A distribution network line inspection method for multi-sensor integrated drones

Abstract

The present invention provides a distribution network line inspection method for a multi-sensor integrated unmanned aerial vehicle (UAV), which belongs to the technical field of UAVs and specifically comprises: combining available inspection processing schemes of different inspection processing intervals to obtain a line inspection scheme for the distribution network line; determining an optimal inspection scheme among the line inspection schemes based on the inspection processing reliability and inspection processing power consumption of the available inspection processing schemes of the different inspection processing intervals; determining inspection sensors for different inspection processing intervals using the optimal inspection scheme; and when determining that an abnormality exists at a current inspection position based on analysis results of monitoring data of different inspection sensors, and when determining that monitoring data meets requirements based on analysis results of monitoring images of all matching sensors, continuing to use the inspection sensors to perform inspection processing in the inspection processing intervals, thereby ensuring the reliability and accuracy of the inspection processing.

Description

Technical Field

[0001] The present invention belongs to the technical field of unmanned aerial vehicles (UAVs), and in particular relates to a distribution network line inspection method for a multi-sensor integrated UAV. Background Art

[0002] With the rapid development of drone technology, the inspection of distribution network lines has gradually shifted from manual inspection to drone inspection, which has greatly improved the efficiency of inspection and processing of distribution network lines.

[0003] Specifically, in invention patent application CN202311309637.4, "A UAV Inspection System for Power Industry Infrastructure," a UAV equipped with multiple sensors, including a fixed-focus camera, a focus-adjustable camera, an infrared thermal imager, and a lidar, is used to achieve reliable inspection of distribution network lines. However, analysis reveals the following technical issues:

[0004] For drones with multiple sensors, existing technical solutions ignore the coordinated processing of data between different sensors. During the inspection process, problems may exist in some sensors at certain line locations of the distribution network. Therefore, if multiple sets of monitoring images from other sensors cannot be obtained in a targeted manner for the line locations of the distribution network with problems, it is possible that the image of the fault location is not accurately obtained, and thus the fault location cannot be accurately identified and processed.

[0005] In response to the above technical problems, the present invention provides a distribution network line inspection method for a multi-sensor integrated drone. Summary of the Invention

[0006] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0007] In order to solve the above technical problems, the present invention provides a distribution network line inspection method for a multi-sensor integrated drone, which specifically includes:

[0008] S1 divides the distribution network lines into different inspection processing intervals and determines the matching coefficients between the inspection processing intervals and different types of sensors and the matching sensors based on the historical fault data of the different inspection processing intervals;

[0009] S2 generates a sensor inspection processing scheme for the inspection processing interval based on the matching sensors, and uses historical fault data to determine the inspection processing reliability of different sensor inspection processing schemes and the available inspection processing schemes for the inspection processing interval;

[0010] S3 combines the available inspection processing schemes in different inspection processing intervals to obtain a line inspection scheme for the distribution network line, and determines the best inspection scheme among the line inspection schemes based on the inspection processing reliability and inspection processing power consumption of the available inspection processing schemes in different inspection processing intervals;

[0011] S4 uses the optimal inspection plan to determine the inspection sensors for different inspection processing intervals. When it is determined that there is an abnormality in the current inspection position based on the analysis results of the monitoring data of different inspection sensors, and when it is determined that the monitoring data meets the requirements based on the analysis results of the monitoring images of all matching sensors, the inspection sensors are continued to be used to perform inspection processing in the inspection processing interval.

[0012] The beneficial effects of the present invention are:

[0013] 1. In the present invention, based on the historical fault data of different inspection processing intervals, the matching coefficients and matching sensors between the inspection processing intervals and different types of sensors are determined, thereby achieving the determination of matching sensors with higher accuracy in identifying historical fault types from the perspective of historical fault data. This not only ensures the accuracy of identifying and processing fault types with higher fault probabilities, but also avoids the occurrence of technical problems such as high power consumption caused by the use of more sensors, thereby improving the reliability of the inspection processing of the drone.

[0014] 2. In the present invention, when it is determined that there is an abnormality at the current inspection location, the monitoring data is determined to meet the requirements based on the analysis results of the monitoring images of all matching sensors, thereby avoiding the technical problem of insufficient data volume of the monitoring data at the current inspection location with an abnormality caused by a single sensor, ensuring the accuracy of the analysis results of the monitoring data, and laying the foundation for further realizing the accurate assessment of the fault type of the inspection location with an abnormality.

[0015] A further technical solution is to divide the distribution network lines into different inspection and processing intervals, including:

[0016] The distribution network line is divided according to a preset length to obtain a division processing result, and the distribution network line is divided into different inspection processing intervals using the division processing result.

[0017] A further technical solution is to divide the distribution network lines into different inspection and processing intervals, including:

[0018] The matching network lines between adjacent distribution network towers are divided into the same inspection and processing interval.

[0019] A further technical solution is that the historical fault data includes the number of occurrences of different types of faults and the number of corresponding fault points.

[0020] A further technical solution is that the method for determining the matching sensor is:

[0021] Determining the number of occurrences of different types of faults and the number of corresponding fault points based on the historical fault data of the inspection processing interval, and determining the historical severity of different types of faults based on the number of occurrences of different types of faults and the number of corresponding fault points;

[0022] Determining the recognition and processing accuracy of the sensor for different types of faults based on the fault characteristics of the sensor for different types of faults, and determining the recognition matching coefficients for different types of faults based on the recognition and processing accuracy and historical severity of different types of faults;

[0023] The matching coefficients of the inspection processing interval and the sensor are determined by using the identification matching coefficients of different types of faults, and the matching sensors are determined by using the matching coefficients.

[0024] A further technical solution is that when the matching coefficient of the sensor is greater than a preset matching coefficient, the sensor is determined to be a matching sensor.

[0025] A further technical solution is that the method for generating the sensor inspection processing solution is:

[0026] The matching sensors in the inspection processing interval are freely combined to obtain a plurality of combination schemes, and the sensor inspection processing scheme for the inspection processing interval is generated using the combination schemes.

[0027] A further technical solution is to confirm that the monitoring data meets the requirements, including:

[0028] Determine the image clarity and fault characteristics of the monitoring images under different matching sensors based on the analysis results of the monitoring images under different matching sensors, and determine the data reliability under different matching sensors based on the number of monitoring images under different matching sensors;

[0029] The reliability of the monitoring data is determined based on the data reliability of different matching sensors, and the reliability of the monitoring data is used to determine whether the monitoring data meets the requirements.

[0030] A further technical solution is that when the reliability of the monitoring data is less than a preset reliability threshold, it is determined that the monitoring data does not meet the requirements.

[0031] Other features and advantages will be described in the following description, and in part will become apparent from the description, or understood by practicing the invention. The purpose and other advantages of the invention are realized and obtained by the structures particularly pointed out in the description and the drawings.

[0032] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the accompanying drawings.

[0034] Figure 1 It is a flow chart of a distribution network line inspection method for a multi-sensor integrated drone;

[0035] Figure 2 is a flow chart of a method for determining a matching sensor;

[0036] Figure 3 It is a flow chart of a method for determining available inspection treatment solutions. DETAILED DESCRIPTION

[0037] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be embodied in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art. Like reference numerals in the figures represent like or similar structures, and thus their detailed description will be omitted.

[0038] The terms "a", "an", "the", and "said" are used to indicate the presence of one or more elements / components / etc.; the terms "including" and "having" are used to express an open-ended inclusive meaning and mean that additional elements / components / etc. may be present in addition to the listed elements / components / etc.

[0039] To solve the above problems, according to one aspect of the present invention, Figure 1 According to one aspect of the present invention, a distribution network line inspection method for a multi-sensor integrated drone is provided, specifically comprising:

[0040] S1 divides the distribution network lines into different inspection processing intervals and determines the matching coefficients between the inspection processing intervals and different types of sensors and the matching sensors based on the historical fault data of the different inspection processing intervals;

[0041] Furthermore, the distribution network lines are divided into different inspection and processing intervals, including:

[0042] The distribution network line is divided according to a preset length to obtain a division processing result, and the distribution network line is divided into different inspection processing intervals using the division processing result.

[0043] Specifically, the distribution network lines are divided into different inspection and processing intervals, including:

[0044] The matching network lines between adjacent distribution network towers are divided into the same inspection and processing interval.

[0045] It is understandable that the historical fault data includes the number of occurrences of different types of faults and the number of corresponding fault points.

[0046] Further, such as Figure 2 As shown, the method for determining the matching sensor is:

[0047] Determining the number of occurrences of different types of faults and the number of corresponding fault points based on the historical fault data of the inspection processing interval, and determining the historical severity of different types of faults based on the number of occurrences of different types of faults and the number of corresponding fault points;

[0048] Determining the recognition and processing accuracy of the sensor for different types of faults based on the fault characteristics of the sensor for different types of faults, and determining the recognition matching coefficients for different types of faults based on the recognition and processing accuracy and historical severity of different types of faults;

[0049] The matching coefficients of the inspection processing interval and the sensor are determined by using the identification matching coefficients of different types of faults, and the matching sensors are determined by using the matching coefficients.

[0050] Furthermore, when the matching coefficient of the sensor is greater than a preset matching coefficient, the sensor is determined to be a matching sensor.

[0051] In another embodiment, the matching sensor is determined by:

[0052] Determine the number of fault points corresponding to different types of faults based on the historical fault data of the inspection processing interval, and determine the number of serious fault points based on the historical fault times of different fault points;

[0053] Determining the recognition and processing accuracy of the sensor for different types of faults based on the fault characteristics of the sensor for different types of faults, and determining the recognition matching coefficients for different types of faults based on the recognition and processing accuracy of different types of faults and the number of serious fault points;

[0054] The identification matching coefficients of different types of faults are used to determine the accurately identified faults among the different types of faults, and the matching coefficients between the inspection processing interval and the sensor are determined using the matching coefficients. The matching sensors are determined using the matching coefficients.

[0055] In another embodiment, the matching sensor is determined by:

[0056] S11 determines the recognition and processing accuracy of the sensor for different types of faults based on the fault characteristics of the sensor for different types of faults;

[0057] S12: determining the number of occurrences of different types of faults and the number of corresponding fault points based on the historical fault data in the inspection processing interval, determining the historical severity of different types of faults based on the number of occurrences of different types of faults and the number of corresponding fault points, determining the serious fault among different types of faults based on the historical severity, and determining the identification matching coefficients of different types of faults based on the identification and processing accuracy of different types of faults and the historical severity;

[0058] S13 performs matching coefficient matching between the inspection processing interval and the sensor through identification matching coefficients of different types of faults, and determines a matching sensor using the matching coefficient.

[0059] Optionally, the above step S11 includes the following contents:

[0060] Based on the fault characteristics of different types of faults in the sensor, the recognition and processing accuracy of the sensor for different types of faults is determined, and it is judged whether the sensor has a fault whose recognition and processing accuracy is greater than a preset accuracy. If so, the process goes to step S12; if not, it is determined that the sensor is not a matching sensor.

[0061] Optionally, the above step S12 includes the following contents:

[0062] S121 determines the number of occurrences of different types of faults and the number of corresponding fault points based on the historical fault data of the inspection processing interval, and determines the historical severity of different types of faults based on the number of occurrences of different types of faults and the number of corresponding fault points. The historical severity is used to determine the serious fault among the different types of faults, and whether the recognition accuracy of the sensor for the serious fault meets the requirements is judged. If so, the process proceeds to step S13; if not, the process proceeds to the next step.

[0063] S122 determines whether the number of types of faults for which the sensor's recognition processing accuracy is greater than a preset accuracy is greater than a preset number of types. If so, proceed to the next step; if not, determine that the sensor is not a matching sensor.

[0064] S123 determines the identification matching coefficients of different types of faults based on the identification and processing accuracy of different types of faults and their historical severity, and determines whether there is a fault whose identification matching coefficient is greater than a preset matching threshold. If so, proceed to step S13; if not, determine that the sensor is not a matching sensor.

[0065] S2 generates a sensor inspection processing scheme for the inspection processing interval based on the matching sensors, and uses historical fault data to determine the inspection processing reliability of different sensor inspection processing schemes and the available inspection processing schemes for the inspection processing interval;

[0066] It should be noted that the method for generating the sensor inspection processing solution is:

[0067] The matching sensors in the inspection processing interval are freely combined to obtain a plurality of combination schemes, and the sensor inspection processing scheme for the inspection processing interval is generated using the combination schemes.

[0068] Further, such as Figure 3 As shown, the method for determining the available inspection processing solutions is:

[0069] Determining the number of occurrences of different types of faults and the number of corresponding fault points based on the historical fault data of the inspection processing interval, and determining the historical severity of different types of faults based on the number of occurrences of different types of faults and the number of corresponding fault points;

[0070] Based on the matching sensors in the sensor inspection processing solution, determining the fault characteristics of different types of faults in different matching sensors, and determining the fault recognition accuracy of different types of faults in the sensor inspection processing solution based on the fault characteristics of different matching sensors;

[0071] Based on the historical severity of different types of faults and the fault identification accuracy of the sensor inspection processing scheme, the inspection processing reliability of the sensor inspection processing scheme is determined, and the inspection processing reliability is used to determine the available inspection processing schemes in the sensor inspection processing scheme.

[0072] It can be understood that when the inspection processing reliability of the sensor inspection processing scheme meets the requirements, the sensor inspection processing scheme is determined to be an available inspection processing scheme.

[0073] It should also be noted that the method for determining the available inspection processing solutions is:

[0074] S21 determines the fault characteristics of different types of faults in different matching sensors based on the matching sensors in the sensor inspection processing solution, and determines the fault recognition accuracy of different types of faults in the sensor inspection processing solution based on the fault characteristics of different matching sensors.

[0075] S22: faults whose fault identification accuracy is less than a preset accuracy threshold are identified as identification deviation faults, and the number of occurrences of different types of faults and the number of corresponding fault points are determined based on the historical fault data of the inspection processing interval, and the historical severity of different types of faults is determined based on the number of occurrences of different types of faults and the number of corresponding fault points;

[0076] S23 determines the inspection processing reliability of the sensor inspection processing scheme based on the historical severity of different types of faults and the fault identification accuracy of the sensor inspection processing scheme, and uses the inspection processing reliability to determine the available inspection processing schemes in the sensor inspection processing scheme.

[0077] Optionally, the above step S21 includes the following contents:

[0078] Based on the matching sensors in the sensor inspection processing scheme, the fault characteristics of different types of faults in different matching sensors are determined, and based on the fault characteristics of different matching sensors, the fault identification accuracy of different types of faults in the sensor inspection processing scheme is determined, and it is judged whether the fault identification accuracy of different types of faults in the sensor inspection processing scheme is less than the preset accuracy threshold. If so, it is determined that the sensor inspection processing scheme does not belong to the available inspection processing scheme. If not, step S22 is entered.

[0079] Optionally, the above step S22 includes the following contents:

[0080] S221: A fault whose fault recognition accuracy is less than a preset accuracy threshold is regarded as an identification deviation fault, and whether the total number of occurrences of the identification deviation fault is within a preset number interval is determined. If so, the process proceeds to the next step; if not, the process determines that the sensor inspection processing solution is not an available inspection processing solution.

[0081] S222 determines whether the total number of fault points corresponding to the identification deviation fault is within a preset number range. If so, proceed to the next step. If not, determine that the sensor inspection processing solution does not belong to the available inspection processing solution.

[0082] S223 determines the number of occurrences of different types of faults and the corresponding number of fault points based on the historical fault data in the inspection processing interval, and determines the historical severity of different types of faults based on the number of occurrences of different types of faults and the corresponding number of fault points, and judges whether there is an identification deviation fault whose historical fault severity is greater than the preset severity. If so, it is determined that the sensor inspection processing scheme does not belong to the available inspection processing scheme. If not, enter step S23.

[0083] Furthermore, the patrol processing power consumption of the available patrol processing solutions in the patrol processing interval is determined according to the distance of the patrol processing interval and the patrol processing power consumption per unit distance of different matching sensors in the available patrol processing solutions.

[0084] S3 combines the available inspection processing schemes in different inspection processing intervals to obtain a line inspection scheme for the distribution network line, and determines the best inspection scheme among the line inspection schemes based on the inspection processing reliability and inspection processing power consumption of the available inspection processing schemes in different inspection processing intervals;

[0085] Specifically, the method for determining the best inspection plan among the line inspection plans is:

[0086] Determine the comprehensive inspection reliability of different line inspection plans based on the inspection processing reliability of available inspection processing plans in different inspection processing intervals;

[0087] Determine the power consumption of different line inspection plans based on the inspection processing power consumption of the available inspection processing plans in different inspection processing intervals, and determine the remaining available power based on the power consumption and the deviation of the available power of the drone;

[0088] The inspection processing priority value of the line inspection scheme is determined according to the remaining available power and the comprehensive inspection reliability, and the inspection processing priority value is used to determine the best inspection scheme among the line inspection schemes.

[0089] Furthermore, the optimal inspection plan is the line inspection plan with the largest inspection processing priority value.

[0090] It is understandable that the method for determining the inspection processing priority value of the line inspection solution is:

[0091] Determining the power inspection reliability of the line inspection plan based on the remaining available power;

[0092] The inspection processing priority value of the line inspection plan is determined according to the average value of the power inspection reliability and the comprehensive inspection reliability.

[0093] It should also be noted that the method for determining the best inspection plan among the line inspection plans is:

[0094] The power consumption of different line inspection plans is determined based on the inspection processing power consumption of the available inspection processing plans in different inspection processing intervals, and the remaining available power is determined based on the power consumption and the deviation of the available power of the drone, and it is judged whether the remaining available power is less than a preset power threshold. If so, it is determined that the line inspection plan is not the optimal inspection plan. If not, proceed to the next step;

[0095] Determining the minimum value of the remaining available power according to the inspection distance of the distribution network line, and judging whether the remaining available power is less than the minimum value of the remaining available power; if so, determining that the line inspection plan is not an optimal inspection plan; if not, proceeding to the next step;

[0096] Determining an average value of the inspection processing reliability of different inspection processing intervals based on the inspection processing reliability of the available inspection processing solutions in different inspection processing intervals, and judging whether the average value of the inspection processing reliability of different inspection processing intervals is within a preset processing reliability interval; if so, proceeding to the next step; if not, determining that the line inspection solution is not an optimal inspection solution;

[0097] Determine the comprehensive inspection reliability of different line inspection plans based on the inspection processing reliability of the available inspection processing plans in different inspection processing intervals, and determine whether the comprehensive inspection reliability of the line inspection plan is less than the average value of the comprehensive inspection reliability of the different line inspection plans. If so, determine that the line inspection plan is not the optimal inspection plan. If not, proceed to the next step.

[0098] The inspection processing priority value of the line inspection scheme is determined according to the remaining available power and the comprehensive inspection reliability, and the inspection processing priority value is used to determine the best inspection scheme among the line inspection schemes.

[0099] S4 uses the optimal inspection plan to determine the inspection sensors for different inspection processing intervals. When it is determined that there is an abnormality in the current inspection position based on the analysis results of the monitoring data of different inspection sensors, and when it is determined that the monitoring data meets the requirements based on the analysis results of the monitoring images of all matching sensors, the inspection sensors are continued to be used to perform inspection processing in the inspection processing interval.

[0100] Furthermore, it is determined that there is an abnormality in the current inspection location, specifically including:

[0101] Determine if there is an abnormality at the current inspection location based on the analysis results of the monitoring data from different inspection sensors

[0102] Determine the fault characteristics of the current inspection position under different inspection sensors based on the analysis results of the monitoring data of different inspection sensors, and determine the fault state values ​​under different inspection sensors using the fault characteristics under different inspection sensors;

[0103] The fault probability of the current inspection position is determined according to the fault state values ​​of different inspection sensors, and the fault probability is used to determine whether there is an abnormality at the current position.

[0104] Specifically, the fault probability of the current inspection position is determined based on the fault state values ​​of different inspection sensors, including:

[0105] The suspected faulty patrol sensor is determined based on the fault status values ​​under different patrol sensors, and the fault probability of the current patrol position is determined by multiplying the proportion of the suspected faulty patrol sensors in the patrol sensors by the average value of the fault status values ​​under different patrol sensors.

[0106] Furthermore, it is determined that the monitoring data meets the requirements, including:

[0107] Determine the image clarity and fault characteristics of the monitoring images under different matching sensors based on the analysis results of the monitoring images under different matching sensors, and determine the data reliability under different matching sensors based on the number of monitoring images under different matching sensors;

[0108] The reliability of the monitoring data is determined based on the data reliability of different matching sensors, and the reliability of the monitoring data is used to determine whether the monitoring data meets the requirements.

[0109] It can be understood that when the reliability of the monitoring data is less than a preset reliability threshold, it is determined that the monitoring data does not meet the requirements.

[0110] Through the above embodiments, the present invention achieves the following beneficial effects:

[0111] 1. In the present invention, based on the historical fault data of different inspection processing intervals, the matching coefficients and matching sensors between the inspection processing intervals and different types of sensors are determined, thereby achieving the determination of matching sensors with higher accuracy in identifying historical fault types from the perspective of historical fault data. This not only ensures the accuracy of identifying and processing fault types with higher fault probabilities, but also avoids the occurrence of technical problems such as high power consumption caused by the use of more sensors, thereby improving the reliability of the inspection processing of the drone.

[0112] 2. In the present invention, when it is determined that there is an abnormality at the current inspection location, the monitoring data is determined to meet the requirements based on the analysis results of the monitoring images of all matching sensors, thereby avoiding the technical problem of insufficient data volume of the monitoring data at the current inspection location with an abnormality caused by a single sensor, ensuring the accuracy of the analysis results of the monitoring data, and laying the foundation for further realizing the accurate assessment of the fault type of the inspection location with an abnormality.

[0113] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the device, apparatus, and non-volatile computer storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simplified. For relevant details, refer to the descriptions of the method embodiments.

[0114] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0115] The foregoing description is merely one or more embodiments of this specification and is not intended to limit this specification. It will be apparent to those skilled in the art that various modifications and variations may be made to one or more embodiments of this specification. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of one or more embodiments of this specification are intended to be within the scope of the claims of this specification.

Claims

1. A distribution network line inspection method for a multi-sensor integrated drone, characterized in that: Specifically include: Divide the distribution network lines into different inspection processing intervals, and determine the matching coefficients between the inspection processing intervals and different types of sensors and the matching sensors based on the historical fault data of the different inspection processing intervals; Generate sensor inspection processing plans for the inspection processing interval based on matching sensors, and use historical fault data to determine the inspection processing reliability of different sensor inspection processing plans and the available inspection processing plans for the inspection processing interval; Combining available inspection processing schemes in different inspection processing intervals to obtain a line inspection scheme for the distribution network line, and determining the best inspection scheme among the line inspection schemes based on the inspection processing reliability and inspection processing power consumption of the available inspection processing schemes in different inspection processing intervals; The optimal inspection plan is used to determine the inspection sensors for different inspection processing intervals. When it is determined that there is an abnormality in the current inspection position based on the analysis results of the monitoring data of different inspection sensors, and when it is determined that the monitoring data meets the requirements based on the analysis results of the monitoring images of all matching sensors, the inspection sensors are continued to be used to perform inspection processing in the inspection processing interval.

2. The distribution network line inspection method for a multi-sensor integrated drone according to claim 1, characterized in that: Divide the distribution network lines into different inspection and processing intervals, including: The distribution network line is divided according to a preset length to obtain a division processing result, and the distribution network line is divided into different inspection processing intervals using the division processing result.

3. The distribution network line inspection method for a multi-sensor integrated drone according to claim 1, characterized in that: Divide the distribution network lines into different inspection and processing intervals, including: The matching network lines between adjacent distribution network towers are divided into the same inspection and processing interval.

4. The distribution network line inspection method for a multi-sensor integrated drone according to claim 1, characterized in that: The method for determining the matching sensor is: Determining the number of occurrences of different types of faults and the number of corresponding fault points based on the historical fault data of the inspection processing interval, and determining the historical severity of different types of faults based on the number of occurrences of different types of faults and the number of corresponding fault points; Determining the recognition and processing accuracy of the sensor for different types of faults based on the fault characteristics of the sensor for different types of faults, and determining the recognition matching coefficients for different types of faults based on the recognition and processing accuracy and historical severity of different types of faults; The matching coefficients of the inspection processing interval and the sensor are determined by using the identification matching coefficients of different types of faults, and the matching sensors are determined by using the matching coefficients.

5. The distribution network line inspection method for a multi-sensor integrated drone according to claim 4, characterized in that: When the matching coefficient of the sensor is greater than a preset matching coefficient, the sensor is determined to be a matching sensor.

6. The distribution network line inspection method for a multi-sensor integrated drone according to claim 1, characterized in that: The method for generating the sensor inspection processing solution is: The matching sensors in the inspection processing interval are freely combined to obtain a plurality of combination schemes, and the sensor inspection processing scheme for the inspection processing interval is generated using the combination schemes.

7. The distribution network line inspection method for a multi-sensor integrated drone according to claim 1, characterized in that: The method for determining the available inspection processing solutions is as follows: Determining the number of occurrences of different types of faults and the number of corresponding fault points based on the historical fault data of the inspection processing interval, and determining the historical severity of different types of faults based on the number of occurrences of different types of faults and the number of corresponding fault points; Based on the matching sensors in the sensor inspection processing solution, determining the fault characteristics of different types of faults in different matching sensors, and determining the fault recognition accuracy of different types of faults in the sensor inspection processing solution based on the fault characteristics of different matching sensors; Based on the historical severity of different types of faults and the fault identification accuracy of the sensor inspection processing scheme, the inspection processing reliability of the sensor inspection processing scheme is determined, and the inspection processing reliability is used to determine the available inspection processing schemes in the sensor inspection processing scheme.

8. The distribution network line inspection method for a multi-sensor integrated drone according to claim 7, characterized in that: When the inspection processing reliability of the sensor inspection processing solution meets the requirement, the sensor inspection processing solution is determined to be an available inspection processing solution.

9. The distribution network line inspection method for a multi-sensor integrated drone according to claim 1, characterized in that: Confirm that the monitoring data meets the requirements, including: Determine the image clarity and fault characteristics of the monitoring images under different matching sensors based on the analysis results of the monitoring images under different matching sensors, and determine the data reliability under different matching sensors based on the number of monitoring images under different matching sensors; The reliability of the monitoring data is determined based on the data reliability of different matching sensors, and the reliability of the monitoring data is used to determine whether the monitoring data meets the requirements.

10. The distribution network line inspection method for a multi-sensor integrated drone according to claim 9, characterized in that: When the reliability of the monitoring data is less than a preset reliability threshold, it is determined that the monitoring data does not meet the requirements.

Images