A high voltage transmission line inspection method and system

Abstract

The present invention discloses a high-voltage transmission line inspection method and system, which relates to the technical field of high-voltage circuit inspection, including preprocessing the acquired data to obtain an inspection basic data set; constructing a risk feature data set based on the inspection basic data set; constructing a risk level prediction model and training it to obtain a risk score; calculating a comprehensive score, dividing the inspection area into blocks with different risk levels; finding the final inspection path in the divided blocks; the invention realizes accurate risk assessment and path optimization through fine data integration and intelligent algorithm application, ensuring efficient and safe operation and maintenance of power grids; from unified processing of multi-source data to risk feature construction, a comprehensive risk view is formed, a dynamic prediction model guides efficient resource allocation in real time, intelligent path planning reduces costs and risks, and a feedback loop optimization model is used in the closed-loop execution of tasks, which improves the overall intelligence level, response speed and safety of power grid operation and maintenance, and ensures stable power transmission.

Description

Technical Field

[0001] The present invention relates to the technical field of high-voltage circuit inspection, and in particular to a high-voltage transmission line inspection method and system. Background Art

[0002] Under the background of smart grid development, high-voltage transmission line inspection technology is becoming increasingly intelligent, but it still faces the problem of multi-source data integration and dynamic risk assessment. Existing technologies focus on single risk factors and ignore comprehensive considerations. Path planning lacks response to immediate risks, which affects inspection efficiency and safety.

[0003] In view of the above limitations, the present invention proposes a high-voltage transmission line inspection solution that integrates intelligent inspection data and environmental monitoring information. Through risk feature extraction and random forest model, multi-dimensional risk prediction and dynamic area division are realized, and the inspection path planning is optimized by combining Dijkstra algorithm and cost analysis, aiming to improve operation and maintenance efficiency and safety, and fill the gap in existing technologies. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a high-voltage transmission line inspection method and system to solve the problems faced by multi-source data integration and dynamic risk assessment.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a high-voltage transmission line inspection method, which includes acquiring intelligent inspection equipment data, external environment data, and high-voltage line data, and preprocessing the acquired data to obtain an inspection basic data set;

[0008] Extract fault characteristics, extreme weather characteristics and corrosion degree characteristics based on the inspection basic data set, and construct a risk characteristic data set;

[0009] Using the random forest algorithm, we built and trained a risk level prediction model to predict the risk level in each future period and obtain a risk score.

[0010] Based on the risk score, calculate the comprehensive score of each area, and divide the inspection area into blocks with different risk levels according to the comprehensive score;

[0011] Use the Dijkstra algorithm to find the shortest path to the target tower base in the divided blocks, then further estimate the passing time and potential risk cost, and select the path with the lowest total cost as the final inspection path;

[0012] Based on the final inspection path, execute the task until it is completed.

[0013] As a preferred solution of the high-voltage transmission line inspection method of the present invention, wherein: the intelligent inspection equipment data includes basic information, operating status, performance parameters and health and maintenance information; the external environment data includes wind speed, relative humidity, precipitation probability and temperature; the high-voltage line data includes power line data and transportation line data;

[0014] The preprocessing includes missing value processing, time series alignment and data normalization.

[0015] As a preferred solution of the high-voltage transmission line inspection method of the present invention, the acquired data is preprocessed to obtain an inspection basic data set, fault characteristics, extreme weather characteristics and corrosion degree characteristics are extracted based on the inspection basic data set, and a risk characteristic data set is constructed, as follows:

[0016] Integrate data from different formats and sources into a unified database, use time series alignment tools to align all time-related data by timestamp, use interpolation and average filling methods to handle missing data, and then use minimum-maximum scaling to process the data to obtain the inspection basic data set X′;

[0017] Among them, the inspection basic data set X′={x′1,x′2,...,x′ m},x′ i represents the i-th data in the inspection basic data set, i = 1, 2, ..., m, where m represents the total number of data, and extracts the fault feature F freq 、Extreme weather characteristics weather and corrosion degree characteristics C corrosion ;

[0018]

[0019] Where λ is the failure rate, T is the time window length, and x′ freq i is the value of the fault data after preprocessing, σ i is the data standard deviation, n freq Indicates the total number of failure events;

[0020]

[0021] Where Φ is the cumulative distribution function of the standard normal distribution, μ weather represents the average frequency of extreme weather events, σ weather represents the standard deviation, w j represents the weight, Represents the value of extreme weather data after preprocessing, n weather represents the total number of extreme weather events;

[0022]

[0023] Among them, β0, β1, β2 are coefficients, ω is the periodic frequency, φ is the phase, δ is the decay rate coefficient, is the value of corrosion data after preprocessing, n corrosion represents the number of corrosion data samples, and t represents time;

[0024] Construct the risk feature dataset R, the expression is:

[0025] R=H(F freq ,W weather ,C corrosion ;θ)

[0026] Among them, θ is the parameter set that controls the nonlinear combination, and H is the nonlinear combination function.

[0027] As a preferred solution of the high-voltage transmission line inspection method of the present invention, the random forest algorithm is used to construct and train a risk level prediction model to predict the risk level of each future period and obtain a risk score, which is specifically as follows:

[0028] Based on the risk feature dataset X, the random forest algorithm is used to build and train the risk level prediction model, and the risk score expression is obtained as follows:

[0029]

[0030] In the formula, F(R,t) represents the risk score, R represents the risk feature dataset, t represents the current time point, and n trees represents the total number of decision trees in the random forest, w j represents the weight of the jth decision tree, T j represents the prediction function of the jth decision tree, f j represents the feature selection function, g j represents the splitting rule, I(R t ) represents the information filtering function, m represents the number of historical periods considered, e represents the base of the natural logarithm, and λ k is the risk attenuation coefficient for the kth time period, γ k Parameters that affect the decay rate, is the time integral term, s is the integral variable, k is the variable, R s is the risk characteristic value at time s;

[0031] The value range of risk score F is [0,1];

[0032] When F∈(0, 0.3], it means the risk level is low and safer;

[0033] When F∈[0.3, 0.6), it indicates that there is a moderate risk and special attention is needed;

[0034] When F∈[0.6, 1], it indicates a high risk, meaning that a failure is about to occur.

[0035] As a preferred solution of the high-voltage transmission line inspection method of the present invention, the comprehensive score of each area is calculated based on the risk score, and the inspection area is divided into blocks of different risk levels according to the comprehensive score, as follows:

[0036] Comprehensive score expression:

[0037]

[0038] Among them, F 综合 is the comprehensive score, w i is the weight of the i-th feature, F i is the single score of the ith feature, and n is the total number of features;

[0039] The combined scores of all regions were processed using min-max scaling;

[0040] Determine the risk level classification, low risk F 综合 <0.3, medium risk 0.3≤F 综合 <0.6, high risk F 综合 ≥0.6;

[0041] Based on the risk level, the map is divided into blocks of different colors, green represents low-risk areas, yellow represents medium risk, and red represents high risk.

[0042] As a preferred solution of the high-voltage transmission line inspection method of the present invention, the Dijkstra algorithm is used to find the shortest path to the target tower base in the divided blocks, and then the passing time and potential risk cost are further estimated, and the path with the lowest total cost is selected as the final inspection path, which is specifically as follows:

[0043] In the above map, create an unvisited node set to store all nodes that have not been explored. Each tower base is regarded as a node N in the graph. i ,Node information includes the geographical coordinates of the tower base and the current risk level;

[0044] Set the distance of the starting node to 0, mark all nodes as unvisited, and select the node N with the smallest distance from the unvisited nodes min , mark it as visited;

[0045] For N min Each unvisited neighbor N j Calculate by Nmin to N j the distance d new If the current distance dnew < Nj, update N j with the distance being d new and record the path;

[0046] Repeat the above steps until all nodes are visited to obtain the shortest path;

[0047] According to the total distance D of the shortest path total and the average inspection speed v, calculate the passing time as T = D total / v. According to the risk level R ij calculate the risk cost C risk = α·R ij where α is the risk cost coefficient;

[0048] The total cost C total = β·T + C risk where C total represents the total cost, β represents the time cost coefficient, T represents the passing time, and C risk represents the risk cost;

[0049] Repeat the above steps to calculate the total cost C of each path total and finally select the path with the lowest total cost as the final inspection path.

[0050] As a preferred solution of the high-voltage transmission line inspection method described in the present invention, wherein: performing tasks based on the final inspection path until the tasks are completed includes the following steps:

[0051] Based on the final inspection path, form an inspection instruction packet and start executing the inspection instructions until the tasks are completed;

[0052] The inspection instruction packet includes the inspection path, inspection speed, and starting node;

[0053] Identify potential problems during the inspection process. If a problem is found, immediately notify the safety team;

[0054] Collect data throughout the task, calculate the energy consumption efficiency ratio, analyze the task efficiency, evaluate the entire task, and based on the evaluation results, adjust the weights w j of each decision tree, the risk attenuation coefficient γ k the parameter λ affecting the attenuation speed k and the number of decision trees n to be increased trees and further optimize the risk level prediction model.

[0055] In a second aspect, the present invention provides a high-voltage transmission line inspection system, including: a data acquisition module for acquiring real-time and historical data from intelligent inspection equipment, external environment monitoring equipment, and high-voltage line monitoring equipment;

[0056] The data preprocessing module is used to clean, verify, align, process missing values, and standardize the received raw data to form a unified format inspection basic data set X′;

[0057] Feature extraction module, based on the preprocessed data set X′, extracts fault features F freq 、Extreme weather characteristics weather and corrosion degree characteristics C corrosion , construct the risk feature data set R through the nonlinear combination function H;

[0058] The model building module uses the random forest algorithm to train the risk level prediction model based on the risk feature dataset R to obtain the risk score F(R,t), which is used to indicate the risk level in different time periods and regions;

[0059] The path planning module calculates the regional comprehensive score F based on the risk score, divides the risk level, and uses the Dijkstra algorithm to plan the shortest path, considering the time and risk cost, and selects the optimal inspection path;

[0060] The task execution module executes inspection tasks according to the planned inspection routes, monitors line data in real time, and discovers and responds to problems in a timely manner.

[0061] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the high-voltage transmission line inspection method as described in the first aspect of the present invention is implemented.

[0062] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the high-voltage transmission line inspection method as described in the first aspect of the present invention is implemented.

[0063] The beneficial effects of the present invention are as follows: the invention realizes accurate risk assessment and path optimization through fine data integration and intelligent algorithm application, thus ensuring efficient and safe operation and maintenance of power grids; from unified processing of multi-source data to risk feature construction, a comprehensive risk view is formed, dynamic prediction models guide efficient resource allocation in real time, intelligent path planning reduces costs and risks, and feedback loop optimization models are used in closed-loop execution of tasks, which overall improves the intelligence level, response speed and safety of power grid operation and maintenance, and ensures stable power transmission. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0065] Figure 1 This is a flow chart of the high-voltage transmission line inspection method in Example 1. DETAILED DESCRIPTION

[0066] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0067] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0068] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0069] Example 1

[0070] Reference Figure 1 , which is the first embodiment of the present invention, and provides a high-voltage transmission line inspection method, comprising the following steps:

[0071] S1. Acquire intelligent inspection equipment data, external environment data and high-voltage line data, and pre-process the acquired data to obtain an inspection basic data set;

[0072] Extract fault characteristics, extreme weather characteristics and corrosion degree characteristics based on the inspection basic data set, and construct a risk characteristic data set;

[0073] Using the random forest algorithm, we built and trained a risk level prediction model to predict the risk level in each future period and obtain a risk score.

[0074] Based on the risk score, calculate the comprehensive score of each area, and divide the inspection area into blocks with different risk levels according to the comprehensive score;

[0075] Use the Dijkstra algorithm to find the shortest path to the target tower base in the divided blocks, then further estimate the passing time and potential risk cost, and select the path with the lowest total cost as the final inspection path;

[0076] Based on the final inspection path, execute the task until it is completed.

[0077] S2. Intelligent inspection equipment data includes basic information, operating status, performance parameters, and health and maintenance information; external environment data includes wind speed, relative humidity, precipitation probability, and temperature; high-voltage line data includes power line data and transportation line data;

[0078] Preprocessing includes missing value handling, time series alignment, and data normalization.

[0079] S3. Preprocess the acquired data to obtain a basic inspection data set, extract fault characteristics, extreme weather characteristics and corrosion degree characteristics based on the basic inspection data set, and construct a risk characteristic data set, as follows:

[0080] Integrate data from different formats and sources into a unified database, use time series alignment tools to align all time-related data by timestamp, use interpolation and average filling methods to handle missing data, and then use minimum-maximum scaling to process the data to obtain the inspection basic data set X′;

[0081] Among them, the inspection basic data set X′={x′1,x′2,...,x′ m},x′ i represents the i-th data in the inspection basic data set, i = 1, 2, ..., m, where m represents the total number of data, and extracts the fault feature F freq 、Extreme weather characteristics weather and corrosion degree characteristics C corrosion ;

[0082]

[0083] Where λ is the failure rate, T is the time window length, and x′ freq i is the value of the fault data after preprocessing, σ i is the data standard deviation, n freq Indicates the total number of failure events;

[0084]

[0085] Where Φ is the cumulative distribution function of the standard normal distribution, μ weather represents the average frequency of extreme weather events, σ weather represents the standard deviation, w j represents the weight, Represents the value of extreme weather data after preprocessing, n weather represents the total number of extreme weather events;

[0086]

[0087] Among them, β0, β1, β2 are coefficients, ω is the periodic frequency, φ is the phase, δ is the decay rate coefficient, is the value of corrosion data after preprocessing, n corrosion represents the number of corrosion data samples, and t represents time;

[0088] Construct the risk feature dataset R, the expression is:

[0089] R=H(F freq ,W weather ,C corrosion ;θ)

[0090] Among them, θ is the parameter set that controls the nonlinear combination, and H is the nonlinear combination function;

[0091] The expression of nonlinear combination function is:

[0092]

[0093] It should be noted that by integrating multi-source data into a unified database and using time series alignment tools, the temporal and spatial consistency of the data is ensured, solving the problem that data from different sources are difficult to directly compare and analyze. Preprocessing techniques such as interpolation, mean value filling, and minimum-maximum scaling are used to improve data quality, making the data suitable for subsequent advanced analysis. In particular, the fault feature F constructed freq 、Extreme weather characteristics weather and corrosion degree characteristics C corrosion , which provides accurate quantitative indicators for risk quantification. By integrating these features through the nonlinear combination function H, a comprehensive risk feature data set R is formed, which improves the accuracy and comprehensiveness of risk assessment.

[0094] S4. Use the random forest algorithm to build and train a risk level prediction model to predict the risk level in each future period and obtain the risk score, as follows:

[0095] Based on the risk feature dataset X, the random forest algorithm is used to build and train the risk level prediction model, and the risk score expression is obtained as follows:

[0096]

[0097] In the formula, F(R,t) represents the risk score, R represents the risk feature dataset, t represents the current time point, and n treesrepresents the total number of decision trees in the random forest, w j represents the weight of the jth decision tree, T j represents the prediction function of the jth decision tree, f j represents the feature selection function, g j represents the splitting rule, I(R t ) represents the information filtering function, m represents the number of historical periods considered, e represents the base of the natural logarithm, and λ k is the risk attenuation coefficient for the kth time period, γ k Parameters that affect the decay rate, is the time integral term, s is the integral variable, k is the variable, R s is the risk characteristic value at time s;

[0098] The value range of risk score F is [0,1];

[0099] When F∈(0, 0.3], it indicates that the current assessed risk level is low, indicating that the line is in good operating condition, various indicators are close to ideal values, the possibility of failure in the short term is small, the safety margin is large, and daily maintenance is sufficient;

[0100] When F∈[0.3, 0.6), it indicates that there is a moderate risk, indicating that there is a certain degree of risk. Although it is not immediately dangerous, it requires special attention. At this time, if there is a slight abnormality, targeted inspection is required to prevent the risk from escalating;

[0101] When F∈[0.6, 1], it indicates a high risk, which means that the risk is extremely high and the possibility of failure is very high, indicating that there are serious problems in the line, which may be caused by serious equipment damage, extreme weather or severe corrosion. Emergency measures must be taken immediately to avoid possible power outages or safety accidents.

[0102] It should be noted that the risk level prediction model established using the random forest algorithm not only takes into account the complex interactions between multi-dimensional features, but also reflects the risk level at the current time point in real time through the dynamic F(R,t) score. This dynamic scoring mechanism enables operation and maintenance decisions to respond quickly to risk changes, improving the timeliness and proactiveness of responding to failures. The division of risk value domains intuitively guides risk management strategies at different levels and ensures the effective allocation of resources.

[0103] S5. Based on the risk score, calculate the comprehensive score of each area, and divide the inspection area into blocks of different risk levels according to the comprehensive score, as follows:

[0104] Comprehensive score expression:

[0105]

[0106] Among them, F 综合 is the comprehensive score, w i is the weight of the i-th feature, Fi i is the single-item score of the i-th feature, and n is the total number of features;

[0107] The comprehensive scores of all regions are processed by min-max scaling;

[0108] Determine the risk level division. Low risk F 综合 < 0.3, medium risk 0.3 ≤ F 综合 < 0.6, high risk F 综合 ≥ 0.6;

[0109] According to the risk level, the map is divided into blocks of different colors. Green represents low-risk areas, yellow represents medium risk, and red represents high risk;

[0110] It should be noted that based on the comprehensive score F 综合 to conduct risk area division, combined with min-max scaling processing, ensures the fairness and comparability of the scores; the risk level division strategy (low, medium, high) provides clear guidance for the allocation of inspection resources, and the map color coding intuitively shows the risk distribution, facilitating quick decision-making and improving the pertinence and efficiency of inspections.

[0111] S6. Use the Dijkstra algorithm to find the shortest path to the target tower base in the divided blocks, and then further estimate the passing time and potential risk cost, and select the path with the lowest total cost as the final inspection path, as follows:

[0112] Create a set of unvisited nodes in the above map to store all unexplored nodes. Each tower base is regarded as a node N i , and the node information includes the geographical coordinates and current risk level of the tower base;

[0113] Set the distance of the starting node to 0, mark all nodes as unvisited, and select the node N with the smallest distance from the unvisited nodes min , and mark it as visited;

[0114] For each unvisited neighbor N of N min calculate the distance d j from N min to N j , if dnew < the current distance of Nj, then update the distance of N new to d j and record the path;

[0115] ​​Repeat the above steps until all nodes are visited and the shortest path is obtained;

[0116] According to the total distance D of the shortest path total and the average inspection speed v, the passing time is calculated as T = D total / v, according to the risk level R ij Calculate the risk cost risk =α·R ij , where α is the risk cost coefficient;

[0117] Total cost C total =β·T+C risk , where C total represents the total cost, β represents the time cost coefficient, T represents the passing time, C risk represents the risk cost;

[0118] Repeat the above steps to calculate the total cost C of each path total ,Finally, the path with the lowest total cost is selected as the final inspection path;

[0119] It should be noted that the use of Dijkstra algorithm combined with risk cost analysis not only finds the shortest path, but also takes risk cost into account, ensuring the economy and safety of the inspection path; by dynamically adjusting the total cost C total The calculation optimizes the inspection path selection, reduces potential operation and maintenance costs and risk exposure, and improves the overall inspection efficiency and safety.

[0120] S7, based on the final inspection path, executing the task until the task is completed includes the following steps:

[0121] Based on the final inspection path, an inspection instruction package is formed and the inspection instructions are executed until the task is completed;

[0122] The inspection instruction packet includes the inspection path, inspection speed and starting node;

[0123] Identify potential problems during inspections and immediately notify the security team if any problems are found;

[0124] Collect data from the entire task, calculate the energy efficiency ratio, analyze the task efficiency, evaluate the entire task, and adjust the weights w of each decision tree based on the evaluation results. j , risk attenuation coefficient γ k , Parameter λ that affects the decay rate k And increase the number of decision trees n trees , and then optimize the risk level prediction model;

[0125] It should be noted that the execution of tasks based on the final inspection path has achieved automation and standardization of the inspection process; the setting of the inspection instruction package has simplified the operating process and improved execution efficiency; the instant problem feedback mechanism during the inspection has enhanced the emergency response capability and ensured the safety of the line; the data collection and evaluation throughout the task not only provides a closed-loop management for this task, but also adjusts the decision tree parameters through performance analysis and model optimization, providing a basis for continuous improvement of future inspection strategies and model upgrades, and improving the system's self-evolution capability and long-term operation and maintenance efficiency.

[0126] This embodiment also provides a high-voltage transmission line inspection system, including: a data acquisition module for acquiring real-time and historical data from intelligent inspection equipment, external environment monitoring equipment, and high-voltage line monitoring equipment;

[0127] The data preprocessing module is used to clean, verify, align, process missing values, and standardize the received raw data to form a unified format inspection basic data set X′;

[0128] Feature extraction module, based on the preprocessed data set X′, extracts fault features F freq 、Extreme weather characteristics weather and corrosion degree characteristics C corrosion , construct the risk feature data set R through the nonlinear combination function H;

[0129] The model building module uses the random forest algorithm to train the risk level prediction model based on the risk feature dataset R to obtain the risk score F(R,t), which is used to indicate the risk level in different time periods and regions;

[0130] The path planning module calculates the regional comprehensive score F based on the risk score, divides the risk level, and uses the Dijkstra algorithm to plan the shortest path, considering the time and risk cost, and selects the optimal inspection path;

[0131] The task execution module executes inspection tasks according to the planned inspection routes, monitors line data in real time, and discovers and responds to problems in a timely manner.

[0132] This embodiment also provides a computer device, which is suitable for the high-voltage transmission line inspection method, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the high-voltage transmission line inspection method proposed in the above embodiment.

[0133] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0134] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the high-voltage transmission line inspection method proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (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 Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0135] In summary, the present invention realizes accurate risk assessment and path optimization through fine data integration and intelligent algorithm application, thus ensuring efficient and safe operation and maintenance of power grids; from unified processing of multi-source data to risk feature construction, a comprehensive risk view is formed, dynamic prediction models guide efficient resource allocation in real time, intelligent path planning reduces costs and risks, and feedback loop optimization models are used in closed-loop execution of tasks, which overall improves the intelligence level, response speed and safety of power grid operation and maintenance, and ensures stable power transmission.

[0136] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A high voltage transmission line inspection method, characterized in that: include, Acquire intelligent inspection equipment data, external environment data and high-voltage line conditions, and pre-process the acquired data to obtain inspection basic data sets; Extract fault characteristics, extreme weather characteristics and corrosion degree characteristics based on the inspection basic data set, and construct a risk characteristic data set; Using the random forest algorithm, we built and trained a risk level prediction model to predict the risk level in each future period and obtain a risk score. Based on the risk score, calculate the comprehensive score of each area, and divide the inspection area into blocks with different risk levels according to the comprehensive score; Use the Dijkstra algorithm to find the shortest path to the target tower base in the divided blocks, then further estimate the passing time and potential risk cost, and select the path with the lowest total cost as the final inspection path; Based on the final inspection path results, execute the task until it is completed; The intelligent inspection equipment data includes basic information, operating status, performance parameters, and health and maintenance information; The external environment data includes wind speed, relative humidity, precipitation probability and temperature; the high-voltage line conditions include power line conditions and transportation line conditions; The preprocessing includes missing value processing, time series alignment and data standardization; The acquired data is preprocessed to obtain a basic inspection data set, and fault characteristics, extreme weather characteristics and corrosion degree characteristics are extracted based on the basic inspection data set to construct a risk characteristic data set, as follows: Integrate data from different formats and sources into a unified database, use time series alignment tools to align all time-related data by timestamp, use interpolation and average filling methods to handle missing data, and then use minimum-maximum scaling to process the data to obtain the inspection basic data set X'; Based on the inspection basic data set X'={x'1,x'2,...,x' m },x' i represents the i-th data in the inspection basic data set, i = 1, 2, ..., m, where m represents the total number of data, and extracts the fault feature F freq 、Extreme weather characteristics weather and corrosion degree characteristics C corrosion ; Where λ is the failure rate, T is the time window length, and x' freq i is the value of the fault data after preprocessing, σ i is the data standard deviation, n freq Indicates the total number of failure events; Where Φ is the cumulative distribution function of the standard normal distribution, μ weather represents the average frequency of extreme weather events, σ weather represents the standard deviation, w j represents the weight, Represents the value of extreme weather data after preprocessing, n weather represents the total number of extreme weather events; Among them, β0, β1, β2 are coefficients, ω is the periodic frequency, φ is the phase, δ is the decay rate coefficient, is the value of corrosion data after preprocessing, n corrosion represents the number of corrosion data samples, and t represents time; Construct the risk feature dataset R, the expression is: R=H(F freq ,W weather ,C corrosion ;θ) Among them, θ is the parameter set that controls the nonlinear combination, and H is the nonlinear combination function; The risk level prediction model is constructed and trained to obtain the risk score, which is as follows: Based on the risk feature dataset X, the random forest algorithm is used to build and train the risk level prediction model, and the risk score expression is obtained as follows: In the formula, F(R,t) represents the risk score, R represents the risk feature dataset, t represents the current time point, and n trees represents the total number of decision trees in the random forest, w j represents the weight of the jth decision tree, T j represents the prediction function of the jth decision tree, f j represents the feature selection function, g j represents the splitting rule, I(R t ) represents the information filtering function, m represents the number of historical periods considered, e represents the base of the natural logarithm, and λ k is the risk attenuation coefficient for the kth time period, γ k Parameters that affect the decay rate, is the time integral term, s is the integral variable, k is the variable, and Rs is the risk characteristic value at time s; The step of executing the task based on the final inspection path result until the task is completed includes the following steps: Based on the final inspection path results, an inspection instruction package is formed and the inspection instructions are executed until the task is completed; The inspection instruction packet includes an inspection path, an inspection speed and a starting node; Identify potential problems during inspections and immediately notify the security team if any problems are found; Finally, collect the whole task data, calculate the energy efficiency ratio, analyze the task efficiency, evaluate the whole task, and adjust the weight w of each decision tree based on the evaluation results. j , risk attenuation coefficient γ k , Parameter λ that affects the decay rate k And increase the number of decision trees n trees , and then optimize the risk level prediction model.

2. The high-voltage transmission line inspection method according to claim 1, characterized in that: The value range of risk score F is [0,1]; When F∈(0,0.3], it means the risk level is low and safer; When F∈[0.3,0.6), it indicates that there is a moderate risk and special attention is needed; When F∈[0.61], it indicates a high risk, meaning that a failure is about to occur.

3. The high-voltage transmission line inspection method according to claim 2, characterized in that: Based on the risk score, the comprehensive score of each area is calculated, and the inspection area is divided into blocks of different risk levels according to the comprehensive score, as follows: Comprehensive score expression: Among them, F 综合 is the comprehensive score, w i is the weight of the i-th feature, F i is the single score of the ith feature, and n is the total number of features; The combined scores of all regions were processed using min-max scaling; Determine the risk level classification, low risk F 综合 <0.3, medium risk 0.3≤F 综合 <0.6, high risk F 综合 ≥0.6; Based on the risk level, the map is divided into blocks of different colors, green represents low-risk areas, yellow represents medium risk, and red represents high risk.

4. The high-voltage transmission line inspection method according to claim 3, characterized in that: The Dijkstra algorithm is used to find the shortest path to the target tower base in the divided blocks, and then the passing time and potential risk cost are further estimated, and the path with the lowest total cost is selected as the final inspection path, as follows: In the above map, create an unvisited node set to store all nodes that have not been explored. Each tower base is regarded as a node Ni in the graph. The node information includes the geographical coordinates of the tower base and the current risk level. Set the distance of the starting node to 0, mark all nodes as unvisited, and select the node N with the smallest distance from the unvisited nodes min , mark it as visited; For N min Each unvisited neighbor N j Calculate by N min To N j The distance d new , if d new <N j The current distance, then update N j The distance is d new And record the path; Repeat the above steps until all nodes are visited and the shortest path is obtained; According to the total distance D of the shortest path total and the average inspection speed v, the passing time is calculated as T = D total / v, according to the risk level R ij Calculate the risk cost risk =α·R ij , where α is the risk cost coefficient; Total cost C total =β·T+C risk , where C total represents the total cost, β represents the time cost coefficient, T represents the passing time, C risk represents the risk cost; Repeat the above steps to calculate the total cost C of each path total ,Finally, the path with the lowest total cost is selected as the final inspection path.

5. A high-voltage transmission line inspection system, based on the high-voltage transmission line inspection method according to any one of claims 1 to 4, characterized in that: include, Data acquisition module, used to obtain real-time and historical data from intelligent inspection equipment, external environment monitoring equipment and high-voltage line monitoring equipment; The data preprocessing module is used to clean, verify, align, process missing values, and standardize the received raw data to form a unified format inspection basic data set X'; Feature extraction module, based on the preprocessed data set X', extracts fault features F freq 、Extreme weather characteristics weather and corrosion degree characteristics C corrosion , construct the risk feature data set R through the nonlinear combination function H; The model building module uses the random forest algorithm to train the risk level prediction model based on the risk feature dataset R to obtain the risk score F(R,t), which is used to indicate the risk level in different time periods and regions; The path planning module calculates the regional comprehensive score F based on the risk score, divides the risk level, and uses the Dijkstra algorithm to plan the shortest path, considering the time and risk cost, and selects the optimal inspection path; The task execution module executes inspection tasks according to the planned inspection routes, monitors line conditions in real time, and detects and responds to problems in a timely manner.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the high-voltage transmission line inspection method according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the high-voltage transmission line inspection method according to any one of claims 1 to 4 are implemented.

Images