A vehicle-mounted multi-unmanned aerial vehicle cooperative inspection system and method

Abstract

The application relates to the technical field of unmanned aerial vehicle cooperative inspection, and discloses a vehicle-mounted multi-unmanned aerial vehicle cooperative inspection system and method, which comprises a power inspection unmanned aerial vehicle mobile aircraft carrier and a control module; a collection layer is configured to analyze task information, determine an initial inspection interval of an unmanned aerial vehicle based on an analysis result, a judgment layer is configured to judge whether to adjust the initial inspection interval based on the analysis result, an adjustment layer is configured to determine an inspection influence factor according to historical inspection records, adjust the initial inspection interval according to the inspection influence factor, and obtain a final inspection interval, and an execution layer is configured to carry out a next inspection task on an inspection area according to the final inspection interval. The application can dynamically adjust the inspection interval according to the actual situation of an inspection task, thereby effectively improving the inspection effect.

Description

Technical Field

[0001] This invention relates to the field of drone collaborative inspection technology, and more specifically, to a vehicle-mounted multi-drone collaborative inspection system and method. Background Technology

[0002] Traditional inspection methods suffer from low efficiency, high cost, and limited coverage when dealing with complex power facilities and vast inspection areas. Manual inspections not only consume significant manpower and time, but also pose safety risks to inspectors in dangerous or inaccessible areas. Existing drone inspection systems often lack effective coordination mechanisms and cannot dynamically adjust inspection intervals based on actual conditions, resulting in poor inspection effectiveness and failure to promptly identify potential safety hazards.

[0003] Therefore, it is necessary to design a vehicle-mounted multi-UAV collaborative inspection system and method to solve the problems existing in the current technology. Summary of the Invention

[0004] In view of this, the present invention proposes a vehicle-mounted multi-UAV collaborative inspection system and method, which aims to solve the problem that the current technology cannot dynamically adjust the inspection interval according to the actual inspection situation, resulting in poor inspection effect and failure to detect potential safety hazards in a timely manner.

[0005] In one aspect, the present invention proposes a vehicle-mounted multi-UAV collaborative inspection system, comprising:

[0006] A mobile carrier vehicle for power line inspection drones and a control module; the mobile carrier vehicle for power line inspection drones is equipped with four drones on its top, and the control module is connected to all four drones. The control module includes a data acquisition layer, a judgment layer, an adjustment layer, and an execution layer.

[0007] The acquisition layer is configured to determine the inspection task and inspection area, acquire the task information of the inspection task, parse the task information, and determine the initial inspection interval of the UAV based on the parsing result.

[0008] The judgment layer is configured to collect real-time image information in the inspection task, parse the real-time image information, and determine whether to adjust the initial inspection interval based on the parsing result;

[0009] The adjustment layer is configured to, when it is determined that the initial inspection interval needs to be adjusted, extract the corresponding historical inspection records based on the inspection task, determine the inspection impact factor based on the historical inspection records, adjust the initial inspection interval based on the inspection impact factor, and obtain the final inspection interval.

[0010] The execution layer is configured to perform the next inspection task on the inspection area based on the final inspection interval.

[0011] Furthermore, when parsing the task information and determining the initial inspection interval of the UAV based on the parsing results, the process includes:

[0012] The task information is parsed to obtain the inspection difficulty and importance of the inspection task;

[0013] Construct an inspection interval vector group based on the inspection difficulty and inspection importance;

[0014] The inspection interval vector group is compared with the historical inspection interval group, and the initial inspection interval of the UAV is determined based on the comparison result.

[0015] Furthermore, when determining the initial inspection interval of the UAV based on the comparison results, the process includes:

[0016] If there is a historical inspection interval vector group in the historical inspection interval group that is the same as the inspection interval vector group, the historical inspection interval corresponding to the historical inspection interval vector group shall be used as the initial inspection interval.

[0017] If there is no historical inspection interval vector group in the historical inspection interval group that is the same as the inspection interval vector group, the initial inspection interval of the UAV is determined according to the inspection interval vector group.

[0018] Further, when determining the initial inspection interval of the UAV based on the inspection interval vector group, the process includes:

[0019] Set thresholds for inspection difficulty and inspection importance;

[0020] The inspection difficulty is compared with the inspection difficulty threshold, and the inspection importance is compared with the inspection importance threshold. The initial inspection interval of the UAV is determined based on the comparison results.

[0021] When the inspection difficulty is greater than or equal to the inspection difficulty threshold, and the inspection importance is greater than or equal to the inspection importance threshold, the initial inspection interval of the UAV is determined to be the first inspection interval.

[0022] When the inspection difficulty is less than the inspection difficulty threshold and the inspection importance is greater than or equal to the inspection importance threshold, the initial inspection interval of the UAV is determined to be the second inspection interval.

[0023] When the inspection difficulty is greater than or equal to the inspection difficulty threshold and the inspection importance is less than the inspection importance threshold, the initial inspection interval of the UAV is determined to be the third inspection interval.

[0024] When the inspection difficulty is less than the inspection difficulty threshold and the inspection importance is less than the inspection importance threshold, the initial inspection interval of the UAV is determined to be the fourth inspection interval.

[0025] Further, when analyzing the real-time image information and determining whether to adjust the initial inspection interval based on the analysis results, the process includes:

[0026] The real-time image information is preprocessed;

[0027] The preprocessed image is segmented to extract the inspection target area;

[0028] Extract the feature information of the inspection target area;

[0029] The feature information is compared with the defect feature database, and the initial inspection interval is adjusted based on the comparison results.

[0030] Further, when comparing the feature information with the defect feature database and determining whether to adjust the initial inspection interval based on the comparison result, the process includes:

[0031] Calculate the maximum matching degree between the feature information and the defect feature library;

[0032] Set a matching degree threshold, compare the maximum matching degree with the matching degree threshold, and determine whether to adjust the initial inspection interval based on the comparison result;

[0033] If the maximum matching degree is greater than the matching degree threshold, it is determined that the initial inspection interval should be adjusted.

[0034] Otherwise, it is determined that the initial inspection interval will not be adjusted.

[0035] Furthermore, when determining the inspection impact factors based on the historical inspection records, the following are included:

[0036] The historical inspection records are parsed to obtain the historical defect feature information of the inspection target area during the last inspection;

[0037] Calculate the defect change rate of the inspection target area based on the aforementioned feature information and historical defect feature information;

[0038] Collect the wind speed and light intensity of the inspection target area;

[0039] The environmental impact index is determined based on the wind speed and light intensity during the inspection.

[0040] The inspection impact factor is determined based on the defect change rate and the environmental impact index.

[0041] Furthermore, when calculating the defect change rate of the inspected object area based on the aforementioned feature information and historical defect feature information, the calculation includes:

[0042] The feature information is parsed to obtain the current number of defects and the distribution of defect types in the inspection target area;

[0043] The historical defect feature information is analyzed to obtain the number of historical defects and the distribution of historical defect types in the inspection target area;

[0044] Calculate the difference between the current number of defects and the historical number of defects, as well as the degree of difference between the current defect type distribution and the historical defect type distribution;

[0045] The defect change rate of the inspected object area is determined based on the difference and the degree of difference.

[0046] Further, when adjusting the initial inspection interval based on the inspection impact factor to obtain the final inspection interval, the process includes:

[0047] The inspection impact factor is compared with the first inspection impact factor and the second inspection impact factor, and the adjustment coefficient of the initial inspection interval is determined based on the comparison result; wherein, the first inspection impact factor is smaller than the second inspection impact factor.

[0048] If the inspection impact factor is less than or equal to the first inspection impact factor, the adjustment coefficient of the initial inspection interval is determined to be the first coefficient;

[0049] If the inspection impact factor is greater than the first inspection impact factor and less than or equal to the second inspection impact factor, the adjustment coefficient of the initial inspection interval is determined to be the second coefficient.

[0050] If the inspection impact factor is greater than the second inspection impact factor, the adjustment coefficient of the initial inspection interval is determined to be the third coefficient;

[0051] The final inspection interval is obtained by multiplying the initial inspection interval by the adjustment coefficient.

[0052] Compared with existing technologies, the beneficial effects of this invention are as follows: The vehicle-mounted multi-UAV collaborative inspection system provided in this embodiment can dynamically adjust the inspection interval according to the actual situation of the inspection task, thereby effectively improving the inspection effect. By collecting and analyzing image information in real time, potential safety hazards can be detected in a timely manner. For example, when a large rate of defect change or a high environmental impact index is found in the inspection area during the inspection process, the system will adjust the inspection interval in a timely manner and increase the inspection frequency to monitor the condition of the inspection area more closely. At the same time, the system uses historical inspection records to determine the inspection influencing factors, making the adjusted inspection interval more scientific and reasonable. Historical inspection records contain rich information, such as previous defect characteristics and inspection environment. By analyzing and utilizing this information, the changing trend of the inspection object can be better predicted, thereby optimizing the inspection plan. In addition, the division of labor among the layers in the system is clear and they work collaboratively. The acquisition layer is responsible for accurately acquiring task information and determining the initial inspection interval, the judgment layer can accurately determine whether adjustment is needed, the adjustment layer makes reasonable adjustments based on reliable factors, and the execution layer efficiently executes the final inspection task. This hierarchical structure ensures the efficient operation of the entire inspection system, improves the efficiency and quality of inspections, reduces the waste of manpower and resources, and provides strong support for ensuring the safe and stable operation of the inspection area.

[0053] In another aspect, the present invention also proposes a vehicle-mounted multi-UAV collaborative inspection method, comprising the following steps:

[0054] The inspection task and inspection area are determined, the task information of the inspection task is collected, the task information is parsed, and the initial inspection interval of the UAV is determined based on the parsing results.

[0055] Collect real-time image information during the inspection task, parse the real-time image information, and determine whether to adjust the initial inspection interval based on the parsing results;

[0056] When it is determined that the initial inspection interval needs to be adjusted, the corresponding historical inspection records are extracted based on the inspection task, and the inspection impact factor is determined based on the historical inspection records. The initial inspection interval is then adjusted based on the inspection impact factor to obtain the final inspection interval.

[0057] Based on the final inspection interval, the next inspection task will be carried out on the inspection area.

[0058] It is understandable that the above-mentioned vehicle-mounted multi-UAV collaborative inspection system and method have the same beneficial effects, and will not be elaborated further here. Attached Figure Description

[0059] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0060] Figure 1 This is a structural block diagram of the vehicle-mounted multi-UAV collaborative inspection system provided in an embodiment of the present invention;

[0061] Figure 2 A flowchart of a vehicle-mounted multi-UAV collaborative inspection method provided in an embodiment of the present invention. Detailed Implementation

[0062] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specified, embodiments and features in the embodiments of the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0063] See Figure 1 As shown in some embodiments of this application, this embodiment provides a vehicle-mounted multi-UAV collaborative inspection system, including:

[0064] A mobile carrier vehicle for power line inspection drones and a control module; the mobile carrier vehicle for power line inspection drones is equipped with four drones on its top, and the control module is connected to all four drones. The control module includes a data acquisition layer, a judgment layer, an adjustment layer, and an execution layer.

[0065] The acquisition layer is configured to determine the inspection task and inspection area, acquire the task information of the inspection task, parse the task information, and determine the initial inspection interval of the UAV based on the parsing result.

[0066] The judgment layer is configured to collect real-time image information in the inspection task, parse the real-time image information, and determine whether to adjust the initial inspection interval based on the parsing result;

[0067] The adjustment layer is configured to, when it is determined that the initial inspection interval needs to be adjusted, extract the corresponding historical inspection records based on the inspection task, determine the inspection impact factor based on the historical inspection records, adjust the initial inspection interval based on the inspection impact factor, and obtain the final inspection interval.

[0068] The execution layer is configured to perform the next inspection task on the inspection area based on the final inspection interval.

[0069] In this embodiment, the inspection interval refers to the time interval between the start of the current inspection task and the start of the next inspection task. The initial inspection interval is the initial value of this time interval, and the final inspection interval is the time interval determined after adjustment for carrying out the next inspection task. This dynamic adjustment of the inspection interval enables the inspection system to better adapt to different inspection situations.

[0070] It is understood that the vehicle-mounted multi-UAV collaborative inspection system provided in this embodiment can dynamically adjust the inspection interval according to the actual situation of the inspection task, thereby effectively improving the inspection effect. By collecting and analyzing image information in real time, potential safety hazards can be detected in a timely manner. For example, when a large rate of defect change or a high environmental impact index is found in the area of ​​the inspection target during the inspection process, the system will adjust the inspection interval in a timely manner and increase the inspection frequency to monitor the condition of the inspection area more closely. At the same time, the system uses historical inspection records to determine the inspection influencing factors, making the adjusted inspection interval more scientific and reasonable. Historical inspection records contain rich information, such as previous defect characteristics and inspection environment. By analyzing and utilizing this information, the changing trend of the inspection target can be better predicted, thereby optimizing the inspection plan. In addition, the division of labor among the layers in the system is clear and they work together. The acquisition layer is responsible for accurately acquiring task information and determining the initial inspection interval, the judgment layer can accurately determine whether adjustment is needed, the adjustment layer makes reasonable adjustments based on reliable factors, and the execution layer efficiently executes the final inspection task. This hierarchical structure ensures the efficient operation of the entire inspection system, improves the efficiency and quality of inspections, reduces the waste of manpower and resources, and provides strong support for ensuring the safe and stable operation of the inspection area.

[0071] Specifically, when parsing the task information and determining the initial inspection interval of the UAV based on the parsing results, the process includes:

[0072] The task information is parsed to obtain the inspection difficulty and importance of the inspection task;

[0073] Construct an inspection interval vector group based on the inspection difficulty and inspection importance;

[0074] The inspection interval vector group is compared with the historical inspection interval group, and the initial inspection interval of the UAV is determined based on the comparison result.

[0075] Understandably, inspection difficulty and inspection importance refer to the degree of difficulty faced during the execution of the inspection task and the importance of the task in ensuring the safe and stable operation of the inspected area, respectively. Inspection difficulty can be affected by various factors, such as the geographical environment of the inspection area—whether it is mountainous, a body of water, or a densely populated urban area. Complex geographical environments increase the difficulty of drone flights and inspections. The type and condition of the inspected object also affect the difficulty, such as the aging of the equipment and its installation location. Inspection importance, on the other hand, is related to the function and role of the inspected object. If the inspected object is a critical power facility, and a failure would cause serious consequences such as power outages over a large area, then the inspection task is of high importance.

[0076] Specifically, when determining the initial inspection interval of the UAV based on the comparison results, the process includes:

[0077] If there is a historical inspection interval vector group in the historical inspection interval group that is the same as the inspection interval vector group, the historical inspection interval corresponding to the historical inspection interval vector group shall be used as the initial inspection interval.

[0078] If there is no historical inspection interval vector group in the historical inspection interval group that is the same as the inspection interval vector group, the initial inspection interval of the UAV is determined according to the inspection interval vector group.

[0079] Understandably, determining the initial inspection interval by constructing an inspection interval vector set and comparing it with the historical inspection interval set is a scientific and reasonable method. The historical inspection interval set records the inspection intervals used in the past under different inspection difficulties and importance conditions. By comparing them, past experience can be referenced to make the initial inspection interval more in line with the actual situation.

[0080] Understandably, when there is no historical inspection interval vector group in the historical inspection interval group that is the same as the inspection interval vector group, it is necessary to scientifically estimate the initial inspection interval by comprehensively considering the inspection difficulty and inspection importance.

[0081] Specifically, determining the initial inspection interval of the UAV based on the inspection interval vector group includes:

[0082] Set thresholds for inspection difficulty and inspection importance;

[0083] The inspection difficulty is compared with the inspection difficulty threshold, and the inspection importance is compared with the inspection importance threshold. The initial inspection interval of the UAV is determined based on the comparison results.

[0084] When the inspection difficulty is greater than or equal to the inspection difficulty threshold, and the inspection importance is greater than or equal to the inspection importance threshold, the initial inspection interval of the UAV is determined to be the first inspection interval.

[0085] When the inspection difficulty is less than the inspection difficulty threshold and the inspection importance is greater than or equal to the inspection importance threshold, the initial inspection interval of the UAV is determined to be the second inspection interval.

[0086] When the inspection difficulty is greater than or equal to the inspection difficulty threshold and the inspection importance is less than the inspection importance threshold, the initial inspection interval of the UAV is determined to be the third inspection interval.

[0087] When the inspection difficulty is less than the inspection difficulty threshold and the inspection importance is less than the inspection importance threshold, the initial inspection interval of the UAV is determined to be the fourth inspection interval.

[0088] Understandably, the order of inspection intervals is: first inspection interval < second inspection interval, second inspection interval < third inspection interval, and third inspection interval < fourth inspection interval. This is because when both inspection difficulty and importance are high, it means the inspection task faces significant challenges and is crucial for ensuring the safe and stable operation of the inspected area, requiring more frequent inspections. Therefore, the initial inspection interval should be the shortest, i.e., the first inspection interval. When inspection difficulty is low but inspection importance is high, although the task is relatively easy to execute, its importance cannot be ignored, and the inspection frequency should also be high, so the second inspection interval is next. When inspection difficulty is high but inspection importance is low, although the task is difficult to execute, its impact on overall safe and stable operation is relatively small, so the inspection frequency can be appropriately reduced, so the third inspection interval is next. When both inspection difficulty and importance are low, the urgency and necessity of the inspection task are relatively weak, and the inspection frequency can be the lowest, so the fourth inspection interval is the longest. By scientifically and rationally determining different initial inspection intervals based on the difficulty and importance of inspections, the vehicle-mounted multi-UAV collaborative inspection system can more accurately adapt to the actual needs of various inspection tasks, further improve the effectiveness and efficiency of inspections, and better ensure the safe and stable operation of the inspection area.

[0089] Specifically, when parsing the real-time image information and determining whether to adjust the initial inspection interval based on the parsing results, the process includes:

[0090] The real-time image information is preprocessed;

[0091] The preprocessed image is segmented to extract the inspection target area;

[0092] Extract the feature information of the inspection target area;

[0093] The feature information is compared with the defect feature database, and the initial inspection interval is adjusted based on the comparison result.

[0094] Understandably, the preprocessing steps for real-time image information are as follows: First, denoising is performed to remove random noise points caused by sensor noise, transmission interference, and other factors, thereby improving image clarity and quality. Methods such as mean filtering, median filtering, or Gaussian filtering can be used, with the appropriate filtering method selected based on the image characteristics and noise type. Next, image enhancement is performed to increase contrast and brightness, highlighting key features. For example, histogram equalization can be used to improve the overall visual effect of the image, making details more apparent and facilitating subsequent analysis and recognition. Then, image segmentation is performed to separate target objects from the background. Methods such as thresholding, edge detection, or region growing can be used, with the appropriate segmentation algorithm selected based on the image content and target object characteristics. Image segmentation allows for more accurate extraction of inspection targets, such as power equipment and lines. Afterward, feature extraction is performed on the segmented target objects, extracting features such as shape, size, color, and texture. These features serve as important bases for subsequent judgment and analysis; by quantifying and analyzing these features, it can be determined whether any anomalies exist in the target objects. Finally, the preprocessed image information is encoded and compressed to reduce data volume, facilitating storage and transmission. Appropriate encoding algorithms, such as JPEG and PNG, are employed to minimize storage space and transmission bandwidth requirements while maintaining image quality. This series of preprocessing steps provides a more accurate and reliable data foundation for subsequent analysis and judgment of real-time image information.

[0095] As can be understood, feature information represents a vector composed of the current number of defects and the distribution of defect types, while the defect feature database is a database that stores historical vectors composed of historical defect numbers and defect type distributions. By comparing the feature information of the inspection target area with the defect feature database, it is possible to accurately determine whether there are potential safety hazards in the current inspection area.

[0096] Specifically, when comparing the feature information with the defect feature database and determining whether to adjust the initial inspection interval based on the comparison result, the following steps are included:

[0097] Calculate the maximum matching degree between the feature information and the defect feature library;

[0098] Set a matching degree threshold, compare the maximum matching degree with the matching degree threshold, and determine whether to adjust the initial inspection interval based on the comparison result;

[0099] If the maximum matching degree is greater than the matching degree threshold, it is determined that the initial inspection interval should be adjusted.

[0100] Otherwise, it is determined that the initial inspection interval will not be adjusted.

[0101] The preferred matching degree calculation method is cosine similarity, which measures similarity by calculating the cosine of the angle between two vectors and extracts the maximum matching degree. After obtaining the maximum matching degree, it is compared with a set matching degree threshold: if it is greater than the threshold, it indicates a high similarity between the current inspection target area's feature information and the defect feature database, suggesting a potential safety hazard. In this case, the initial inspection interval is adjusted to increase the inspection frequency; for example, if the threshold is set to 0.7 and the maximum matching degree is 0.8, the system triggers the adjustment mechanism. If it is less than or equal to the threshold, it indicates a low similarity and no immediate significant safety hazard. Therefore, the initial inspection interval is not adjusted, and the original plan is maintained, avoiding frequent inspections and saving resources and costs. Furthermore, the matching degree threshold can be flexibly adjusted according to different inspection scenarios and needs. For example, the threshold can be lowered for inspecting power facilities around nuclear power plants, while it can be raised for inspecting small electrical equipment in ordinary residential areas. This approach enhances the adaptability and effectiveness of the vehicle-mounted multi-UAV collaborative inspection system.

[0102] Specifically, when determining the inspection impact factors based on the historical inspection records, the following are included:

[0103] The historical inspection records are parsed to obtain the historical defect feature information of the inspection target area during the last inspection;

[0104] Calculate the defect change rate of the inspection target area based on the aforementioned feature information and historical defect feature information;

[0105] Collect the wind speed and light intensity of the inspection target area;

[0106] The environmental impact index is determined based on the wind speed and light intensity during the inspection.

[0107] The inspection impact factor is determined based on the defect change rate and the environmental impact index.

[0108] Understandably, the calculation method for the Environmental Impact Index involves normalizing the inspected wind speed and inspected light intensity, and then performing a weighted summation of the normalized wind speed and light intensity. Normalization eliminates the influence of different dimensions on the calculation results, ensuring that the inspected wind speed and light intensity are on the same scale, facilitating the subsequent weighted summation. The weights in the weighted summation can be adjusted according to the actual situation. For example, if the wind speed in the inspected area has a significant impact on the inspection results, the weight of the wind speed can be appropriately increased; conversely, if the light intensity has a more significant impact on the inspection results, the weight of the light intensity can be increased.

[0109] Specifically, when calculating the defect change rate of the inspected object area based on the aforementioned feature information and historical defect feature information, the following steps are included:

[0110] The feature information is parsed to obtain the current number of defects and the distribution of defect types in the inspection target area;

[0111] The historical defect feature information is analyzed to obtain the number of historical defects and the distribution of historical defect types in the inspection target area;

[0112] Calculate the difference between the current number of defects and the historical number of defects, as well as the degree of difference between the current defect type distribution and the historical defect type distribution;

[0113] The defect change rate of the inspected object area is determined based on the difference and the degree of difference.

[0114] It is understandable that, after parsing the feature information of the current inspection target area, the current number of defects is 15, and the defect type distribution is 40% for type A defects, 30% for type B defects, and 30% for type C defects; after parsing the historical defect feature information from the last inspection, the number of historical defects is 10, and the historical defect type distribution is 50% for type A defects, 25% for type B defects, and 25% for type C defects.

[0115] First, calculate the difference between the current number of defects and the historical number of defects, which is 15-10=5.

[0116] Then, calculate the difference between the current defect type distribution and the historical defect type distribution. This can be measured by summing the absolute values ​​of the differences in the proportion of each type of defect. The absolute value of the difference in the proportion of type A defects is |40%-50%|=10%, the absolute value of the difference in the proportion of type B defects is |30%-25%|=5%, and the absolute value of the difference in the proportion of type C defects is |30%-25%|=5%. Therefore, the difference is 10%+5%+5%=20%.

[0117] Next, to comprehensively consider the impact of quantity difference and type distribution difference on the defect change rate, different weights can be assigned to quantity difference and difference based on the actual situation. Let's assume the weight of quantity difference is 0.6 and the weight of difference is 0.4.

[0118] The defect change rate is calculated as follows: Quantity difference weight × (Quantity difference / Historical defect quantity) + Difference weight × Difference = 0.6 × (5 / 10) + 0.4 × 20% = 0.6 × 0.5 + 0.4 × 0.2 = 0.3 + 0.08 = 0.38, or 38%.

[0119] This calculation process allows for a more accurate determination of the defect change rate in the inspected area. Combined with the environmental impact index, this identifies the inspection influencing factors, ultimately enabling a scientific adjustment of the inspection interval. This allows the vehicle-mounted multi-UAV collaborative inspection system to more precisely address different inspection conditions, improving inspection quality and efficiency, and providing a more reliable guarantee for the safe and stable operation of the inspected area. In practical applications, as the number of inspections increases and data accumulates, the calculation of the defect change rate will become more accurate, and the system adjustments will become more reasonable and efficient.

[0120] Specifically, when adjusting the initial inspection interval based on the inspection impact factor to obtain the final inspection interval, the process includes:

[0121] The inspection impact factor is compared with the first inspection impact factor and the second inspection impact factor, and the adjustment coefficient of the initial inspection interval is determined based on the comparison result; wherein, the first inspection impact factor is smaller than the second inspection impact factor.

[0122] If the inspection impact factor is less than or equal to the first inspection impact factor, the adjustment coefficient of the initial inspection interval is determined to be the first coefficient;

[0123] If the inspection impact factor is greater than the first inspection impact factor and less than or equal to the second inspection impact factor, the adjustment coefficient of the initial inspection interval is determined to be the second coefficient.

[0124] If the inspection impact factor is greater than the second inspection impact factor, the adjustment coefficient of the initial inspection interval is determined to be the third coefficient;

[0125] The final inspection interval is obtained by multiplying the initial inspection interval by the adjustment coefficient.

[0126] Understandably, the adjustment coefficients are arranged in the following order: the first coefficient is greater than the second, and the second is greater than the third. This is because when the inspection impact factor is small, it indicates that the defect changes and environmental impacts in the inspected area are relatively stable, and the need to adjust the inspection interval is small. Therefore, the inspection interval can be appropriately extended, and a larger adjustment coefficient (the first coefficient) is used. When the inspection impact factor is in the middle range, it means that the condition of the inspected area has changed to some extent, but has not yet reached the point where a significant reduction in the inspection interval is required. In this case, a moderate adjustment coefficient (the second coefficient) is used. When the inspection impact factor is large, it indicates that the defect changes in the inspected area are significant and the environmental impact is substantial, posing a high safety risk. More frequent inspections are required, so a smaller adjustment coefficient (the third coefficient) is used. By scientifically adjusting the initial inspection interval according to the inspection impact factor in this way, the vehicle-mounted multi-UAV collaborative inspection system can more flexibly adapt to the actual conditions of the inspection area. For example, in a certain inspection area, if the calculated inspection impact factor is relatively small, the adjustment coefficient is set as the first coefficient. Assuming the initial inspection interval is 7 days and the first coefficient is 1.2, the final inspection interval will be 7 × 1.2 = 8.4 days. This appropriately extends the inspection interval, reduces unnecessary inspections, and saves resources. Conversely, if the inspection impact factor is relatively large, the adjustment coefficient is set as the third coefficient. Assuming the third coefficient is 0.8, and the initial inspection interval remains 7 days, the final inspection interval will be 7 × 0.8 = 5.6 days. This shortens the inspection interval, increases the inspection frequency, and better ensures the safe and stable operation of the inspection area.

[0127] See Figure 2 As shown in some embodiments of this application, this embodiment provides a vehicle-mounted multi-UAV collaborative inspection method, including the following steps:

[0128] S100: Determine the inspection task and inspection area, collect the task information of the inspection task, parse the task information, and determine the initial inspection interval of the UAV based on the parsing result;

[0129] S200: Collect real-time image information during the inspection task, parse the real-time image information, and determine whether to adjust the initial inspection interval based on the parsing result;

[0130] S300: When it is determined that the initial inspection interval needs to be adjusted, the corresponding historical inspection records are extracted based on the inspection task, and the inspection impact factor is determined according to the historical inspection records. The initial inspection interval is adjusted according to the inspection impact factor, and the final inspection interval is obtained.

[0131] S400: Based on the final inspection interval, carry out the next inspection task for the inspection area.

[0132] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program goods. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program goods embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0133] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program goods according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0134] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0135] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0136] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A vehicle-mounted multi-UAV collaborative inspection system, characterized in that, include: Mobile carrier vehicle and control module for power line inspection drones; The mobile carrier vehicle for power line inspection drones is equipped with four drones on its top. The control module is connected to all four drones and includes a data acquisition layer, a judgment layer, an adjustment layer, and an execution layer. The acquisition layer is configured to determine the inspection task and inspection area, acquire the task information of the inspection task, parse the task information, and determine the initial inspection interval of the UAV based on the parsing result. The judgment layer is configured to collect real-time image information in the inspection task, parse the real-time image information, and determine whether to adjust the initial inspection interval based on the parsing result; The adjustment layer is configured to, when it is determined that the initial inspection interval needs to be adjusted, extract the corresponding historical inspection records based on the inspection task, determine the inspection impact factor based on the historical inspection records, adjust the initial inspection interval based on the inspection impact factor, and obtain the final inspection interval. When adjusting the initial inspection interval based on the inspection impact factor to obtain the final inspection interval, the process includes: The inspection impact factor is compared with the first inspection impact factor and the second inspection impact factor, and the adjustment coefficient of the initial inspection interval is determined based on the comparison result; wherein, the first inspection impact factor is smaller than the second inspection impact factor. If the inspection impact factor is less than or equal to the first inspection impact factor, the adjustment coefficient of the initial inspection interval is determined to be the first coefficient; If the inspection impact factor is greater than the first inspection impact factor and less than or equal to the second inspection impact factor, the adjustment coefficient of the initial inspection interval is determined to be the second coefficient. If the inspection impact factor is greater than the second inspection impact factor, the adjustment coefficient of the initial inspection interval is determined to be the third coefficient; Multiply the initial inspection interval by the adjustment coefficient to obtain the final inspection interval; The adjustment coefficients are arranged in the following order: the first coefficient is greater than the second coefficient, and the second coefficient is greater than the third coefficient. The execution layer is configured to perform the next inspection task on the inspection area based on the final inspection interval.

2. The vehicle-mounted multi-UAV collaborative inspection system according to claim 1, characterized in that, When parsing the task information and determining the initial inspection interval of the UAV based on the parsing results, the process includes: The task information is parsed to obtain the inspection difficulty and importance of the inspection task; Construct an inspection interval vector group based on the inspection difficulty and inspection importance; The inspection interval vector group is compared with the historical inspection interval group, and the initial inspection interval of the UAV is determined based on the comparison result.

3. The vehicle-mounted multi-UAV collaborative inspection system according to claim 2, characterized in that, When determining the initial inspection interval of the UAV based on the comparison results, the following are included: If there is a historical inspection interval vector group in the historical inspection interval group that is the same as the inspection interval vector group, the historical inspection interval corresponding to the historical inspection interval vector group shall be used as the initial inspection interval. If there is no historical inspection interval vector group in the historical inspection interval group that is the same as the inspection interval vector group, the initial inspection interval of the UAV is determined according to the inspection interval vector group.

4. The vehicle-mounted multi-UAV collaborative inspection system according to claim 3, characterized in that, When determining the initial inspection interval of the UAV based on the inspection interval vector group, the following is included: Set thresholds for inspection difficulty and inspection importance; The inspection difficulty is compared with the inspection difficulty threshold, and the inspection importance is compared with the inspection importance threshold. The initial inspection interval of the UAV is determined based on the comparison results. When the inspection difficulty is greater than or equal to the inspection difficulty threshold, and the inspection importance is greater than or equal to the inspection importance threshold, the initial inspection interval of the UAV is determined to be the first inspection interval. When the inspection difficulty is less than the inspection difficulty threshold and the inspection importance is greater than or equal to the inspection importance threshold, the initial inspection interval of the UAV is determined to be the second inspection interval. When the inspection difficulty is greater than or equal to the inspection difficulty threshold and the inspection importance is less than the inspection importance threshold, the initial inspection interval of the UAV is determined to be the third inspection interval. When the inspection difficulty is less than the inspection difficulty threshold and the inspection importance is less than the inspection importance threshold, the initial inspection interval of the UAV is determined to be the fourth inspection interval.

5. The vehicle-mounted multi-UAV collaborative inspection system according to claim 4, characterized in that, When parsing the real-time image information and determining whether to adjust the initial inspection interval based on the parsing results, the process includes: The real-time image information is preprocessed; The preprocessed image is segmented to extract the inspection target area; Extract the feature information of the inspection target area; The feature information is compared with the defect feature database, and the initial inspection interval is adjusted based on the comparison result.

6. The vehicle-mounted multi-UAV collaborative inspection system according to claim 5, characterized in that, When comparing the feature information with a defect feature database and determining whether to adjust the initial inspection interval based on the comparison result, the process includes: Calculate the maximum matching degree between the feature information and the defect feature library; Set a matching degree threshold, compare the maximum matching degree with the matching degree threshold, and determine whether to adjust the initial inspection interval based on the comparison result; If the maximum matching degree is greater than the matching degree threshold, it is determined that the initial inspection interval should be adjusted. Otherwise, it is determined that the initial inspection interval will not be adjusted.

7. The vehicle-mounted multi-UAV collaborative inspection system according to claim 6, characterized in that, When determining the inspection impact factors based on the historical inspection records, the following are included: The historical inspection records are parsed to obtain the historical defect feature information of the inspection target area during the last inspection; Calculate the defect change rate of the inspection target area based on the aforementioned feature information and historical defect feature information; Collect the wind speed and light intensity of the inspection target area; The environmental impact index is determined based on the wind speed and light intensity during the inspection. The inspection impact factor is determined based on the defect change rate and the environmental impact index.

8. The vehicle-mounted multi-UAV collaborative inspection system according to claim 7, characterized in that, When calculating the defect change rate of the inspection target area based on the aforementioned feature information and historical defect feature information, the following steps are included: The feature information is parsed to obtain the current number of defects and the distribution of defect types in the inspection target area; The historical defect feature information is analyzed to obtain the number of historical defects and the distribution of historical defect types in the inspection target area; Calculate the difference between the current number of defects and the historical number of defects, as well as the degree of difference between the current defect type distribution and the historical defect type distribution; The defect change rate of the inspected object area is determined based on the difference and the degree of difference.

9. A vehicle-mounted multi-UAV collaborative inspection method, applied to the vehicle-mounted multi-UAV collaborative inspection system as described in any one of claims 1-8, characterized in that, include: The inspection task and inspection area are determined, the task information of the inspection task is collected, the task information is parsed, and the initial inspection interval of the UAV is determined based on the parsing results. Collect real-time image information during the inspection task, parse the real-time image information, and determine whether to adjust the initial inspection interval based on the parsing results; When it is determined that the initial inspection interval needs to be adjusted, the corresponding historical inspection records are extracted based on the inspection task, and the inspection impact factor is determined based on the historical inspection records. The initial inspection interval is then adjusted based on the inspection impact factor to obtain the final inspection interval. When adjusting the initial inspection interval based on the inspection impact factor to obtain the final inspection interval, the process includes: The inspection impact factor is compared with the first inspection impact factor and the second inspection impact factor, and the adjustment coefficient of the initial inspection interval is determined based on the comparison result; wherein, the first inspection impact factor is smaller than the second inspection impact factor. If the inspection impact factor is less than or equal to the first inspection impact factor, the adjustment coefficient of the initial inspection interval is determined to be the first coefficient; If the inspection impact factor is greater than the first inspection impact factor and less than or equal to the second inspection impact factor, the adjustment coefficient of the initial inspection interval is determined to be the second coefficient. If the inspection impact factor is greater than the second inspection impact factor, the adjustment coefficient of the initial inspection interval is determined to be the third coefficient; Multiply the initial inspection interval by the adjustment coefficient to obtain the final inspection interval; The adjustment coefficients are arranged in the following order: the first coefficient is greater than the second coefficient, and the second coefficient is greater than the third coefficient. Based on the final inspection interval, the next inspection task will be carried out on the inspection area.

Images