wind force coefficient, It is expressed as the wind-exposed area; According to the wind load, the transmission line tension is calculated according to the following formula (3): (3), In formula (3), Expressed as the transmission line tension, Expressed as the static tension of the transmission line, It is expressed as the span of the transmission line; According to the wind load and the transmission line tension, the wind force influence coefficient is calculated according to the following formula (4): (4), In formula (4), Expressed as the wind influence coefficient, Expressed as wind load, Expressed as transmission line tension.

[0006] Optionally, the risk factor includes a line damage factor, and the line damage factor is determined according to the following steps: Dividing the real-time image data into n sub-line images on average; Inputting the sub-line image into a pre-trained line damage probability model to obtain a damage probability corresponding to the sub-line image; The line damage coefficient is calculated according to the following formula (5): (5), In formula (5), Expressed as the line damage coefficient, It is represented as the damage probability of the i-th sub-line image.

[0007] Optionally, the line damage probability model is constructed using a convolutional neural network, and the steps of constructing the line damage probability model include: Step 1: Collect a dataset containing images of transmission lines and annotate the damage or anomalies in the images; Step 2: preprocess the annotated images and divide them into a training set and a test set; wherein the preprocessing includes at least one of resizing, cropping, graying, and contrast enhancement operations; Step 3: Use the training set to train the deep learning model, and use the test set to evaluate the model performance; wherein the performance includes accuracy, precision, recall and F1 score indicators; Step 4: Calculate the model performance index according to the following formula (6): (6), In formula (6), It is expressed as the model performance index, and p1, p2, p3, and p4 represent the accuracy, precision, recall, and F1 score indicators respectively; The model performance index is compared with a preset performance index threshold. If the model performance index is greater than the preset performance index threshold, the current model parameters are output to construct a final line damage probability model. If the model performance index is less than the preset performance index threshold, the process returns to step three to continue optimizing the model parameters until the model performance index is greater than the preset performance index threshold.

[0008] Optionally, the step of using the training set to train the deep learning model includes: Select the cross entropy loss function to measure the difference between the model prediction and the true label; Select the stochastic gradient descent algorithm to update the model parameters to reduce the value of the loss function; Input the prepared training set into the model, and use the back propagation algorithm to update the model parameters so that the value of the loss function gradually decreases until the model reaches the set number of training rounds; The steps of using the test set to evaluate the model performance include: Use the trained model to predict the samples in the test set and record the prediction results; According to the prediction results of the model and the real labels in the test set, the accuracy index of the model is calculated according to the following formula (7), the precision index of the model is calculated according to the following formula (8), the recall index of the model is calculated according to the following formula (9), and the F1 score index of the model is calculated according to the following formula (10): (7), In formula (7), It is expressed as the number of correctly classified samples, It is expressed as the total number of samples; (8), In formula (8), is represented as a true example, It is represented as a false positive example; (9), In formula (9), is represented as a true example, It is represented as a false negative example; (10), In formula (10), Expressed as the accuracy of the model, Expressed as the recall of the model; Analyze the performance metrics of the model and adjust the model's parameters as needed.

[0009] Optionally, the risk factor includes an overload factor, the real-time power data includes a real-time current and a real-time voltage, and the real-time current and the real-time voltage are obtained by a current sensor and a voltage sensor respectively; the overload factor is determined according to the following steps: Preprocessing the real-time current and real-time voltage collected by the current sensor and the voltage sensor respectively; the preprocessing includes at least one of data cleaning, denoising and missing value filling operations; According to the preprocessed real-time current and real-time voltage, the real-time load of the transmission line is calculated according to the following formula (11): (11), In formula (11), Expressed as real-time load, Expressed as real-time voltage, Expressed as real-time current; According to the real-time load, the real-time overload coefficient is calculated according to the following formula (12): (12), In formula (12), Expressed as the real-time overload factor, Expressed as real-time load, Indicated as rated load.

[0010] Optionally, the risk index of the transmission line is calculated according to the following formula (13): (13), In formula (13), Expressed as the risk index, Expressed as the wind influence coefficient, Expressed as line damage coefficient, It is expressed as the overload coefficient, and a1, a2, and a3 are the weight coefficients of wind influence coefficient, line damage coefficient, and overload coefficient, respectively.

[0011] Optionally, the method further comprises: comparing the risk index with a preset risk index threshold; If the risk index is less than or equal to the preset risk index threshold, it is determined that the current transmission line operation state is safe and no line risk warning is required; If the risk index is greater than the preset risk index threshold, the current transmission line operation state is determined to be unsafe, and a line risk warning is issued.

[0012] According to a second aspect of the present disclosure, a transmission line risk assessment device is provided, the transmission line risk assessment device comprising: An acquisition module is configured to acquire real-time data of a transmission line at a key location, wherein the real-time data includes real-time wind data, real-time image data, and real-time power data; A first determination module is configured to determine a risk coefficient corresponding to each item of the real-time data, wherein the risk coefficient is used to characterize the degree of influence of each item of the real-time data on the safe operation of the transmission line; The second determination module is configured to determine a risk index of the transmission line according to the risk coefficient.

[0013] According to a third aspect of the present disclosure, a non-temporary computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the steps of the method described in the first aspect of the present disclosure are implemented.

[0014] According to a fourth aspect of the present disclosure, there is provided an electronic device, comprising: a memory having a computer program stored thereon; A processor is used to execute the computer program in the memory to implement the steps of the method described in the first aspect of the present disclosure.

[0015] Through the above technical scheme, real-time data of the transmission line at key positions are obtained, and the real-time data include real-time wind data, real-time image data and real-time power data; the risk coefficient corresponding to each item of the real-time data is determined, and the risk coefficient is used to characterize the degree of influence of each item of real-time data on the safe operation of the transmission line; according to the risk coefficient, the risk index of the transmission line is determined; according to the comprehensive evaluation, the risk index of the transmission line is obtained, and then the line risk warning and / or maintenance measures can be carried out accordingly, which can greatly improve the accuracy, efficiency and reliability of transmission line risk detection and evaluation, so as to better ensure the safe operation of the transmission line.

[0016] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings: Figure 1 The present invention is a flow chart of a method for risk assessment of a power transmission line according to an exemplary embodiment.

[0018] Figure 2 The present invention is a block diagram of a transmission line risk assessment device according to an exemplary embodiment.

[0019] Figure 3 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0020] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0021] It should be noted that all actions of acquiring signals, information or data in the present disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the device is located and with the authorization given by the owner of the corresponding device.

[0022] Figure 1 is a flow chart of a transmission line risk assessment method according to an exemplary embodiment. Figure 1 As shown, the method comprises the following steps: Step S11, acquiring real-time data of the transmission line at key locations, wherein the real-time data includes real-time wind data, real-time image data and real-time power data; Step S12, determining a risk coefficient corresponding to each item of the real-time data, wherein the risk coefficient is used to characterize the degree of influence of each item of the real-time data on the safe operation of the transmission line; Step S13: Determine the risk index of the transmission line according to the risk coefficient.

[0023] Through the above technical solution, a comprehensive assessment of the operating risks of transmission lines can be achieved, greatly improving the accuracy, efficiency and reliability of transmission line risk detection and assessment, thereby better ensuring the safe operation of transmission lines.

[0024] In order to enable those skilled in the art to better understand the transmission line risk assessment method provided by the present disclosure, the above steps are described in detail with examples below.

[0025] In step S11, key positions of the transmission line such as the top, middle and bottom of the tower are selected.

[0026] Real-time wind data includes real-time wind speed, which can be obtained through a wind speed sensor, preferably a wind speed sensor with high precision and weather resistance, to ensure stable operation under various meteorological conditions. The wind speed sensor is a device for measuring wind speed (including wind speed and direction). In a preferred embodiment, the wind data collected by the wind speed sensor in real time can be processed by the Internet of Things technology before subsequent steps are performed, wherein the data processing mainly includes filtering, denoising and averaging of wind speed data to ensure the accuracy and stability of the data.

[0027] The real-time image data includes images and / or video data of the power transmission lines at key locations, and can be obtained by real-time photographing of the lines using a camera and / or video monitoring equipment.

[0028] Real-time power data includes real-time current and real-time voltage, which can be obtained through current sensors and voltage sensors respectively.

[0029] In step S12, the risk coefficient corresponding to the real-time wind data is the wind impact coefficient, which is used to characterize the degree of influence of the real-time wind conditions on the safe operation of the transmission line. The wind impact coefficient can be used to evaluate the risk level of the transmission line at various wind speeds. Generally, the larger the wind impact coefficient, the more significant the impact of wind speed on the transmission line, and the risk index of the transmission line will increase accordingly.

[0030] The influence of wind conditions on transmission lines is mainly reflected in wind pressure. Specifically, the wind influence coefficient can be determined according to the following steps: According to the real-time wind speed detected by the wind speed sensor, the real-time wind pressure is calculated according to the following formula (1): (1), In formula (1), Expressed as real-time wind pressure, Expressed as air density, usually 1.225kg / m 2 , Expressed as real-time wind speed.

[0031] Then, based on the real-time wind pressure, the wind load is calculated according to the following formula (2): (2), In formula (2), Expressed as wind load, Expressed as the wind force coefficient, is the wind-exposed area; It can be determined according to the shape of the transmission line and the direction of the wind, and can usually be 1.0~1.5. For example, the wind force coefficient can be measured by a wind tunnel test. The wind tunnel test is a prior art, and this embodiment does not provide a detailed description of the specific steps of the wind tunnel test.

[0032] Then, according to the wind load, the transmission line tension is calculated according to the following formula (3): (3), In formula (3), Expressed as transmission line tension (i.e. real-time tension), It is expressed as the static tension of the transmission line (i.e. the tension when there is no wind), is the span of the transmission line; where It can be estimated by the geometric parameters and material properties of the transmission line. For example, it can be calculated according to the following formula (14): (14), In formula (14), Expressed as the weight per unit length of the transmission line, is the elastic modulus of the transmission line, is the cross-sectional area of ​​the transmission line, is the span of the transmission line. The above parameters can be obtained from the transmission line manufacturer respectively.

[0033] Finally, according to the wind load and the transmission line tension, the wind influence coefficient is calculated according to the following formula (4): (4), In formula (4), Expressed as wind influence coefficient.

[0034] The risk factor corresponding to the real-time image data is the line damage coefficient, which is used to characterize the degree of influence of the damage of the transmission line under the action of various external factors on the safe operation of the transmission line. If the line damage coefficient increases, it means that the transmission line is more affected by external factors and the degree of damage is more serious, so the risk index of the transmission line will also increase accordingly.

[0035] The line damage coefficient can be determined by a pre-constructed transmission line damage probability identification model. Specifically, the line damage coefficient is determined according to the following steps: The real-time image data is optionally separated into lines and backgrounds, and then evenly divided into n sub-line images; Input each sub-line image into a pre-trained line damage probability model to obtain the damage probability corresponding to each sub-line image; The line damage coefficient is calculated according to the following formula (5): (5), In formula (5), Expressed as the line damage coefficient, It is represented as the damage probability of the i-th sub-line image.

[0036] The line damage probability model can be constructed using a convolutional neural network (CNN). CNN is a deep learning model that is particularly suitable for processing and analyzing data with a grid structure, such as images and videos containing power transmission lines. The image data of power transmission lines may have complex structures and features. CNN can effectively extract features from image data and adapt to power transmission line images of different scales and shapes. CNN has high efficiency in processing large-scale data sets, can quickly train and process a large amount of power transmission line image data, and improve the generalization ability of the model. The convolution layer of CNN can retain the spatial information of image data, effectively capture local features and structural information in the power transmission line image, and help identify the location and type of damage and faults. CNN can automatically learn abstract features and patterns in image data through multi-layer convolution and pooling operations, without the need for manual feature design, simplifying the process of feature engineering. The structure and parameters of the CNN model can be adjusted and optimized according to specific tasks, with strong flexibility and scalability, and is suitable for power transmission line damage identification tasks of different scales and complexities.

[0037] For example, the step of constructing the line damage probability model may include: Step 1: Collect a dataset containing images of transmission lines and annotate the damage or abnormalities in the images, such as broken wires, tilted towers, damaged insulators, etc. Step 2: preprocess the annotated images and divide them into a training set and a test set; wherein the preprocessing includes at least one of resizing, cropping, graying, and contrast enhancement operations, and the above preprocessing is conducive to improving the accuracy of subsequent image processing and recognition; Step 3: Use the training set to train the deep learning model, and use the test set to evaluate the model performance; wherein the performance includes accuracy, precision, recall and F1 score indicators; through an iterative training process, optimize the parameters of the model so that it can accurately identify the damage in the transmission line image; Step 4: Calculate the model performance index according to the following formula (6): (6), In formula (6), It is expressed as the model performance index, and p1, p2, p3, and p4 represent the accuracy, precision, recall, and F1 score indicators respectively; The model performance index is compared with a preset performance index threshold. If the model performance index is greater than the preset performance index threshold, the current model parameters are output to construct a final line damage probability model. If the model performance index is less than the preset performance index threshold, the process returns to step three to continue optimizing the model parameters until the model performance index is greater than the preset performance index threshold.

[0038] Furthermore, the step of using the training set to train the deep learning model may include: Select a suitable loss function to measure the difference between the model prediction result and the true label; wherein the loss function can be various commonly used loss functions, such as the cross entropy loss function, the mean square error loss function, etc.; in a preferred embodiment, the cross entropy loss function is selected to perform this step; the cross entropy loss function is particularly suitable for classification tasks, which can measure the difference between the probability distribution output by the model and the true label, and can better reflect the uncertainty in the classification task. During the training process, by minimizing the cross entropy loss function, the model can be better approximated to the true probability distribution, thereby improving the accuracy of classification; Then, a suitable optimization algorithm is selected to update the model parameters to reduce the value of the loss function; among them, commonly used optimization algorithms such as stochastic gradient descent, Adam, RMSProp, etc. can be used, preferably the stochastic gradient descent algorithm, which can be used to train deep learning models and solve optimization problems in large-scale data sets and high-dimensional parameter spaces; Finally, the prepared training set is input into the model, and the model parameters are updated through the back propagation algorithm, so that the value of the loss function gradually decreases until the model reaches the set number of training rounds; the model training process usually requires multiple iterations until the model converges or reaches the set number of training rounds. The back propagation algorithm is an algorithm used in deep learning to calculate the gradient of neural network model parameters. The parameter update is achieved by calculating the gradient of the loss function to the model parameters.

[0039] Furthermore, the step of using the test set to evaluate the model performance may include: Use the trained model to predict the samples in the test set and record the prediction results; Then, based on the model's prediction results and the true labels in the test set, the model's accuracy, precision, recall and F1 score are calculated according to the following formulas (7), (8), (9), and (10): (7), In formula (7), It is expressed as the number of correctly classified samples, It is expressed as the total number of samples; (8), In formula (8), is represented as a true example, It is represented as a false positive example; (9), In formula (9), is represented as a true example, It is represented as a false negative example; (10), In formula (10), Expressed as the accuracy of the model, Expressed as the recall of the model; Finally, analyze the performance indicators of the model to understand the performance of the model in different categories, identify possible problems with the model, and adjust the model parameters as needed.

[0040] The risk factor corresponding to the real-time power data is the overload factor, which is used to characterize the impact of the real-time load status of the transmission line on the safe operation of the transmission line. When the overload factor is high, it means that the load of the transmission line is relatively large, and there may be a risk of overload operation.

[0041] The overload factor may be a ratio of the current load of the transmission line to the rated load. Specifically, the overload factor may be determined according to the following steps: Preprocessing the real-time current and real-time voltage collected by the current sensor and the voltage sensor respectively; the preprocessing includes at least one of data cleaning, denoising and missing value filling operations, and the above preprocessing is conducive to ensuring the quality and integrity of the data; Then, based on the preprocessed real-time current and real-time voltage, the real-time load of the transmission line is calculated according to the following formula (11): (11), In formula (11), Expressed as real-time load, Expressed as real-time voltage, Expressed as real-time current; Finally, according to the real-time load, the real-time overload coefficient is calculated according to the following formula (12): (12), In formula (12), Expressed as the real-time overload factor, Expressed as real-time load, Expressed as rated load; wherein, the rated load refers to the maximum load that the power system or equipment can withstand under normal working conditions. It is usually determined during the design or planning stage based on the design parameters, technical specifications and safety requirements of the power system or equipment, and is usually expressed in the form of power.

[0042] In step S13, the risk index of the transmission line is an indicator for evaluating the overall risk level of the transmission line under various risk factors. The risk index of the transmission line is obtained by comprehensive evaluation based on the wind impact coefficient, line damage coefficient and overload coefficient. Specifically, the risk index of the transmission line can be calculated according to the following formula (13): (13), In formula (13), Expressed as the risk index, Expressed as the wind influence coefficient, Expressed as line damage coefficient, It is expressed as the overload coefficient, a1, a2, and a3 respectively represent the weight coefficients of the wind influence coefficient, the line damage coefficient, and the overload coefficient. This embodiment does not perform specific calculations on the specific values ​​of a1, a2, and a3.

[0043] The transmission line risk index obtained through comprehensive evaluation can be used to carry out line risk warning accordingly, and then the relevant staff can take corresponding maintenance measures according to the line risk warning. Specifically, the method can also include the following steps: comparing the risk index with a preset risk index threshold; If the risk index is less than or equal to the preset risk index threshold, it is determined that the current transmission line operation state is safe and no line risk warning is required; If the risk index is greater than the preset risk index threshold, the current transmission line operation state is determined to be unsafe, and a line risk warning is issued to remind relevant staff to repair the transmission line.

[0044] The disclosed method acquires various information of the transmission line by establishing multi-mode perception, and comprehensively analyzes the risks of the transmission line according to real-time wind force, line images and power data, so as to timely identify potential safety hazards and fault risks, help the power system to respond to natural disasters, bad weather and other emergencies in a timely manner, formulate emergency plans and preventive measures, and reduce the occurrence of accidents and losses; it can also help evaluate the reliability level of the transmission line, identify the key factors affecting the reliability of the power grid, thereby optimizing the operation of the power grid, improving the reliability of power supply, and ensuring the safe operation and stable power supply of the power grid. According to the risk index analysis results, it can timely discover problems such as aging, wear or overload, guide the update and upgrade of equipment, improve the performance and safety level of equipment, and ensure the long-term stable operation of the power system; based on the evaluation results of the risk index, a reasonable equipment maintenance plan and strategy can be formulated in a targeted manner, and maintenance resources can be reasonably arranged according to the risk level and maintenance requirements of different equipment, so as to extend the life of equipment and reduce operation and maintenance costs.

[0045] Based on the same inventive concept, in order to implement the above method embodiment, this embodiment provides a transmission line risk assessment device, Figure 2 is a block diagram of a transmission line risk assessment device according to an exemplary embodiment. The transmission line risk assessment device 200 may include: An acquisition module 201 is configured to acquire real-time data of a transmission line at a key location, wherein the real-time data includes real-time wind data, real-time image data, and real-time power data; A first determination module 202 is configured to determine a risk coefficient corresponding to each item of the real-time data, wherein the risk coefficient is used to characterize the degree of influence of each item of the real-time data on the safe operation of the transmission line; The second determination module 203 is configured to determine a risk index of the transmission line according to the risk coefficient.

[0046] Optionally, the transmission line risk assessment device 200 may further include an early warning and response module, which is used to receive a risk index and output early warning and response measures according to the risk index.

[0047] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0048] Based on the same inventive concept, this embodiment also provides a non-temporary computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned transmission line risk assessment method are implemented.

[0049] Based on the same inventive concept, this embodiment also provides an electronic device, Figure 3FIG. 1 is a block diagram of an electronic device according to an exemplary embodiment. Figure 3 As shown, the electronic device 300 may include: a processor 301 , a memory 302 . The electronic device 300 may also include one or more of a multimedia component 303 , an input / output (I / O) interface 304 , and a communication component 305 .

[0050] The processor 301 is used to control the overall operation of the electronic device 300 to complete all or part of the steps in the above-mentioned power transmission line risk assessment method. The memory 302 is used to store various types of data to support the operation of the electronic device 300, and these data may include, for example, instructions for any application or method used to operate on the electronic device 300, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 303 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 302 or sent through the communication component 305. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 304 provides an interface between the processor 301 and other interface modules, and the other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 305 is used for wired or wireless communication between the electronic device 300 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 305 may include: Wi-Fi module, Bluetooth module, NFC module, etc.

[0051] In an exemplary embodiment, the electronic device 300 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned transmission line risk assessment method.

[0052] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned power transmission line risk assessment method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 302 including program instructions, and the above-mentioned program instructions can be executed by the processor 301 of the electronic device 300 to complete the above-mentioned power transmission line risk assessment method.

[0053] In another exemplary embodiment, a computer program product is further provided. The computer program product includes a computer program executable by a programmable device. The computer program has a code portion for executing the above-mentioned transmission line risk assessment method when executed by the programmable device.

[0054] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0055] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0056] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A transmission line risk assessment method, characterized in that: The method includes: Acquire real-time data of transmission lines at key locations, including real-time wind data, real-time image data, and real-time power data; Determine a risk factor corresponding to each item of the real-time data, wherein the risk factor is used to characterize the degree of influence of each item of the real-time data on the safe operation of the transmission line; A risk index of the transmission line is determined according to the risk coefficient.

2. The method according to claim 1, wherein: The risk factor includes a wind influence coefficient, and the real-time wind data includes a real-time wind speed, which is obtained by a wind speed sensor; the wind influence coefficient is determined according to the following steps: According to the real-time wind speed detected by the wind speed sensor, the real-time wind pressure is calculated according to the following formula (1): （1）， In formula (1), Expressed as real-time wind pressure, Expressed as air density, Expressed as real-time wind speed; According to the real-time wind pressure, the wind load is calculated according to the following formula (2): （2）， In formula (2), Expressed as wind load, Expressed as the wind force coefficient, It is expressed as the wind-exposed area; According to the wind load, the transmission line tension is calculated according to the following formula (3): （3）， In formula (3), Expressed as the transmission line tension, Expressed as the static tension of the transmission line, It is expressed as the span of the transmission line; According to the wind load and the transmission line tension, the wind force influence coefficient is calculated according to the following formula (4): （4）， In formula (4), Expressed as wind influence coefficient.

3. The method according to claim 1, wherein: The risk factor includes a line damage factor, and the line damage factor is determined according to the following steps; Dividing the real-time image data into n sub-line images on average; Inputting the sub-line image into a pre-trained line damage probability model to obtain a damage probability corresponding to the sub-line image; The line damage coefficient is calculated according to the following formula (5): （5）， In formula (5), Expressed as the line damage coefficient, It is represented as the damage probability of the i-th sub-line image.

4. The method according to claim 3, wherein: The line damage probability model is constructed using a convolutional neural network, and the steps of constructing the line damage probability model include: Step 1: Collect a dataset containing images of transmission lines and annotate the damage or anomalies in the images; Step 2: preprocess the annotated images and divide them into a training set and a test set; wherein the preprocessing includes at least one of resizing, cropping, graying, and contrast enhancement operations; Step 3: Use the training set to train the deep learning model, and use the test set to evaluate the model performance; wherein the performance includes accuracy, precision, recall and F1 score indicators; Step 4: Calculate the model performance index according to the following formula (6): （6）， In formula (6), It is expressed as the model performance index, and p1, p2, p3, and p4 represent the accuracy, precision, recall, and F1 score indicators respectively; The model performance index is compared with a preset performance index threshold. If the model performance index is greater than the preset performance index threshold, the current model parameters are output to construct a final line damage probability model. If the model performance index is less than the preset performance index threshold, the process returns to step three to continue optimizing the model parameters until the model performance index is greater than the preset performance index threshold.

5. The method according to claim 4, wherein: The step of using the training set to train the deep learning model comprises: Select the cross entropy loss function to measure the difference between the model prediction and the true label; Select the stochastic gradient descent algorithm to update the model parameters to reduce the value of the loss function; Input the prepared training set into the model, and use the back propagation algorithm to update the model parameters so that the value of the loss function gradually decreases until the model reaches the set number of training rounds; The steps of using the test set to evaluate the model performance include: Use the trained model to predict the samples in the test set and record the prediction results; According to the prediction results of the model and the real labels in the test set, the accuracy index of the model is calculated according to the following formula (7), the precision index of the model is calculated according to the following formula (8), the recall index of the model is calculated according to the following formula (9), and the F1 score index of the model is calculated according to the following formula (10): （7）， In formula (7), It is expressed as the number of correctly classified samples, It is expressed as the total number of samples; （8）， In formula (8), is represented as a true example, It is represented as a false positive example; （9）， In formula (9), is represented as a true example, It is represented as a false negative example; （10）， In formula (10), Expressed as the accuracy of the model, Expressed as the recall of the model; Analyze the performance metrics of the model and adjust the model's parameters as needed.

6. The method according to claim 1, wherein: The risk factor includes an overload factor, and the real-time power data includes a real-time current and a real-time voltage, which are acquired by a current sensor and a voltage sensor respectively; the overload factor is determined according to the following steps: Preprocessing the real-time current and real-time voltage collected by the current sensor and the voltage sensor respectively; the preprocessing includes at least one of data cleaning, denoising and missing value filling operations; According to the preprocessed real-time current and real-time voltage, the real-time load of the transmission line is calculated according to the following formula (11): （11）， In formula (11), Expressed as real-time load, Expressed as real-time voltage, Expressed as real-time current; According to the real-time load, the real-time overload coefficient is calculated according to the following formula (12): （12）， In formula (12), Expressed as the real-time overload factor, Expressed as real-time load, Indicated as rated load.

7. The method according to claim 1, wherein: The risk index of the transmission line is calculated according to the following formula (13): （13）， In formula (13), Expressed as the risk index, Expressed as the wind influence coefficient, Expressed as line damage coefficient, It is expressed as the overload coefficient, and a1, a2, and a3 are the weight coefficients of wind influence coefficient, line damage coefficient, and overload coefficient, respectively.

8. The method according to claim 1, wherein: The method further includes: comparing the risk index with a preset risk index threshold; If the risk index is less than or equal to the preset risk index threshold, it is determined that the current transmission line operation state is safe and no line risk warning is required; If the risk index is greater than the preset risk index threshold, the current transmission line operation state is determined to be unsafe, and a line risk warning is issued.

9. A transmission line risk assessment device, characterized in that: The transmission line risk assessment device comprises: An acquisition module is configured to acquire real-time data of a transmission line at a key location, wherein the real-time data includes real-time wind data, real-time image data, and real-time power data; A first determination module is configured to determine a risk coefficient corresponding to each item of the real-time data, wherein the risk coefficient is used to characterize the degree of influence of each item of the real-time data on the safe operation of the transmission line; The second determination module is configured to determine a risk index of the transmission line according to the risk coefficient.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 8 are implemented.

11. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 8.

Images