A transmission line intelligent inspection and optimization system

Abstract

The present invention discloses a transmission line intelligent inspection optimization system, which relates to the field of intelligent inspection technology. The present invention comprises an unmanned aerial vehicle inspection module, an analysis module, a diagnosis module and a decision support module; the unmanned aerial vehicle inspection module is used to obtain images and data of the transmission line; the inspection area and the target transmission line are determined according to the layout and characteristics of the transmission line; the present invention significantly improves the efficiency and accuracy of transmission line inspection by integrating the unmanned aerial vehicle inspection module, the analysis module, the diagnosis module and the decision support module, the unmanned aerial vehicle inspection module can obtain high-definition images and data in real time, the analysis module uses advanced image recognition technology to automatically identify abnormal situations, and the diagnosis module deeply analyzes data and predicts potential problems. The combination of these technologies makes the inspection process more automated and intelligent, reduces the demand for manual inspection, and reduces the labor intensity and the possibility of human error.

Description

Technical Field

[0001] The present invention relates to the field of intelligent inspection technology, and in particular to an intelligent inspection optimization system for power transmission lines. Background Art

[0002] Existing power transmission line inspections mainly rely on manual or simple automated equipment. These methods have problems such as low efficiency, incomplete detection, and significant environmental impact. Manual inspections are labor-intensive and easily interfered with by human factors, resulting in limited accuracy and consistency of detection results. With the expansion of the scale and complexity of transmission lines, traditional inspection methods have been unable to meet the needs of modern power systems for high efficiency and high safety. In addition, transmission line failures may cause large-scale power outages, resulting in huge economic losses and social impacts.

[0003] In recent years, the rapid development of drone technology, image recognition technology, big data analysis and artificial intelligence has brought new technical means to the field of transmission line inspection. The application of these technologies can significantly improve the automation level of inspection work, reduce the interference of human factors, and improve the coverage and accuracy of inspection. However, how to effectively integrate these technologies and build an intelligent and automated inspection system to achieve comprehensive and efficient monitoring and maintenance of transmission lines is still a technical challenge. In addition, with the access of new energy and the continuous expansion of the scale of the power grid, the operating environment of the transmission line has become more complex and changeable, which puts higher requirements on the inspection system.

[0004] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0005] The purpose of the present invention is to solve the problems of low efficiency, insufficient accuracy and difficulty in coping with the expansion of power grid scale and complex environment in the existing power transmission line inspection method, and to propose a power transmission line intelligent inspection optimization system.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] A transmission line intelligent inspection and optimization system, comprising:

[0008] The drone inspection module is used to obtain images and data of power transmission lines through drone inspection. The specific steps are as follows:

[0009] Determine the inspection area and target transmission line, and plan the flight path and altitude of the drone based on the layout and characteristics of the transmission line;

[0010] Collect geographic information and weather conditions of the inspection area, evaluate flight conditions, and calibrate the sensors and cameras on the drone;

[0011] Navigate the drone according to the planned flight path and altitude, and adjust the flight speed of the drone so that the quality of the images and data collected by the sensors and cameras on the drone on the transmission line meets the standards;

[0012] The high-definition cameras and sensors carried by the drones are then used to collect images and data of the power transmission lines in real time. During the collection process, the cameras shoot from multiple angles to cover different parts of the lines.

[0013] The collected images and data are transmitted and stored in real time or periodically. After completing the inspection mission, the drone automatically returns to the take-off point or designated landing area.

[0014] An analysis module for automatically identifying abnormal conditions on the transmission line through image recognition technology;

[0015] A diagnostic module that performs in-depth analysis of the collected data to diagnose the health of the transmission lines and predict potential problems;

[0016] The decision support module is used to provide maintenance and repair suggestions based on the diagnosis results and assist in decision making.

[0017] Furthermore, the process of the drone inspection module adjusting the flight speed of the drone is as follows:

[0018] The optimal flight speed of the UAV is determined by performing a preset short-distance test flight test on the UAV, performing test flights at different speeds during the preset short-distance test flight test, and analyzing the image quality collected at each test flight speed. The image quality collected at different test flight speeds is comprehensively analyzed through quality evaluation parameters, which include:

[0019] Image sharpness: The clarity of edges and details in an image, measured by edge contrast;

[0020] Image resolution: The amount of detail that can be discerned in an image, expressed as the number of pixels;

[0021] Image noise: random variations in brightness or color in an image;

[0022] Dynamic range: The range of detail from the darkest to the brightest that an image can capture;

[0023] Motion blur: Objects in the image appear blurry because the drone moves too fast;

[0024] Assign scores of 1 to 50 to the above quality evaluation parameters respectively, calculate the sum of all quality evaluation parameter scores, and obtain a comprehensive score, which is recorded as the image quality evaluation value, and this image quality evaluation value is used as the quality standard for measuring the acquired images;

[0025] The image quality evaluation values ​​obtained at different test flight speeds are sorted by size, and the top five image quality evaluation values ​​are selected. Then, the obtained image quality evaluation values ​​are corrected by external factors other than image quality, including inspection efficiency and battery life. The inspection efficiency and battery life are quantified in percentage to obtain the inspection efficiency value and battery life value respectively.

[0026] Then, the obtained image quality evaluation value, patrol efficiency value and endurance value are normalized and entered into the following formula: To obtain the modified evaluation value XPZ, where TZP, xx and xh are the map quality evaluation value, patrol efficiency value and endurance value respectively, and the final modified evaluation value XPZ is used as the analysis standard for measuring the optimal speed;

[0027] The revised evaluation values ​​obtained by the test flight speeds corresponding to the first five image quality evaluation values ​​are screened again according to their size, and the test flight speed with the largest revised evaluation value is selected as the optimal flight speed of the UAV for inspection flight.

[0028] Furthermore, the specific operation steps of the analysis module to automatically identify abnormal conditions on the transmission line through image recognition technology are as follows:

[0029] Perform pre-processing operations such as denoising, contrast enhancement and size standardization on the image data collected by the drone inspection module;

[0030] Extract features related to identifying abnormalities from the preprocessed image, including edges, textures, and colors;

[0031] The image is then segmented into multiple regions or objects to identify different components of the transmission line, including conductors, towers, and insulators;

[0032] Apply image recognition algorithms, including convolutional neural networks or support vector machines, to analyze images, identify anomalies, mark detected anomalies on the images, and generate reports;

[0033] Correlate image recognition results with geographic information system data to pinpoint the exact location of anomalies.

[0034] Furthermore, the specific operation steps of the diagnostic module for diagnosing the health status of the power transmission line and predicting potential problems are as follows:

[0035] Collect and integrate data from different sensors and image recognition, and extract diagnostic features from the integrated data, including temperature, humidity, current, and voltage;

[0036] Clean the data, remove outliers and incomplete records, and apply statistical methods to analyze the distribution, trends, and correlations of the data;

[0037] Use historical data to train machine learning models, including decision trees or random forests or gradient boosting machines; verify the accuracy and generalization ability of the models through cross-validation methods;

[0038] Apply trained models to analyze current data to assess the health of transmission lines and use models to predict potential faults and problems, including conductor breakage or insulator damage;

[0039] Assess the severity and urgency of predicted problems and determine the priority of maintenance or repair. Specifically, collect problem indicators and conduct comprehensive analysis to obtain the severity and urgency of all predicted problems.

[0040] Sort the severity scores of all prediction problems by size, and prioritize prediction problems with large severity scores.

[0041] Finally, a detailed diagnostic report is generated, including health status assessment, failure prediction and maintenance recommendations.

[0042] Furthermore, the specific operation steps of the diagnosis module collecting problem indicators and performing comprehensive analysis to obtain the critical evaluation values ​​of all predicted problems are as follows:

[0043] Problem indicators include:

[0044] Fault frequency of a problem point: the number of times a transmission line fails at the problem point within a preset time, recorded as the fault evaluation value, which is used to evaluate the frequency of failures at the problem point;

[0045] The impact of the problem on the power load in the power supply area, including the affected load amount and load importance level. The load importance level is quantified by four digits: 2, 4, 6, and 8. The negative value is obtained by multiplying the affected load amount by the corresponding level number. This negative value is used as the standard for measuring the impact of the problem on the power load in the power supply area.

[0046] Importance of the power supply area to which the problem point belongs: Determine the severity of the impact of the fault based on the function and importance of the power supply area, including residential, commercial or industrial areas, and quantify it through a score of 1-10, which is recorded as the re-evaluation value;

[0047] Maintenance or repair costs required for problem points: The maintenance and repair costs required for different problem situations are measured by calculating the cost and recorded as the required cost. The higher the required cost, the higher the priority required.

[0048] Then, the obtained old evaluation value, negative value, re-evaluation value and required cost are marked as gp, fy, cp and sc respectively, and after normalization, they are entered into the following formula: To obtain the strict evaluation value YPZ, They are the preset weight coefficients of the old evaluation value, negative impact value, re-evaluation value and required cost respectively, and the obtained strict evaluation value YPZ is used to measure the severity and urgency of the prediction problem.

[0049] Furthermore, the decision support module provides maintenance and repair suggestions based on the diagnosis results, and the specific operation steps of assisting decision making are as follows:

[0050] Collect the health status data and predicted potential problems of the transmission lines provided by the diagnostic module, and integrate relevant information such as historical maintenance records, fault data, environmental monitoring data, etc.

[0051] Determine the priority of maintenance and repair work through the severity assessment value YPZ based on the assessment of the severity and urgency of the predicted problems;

[0052] According to the evaluation results, formulate specific maintenance strategies, including preventive maintenance and emergency repairs, analyze the available resources entered in advance, including manpower, material resources and time, and make suggestions for resource allocation;

[0053] Analyze the risks that may be encountered in maintenance and repair work, as well as the impact of these risks on power grid operation, and use operations research methods and simulation technology to optimize maintenance and repair plans to minimize costs and impacts;

[0054] Generate multiple decision-making plans, including recommended action plans, expected effects and possible risks, and prioritize multiple decision-making plans;

[0055] The priority-screened and sorted plans are uploaded to the management or decision-making committee for approval. After approval, the plan with the highest priority is implemented, and alternative plans are prepared for implementation. The implementation results and experience are fed back to the decision support module to form a cycle of continuous improvement.

[0056] Furthermore, the specific operation steps of the decision support module for priority screening of multiple decision solutions are as follows:

[0057] First, the goal of decision support is determined according to user needs, including minimizing costs, maximizing power supply reliability, or minimizing maintenance time;

[0058] Based on the diagnostic results and existing data, multiple decision-making options are generated using different assumptions and constraints, and detailed action plans are developed for each option, including the required resources, timetable and implementation steps;

[0059] Predict the expected effects of each solution, including reduced failure rate, shortened power supply restoration time and cost savings, assess the risks and uncertainties that each solution may face, conduct a cost-benefit analysis for each solution, and compare the costs and expected benefits of the solutions;

[0060] According to the preset evaluation criteria, including cost-effectiveness ratio, risk level and implementation difficulty, the schemes are ranked, the importance of different evaluation criteria is determined, and then weights are assigned to each indicator. Each scheme is comprehensively scored using the weighted scoring method;

[0061] Conduct sensitivity analysis on key parameters, evaluate the robustness of the solutions under different conditions, compare the scoring results of each solution, and identify the advantages and disadvantages of each solution;

[0062] Upload the program evaluation results to the decision makers, collect their feedback and suggestions, and adjust and optimize the program based on their feedback;

[0063] Taking all factors into consideration, including the decision maker's preferences, the options are finally prioritized. In addition to the highest priority option, one or two additional alternative options are developed to deal with unexpected situations.

[0064] Compared with the prior art, the present invention has the following beneficial effects:

[0065] The present invention significantly improves the efficiency and accuracy of power transmission line inspection by integrating UAV inspection module, analysis module, diagnosis module and decision support module. The UAV inspection module can obtain high-definition images and data in real time, the analysis module uses advanced image recognition technology to automatically identify abnormal situations, and the diagnosis module deeply analyzes data and predicts potential problems. The combination of these technologies makes the inspection process more automated and intelligent, reduces the need for manual inspection, and reduces the labor intensity and possibility of human error.

[0066] The decision support module of the present invention provides scientific maintenance and repair suggestions by comprehensively analyzing the diagnosis results and historical maintenance records. The module can evaluate the severity and urgency of the predicted problems and determine the priority of maintenance or repair work, thereby optimizing resource allocation and maintenance strategies. This data-driven decision support mechanism not only improves the scientificity and rationality of decision-making, but also helps to minimize maintenance costs and grid operation risks, ensuring the stability and safety of the grid.

[0067] The present invention takes into account the needs of different users and the complexity of power grid operation, and can generate multiple decision-making plans based on different assumptions and constraints. Through sensitivity analysis and comprehensive scoring methods, the system can prioritize the plans and provide flexible decision support. The system can also make continuous improvements based on implementation results and experience feedback, thereby enhancing the adaptability and flexibility of the system. The ability of dynamic optimization and self-improvement enables the system to better cope with the ever-changing power grid operating environment and maintenance needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0069] Figure 1 This is the overall system block diagram of the present invention. DETAILED DESCRIPTION

[0070] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0071] It should be understood that the terms "include" and "comprising" used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0072] It should also be understood that the terms used in this disclosure are only for the purpose of describing specific embodiments and are not intended to limit the disclosure. As used in this disclosure and claims, the singular forms of "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in this disclosure and claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0073] like Figure 1 As shown, a transmission line intelligent inspection optimization system includes a UAV inspection module, an analysis module, a diagnosis module and a decision support module;

[0074] The drone inspection module is used to obtain images and data of power transmission lines;

[0075] Determine the inspection area and target transmission line, and plan the flight path and altitude of the drone according to the layout and characteristics of the transmission line; collect geographic information and meteorological conditions and environmental data of the inspection area, evaluate flight conditions, and ensure the safe flight of the drone; calibrate the sensors and cameras on the drone to ensure the accuracy of data collection, and check and adjust the drone's navigation system to ensure the accuracy of the aircraft's path;

[0076] The drone is navigated according to the planned flight path and altitude, and the flight speed of the drone is adjusted so that the quality of the images and data collected by the sensors and cameras on the drone for the transmission lines meets the standards. Specifically, the drone is tested for a short distance, and test flights at different speeds are performed during the short distance test. The quality of the images collected at each test flight speed is analyzed to determine the optimal flight speed of the drone. The quality of the images collected at different test flight speeds is comprehensively analyzed through quality evaluation parameters, including:

[0077] Image clarity: the clarity of edges and details in an image, measured by edge contrast; Image resolution: the amount of detail that can be discerned in an image, expressed in terms of the number of pixels; Image noise: random brightness or color variations that occur in an image, which may be more noticeable at high ISO or fast shutter speeds; Dynamic range: the range of detail from the darkest to the brightest that an image can capture; Motion blur: objects in an image appear blurry due to the drone moving too fast;

[0078] The above quality evaluation parameters are assigned scores of 1-50 respectively. The higher the score, the better the corresponding quality evaluation parameter effect. The sum of the scores of all quality evaluation parameters is calculated to obtain a comprehensive score, which is recorded as the image quality evaluation value, and this image quality evaluation value is used as the standard for measuring the quality of the collected images; the image quality evaluation values ​​obtained at different test flight speeds are sorted by size, and the top five image quality evaluation values ​​are selected. Then, the obtained image quality evaluation values ​​are corrected by external factors other than image quality, including inspection efficiency and battery life. The inspection efficiency and battery life are quantified in percentage to obtain the inspection efficiency value and battery life value respectively. Then, the obtained image quality evaluation value, inspection efficiency value and battery life value are normalized and entered into the following formula: To obtain the modified evaluation value XPZ, where TZP, xx and xh are the image quality evaluation value, patrol efficiency value and endurance value respectively, and the final modified evaluation value XPZ is used as the analysis standard for measuring the optimal speed; the modified evaluation values ​​XPZ obtained by the test flight speed corresponding to the first five image quality evaluation values ​​are screened again according to the size, and the test flight speed with the largest modified evaluation value XPZ is selected as the optimal flight speed of the UAV for patrol flight;

[0079] The high-definition camera and other sensors carried by the drone are used to collect images and data of the transmission line in real time. During the collection process, the camera shoots at multiple angles to cover different parts of the line. The collected images and data are transmitted and stored in real time or periodically. After completing the inspection task, the drone automatically returns to the take-off point or designated landing area.

[0080] The analysis module is used to automatically identify abnormal conditions on the transmission line through image recognition technology;

[0081] Perform pre-processing operations such as denoising, contrast enhancement and size standardization on the image data collected by the drone inspection module to improve the accuracy of image recognition; extract features related to identifying abnormalities from the pre-processed images, including edges, textures and colors; and then segment the images into multiple regions or objects for identifying different components of the transmission line, including conductors, towers and insulators;

[0082] Apply image recognition algorithms, including convolutional neural networks (CNN) or support vector machines (SVM), to analyze images to identify anomalies, mark detected anomalies on the images, and generate reports; associate image recognition results with geographic information system (GIS) data to determine the specific location of the anomaly.

[0083] The diagnostic module is used to conduct in-depth analysis of the collected data, diagnose the health of the transmission line, and predict potential problems;

[0084] Collect data from different sensors and image recognition, integrate them, and extract diagnostic features from the integrated data, including temperature, humidity, current, and voltage; clean the data, remove outliers and incomplete records, and apply statistical methods to analyze the distribution, trend, and correlation of the data; use historical data to train machine learning models, including decision trees, random forests, or gradient boosting machines (GBM); verify the accuracy and generalization ability of the model through cross-validation methods; use the trained model to analyze current data, evaluate the health of the transmission line, and use the model to predict potential faults and problems, including wire breakage or insulator damage;

[0085] Evaluate the severity and urgency of the predicted problem and determine the priority of maintenance or repair by collecting problem indicators for comprehensive analysis. Problem indicators include:

[0086] Failure frequency of the problem point: the number of times the transmission line fails at the problem point within a preset time, recorded as the fault evaluation value, which is used to evaluate the frequency of failures at the problem point; the impact of the problem on the power load of the power supply area, including the affected load and the load importance level, and the load importance level is quantified by four numbers 2, 4, 6 and 8, and the affected load is multiplied by the corresponding level number to obtain the negative value, and this negative value is used as the standard for measuring the impact of the problem on the power load of the power supply area; the importance of the power supply area to which the problem point belongs: according to the function and importance of the power supply area, including residential areas, commercial areas or industrial areas, the severity of the impact of the fault is determined, and quantified by a score of 1-10, recorded as the re-evaluation value; the maintenance or repair cost required for the problem point: the maintenance and repair costs required in different problem situations are measured by calculating the cost and recorded as the required cost. The higher the required cost, the higher the priority may be required;

[0087] Then, the obtained old evaluation value, negative value, re-evaluation value and required cost are marked as gp, fy, cp and sc respectively, and after normalization, they are entered into the following formula: To obtain the strict evaluation value YPZ, The preset weight coefficients are respectively the original evaluation value, negative impact value, re-evaluation value and required cost, and the values ​​are set between 1.1-1.3, 0.91-0.94, 0.95-0.97 and 0.11-0.15 respectively; and the obtained severe evaluation value YPZ is used to measure the severity and urgency of the forecast problem; the severe evaluation values ​​YPZ obtained from all forecast problems are sorted according to size, and the forecast problems with large severe evaluation values ​​YPZ are processed first;

[0088] Finally, a detailed diagnostic report is generated, including health status assessment, failure prediction and maintenance recommendations.

[0089] The decision support module is used to provide maintenance and repair suggestions based on the diagnosis results and assist in decision making;

[0090] Collect the health status data of the transmission lines and the predicted potential problems provided by the diagnostic module, and integrate relevant information such as historical maintenance records, fault data, and environmental monitoring data; determine the priority of maintenance and repair work through the severity evaluation value YPZ based on the evaluation of the severity and urgency of the predicted problems; formulate specific maintenance strategies based on the evaluation results, including preventive maintenance and emergency repairs, analyze the available resources entered in advance, including manpower, material resources, and time, and put forward suggestions for resource allocation;

[0091] Analyze the risks that may be encountered in maintenance and repair work, as well as the impact of these risks on power grid operation, and use operations research methods and simulation technology to optimize maintenance and repair plans to minimize costs and impacts; generate multiple decision plans, including recommended action plans, expected effects and possible risks, and prioritize multiple decision plans. The specific steps are as follows:

[0092] First, determine the goal of decision support based on user needs, including minimizing costs, maximizing power supply reliability, or minimizing maintenance time; based on diagnostic results and existing data, use different assumptions and constraints to generate multiple decision plans, and formulate detailed action plans for each plan, including required resources, timetables, implementation steps, etc.; predict the expected effects of each plan, including reduced failure rate, shortened power supply restoration time, and cost savings; assess the risks and uncertainties that each plan may face, including technical risks, operational risks, environmental risks, etc.; conduct a cost-benefit analysis for each plan, and compare the costs and expected benefits of the plans;

[0093] According to the preset evaluation criteria, including cost-effectiveness ratio, risk level and implementation difficulty, the schemes are ranked, the importance of different evaluation criteria is determined, weights are assigned to various indicators, and each scheme is comprehensively scored using the weighted scoring method; sensitivity analysis is performed on key parameters to evaluate the robustness of the scheme under different conditions, and the scoring results of each scheme are compared to identify the advantages and disadvantages of each scheme;

[0094] Present the results of the program evaluation to the decision makers, collect their feedback and suggestions, and adjust and optimize the program based on their feedback; comprehensively consider all factors, including the decision makers' preferences, and make a final priority ranking of the programs. In addition to the highest priority program, develop one or two additional alternative programs to deal with possible unexpected situations;

[0095] The ranked plans are uploaded to the management or decision-making committee for approval. After approval, the plan with the highest priority is implemented, and alternative plans are prepared for implementation. The implementation results and experience are fed back to the decision support module to form a cycle of continuous improvement.

[0096] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A transmission line intelligent inspection and optimization system, It is characterized in that include: The drone inspection module is used to obtain images and data of power transmission lines through drone inspection. The specific steps are as follows: Determine the inspection area and target transmission line, and plan the flight path and altitude of the drone based on the layout and characteristics of the transmission line; Collect geographic information and weather conditions of the inspection area, evaluate flight conditions, and calibrate the sensors and cameras on the drone; Navigate the drone according to the planned flight path and altitude, and adjust the flight speed of the drone so that the quality of the images and data collected by the sensors and cameras on the drone on the transmission line meets the standards; The high-definition cameras and sensors carried by the drones are then used to collect images and data of the power transmission lines in real time. During the collection process, the cameras shoot from multiple angles to cover different parts of the lines. The collected images and data are transmitted and stored in real time or periodically. After completing the inspection mission, the drone automatically returns to the take-off point or designated landing area. The process of adjusting the flight speed of the drone is as follows: The optimal flight speed of the UAV is determined by performing a preset short-distance test flight test on the UAV, performing test flights at different speeds during the preset short-distance test flight test, and analyzing the image quality collected at each test flight speed. The image quality collected at different test flight speeds is comprehensively analyzed through quality evaluation parameters, which include: Image sharpness: The clarity of edges and details in an image, measured by edge contrast; Image resolution: The amount of detail that can be discerned in an image, expressed as the number of pixels; Image noise: random variations in brightness or color in an image; Dynamic range: The range of detail from the darkest to the brightest that an image can capture; Motion blur: Objects in the image appear blurry because the drone moves too fast; Assign scores of 1 to 50 to the above quality evaluation parameters respectively, calculate the sum of all quality evaluation parameter scores, and obtain a comprehensive score, which is recorded as the image quality evaluation value, and this image quality evaluation value is used as the quality standard for measuring the acquired images; The image quality evaluation values ​​obtained at different test flight speeds are sorted by size, and the top five image quality evaluation values ​​are selected. Then, the obtained image quality evaluation values ​​are corrected by external factors other than image quality, including inspection efficiency and battery life. The inspection efficiency and battery life are quantified in percentage to obtain the inspection efficiency value and battery life value respectively. Then, the obtained image quality evaluation value, patrol efficiency value and endurance value are normalized and entered into the following formula: To obtain the modified evaluation value XPZ, where TZP, xx and xh are the map quality evaluation value, patrol efficiency value and endurance value respectively, and the final modified evaluation value XPZ is used as the analysis standard for measuring the optimal speed; The revised evaluation values ​​obtained by the first five image quality evaluation values ​​corresponding to the test flight speeds are screened again according to their size, and the test flight speed with the largest revised evaluation value is selected as the optimal flight speed of the UAV for inspection flight; The analysis module is used to automatically identify abnormal conditions on the transmission line through image recognition technology. The specific operation steps are as follows: Perform pre-processing operations such as denoising, contrast enhancement and size standardization on the image data collected by the drone inspection module; Extract features related to identifying abnormalities from the preprocessed image, including edges, textures, and colors; The image is then segmented into multiple regions or objects to identify different components of the transmission line, including conductors, towers, and insulators; Apply image recognition algorithms, including convolutional neural networks or support vector machines, to analyze images, identify anomalies, mark detected anomalies on the images, and generate reports; Correlate image recognition results with geographic information system data to determine the specific location of anomalies; The diagnostic module is used to conduct in-depth analysis of the collected data, diagnose the health of the transmission line, and predict potential problems. The specific process is as follows: Collect and integrate data from different sensors and image recognition, and extract diagnostic features from the integrated data, including temperature, humidity, current, and voltage; Clean the data, remove outliers and incomplete records, and apply statistical methods to analyze the distribution, trends, and correlations of the data; Use historical data to train machine learning models, including decision trees, random forests, or gradient boosting machines; verify the accuracy and generalization ability of the models through cross-validation methods; Apply trained models to analyze current data to assess the health of transmission lines and use models to predict potential faults and problems, including conductor breakage or insulator damage; Assess the severity and urgency of predicted problems and determine the priority of maintenance or repair. Specifically, collect problem indicators and conduct comprehensive analysis to obtain the severity and urgency of all predicted problems. Sort the severity scores of all prediction problems by size, and prioritize prediction problems with large severity scores. Finally, a detailed diagnostic report is generated, including health status assessment, failure prediction and maintenance recommendations; The specific steps for collecting problem indicators and conducting comprehensive analysis to obtain the strict evaluation values ​​of all predicted problems are as follows: Problem indicators include: Fault frequency of a problem point: the number of times a transmission line fails at the problem point within a preset time, recorded as the fault evaluation value, which is used to evaluate the frequency of failures at the problem point; The impact of the problem on the power load in the power supply area, including the affected load amount and load importance level. The load importance level is quantified by four digits: 2, 4, 6, and 8. The negative value is obtained by multiplying the affected load amount by the corresponding level number. This negative value is used as the standard for measuring the impact of the problem on the power load in the power supply area. Importance of the power supply area to which the problem point belongs: Determine the severity of the impact of the fault based on the function and importance of the power supply area, including residential, commercial or industrial areas, and quantify it through a score of 1-10, which is recorded as the re-evaluation value; Maintenance or repair costs required for problem points: The maintenance and repair costs required for different problem situations are measured by calculating the cost and recorded as the required cost. The higher the required cost, the higher the priority required. Then, the obtained old evaluation value, negative value, re-evaluation value and required cost are marked as gp, fy, cp and sc respectively, and after normalization, they are entered into the following formula: To obtain the strict evaluation value YPZ, The preset weight coefficients are respectively the old evaluation value, negative impact value, re-evaluation value and required cost, and the obtained strict evaluation value YPZ is used to measure the severity and urgency of the forecast problem; The decision support module is used to provide maintenance and repair suggestions based on the diagnosis results and assist in decision making.

2. According to claim 1, a transmission line intelligent inspection and optimization system, It is characterized in that The decision support module provides maintenance and repair suggestions based on the diagnosis results, and the specific operation steps of assisting decision making are as follows: Collect the health status data and predicted potential problems of the transmission lines provided by the diagnostic module, and integrate historical maintenance records, fault data and environmental monitoring data information; Determine the priority of maintenance and repair work through the severity assessment value YPZ based on the assessment of the severity and urgency of the predicted problems; According to the evaluation results, formulate specific maintenance strategies, including preventive maintenance and emergency repairs, analyze the available resources entered in advance, including manpower, material resources and time, and make suggestions for resource allocation; Analyze the risks encountered in maintenance and repair work and the impact of these risks on power grid operation, and use operations research methods and simulation technology to optimize maintenance and repair plans to minimize costs and impacts; Generate multiple decision-making plans, including recommended action plans, expected effects and risks, and prioritize multiple decision-making plans; The priority-screened and sorted plans are uploaded to the management for approval. After approval, the plan with the highest priority is implemented, and alternative plans are prepared for implementation. The implementation results and experience are fed back to the decision support module to form a cycle of continuous improvement.

3. According to claim 2, a transmission line intelligent inspection and optimization system, It is characterized in that The specific operation steps of the decision support module for priority screening of multiple decision solutions are as follows: First, the goal of decision support is determined according to user needs, including minimizing costs, maximizing power supply reliability, or minimizing maintenance time; Based on the diagnostic results and existing data, multiple decision-making options are generated using different assumptions and constraints, and detailed action plans are developed for each option, including the required resources, timetable and implementation steps; Predict the expected effects of each solution, including reduced failure rate, shortened power restoration time and cost savings, assess the risks and uncertainties faced by each solution, conduct a cost-benefit analysis for each solution, and compare the costs and expected benefits of the solutions; According to the preset evaluation criteria, including cost-effectiveness ratio, risk level and implementation difficulty, the schemes are ranked, the importance of different evaluation criteria is determined, and then weights are assigned to each indicator. Each scheme is comprehensively scored using the weighted scoring method; Conduct sensitivity analysis on key parameters, evaluate the robustness of the solutions under different conditions, compare the scoring results of each solution, and identify the advantages and disadvantages of each solution; Upload the program evaluation results to the decision makers, collect their feedback and suggestions, and adjust and optimize the program based on their feedback; Taking all factors into consideration, including the decision maker's preferences, the options are finally prioritized. In addition to the highest priority option, one or two additional alternative options are developed to deal with unexpected situations.

Images