An unmanned aerial vehicle intelligent inspection method and system connected with an intelligent management and control platform

Abstract

The application provides a kind of unmanned aerial vehicle intelligent inspection method and system connected with intelligent management and control platform, the voltage of battery is monitored in real time, and the connection signal is sent;The charging station with minimum arrival cost determined by Dijkstra algorithm is the target charging station, and the unmanned aerial vehicle is guided to the target charging position of the target charging station through multi-level navigation module;Complete the connection with the charging station and charge, when the battery is full, according to the recorded navigation path sequence combined with Dijkstra algorithm to determine the minimum arrival cost of the return position to execute the return, continue to execute the line inspection task. Through multi-level positioning strategy, the charging position of the charging platform can be accurately and automatically positioned for charging, realizing all-weather unmanned independent operation. The charging station and return position with minimum arrival cost determined by Dijkstra algorithm save energy consumption. The multi-modal neural network image visual navigation module processes multi-modal input data and outputs motor control parameters to realize accurate positioning and smooth landing.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicle charging, in particular to an unmanned aerial vehicle intelligent inspection method and system interfaced with an intelligent management and control platform. BACKGROUND

[0002] With the development of unmanned aerial vehicle technology, it has become more and more common to replace manual inspection of power transmission channels with unmanned aerial vehicles. And with the rapid development of China's economy and society and the continuous promotion of airspace management reform, the gradual opening of low-altitude airspace, unmanned aerial vehicles will be developed and more widely applied, for example, unmanned aerial vehicles can be applied to the fields of electric power, communication, meteorology, agriculture and forestry, ocean, exploration, insurance, etc.

[0003] Since the route of the unmanned aerial vehicle performing the inspection task is long, and the unmanned aerial vehicle also continuously performs shooting or data transmission tasks during the inspection process, the power consumption of the unmanned aerial vehicle is very fast, which cannot maintain the smooth execution of the inspection task, and even the unmanned aerial vehicle cannot return to the base due to insufficient power. The short endurance time restricts the continuity of the work. And the current unmanned aerial vehicles on the market usually need to manually replace the battery, and cannot realize automatic charging and automatic control of the unmanned aerial vehicle, so they cannot meet the actual use demand and cannot realize all-weather unmanned independent operation. And in the process of replacing the battery, there is also a problem of real-time detection.

[0004] At present, various docking devices have appeared on the market, which are connected with the charging interface of the unmanned aerial vehicle to realize charging. On the one hand, since the charging device cannot be accurately positioned and the battery voltage cannot be monitored, the unmanned aerial vehicle is not convenient to maintain. On the other hand, due to the diversity of the design structure of the charging platform, the unmanned aerial vehicle and the charging platform still have docking obstacles, which are easy to cause docking errors or docking damage.

[0005] Therefore, it is necessary to design an unmanned aerial vehicle intelligent inspection method interfaced with an intelligent management and control platform to accurately navigate the charging platform and accurately position the charging position and accurately monitor the charging state, which is an important means and urgent task to ensure the stable operation of power grid inspection tasks. SUMMARY

[0006] Therefore, it is necessary to provide an unmanned aerial vehicle intelligent inspection method and system interfaced with an intelligent management and control platform to solve the charging docking problem of the unmanned aerial vehicle during the inspection task, which is easy to popularize and apply, relatively simple to operate, and suitable for popularization and application in more scenes.

[0007] The application provides a kind of unmanned plane intelligent inspection method and system that interface with intelligent management and control platform, by real-time monitoring the voltage of battery, send interface signal;By Dijkstra algorithm, the charging station of minimum arrival cost is determined as target charging station, and the unmanned plane is guided to the target charging position of target charging station by multi-level navigation module;Complete with the interface of charging station and charge, when battery capacity is full, according to the recorded navigation path sequence combined with Dijkstra algorithm, the return position of minimum arrival cost is determined to perform return, continue to perform line inspection task.By multi-level positioning strategy, the charging position of charging platform can be accurately and automatically positioned for charging, and all-weather unmanned independent operation is realized.By Dijkstra algorithm, the charging station of minimum arrival cost and return position are determined, and energy consumption is saved.By the multi-modal neural network image visual navigation module constructed, multi-modal input data are processed, and motor control parameters are output to realize accurate positioning and smooth landing.

[0008] In a first aspect, the embodiments of the application provide a kind of unmanned plane intelligent inspection method that interface with intelligent management and control platform, the method comprises:

[0009] S1. low voltage detection: the voltage of battery is monitored in real time during the inspection process of unmanned plane, when the voltage of the battery is lower than set voltage threshold, interface signal is sent;

[0010] S2. unmanned plane interface first navigation: the target charging station of the charging station of minimum arrival cost is determined by Dijkstra algorithm according to the interface signal by unmanned plane navigation system, and first navigation module is started to guide unmanned plane to the vicinity of the target charging station;

[0011] S3. unmanned plane interface second navigation: when unmanned plane reaches the first preset range from the target charging station, the second navigation module is started by unmanned plane navigation system to guide unmanned plane to the top of the target charging station;

[0012] S4. unmanned plane interface third navigation: when unmanned plane reaches the second preset range from the top of the target charging station, the third navigation module is started by unmanned plane navigation system to guide unmanned plane to the target charging position of charging station;

[0013] S5. unmanned plane interface: interface module is used to complete the interface of unmanned plane with charging station;

[0014] S6. unmanned plane charging monitoring: after interface completion, unmanned plane will be matched with charging station by Bluetooth, after Bluetooth matching succeeds, unmanned plane will send charging signal to charging station, and charging station will charge battery pack of unmanned plane in the form of wireless electric energy transmission;During charging, unmanned plane will continuously monitor battery capacity, and when battery capacity is full, unmanned plane will send stop charging signal to charging station;

[0015] S7. Drone Return Trip: The drone determines the return position with the minimum arrival cost based on the recorded navigation path sequence and Dijkstra's algorithm, and then performs the return trip to continue the line inspection task.

[0016] Optionally, in one implementation of the first aspect of the present invention, S1. Low voltage detection: The UAV monitors the battery voltage in real time during the inspection process, and when the battery voltage is lower than a set voltage threshold, it sends a docking signal, including:

[0017] The battery load voltage is acquired in real time using high-frequency sampling.

[0018] Use hardware filtering circuits combined with software sliding window algorithms to eliminate voltage fluctuation interference;

[0019] A voltage-power mapping table is established using a dynamic threshold strategy, and early warning methods are established based on the mapping table, including: Level 1 warning: triggering a status prompt; Level 2 warning: forcibly initiating a return-to-base procedure; and emergency protection: immediately executing a landing on the spot.

[0020] The intelligent decision-making module assesses whether charging or returning to base is necessary based on the warning method, estimated remaining battery power, terrain complexity of the return route, backup power status, and mission criticality level.

[0021] When it is determined that charging is needed, a docking signal is sent.

[0022] Optionally, in one implementation of the first aspect of the present invention, S2. UAV docking with the first navigation: the UAV navigation system determines the charging base station with the minimum arrival cost as the target charging base station based on the docking signal using the Dijkstra algorithm, and simultaneously activates the first navigation module to guide the UAV to the vicinity of the target charging base station, including:

[0023] S2.1, Initialization: Set the distance to the starting point to 0, set the distance to all other nodes to infinity, and create a set U of unvisited nodes containing all nodes;

[0024] S2.2, Select the node with the smallest distance: Select the node u that is closest to the starting point from the unvisited node set U, and move node u from the unvisited set U to the visited set S;

[0025] S2.3, Update the distance of adjacent nodes: Traverse all adjacent nodes v of node u, calculate the distance to these adjacent nodes through node u; if the distance to adjacent node v through node u is less than the distance recorded in the current record, update the distance of v. After updating, add these adjacent nodes back to the set of unvisited nodes U.

[0026] S2.4, Repeat steps S2.2 and S2.3: Repeatedly select the node with the minimum distance and update the distance of its adjacent nodes until the set of unvisited nodes U becomes empty, or all nodes have been processed;

[0027] S2.5, Output: The final distance array D, where d[i] represents the shortest path length from the starting point to node i, and the predecessor node is recorded to reconstruct the specific shortest path;

[0028] The node set includes charging stations and key points along the path, and the edge weights are defined by a cost function, the formula of which is:

[0029] Cost total =α×E+β×T+γ×P+λ×T2;

[0030] E=(d×e_base×w_factor×a_factor)+e_hover×t_hover;

[0031]

[0032] Where d is the total flight distance, e_base is the base energy consumption per unit distance, w_factor is the weather correction factor, w_factor is the altitude correction factor, e_hover is the energy consumption per unit hovering time, t_hover is the expected hovering waiting time, E is the energy cost, T is the mission delay penalty, P is the priority cost, and α, β, γ are the corresponding weighting coefficients.

[0033] Dijkstra's algorithm is used to optimize path planning, ensuring the shortest and safest route.

[0034] S2.6, the UAV navigation system determines the priority of the navigation module based on the detection distance, and the priority includes a first priority, a second priority, and a third priority;

[0035] S2.7, when the priority is the first priority, the first navigation module is matched;

[0036] S2.8, Activate the first navigation module to guide the drone to the vicinity of the target charging base station, wherein the first navigation module is GPS.

[0037] Optionally, in one implementation of the first aspect of the present invention, step S3. UAV docking with the second navigation: after the UAV reaches a first preset range from the target charging base station, the UAV navigation system activates the second navigation module to guide the UAV to the top of the target charging base station, including:

[0038] Determine whether the first preset range meets the detection distance corresponding to the second priority.

[0039] When the conditions are met, the second navigation module is matched;

[0040] The drone navigation system activates a second navigation module to guide the drone to a preset position above the target charging base station; wherein, the second navigation module is a GPS and ultrasonic combined navigation module.

[0041] Optionally, in one implementation of the first aspect of the present invention, step S4. UAV docking with third navigation: after the UAV reaches a second preset range above the target charging base station, the UAV navigation system activates the third navigation module to guide the UAV to the target charging location of the charging base station, including:

[0042] Determine whether the second preset range meets the detection distance corresponding to the third priority;

[0043] When the conditions are met, the third navigation module is matched;

[0044] The drone navigation system activates a third navigation module to guide the drone to the target charging location at the charging base station; wherein, the third navigation module is an image visual navigation module;

[0045] The image visual navigation module is a multimodal neural network architecture. It processes multimodal input data and outputs motor control parameters through the multimodal neural network architecture. Based on the control parameters, it controls the motor to achieve accurate positioning and smooth landing. The second preset range is smaller than the first preset range.

[0046] Optionally, in one implementation of the first aspect of the present invention, the step of processing the multimodal input data and outputting motor control parameters through a multimodal neural network architecture includes:

[0047] A multimodal neural network architecture is constructed, which includes an input layer, a modality-specific encoder, and a multimodal fusion module;

[0048] The drone's data acquisition module collects visual image data, as well as the drone's attitude angle, altitude, and position information.

[0049] The visual image data is segmented using a multimodal neural network architecture to obtain the outer contour of the target charging platform. The charging location area is further identified, and the relative position is calculated by combining altitude and location information. The attitude angle of the drone is then adjusted, and motor control parameters are output.

[0050] Optionally, in one implementation of the first aspect of the present invention, S6. UAV return trip: The UAV determines the return position with minimum arrival cost based on the recorded navigation path sequence and Dijkstra's algorithm, and performs the return trip to continue performing the line inspection task, including:

[0051] Use Dijkstra's algorithm to determine the return path with minimum arrival cost, and record D', which represents the shortest path length from the endpoint X to node j;

[0052] Compare array D' with the minimum arrival cost of array D, select the shortest path corresponding to the smaller minimum arrival cost array to perform the return trip, and continue the line patrol task.

[0053] Secondly, embodiments of this application provide a drone intelligent inspection system that interfaces with an intelligent management and control platform, applied to the drone intelligent inspection method that interfaces with an intelligent management and control platform as described in any one of claims 1 to 7, characterized in that it includes:

[0054] The low voltage detection module is used by the UAV to monitor the battery voltage in real time during the inspection process. When the battery voltage is lower than the set voltage threshold, a docking signal is sent.

[0055] The drone docks with the first navigation module, which is used by the drone navigation system to determine the charging base station with the minimum arrival cost as the target charging base station based on the docking signal and the Dijkstra algorithm. At the same time, the first navigation module is activated to guide the drone to the vicinity of the target charging base station.

[0056] The drone is connected to a second navigation module, which is used to guide the drone to the top of the target charging base station after the drone reaches a first preset range away from the target charging base station.

[0057] The drone docks with a third navigation module, which is used to guide the drone to the target charging location of the charging base station after the drone reaches a second preset range above the target charging base station.

[0058] The drone docking module is used to dock with the charging base station using the docking module installed on the drone.

[0059] The drone charging monitoring module is used to pair the drone with the charging base station via Bluetooth after docking is completed. Once Bluetooth pairing is successful, the drone will send a charging signal to the charging base station, which will then charge the drone's battery pack via wireless power transmission. During the charging process, the drone will continuously monitor the battery level. When the battery is fully charged, the drone will send a stop charging signal to the charging base station.

[0060] The drone return module is used by the drone to determine the return position with the minimum arrival cost based on the recorded navigation path sequence and Dijkstra's algorithm, and then continue to perform the line inspection task.

[0061] Thirdly, embodiments of this application provide an electronic device, characterized in that it includes:

[0062] processor;

[0063] Memory used to store processor-executable instructions;

[0064] The processor is configured to implement the intelligent inspection method for unmanned aerial vehicles (UAVs) that interfaces with the intelligent management and control platform as described in the first aspect when executing the instructions.

[0065] Fourthly, embodiments of this application provide a computer-readable storage medium, characterized in that the computer-readable storage medium stores a program that instructs a device to execute the unmanned aerial vehicle (UAV) intelligent inspection method interfaced with an intelligent management and control platform as described in the first aspect.

[0066] This application provides a method and system for intelligent drone inspection that interfaces with an intelligent management and control platform. During inspection, the drone monitors the battery voltage in real time. When the battery voltage falls below a set voltage threshold, a docking signal is emitted. Based on the docking signal, the drone navigation system uses the Dijkstra algorithm to determine the charging base station with the lowest reach cost as the target charging base station. Simultaneously, a first navigation module is activated to guide the drone to the vicinity of the target charging base station. Once the drone reaches a first preset range from the target charging base station, the drone navigation system activates a second navigation module to guide the drone to above the target charging base station. Once the drone reaches a second preset range above the target charging base station... The drone's navigation system activates the third navigation module to guide the drone to the target charging location at the charging base station. The drone then uses its docking module to connect with the charging base station. After docking, the drone and charging base station pair via Bluetooth. Once pairing is successful, the drone sends a charging signal to the charging base station, which then charges the drone's battery pack via wireless power transfer. During charging, the drone continuously monitors the battery level. When the battery is fully charged, the drone sends a stop charging signal to the charging base station. Based on the recorded navigation path sequence and Dijkstra's algorithm, the drone determines the minimum cost return point and returns to continue its line-following mission.

[0067] Beneficial effects:

[0068] (1) Through a multi-level positioning strategy, it can accurately and automatically locate the charging position of the charging platform for charging, and realize unmanned independent operation around the clock.

[0069] (2) The charging base station and return location with the minimum arrival cost are determined by Dijkstra's algorithm, which saves energy and provides strong support for the smooth charging process.

[0070] (3) The multimodal neural network image vision navigation module is constructed to process multimodal input data and output motor control parameters to achieve precise positioning and smooth landing. It utilizes the powerful data fusion capability and optimization algorithm of the multimodal neural network, and combines multiple sensor data and advanced control strategies to ensure the efficiency and accuracy of the navigation task.

[0071] (4) It is easy to promote and apply, and the operation is relatively simple, making it suitable for promotion and application in more application scenarios. Attached Figure Description

[0072] Figure 1 This is a schematic diagram of a drone intelligent inspection method that interfaces with an intelligent management and control platform, provided as an embodiment of this application.

[0073] Figure 2 This is a flowchart illustrating navigation using the Dijkstra algorithm and a first navigation module, provided as an embodiment of this application.

[0074] Figure 3 This is a schematic diagram of a drone intelligent inspection system module that interfaces with an intelligent management and control platform, provided as an embodiment of this application.

[0075] Figure 4 A schematic diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0076] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them.

[0077] It should be noted that, in the embodiments of this application, "at least one" refers to one or more, and "more than one" refers to two or more. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the specification of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application.

[0078] It should be noted that in the embodiments of this application, the terms "first," "second," etc., are used only for descriptive purposes and should not be construed as indicating or implying relative importance, nor as indicating or implying order. Features specified as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0079] Based on the embodiments described in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0080] Example 1

[0081] This application provides a method and system for intelligent inspection of unmanned aerial vehicles (UAVs) that interfaces with an intelligent management and control platform. It monitors battery voltage in real time and sends a docking signal. The Dijkstra algorithm determines the charging base station with the lowest arrival cost as the target charging base station. A multi-level navigation module guides the UAV to the target charging location at the target charging base station. After docking with the charging base station and charging, when the battery is fully charged, the UAV uses the recorded navigation path sequence combined with the Dijkstra algorithm to determine the return location with the lowest arrival cost and performs the return trip to continue the inspection task. Through a multi-level positioning strategy, it can accurately and automatically locate the charging platform for charging, achieving all-weather unmanned independent operation. The use of the Dijkstra algorithm to determine the charging base station and return location with the lowest arrival cost saves energy. A constructed multimodal neural network image vision navigation module processes multimodal input data and outputs motor control parameters to achieve precise positioning and smooth landing.

[0082] Figure 1 This is a schematic diagram of a drone intelligent inspection method that interfaces with an intelligent management and control platform, provided as an embodiment of this application.

[0083] like Figure 1 As shown, a method for intelligent inspection of unmanned aerial vehicles (UAVs) that interfaces with an intelligent management and control platform includes:

[0084] S1. Low Voltage Detection: The UAV monitors the battery voltage in real time during the inspection process. When the battery voltage is lower than the set voltage threshold, it sends a docking signal.

[0085] It is understood that in this embodiment, S1. Low voltage detection: The UAV monitors the battery voltage in real time during the inspection process. When the battery voltage is lower than a set voltage threshold, a docking signal is issued, including:

[0086] The battery load voltage is acquired in real time using high-frequency sampling.

[0087] Use hardware filtering circuits combined with software sliding window algorithms to eliminate voltage fluctuation interference;

[0088] A voltage-power mapping table is established using a dynamic threshold strategy, and early warning methods are established based on the mapping table, including: Level 1 warning: triggering a status prompt; Level 2 warning: forcibly initiating a return-to-base procedure; and emergency protection: immediately executing a landing on the spot.

[0089] The intelligent decision-making module assesses whether charging or returning to base is necessary based on the warning method, estimated remaining battery power, terrain complexity of the return route, backup power status, and mission criticality level.

[0090] When it is determined that charging is needed, a docking signal is sent.

[0091] Specifically, the drone monitors the battery voltage in real time during inspections. When the battery voltage falls below a set threshold, a docking signal is triggered. This feature ensures that the drone can return to the charging station in time when its power is low, thus avoiding mission interruption due to depleted battery. For example, the drone triggers a return command by setting a preset battery alarm threshold; when the battery level falls below the set value, the drone will automatically return to the charging platform to complete charging. Furthermore, the drone monitors the remaining battery power and compares it to a set threshold; when the battery level falls below the threshold, it will issue an alarm signal or perform a return-to-home operation.

[0092] S2. Drone docking first navigation: Based on the docking signal, the drone navigation system uses the Dijkstra algorithm to determine the charging base station with the minimum arrival cost as the target charging base station, and simultaneously activates the first navigation module to guide the drone to the vicinity of the target charging base station.

[0093] Figure 2 This is a flowchart illustrating navigation using the Dijkstra algorithm and a first navigation module, provided as an embodiment of this application. Figure 2 As shown, it can be understood that in this embodiment, S2. UAV docking with the first navigation: The UAV navigation system determines the charging base station with the minimum arrival cost as the target charging base station based on the docking signal using the Dijkstra algorithm, and simultaneously activates the first navigation module to guide the UAV to the vicinity of the target charging base station, including:

[0094] S2.1, Initialization: Set the distance to the starting point to 0, set the distance to all other nodes to infinity, and create a set U of unvisited nodes containing all nodes;

[0095] S2.2, Select the node with the smallest distance: Select the node u that is closest to the starting point from the unvisited node set U, and move node u from the unvisited set U to the visited set S;

[0096] S2.3, Update the distance of adjacent nodes: Traverse all adjacent nodes v of node u, calculate the distance to these adjacent nodes through node u; if the distance to adjacent node v through node u is less than the distance recorded in the current record, update the distance of v. After updating, add these adjacent nodes back to the set of unvisited nodes U.

[0097] S2.4, Repeat steps S2.2 and S2.3: Repeatedly select the node with the minimum distance and update the distance of its adjacent nodes until the set of unvisited nodes U becomes empty, or all nodes have been processed;

[0098] S2.5, Output: The final distance array D, where d[i] represents the shortest path length from the starting point to node i, and the predecessor node is recorded to reconstruct the specific shortest path;

[0099] The node set includes charging stations and key points along the path, and the edge weights are defined by a cost function, the formula of which is:

[0100] Cost total =α×E+β×T+γ×P+λ×T2;

[0101] E=(d×e_base×w_factor×a_factor)+e_hover×t_hover;

[0102]

[0103] Where d is the total flight distance, e_base is the base energy consumption per unit distance, w_factor is the weather correction factor, w_factor is the altitude correction factor, e_hover is the energy consumption per unit hovering time, t_hover is the expected hovering waiting time, E is the energy cost, T is the mission delay penalty, P is the priority cost, and α, β, γ are the corresponding weighting coefficients.

[0104] Dijkstra's algorithm is used to optimize path planning, ensuring the shortest and safest route.

[0105] S2.6, the UAV navigation system determines the priority of the navigation module based on the detection distance, and the priority includes a first priority, a second priority, and a third priority;

[0106] S2.7, when the priority is the first priority, the first navigation module is matched;

[0107] S2.8, Activate the first navigation module to guide the drone to the vicinity of the target charging base station, wherein the first navigation module is GPS.

[0108] Specifically, after receiving the docking signal, the UAV navigation system uses the Dijkstra algorithm to determine the location of the target charging base station and activates the first navigation module to guide the UAV to the vicinity of the target charging base station. This process involves path planning and navigation control. The UAV uses GPS to locate its own position and combines this with the location and navigation of charging platforms within the detection range of the UWB base station. The UAV automatically searches for and lands at the wireless charging base station in the flight control system to complete the docking.

[0109] S3. Drone docking with second navigation: When the drone reaches a first preset range from the target charging base station, the drone navigation system activates the second navigation module to guide the drone to the top of the target charging base station.

[0110] It is understood that in this embodiment, S3. UAV docking with the second navigation: after the UAV reaches a first preset range from the target charging base station, the UAV navigation system activates the second navigation module to guide the UAV to the top of the target charging base station, including:

[0111] Determine whether the first preset range meets the detection distance corresponding to the second priority.

[0112] When the conditions are met, the second navigation module is matched;

[0113] The drone navigation system activates a second navigation module to guide the drone to a preset position above the target charging base station; wherein, the second navigation module is a GPS and ultrasonic combined navigation module.

[0114] Specifically, once the drone reaches the vicinity of the target charging station (within the first preset range), the navigation system activates the second navigation module to guide the drone above the charging station. This step further refines the drone's precise positioning capabilities, facilitating subsequent attitude adjustments as the drone approaches the charging station to ensure proper docking.

[0115] S4. Drone docking with third navigation: When the drone reaches the second preset range above the target charging base station, the drone navigation system activates the third navigation module to guide the drone to the target charging location of the charging base station.

[0116] It is understood that in this embodiment, S4. UAV docking with third navigation: After the UAV reaches a second preset range above the target charging base station, the UAV navigation system activates the third navigation module to guide the UAV to the target charging location of the charging base station, including:

[0117] Determine whether the second preset range meets the detection distance corresponding to the third priority;

[0118] When the conditions are met, the third navigation module is matched;

[0119] The drone navigation system activates a third navigation module to guide the drone to the target charging location at the charging base station; wherein, the third navigation module is an image visual navigation module;

[0120] The image visual navigation module is a multimodal neural network architecture. It processes multimodal input data and outputs motor control parameters through the multimodal neural network architecture. Based on the control parameters, it controls the motor to achieve accurate positioning and smooth landing. The second preset range is smaller than the first preset range.

[0121] Specifically, the step of processing multimodal input data and outputting motor control parameters using a multimodal neural network architecture includes:

[0122] A multimodal neural network architecture is constructed, which includes an input layer, a modality-specific encoder, and a multimodal fusion module;

[0123] The drone's data acquisition module collects visual image data, as well as the drone's attitude angle, altitude, and position information.

[0124] The visual image data is segmented using a multimodal neural network architecture to obtain the outer contour of the target charging platform. The charging location area is further identified, and the relative position is calculated by combining altitude and location information. The attitude angle of the drone is then adjusted, and motor control parameters are output.

[0125] Specifically, once the drone reaches above the target charging base station (within the second preset range), the navigation system activates the third navigation module to guide the drone to the target charging location. This step further enhances the drone's precise spatial control capabilities. The drone achieves millimeter-level precision positioning through multi-information collaborative positioning technology, progressing from coarse positioning to precise positioning step by step.

[0126] Specifically, the image-based visual navigation module processes multimodal input data through a multimodal neural network and outputs motor control parameters to achieve precise positioning and a smooth landing. This process relies on the powerful data fusion capabilities and optimization algorithms of the multimodal neural network, while also incorporating data from multiple sensors and advanced control strategies, thereby ensuring the efficiency and accuracy of the navigation mission.

[0127] Specifically, the multimodal neural network architecture includes an input layer, a modality-specific encoder, and a multimodal fusion module. This architecture can integrate data from different sensors, such as visual image data, the drone's attitude angles, altitude, and position information, thereby improving the accuracy and robustness of drone navigation.

[0128] Drones acquire multimodal data in real time, including visual image data, attitude angles, altitude, and position information, through their built-in sensors (such as cameras, IMUs, and GPS). After preprocessing (such as filtering, dimensionality reduction, and normalization), these data are used to form training and testing sets for subsequent model training and validation.

[0129] In multimodal neural networks, data from each modality undergoes feature extraction via a specific encoder. For example, spatial features of visual image data can be extracted using a convolutional neural network (CNN), while pose angles, height, and position information are extracted as temporal features using fully connected layers or recurrent neural networks (RNNs). These features are then integrated in a multimodal fusion module to generate a unified representation through self-attention mechanisms or other fusion methods.

[0130] A multimodal neural network is used to segment visual image data, identify the outer contour of the target charging platform, and further determine the charging location area. Combining altitude and position information, the relative position between the drone and the target is calculated, thereby adjusting the drone's attitude angle to achieve precise positioning.

[0131] Based on the fused multimodal features, the multimodal neural network outputs motor control parameters. These parameters are used to adjust the drone's flight status (such as speed, direction, and attitude) to ensure that the drone can land smoothly at the target location.

[0132] To improve model performance, a random forest algorithm can be used to optimize the combination of multi-teacher models, and the effectiveness of the model can be verified using a test set. Furthermore, a lightweight student network can be used to further reduce computational complexity, thereby improving operational efficiency.

[0133] S5. Drone docking: Use the docking module installed on the drone to dock with the charging base station.

[0134] Understandably, in this embodiment, the docking module on the drone is used to complete the docking with the charging base station. The drone achieves precise docking with the charging battery holder through an auxiliary battery swapping module and a positioning device. The drone adjusts its attitude during the docking process to ensure accurate contact.

[0135] S6. Drone Charging Monitoring: After docking, the drone will pair with the charging base station via Bluetooth. Once Bluetooth pairing is successful, the drone will send a charging signal to the charging base station, which will then charge the drone's battery pack via wireless power transmission. During the charging process, the drone will continuously monitor the battery level. When the battery is fully charged, the drone will send a stop charging signal to the charging base station.

[0136] Understandably, in this embodiment, after docking is complete, the drone will pair with the charging base station via Bluetooth and send a charging signal. The charging base station charges the drone's battery pack via wireless power transfer. During charging, the drone continuously monitors the battery level and sends a stop charging signal when the battery is fully charged. The drone uses wireless electromagnetic induction power transfer technology to charge and monitors the battery status in real time. Current and voltage are monitored in real time during charging to ensure safety and efficiency.

[0137] S7. Drone Return Trip: The drone determines the return position with the minimum arrival cost based on the recorded navigation path sequence and Dijkstra's algorithm, and then performs the return trip to continue the line inspection task.

[0138] It is understood that in this embodiment, S7. UAV return trip: The UAV determines the return position with the minimum arrival cost based on the recorded navigation path sequence and Dijkstra's algorithm, and continues to perform the line patrol task, including:

[0139] Use Dijkstra's algorithm to determine the return path with minimum arrival cost, and record D', which represents the shortest path length from the endpoint X to node j;

[0140] Compare array D' with the minimum arrival cost of array D, select the shortest path corresponding to the smaller minimum arrival cost array to perform the return trip, and continue the line patrol task.

[0141] During the inspection process, the drone achieves a complete automated inspection and charging process by monitoring battery voltage in real time, performing precise navigation and docking, wireless power transfer charging, and route planning for return. The combination of these functions and technologies not only improves inspection efficiency but also effectively solves the problem of insufficient battery life.

[0142] Example 2

[0143] like Figure 3As shown, this application provides an intelligent inspection system for unmanned aerial vehicles (UAVs) that interfaces with an intelligent management and control platform. It is applied to the intelligent inspection method for UAVs that interfaces with an intelligent management and control platform as described in Embodiment 1, and includes: a low voltage detection module 11, a UAV docking first navigation module 12, a UAV docking second navigation module 13, a UAV docking third navigation module 14, a UAV docking module 15, a UAV charging monitoring module 16, and a UAV return module 17.

[0144] It is understood that in this embodiment, the low voltage detection module 11 is used to monitor the battery voltage in real time during the inspection process of the UAV, and to send a docking signal when the battery voltage is lower than a set voltage threshold.

[0145] It is understood that in this embodiment, the UAV docks with the first navigation module 12, which is used by the UAV navigation system to determine the charging base station with the minimum arrival cost as the target charging base station based on the docking signal and the Dijkstra algorithm, and at the same time activate the first navigation module to guide the UAV to the vicinity of the target charging base station.

[0146] It is understood that in this embodiment, the drone is connected to the second navigation module 13, which is used to guide the drone to the top of the target charging base station after the drone reaches a first preset range away from the target charging base station.

[0147] It is understood that in this embodiment, the drone is connected to the third navigation module 14, which is used to guide the drone to the target charging location of the charging base station after the drone reaches the second preset range above the target charging base station.

[0148] It is understood that in this embodiment, the drone docking module 15 is used to complete the docking with the charging base station by utilizing the docking module set on the drone.

[0149] Understandably, in this embodiment, the drone charging monitoring module 16 is used to perform Bluetooth pairing between the drone and the charging base station after docking is completed. After successful Bluetooth pairing, the drone will send a charging signal to the charging base station, and the charging base station will charge the drone battery pack via wireless power transmission. During the charging process, the drone will continuously monitor the battery level. When the battery is fully charged, the drone will send a stop charging signal to the charging base station.

[0150] It is understood that in this embodiment, the UAV return module 17 is used for the UAV to determine the return position with the minimum arrival cost based on the recorded navigation path sequence and the Dijkstra algorithm, and to continue performing the line inspection task.

[0151] This application provides a method and system for intelligent inspection of unmanned aerial vehicles (UAVs) that interfaces with an intelligent management and control platform. It monitors battery voltage in real time and sends a docking signal. The Dijkstra algorithm determines the charging base station with the lowest arrival cost as the target charging base station. A multi-level navigation module guides the UAV to the target charging location at the target charging base station. After docking with the charging base station and charging, when the battery is fully charged, the UAV uses the recorded navigation path sequence combined with the Dijkstra algorithm to determine the return location with the lowest arrival cost and performs the return trip to continue the inspection task. Through a multi-level positioning strategy, it can accurately and automatically locate the charging platform for charging, achieving all-weather unmanned independent operation. The use of the Dijkstra algorithm to determine the charging base station and return location with the lowest arrival cost saves energy. A constructed multimodal neural network image vision navigation module processes multimodal input data and outputs motor control parameters to achieve precise positioning and smooth landing.

[0152] Figure 4 This is an electronic device provided in one embodiment of this application. For example... Figure 4 As shown, the electronic device includes at least the following components: processor 101 and memory 100, communication interface 103, and bus 102.

[0153] In this embodiment, the memory 100 is used to store executable instructions of the processor 101, which, when configured to execute instructions, implements... Figure 3 The image shows a device module for intelligent drone inspection that interfaces with an intelligent management and control platform.

[0154] In embodiments of this application, a computer-readable storage medium includes instructions that instruct a device to perform the method as described in the first aspect. For example, the instructions instruct the device to perform... Figure 1 The method is shown in the process steps.

[0155] In one embodiment of this application, the program operating in the electronic device may be a program that controls a central processing unit (CPU) or similar device to achieve the functions of the above-described embodiments of the present invention (a program that enables the computer to function). The information processed by these devices is then temporarily stored in random access memory (RAM) during processing, and subsequently stored in various ROMs such as read-only memory (FlashROM) or hard disk drives (HDDs), and read, corrected, and written by the CPU as needed.

[0156] It should be noted that a portion of the electronic device described in the above embodiments can also be implemented using a computer. In this case, the program for implementing the control function can be recorded on a computer-readable recording medium, and the program recorded on the recording medium can be read into the computer and executed.

[0157] It should be noted that the term "computer" as used here refers to a computer built into an electronic device, employing hardware including an operating system and peripheral devices. Furthermore, "computer-readable recording media" refers to removable media such as floppy disks, magneto-optical disks, ROMs, and CD-ROMs, as well as storage devices such as hard drives built into a computer.

[0158] Furthermore, a "computer-readable recording medium" can include: a medium that dynamically stores a program for a short period of time, such as a communication line used when transmitting a program via a network such as the Internet or a communication line such as a telephone line; or a medium that stores a program for a fixed period of time, such as volatile memory inside a computer that serves as a server or client in this case. In addition, the aforementioned program can be a program used to implement the above-mentioned functions, or it can be a program that can implement the above-mentioned functions by combining with programs already recorded in the computer.

[0159] Furthermore, the electronic device in the above embodiments can also be implemented as an assembly (device group) composed of multiple devices. Each device constituting the device group can possess some or all of the functions or functional blocks of the electronic device in the above embodiments. As a device group, it is sufficient to have all the functions or functional blocks of the electronic device.

[0160] Those skilled in the art should recognize that the above embodiments are only used to illustrate this application and are not intended to limit this application. Any appropriate changes and variations made to the above embodiments within the essential spirit and scope of this application fall within the scope of protection claimed in this application.

Claims

1. A method for intelligent inspection of unmanned aerial vehicles (UAVs) that interfaces with an intelligent management and control platform, characterized in that, The method includes: S1. Low voltage detection: The UAV monitors the battery voltage in real time during the inspection process. When the battery voltage is lower than the set voltage threshold, it sends a docking signal. S2. Drone docking with first navigation: Based on the docking signal, the drone navigation system uses the Dijkstra algorithm to determine the charging base station with the minimum arrival cost as the target charging base station, and simultaneously activates the first navigation module to guide the drone to the vicinity of the target charging base station; S3. Drone docking with second navigation: When the drone reaches a first preset range from the target charging base station, the drone navigation system activates the second navigation module to guide the drone to the top of the target charging base station; S4. Drone docking with third navigation: When the drone reaches the second preset range above the target charging base station, the drone navigation system activates the third navigation module to guide the drone to the target charging location of the charging base station; S5. Drone docking: Using the docking module installed on the drone to complete the docking with the charging base station; S6. Drone charging monitoring: After docking, the drone will pair with the charging base station via Bluetooth. Once Bluetooth pairing is successful, the drone will send a charging signal to the charging base station, which will then charge the drone's battery pack via wireless power transmission. During the charging process, the drone will continuously monitor the battery level. When the battery is fully charged, the drone will send a stop charging signal to the charging base station. S7. Drone return trip: The drone determines the return position with the minimum arrival cost based on the recorded navigation path sequence and Dijkstra's algorithm, and then returns to continue the line inspection task. S2. UAV docking with first navigation: Based on the docking signal, the UAV navigation system uses the Dijkstra algorithm to determine the charging base station with the minimum arrival cost as the target charging base station, and simultaneously activates the first navigation module to guide the UAV to the vicinity of the target charging base station, including: S2.1, Initialization: Set the distance to the starting point to 0, set the distance to all other nodes to infinity, and create a set U of unvisited nodes containing all nodes; S2.2, Select the node with the smallest distance: Select the node u that is closest to the starting point from the unvisited node set U, and move node u from the unvisited set U to the visited set S; S2.3, Update the distance of adjacent nodes: Traverse all adjacent nodes v of node u, calculate the distance to these adjacent nodes through node u; if the distance to adjacent node v through node u is less than the distance recorded in the current record, update the distance of v. After updating, add these adjacent nodes back to the unvisited node set U; S2.4, Repeat steps S2.2 and S2.3: Repeatedly select the node with the minimum distance and update the distance of its adjacent nodes until the set of unvisited nodes U becomes empty, or all nodes have been processed; S2.5, Output: The final distance array D, where d[i] represents the shortest path length from the starting point to node i, and the predecessor node is recorded to reconstruct the specific shortest path; The node set includes charging stations and key points along the path, and the edge weights are defined by a cost function, the formula of which is: ； ； ； Where d is the total flight distance, e_base is the base energy consumption per unit distance, w_factor is the weather correction factor, a_factor is the altitude correction factor, e_hover is the energy consumption per unit hovering time, t_hover is the expected hovering waiting time, E is the energy cost, T is the mission delay penalty, P is the priority cost, and α, β, γ are the corresponding weighting coefficients. Dijkstra's algorithm is used to optimize route planning, ensuring the shortest and safest flight path. S2.6, the UAV navigation system determines the priority of the navigation module based on the detection distance, and the priority includes a first priority, a second priority, and a third priority; S2.7, when the priority is the first priority, the first navigation module is matched; S2.8, Activate the first navigation module to guide the drone to the vicinity of the target charging base station, wherein the first navigation module is GPS.

2. The intelligent inspection method for unmanned aerial vehicles (UAVs) that interfaces with an intelligent management and control platform according to claim 1, characterized in that, S1. Low Voltage Detection: During the inspection process, the UAV monitors the battery voltage in real time. When the battery voltage is lower than a set voltage threshold, it sends a docking signal, including: The battery load voltage is acquired in real time using high-frequency sampling. Use hardware filtering circuits combined with software sliding window algorithms to eliminate voltage fluctuation interference; A voltage-power mapping table is established using a dynamic threshold strategy, and early warning methods are established based on the mapping table, including: Level 1 warning: triggering a status prompt; Level 2 warning: forcibly initiating a return-to-base procedure; and emergency protection: immediately executing a landing on the spot. The intelligent decision-making module assesses whether charging or returning to base is necessary based on the warning method, estimated remaining battery power, terrain complexity of the return route, backup power status, and mission criticality level. When it is determined that charging is needed, a docking signal is sent.

3. The intelligent inspection method for unmanned aerial vehicles (UAVs) that interfaces with an intelligent management and control platform according to claim 2, characterized in that, S3. UAV docking with second navigation: When the UAV reaches a first preset range from the target charging base station, the UAV navigation system activates the second navigation module to guide the UAV to above the target charging base station, including: Determine whether the first preset range meets the detection distance corresponding to the second priority. When the conditions are met, match the second navigation module; The drone navigation system activates a second navigation module to guide the drone to a preset position above the target charging base station; wherein, the second navigation module is a GPS and ultrasonic combined navigation module.

4. The intelligent inspection method for unmanned aerial vehicles (UAVs) that interfaces with an intelligent management and control platform according to claim 3, characterized in that, S4. Drone docking with third navigation: When the drone reaches a second preset range above the target charging base station, the drone navigation system activates the third navigation module to guide the drone to the target charging location of the charging base station, including: Determine whether the second preset range meets the detection distance corresponding to the third priority; When the conditions are met, the third navigation module is matched; The drone navigation system activates a third navigation module to guide the drone to the target charging location at the charging base station; wherein, the third navigation module is an image visual navigation module; The image visual navigation module is a multimodal neural network architecture. It processes multimodal input data and outputs motor control parameters through the multimodal neural network architecture. Based on the control parameters, it controls the motor to achieve accurate positioning and smooth landing. The second preset range is smaller than the first preset range.

5. The intelligent inspection method for unmanned aerial vehicles (UAVs) that interfaces with an intelligent management and control platform, as described in claim 4, is characterized in that... The process of processing multimodal input data and outputting motor control parameters using a multimodal neural network architecture includes: A multimodal neural network architecture is constructed, which includes an input layer, a modality-specific encoder, and a multimodal fusion module; The drone's data acquisition module collects visual image data, as well as the drone's attitude angles, altitude, and position information. The visual image data is segmented using a multimodal neural network architecture to obtain the outer contour of the target charging platform. The charging location area is further identified, and the relative position is calculated by combining altitude and location information. The attitude angle of the drone is then adjusted, and motor control parameters are output.

6. The intelligent inspection method for unmanned aerial vehicles (UAVs) that interfaces with an intelligent management and control platform according to claim 5, characterized in that, S7. UAV Return Trip: The UAV determines the return position with minimum arrival cost based on the recorded navigation path sequence and Dijkstra's algorithm, and continues to perform the line-following task, including: Use Dijkstra's algorithm to determine the return path with minimum arrival cost and record it. , represents the shortest path length from endpoint X to node j; Comparing arrays Based on the minimum arrival cost consumed by array D, select the shortest path corresponding to the smaller minimum arrival cost array to perform the return trip and continue the line patrol task.

7. A drone intelligent inspection system interfaced with an intelligent management and control platform, applied to the drone intelligent inspection method interfaced with an intelligent management and control platform as described in any one of claims 1 to 6, characterized in that, include: The low voltage detection module is used by the UAV to monitor the battery voltage in real time during the inspection process. When the battery voltage is lower than the set voltage threshold, a docking signal is sent. The drone docks with the first navigation module, which is used by the drone navigation system to determine the charging base station with the minimum arrival cost as the target charging base station based on the docking signal and the Dijkstra algorithm. At the same time, the first navigation module is activated to guide the drone to the vicinity of the target charging base station. The drone is connected to a second navigation module, which is used to guide the drone to the top of the target charging base station after the drone reaches a first preset range away from the target charging base station. The drone docks with a third navigation module, which is used to guide the drone to the target charging location of the charging base station after the drone reaches a second preset range above the target charging base station. The drone docking module is used to dock with the charging base station using the docking module installed on the drone. The drone charging monitoring module is used to pair the drone with the charging base station via Bluetooth after docking is completed. Once Bluetooth pairing is successful, the drone will send a charging signal to the charging base station, which will then charge the drone's battery pack via wireless power transmission. During the charging process, the drone will continuously monitor the battery level. When the battery is fully charged, the drone will send a stop charging signal to the charging base station. The drone return module is used by the drone to determine the return position with the minimum arrival cost based on the recorded navigation path sequence and Dijkstra's algorithm, and then continue to perform the line inspection task.

8. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to implement the intelligent inspection method for unmanned aerial vehicles (UAVs) that interfaces with an intelligent management and control platform as described in any one of claims 1 to 6 when executing the instructions.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program that instructs the device to perform the unmanned aerial vehicle (UAV) intelligent inspection method that interfaces with an intelligent management and control platform as described in any one of claims 1 to 6.

Images