Safety assessment method for patrol inspection electric flight path of unmanned aerial vehicle

Abstract

The invention belongs to the field of power grid systems, and particularly relates to an unmanned aerial vehicle patrol inspection electric flight path safety assessment method. Various risk variables in flight are identified and classified, a flight route containing multiple nodes and acquisition equipment is designed to construct a risk parameter matrix, a complex risk model and a threshold function of a comprehensive correction value, a residual distance and the risk matrix are constructed, and an initial route risk is evaluated before a task to determine whether to execute or not. The method has the advantages of accurately evaluating the risk, dynamically coping with the change, improving the task safety and reliability and the like, provides comprehensive and effective guarantee for the safety application of the unmanned aerial vehicle in the power transmission line electricity inspection tour task, facilitates the optimization of the power inspection tour work, and improves the safety of the unmanned aerial vehicle. And stable operation of power transmission lines is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of safety assessment of unmanned aerial vehicle electrical inspection, and in particular to a safety assessment method for a flight path of an unmanned aerial vehicle for electrical inspection. Background Art

[0002] In modern power systems, transmission lines are widely distributed in various complex geographical environments, with long spans, wide coverage areas, and complex and changeable environments. With the continuous growth of electricity demand, the operation and maintenance of transmission lines has become increasingly important and arduous.

[0003] The traditional power transmission line inspection method mainly relies on manual inspection, which has many limitations. Manual inspection is inefficient, and workers need to walk or use transportation to inspect along the transmission line, which consumes a lot of time and manpower. Moreover, in some complex terrain and harsh weather conditions, manual inspection is difficult to reach or implement, resulting in untimely inspection or even omission of some line sections, increasing the risk of transmission line failure.

[0004] In recent years, drone technology has been widely used in the field of power transmission line inspection. It can quickly reach the designated area, obtain high-resolution images and data, and effectively improve the efficiency and quality of inspection. However, drones face a series of severe challenges during flight. Complex meteorological conditions, such as strong winds, heavy rains, lightning, and fog, may cause drones to lose control, deviate from their routes, or even crash; diverse geographical environments, including mountains, canyons, rivers, and densely built areas, can cause signal obstruction and interference, affecting drone communications and navigation; at the same time, drones themselves may also malfunction, such as low battery, motor failure, sensor failure, communication module abnormality, etc. These problems pose a serious threat to the safety of drone power inspection tasks. Summary of the invention

[0005] In view of the shortcomings of the existing technology, the present invention proposes a method for assessing the flight path safety of UAV electrical inspection and testing, which monitors and responds to risk changes in real time during the flight, ensures that the UAV electrical inspection and testing tasks are completed safely and efficiently, and guarantees the stable operation of the power system transmission lines.

[0006] The technical solution of the present invention is as follows:

[0007] A method for evaluating the safety of a UAV inspection and power supply flight path, comprising:

[0008] Identify the risk variables encountered during drone flight inspections and classify the risk variables into categories I, II, and III;

[0009] Design several groups of UAV flight routes, preset several nodes on each flight route, equip each node with risk variable collection equipment, and build the risk parameter matrix of each node in the UAV electrical inspection based on the data collected by the collection equipment;

[0010] Build the UAV calibration value A, the remaining distance S of the UAV flight, and the risk parameter matrix R i The risk model of UAV electrical inspection is developed. The model outputs the risk value M and sets the risk threshold calculation function.

[0011] The risk value of the initial flight route is calculated based on the risk model. When the risk value M is less than the preset risk threshold, the current initial flight route is determined to be safe and the UAV electrical inspection task is performed.

[0012] Take the current position of the drone and the power test point of the drone as endpoints, re-intercept the pre-route from the current flight route, and obtain the nodes on the pre-route. Calculate the risk value of the pre-route through the risk model. When the risk value of the pre-route is less than the risk threshold, the pre-route is determined to be safe and the drone power test task is performed. When the risk value is greater than or equal to the risk threshold, it is determined that there is a risk in the current flight process, modify the pre-route and repeat this step.

[0013] Among them, the risk M1 related to the UAV calibration value is calculated as follows:

[0014]

[0015] In the formula, A is the UAV calibration value, indicating the number of times the flight route is adjusted, the initial value is 0, and e is an exponential function;

[0016] Among them, the calculation formula for the risk value M2 of the remaining distance is:

[0017]

[0018] In the formula, S is the remaining distance of the UAV flight, S0 is the initial flight distance, ΔS is the flight distance, E is the current energy consumption rate of the UAV, and Emax is the maximum energy consumption rate of the UAV;

[0019] Among them, the risk M3 related to the risk parameter matrix is ​​calculated as follows:

[0020]

[0021] Where PCi is the principal component of the i-th risk parameter matrix, i = 1, 2, ..., q, q is the number of principal components extracted, θi is the weight of the i-th principal component, a is the variable loading, xi is the i-th Class I risk variable, m is the number of Class I risk variables, yi is the i-th Class II risk variable, n is the number of Class II risk variables, zi is the i-th Class III risk variable, and p is the number of Class III risk variables;

[0022] The risk model of UAV electrical inspection is calculated as follows:

[0023]

[0024] Where M is the final risk value.

[0025] Furthermore, the risk variables are identified through data collection and feature parameter extraction;

[0026] Among them, data include meteorological data, geospatial data and equipment operation data;

[0027] Among them, the characteristic parameters are extracted based on the performance parameters and safe flight standards of the UAV.

[0028] Furthermore, the classification principle of the risk variables is:

[0029] Risk variables that pose a direct and serious threat to drone flight safety and are difficult to avoid immediately through conventional operations are classified as Category I;

[0030] Variables that have an impact on flight but can reduce risk by adjusting flight attitude, altitude or speed are classified as Category II;

[0031] Variables that will not directly lead to flight accidents in the short term but will create risks as time accumulates are defined as Class III.

[0032] Furthermore, the risk parameter matrix is ​​constructed as follows:

[0033]

[0034] Among them, Ri is the risk parameter matrix of node i. The i-th node has m type I risk variables, and the collected data are xi1, xi2, ..., xim; there are n type II risk variables, and the data are yi1, yi2, ..., yin; there are p type III risk variables, and the data are zi1, zi2, ..., zip.

[0035] Furthermore, the risk threshold calculation function T is:

[0036] T = δS·B;

[0037] Among them, S is the remaining flight distance of the UAV, B is the battery power, the battery capacity range is 0-100%, and δ is a constant determined according to the UAV performance and mission requirements.

[0038] The beneficial effects of the present invention are as follows: the present invention can evaluate the flight risk of UAVs during electrical inspections in real time and accurately through classification and identification of risk variables, detailed design of flight routes, establishment of risk parameter matrices, and construction of risk models and threshold calculation functions.

[0039] The flight route can be dynamically adjusted during the flight, which improves the safety and reliability of the UAV electrical inspection mission and reduces mission failures or safety accidents caused by risk factors.

[0040] It helps to optimize the UAV flight mission planning and improve the efficiency and quality of power system transmission line power inspection. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a schematic diagram of the overall process of the safety assessment method for the UAV inspection and power flight path;

[0042] Figure 2 A detailed flowchart of the S100 step of the safety assessment method for the UAV inspection and power flight path;

[0043] Figure 3 A detailed flowchart of the S200 step of the safety assessment method for the UAV inspection and power flight path;

[0044] Figure 4 A detailed flowchart of the S300 step of the safety assessment method for the UAV inspection and power flight path;

[0045] Figure 5 A detailed flowchart of the S400 step of the safety assessment method for the UAV inspection and power flight path;

[0046] Figure 6 This is a detailed flow chart of the S400 step of the UAV inspection and power flight path safety assessment method. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0048] See also Figure 1, which shows a method for evaluating the safety of a UAV inspection and electrical flight path provided by an embodiment of the present invention, comprising:

[0049] S100: Identify risk variables encountered during drone flight inspections and classify risk variables into categories I, II, and III;

[0050] S200: Design several groups of flight routes for drones, preset several nodes on each flight route, equip each node with risk variable collection equipment, and build a risk parameter matrix for each node in the drone electrical inspection based on the data collected by the collection equipment;

[0051] S300: Build the UAV calibration value A, the remaining flight distance S of the UAV, and the risk parameter matrix R i The risk model of UAV electrical inspection is shown in Figure 1. A represents the number of times the flight route is adjusted. The model outputs the risk value M and sets the risk threshold calculation function.

[0052] S400: Calculate the risk value of the initial flight route based on the risk model. When the risk value M is less than a preset risk threshold, determine that the current initial flight route is in a safe state, and execute the UAV electrical inspection task;

[0053] S500: With the current position of the drone and the drone power test point as endpoints, re-intercept the planned route from the current flight route, and obtain the nodes on the planned route. Calculate the risk value of the planned route through the risk model. When the risk value of the planned route is less than the risk threshold, determine that the planned route is in a safe state, and execute the drone power test task. When the risk value is greater than or equal to the risk threshold, determine that there is a risk in the current flight process, modify the planned route and repeat this step.

[0054] S100 collects environmental and working condition data during the flight of drones and divides them into Class I, Class II, and Class III with different degrees of impact on flight safety. Comprehensive data collection and sophisticated analysis and processing can accurately locate factors that affect flight safety and provide an accurate basis for subsequent evaluation; reasonable classification helps to formulate corresponding strategies for different risk levels and improve the pertinence and effectiveness of risk response.

[0055] Please refer to Figure 2 , which shows a flowchart of an exemplary method S100 for evaluating the safety of a drone inspection and power flight path in the present application, and the contents include:

[0056] S110: Build a comprehensive data collection system to continuously collect various types of data during the flight.

[0057] The collected data includes but is not limited to:

[0058] Meteorological data includes wind speed, wind direction, temperature, humidity and air pressure, which are collected by anemometer, wind direction sensor, temperature sensor, humidity sensor and air pressure sensor;

[0059] Geospatial data includes: longitude and latitude, altitude, terrain slope, etc. Geospatial data uses high-precision GPS / Beidou dual-mode positioning, combined with a laser rangefinder to accurately measure the distance between the drone and the ground or obstacles, thereby obtaining accurate terrain data;

[0060] Equipment operation data: battery voltage, current, power, motor speed, communication signal strength, etc., collected through the battery monitoring module, motor speed sensor and communication module.

[0061] The collected data is used as the basis for identifying risk variables.

[0062] S120: Preprocess the collected data to extract characteristic parameters related to flight safety.

[0063] Preprocess the collected data to remove interference factors such as noise and outliers. Use data mining and analysis techniques to extract characteristic parameters related to flight safety. For example, calculate the average and variance of wind speed over a period of time, the rate of change of terrain height, the rate of battery power consumption, etc.

[0064] S130: Identify risk variables that may affect flight safety based on the extracted characteristic parameters, and classify the risk variables.

[0065] According to the performance parameters and safe flight standards of the drone, risk variables that have a significant impact on flight safety are screened out from the characteristic parameters. For example, for wind speed, when the 10-second sliding average wind speed exceeds 12m / s, the wind speed is identified as a risk variable; when the temperature change rate exceeds 0.5℃ / min, the temperature change is considered a risk variable; when the terrain slope is greater than 15°, the terrain factor enters the risk consideration range; when the battery power consumption rate exceeds 0.5% / min, the battery status is marked as a risk variable; when the communication signal strength is lower than -80dBm or the average bit error rate exceeds 0.1%, the communication status is considered a risk factor.

[0066] S140: Classify the identified risk variables.

[0067] The principles for classifying risk variables are as follows:

[0068] Risk variables that pose a direct and serious threat to the flight safety of drones and are difficult to avoid immediately through conventional operations are classified as Category I. For example, severe weather conditions such as strong winds exceeding 15m / s, heavy rains exceeding 25mm / h, and heavy snow exceeding 10mm / h.

[0069] Variables that have a certain impact on flight, but can be reduced to a certain extent by adjusting flight attitude, altitude or speed, are classified as Class II. Examples include complex terrains such as mountains and hills, and local electromagnetic interference areas.

[0070] Class III variables are defined as those that have a relatively small impact on flight and will not directly cause flight accidents in the short term, but may accumulate over time or work together with other factors to create risks. Examples include minor equipment failures or status changes such as slight fluctuations in battery power and short-term weak but automatically recoverable communication signals.

[0071] S200 considers factors such as electrical inspection tasks, drone performance and geographical environment, plans multiple flight routes with multiple nodes, deploys various collection devices at the nodes, collects data, and finally builds a risk parameter matrix containing various risk variables. Scientific route planning and node settings can ensure comprehensive acquisition of risk information; accurate collection equipment and data processing can truly reflect the risk status of the flight environment; the risk parameter matrix lays the foundation for quantitative risk assessment.

[0072] Please refer to Figure 3 , which shows a flowchart of an exemplary method S200 for evaluating the safety of a UAV inspection and electrical flight path of the present application, and the contents include:

[0073] S210: Design several flight routes from the take-off point to the power testing point according to the power testing mission objectives and the UAV performance parameters.

[0074] On each flight route, multiple nodes are preset at certain distance intervals or key locations. The number of nodes is determined based on the complexity of the flight route and the accuracy requirements of the risk assessment. It is generally not less than 5, and nodes must be set at key locations, such as points where the terrain changes dramatically, around obstacles, at the edges of no-fly zones, etc., to ensure that risk data can be collected comprehensively and accurately.

[0075] S220: Equip each node with risk variable collection equipment to collect risk variable data and construct a risk parameter matrix.

[0076] Assume that there are m type I risk variables of the i-th node, and the collected data are xi1, xi2, ..., xim; there are n type II risk variables, and the data are yi1, yi2, ..., yin; there are p type III risk variables, and the data are zi1, zi2, ..., zip, and the risk parameter matrix Ri of node i is constructed as follows:

[0077]

[0078] S300 builds a risk model for drone electrical inspection that includes risks related to drone calibration values, remaining flight distance, and risk parameter matrix. The risk model integrates multiple key factors and has complex and accurate relationships, which can objectively reflect the actual risk level. At the same time, the comprehensive remaining distance and drone status risk threshold calculation function is set. The threshold calculation function is comprehensive and flexible, and the threshold can be dynamically adjusted according to the flight conditions to enhance the adaptability of the assessment and ensure the accuracy of risk judgment.

[0079] Please refer to Figure 4 , which shows a flowchart of an exemplary method S300 for evaluating the safety of a drone inspection and power flight path in the present application, and the contents include:

[0080] S310: Considering that multiple calibration changes may indicate a complex flight environment or unreasonable initial planning, the risk value M1 associated with the calibration value of the drone is calculated using the following formula:

[0081]

[0082] Among them, A is the UAV calibration value, the initial value is 0, and e is an exponential function.

[0083] For the risk value M1 related to the UAV calibration value, when the number of calibrations is small, the risk growth is relatively slow, but as the number of calibrations gradually increases, the risk growth rate accelerates, and after exceeding a certain number of times, the risk increases exponentially.

[0084] S320: Considering the impact of the rate of change of the remaining distance on the risk, the risk value M2 associated with the remaining distance is calculated. The calculation formula is:

[0085]

[0086] Among them, S is the remaining flight distance of the UAV, S0 is the initial flight distance, ΔS is the flight distance, E is the current energy consumption rate of the UAV, and Emax is the maximum energy consumption rate of the UAV.

[0087] For the risk M2 related to the remaining distance, the shorter the remaining distance, the higher the risk; if the distance flown deviates further from the middle of the total distance, it means that the flight route may be unreasonable and the risk increases; at the same time, the higher the energy consumption rate, the weaker the flight capability that can be supported by the remaining energy, and the risk increases accordingly.

[0088] S330: Taking into account the value of the risk variable, calculate the risk value M3 associated with the risk parameter matrix, the calculation formula is:

[0089]

[0090] Among them, PCi is the principal component of the i-th risk parameter matrix, i = 1, 2, ..., q, q is the number of principal components extracted, θi is the weight of the i-th principal component, a is the variable loading, xi is the i-th Class I risk variable, m is the number of Class I risk variables, yi is the i-th Class II risk variable, n is the number of Class II risk variables, zi is the i-th Class III risk variable, and p is the number of Class III risk variables.

[0091] S340: Combining the above three parts, the risk model of UAV electrical inspection is obtained, and the calculation formula is:

[0092]

[0093] Where M is the final risk value.

[0094] S350: Setting a risk threshold calculation function.

[0095] The risk threshold calculation function T is:

[0096] T = δS·B;

[0097] Among them, S is the remaining flight distance of the UAV, B is the battery power, the battery capacity range is 0-100%, and δ is a constant determined according to the UAV performance and mission requirements.

[0098] S400 provides a reliable decision-making basis for initial flight route risk assessment, mission execution determination, and mission initiation.

[0099] Please refer to Figure 5 , which shows a flowchart of an exemplary method S400 for evaluating the safety of a drone inspection and power flight path in the present application, and the contents include:

[0100] S410: Substitute the risk parameter matrix of each node on the initial flight route and the flight distance of the UAV into the risk model, calculate the risk value M0 of the initial flight route, and calculate the risk threshold T0 of the initial flight route.

[0101] According to the risk model calculation formula in step S300, M1, M2, and M3 of each node are calculated in sequence, and then the risk value M0 of the initial flight route is calculated according to the final risk value calculation formula.

[0102] The risk threshold T0 of the initial flight route is calculated according to the risk threshold calculation function.

[0103] S420: Compare the risk value of the initial flight route with the risk threshold of the initial flight route, and make a mission determination.

[0104] The calculated risk value M0 of the initial flight route is compared with the risk threshold T0 of the initial flight route. If M0 < T0, the current initial flight route is determined to be in a safe state and the drone power test mission can be performed; if M0 ≥ T0, the initial flight route is determined to be risky and further analysis and adjustment are required.

[0105] S500 dynamically evaluates risks and adjusts routes during flight, calculates node and pre-route risk values ​​and compares them with dynamically calculated thresholds to determine safety. If it is unsafe, it analyzes the risk source, formulates strategies, modifies the route, and repeats the evaluation. This ensures that drones can continue to fly safely in complex environments and improves mission completion rate and reliability.

[0106] Please refer to Figure 6 , which shows a flowchart of an exemplary method S500 for evaluating the safety of a UAV inspection and power flight path in the present application, and the contents include:

[0107] S510: intercepting a pre-travel route based on the real-time position of the UAV and the power test target point, and selecting nodes on the pre-travel route through distance calculation.

[0108] When the drone reaches a certain location during flight, the current location of the drone and the power test point of the drone are used as endpoints to re-intercept the pre-route from the current flight route. The nodes included in the pre-route are determined based on the real-time location information of the drone and the pre-defined node locations.

[0109] S520: Obtain a risk parameter matrix of nodes in the planned route, and calculate the risk value of each node according to the risk model.

[0110] According to the risk model in step S300, the risk parameter matrix of each node on the planned route is substituted to calculate the risk value M of the planned route. The calculation process is the same as the calculation of the risk value of the initial flight route, ensuring that changes in factors such as the current flight environment and the remaining distance are taken into account.

[0111] S530: Compare the predicted route risk value with a threshold value to determine route safety.

[0112] The risk value M of the predicted route is compared with the risk threshold T calculated based on the current remaining distance. If M < T, the predicted route is considered safe and the drone power test mission continues; if M ≥ T, the current predicted route is considered to be risky.

[0113] S540: Analyze risk factors to determine route modification strategies, such as detours, adjustment of altitude and speed, or energy-saving mode, and repeat the risk assessment process after modification.

[0114] When it is determined that the planned route has risks, the route modification strategy is initiated. According to the type and location of the risk factors, corresponding modification measures are taken. For example:

[0115] If it is a Class I risk, it is preferred to fly away from the risk area. Use real-time geographic information systems and meteorological data to find alternative routes with less wind resistance and no no-fly restrictions. The detour route can be determined by using a path search algorithm based on the gradient descent method, with the current position as the starting point and the direction away from the risk area and toward the target point as the optimization goal, gradually searching for suitable path points to construct a new flight route segment;

[0116] If it is a Class II risk, if the risk is concentrated in a certain local area, you can choose to increase the flight altitude or adjust the flight speed to pass through the area. At the same time, update the terrain cost function in the path planning algorithm so that subsequent path planning can avoid such complex terrain areas as much as possible.

[0117] If it is a Class III risk, if there is a battery problem, try to reduce unnecessary loads and adjust the flight mode to energy-saving mode. At the same time, give priority to routes with shorter distances and better signal coverage in path planning to complete the mission and return home as soon as possible. If there is a communication signal problem, try to adjust the antenna direction or switch the communication frequency band, and avoid signal interference source areas in path planning.

[0118] After modifying the pre-route, return to sub-step 501, re-intercept the new pre-route and perform risk assessment, and repeat the above process until a safe pre-route is found or it is determined that the mission cannot be completed. During the whole process, the drone status, environmental changes and risk assessment results are continuously monitored to ensure flight safety.

[0119] During the electrical test, a drone carrying an electrical tester is used to hover above the wire, and the tester is slowly lowered to land on the wire. The test data is transmitted remotely via wireless transmission. After the test is completed, the drone increases its flight altitude and retracts the tester.

[0120] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0121] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0122] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0123] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features of the present invention.

[0124] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for evaluating the safety of a UAV inspection flight path, characterized in that: include: Identify the risk variables encountered during drone flight inspections and classify the risk variables into categories I, II, and III; Design several groups of UAV flight routes, preset several nodes on each flight route, equip each node with risk variable collection equipment, and build the risk parameter matrix of each node in the UAV electrical inspection based on the data collected by the collection equipment; Build the UAV calibration value A, the remaining distance S of the UAV flight, and the risk parameter matrix R i The risk model of UAV electrical inspection is developed. The risk model outputs the risk value M and sets the risk threshold calculation function. The risk value of the initial flight route is calculated based on the risk model. When the risk value M is less than the preset risk threshold, the current initial flight route is determined to be safe and the UAV electrical inspection task is performed. Take the current position of the drone and the power test point of the drone as endpoints, re-intercept the pre-route from the current flight route, and obtain the nodes on the pre-route. Calculate the risk value of the pre-route through the risk model. When the risk value of the pre-route is less than the risk threshold, the pre-route is determined to be safe and the drone power test task is performed. When the risk value is greater than or equal to the risk threshold, it is determined that there is a risk in the current flight process, modify the pre-route and repeat this step. Among them, the calculation formula for the risk M1 related to the unmanned aerial vehicle calibration value is: In the formula, A is the UAV calibration value, indicating the number of times the flight route is adjusted, the initial value is 0, and e is an exponential function; Among them, the calculation formula for the risk value M2 of the remaining distance is: In the formula, S is the remaining distance of the UAV flight, S0 is the initial flight distance, ΔS is the flight distance, E is the current energy consumption rate of the UAV, and Emax is the maximum energy consumption rate of the UAV; Among them, the risk M3 related to the risk parameter matrix is ​​calculated as follows: Where PCi is the principal component of the i-th risk parameter matrix, i = 1, 2, ..., q, q is the number of principal components extracted, θi is the weight of the i-th principal component, a is the variable loading, xi is the i-th Class I risk variable, m is the number of Class I risk variables, yi is the i-th Class II risk variable, n is the number of Class II risk variables, zi is the i-th Class III risk variable, and p is the number of Class III risk variables; The risk model of UAV electrical inspection is calculated as follows: Where M is the final risk value.

2. A method for evaluating the safety of a UAV inspection flight path according to claim 1, characterized in that: The risk variables are identified through data collection and feature parameter extraction; Among them, data include meteorological data, geospatial data and equipment operation data; Among them, the characteristic parameters are extracted based on the performance parameters and safe flight standards of the UAV.

3. A method for evaluating the safety of a UAV inspection and power flight path according to claim 2, characterized in that: The classification principles of the risk variables are: Risk variables that pose a direct and serious threat to drone flight safety and are difficult to avoid immediately through conventional operations are classified as Category I; Variables that have an impact on flight but can reduce risk by adjusting flight attitude, altitude or speed are classified as Category II; Variables that will not directly lead to flight accidents in the short term but will create risks as time accumulates are defined as Class III.

4. The method for evaluating the safety of a UAV inspection and power flight path according to claim 1, characterized in that: The risk parameter matrix is: Among them, Ri is the risk parameter matrix of node i. The i-th node has m type I risk variables, and the collected data are xi1, xi2, ..., xim; there are n type II risk variables, and the data are yi1, yi2, ..., yin; there are p type III risk variables, and the data are zi1, zi2, ..., zip.

5. The method for evaluating the safety of a UAV inspection and power flight path according to claim 1, characterized in that: The risk threshold calculation function T is: T = δS·B; Among them, S is the remaining flight distance of the UAV, B is the battery power, the battery capacity range is 0-100%, and δ is a constant determined according to the UAV performance and mission requirements.

Images