On-orbit movement control system for air mobile charging equipment

Abstract

The invention discloses an on-orbit mobile control system for air mobile charging equipment, which relates to the technical field of intelligent charging and comprises a state sensing module, a platform management module, a control center module, a mobile operation module, a wireless communication module and a fault detection and diagnosis module, charging pack state information is monitored in real time, user information registration, charging parameter setting and remote charging state checking are carried out, a cloud server is adopted to carry out data processing, decision making and instruction generation, on-orbit movement operation of the air mobile charging equipment is carried out based on a movement control instruction, and charging pack work abnormity detection and abnormity response are carried out; the problems that an existing shared charging pile is insufficient in number of charging bags, and air mobile charging equipment is complex in structure and high in fault cost are solved, and on-orbit intelligent control and efficient charging service of the air mobile charging equipment can be achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent charging technology, and in particular to an on-orbit mobile control system for an aerial mobile charging device. Background Art

[0002] With the development of new energy vehicles, the proportion of new energy vehicles is getting higher and higher, and the demand for charging piles is getting stronger and stronger, but the number of fuel vehicles still accounts for the majority. At present, one new energy parking space is equipped with one charging pile, but it often happens that new energy parking spaces are occupied by fuel vehicles, resulting in charging piles becoming a kind of decoration or low utilization rate. In response to this phenomenon, the existing technology uses shared charging piles to flexibly allocate according to user needs, arrange a guide rail above the new energy parking space, and install a movable charging pack on a track to realize charging. When the user parks the car, just scan the QR code corresponding to this parking space, and the charging pack will automatically move to the corresponding parking space. This design can greatly improve the utilization rate of charging piles and provide users with more convenient charging services.

[0003] However, the existing shared charging piles can only hang one charging pack on one rail. For the increasing number of new energy vehicles, the number of charging packs is far from enough. In addition, the existing aerial mobile charging equipment installs multiple sensors on the track to ensure that the parking spaces and obstacles can be accurately identified during the movement control of the charging pack. The components and links involved are complex. Failure in any link may cause the entire system to fail to operate normally, and the failure cost is high.

[0004] Therefore, a mobile control system for an aerial mobile charging device on track is needed to solve the above problems. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention discloses an on-orbit mobile control system for an aerial mobile charging device. The charging pack moves to a designated position for charging through a track mechanical structure according to control instructions, and returns to a standby state after charging is completed, thereby reducing failure costs and having a high degree of automation and intelligence.

[0006] The present invention adopts the following technical solutions:

[0007] An on-orbit mobile control system for an aerial mobile charging device, comprising:

[0008] A state sensing module, wherein the state sensing module monitors the charging package state information in real time through a sensor network, and transmits the acquired charging package state information to a cloud server for processing, wherein the charging package state information includes at least location information, power information, and working state information;

[0009] A platform management module, which performs user information registration, charging parameter setting, and remote charging status checking based on a mobile phone APP or web platform, and transmits user registration information and charging parameters set by the user to a cloud server for processing;

[0010] A control center module, which uses a cloud server for data processing, decision making and instruction generation. The cloud server makes on-orbit movement decisions of the aerial mobile charging device based on the location information and power information of the charging package and the charging parameters set by the user, and generates movement control instructions based on a multi-objective path control model;

[0011] A mobile operation module, wherein the mobile operation module performs on-track mobile operation of the aerial mobile charging device based on the mobile control instruction, wherein the aerial mobile charging device comprises a plurality of charging packs, a main track and a track-changing mechanism, wherein the charging pack is an independent charging unit, and the charging pack is moved and docked to a designated vehicle for charging via the main track and the track-changing mechanism, wherein the main track is used to support the movement of the charging pack, and the track-changing mechanism is used for temporary parking and movement of the charging pack, and the track-changing mechanism adopts a bilateral locking mechanism and a unilateral locking mechanism to realize the switching of the charging pack between the main track and the temporary parking track;

[0012] Wireless communication module, the user triggers a communication request by scanning the QR code corresponding to the parking space. The wireless communication module uses the wireless communication network to transmit the charging package status information to the control center module, and transmits the control instructions generated by the control center module to the aerial mobile charging device.

[0013] Furthermore, the multi-objective path control model adopts the combination of the A-star algorithm and the ant colony optimization algorithm to realize the optimal mobile control of the charging package, and introduces the pheromone compensation factor to adjust the priority of path selection. The working method of the multi-objective path control model includes the following steps:

[0014] Setting initial parameters of the A-star algorithm and the ant colony optimization algorithm, wherein the initial parameters at least include a heuristic function weight, a pheromone initial value, a pheromone evaporation rate, and an ant colony number;

[0015] A mobile path graph model of the aerial mobile charging device is constructed according to the charging package status information, the charging parameters set by the user, and the layout of the main track and the track change mechanism. The mobile path graph model consists of nodes and edges. The nodes represent charging points and temporary parking points, and the edges represent the moving tracks of the charging package.

[0016] The A-star algorithm is used for preliminary path search to obtain a set of paths from the current charging package location to the target charging location, and the priority of the node is evaluated through the heuristic function;

[0017] The ant colony optimization algorithm is used for path optimization. The obtained path set is used as the initial search space of the ant colony algorithm. The starting point of the ant colony is set as the charging package location, and the target point is set as the charging station location. The pheromone concentration of each path in the path set is set as the pheromone initial value. The pheromone compensation factor adjusts the distribution of pheromones according to the distance, charging efficiency and congestion of the path, and the optimal path is obtained through iterative calculation.

[0018] According to the real-time status information of the charging package and the charging parameters set by the user, the optimal path is dynamically updated and new mobile control instructions are generated.

[0019] Furthermore, the pheromone compensation factor adjusts the distribution of pheromones according to the distance, charging efficiency and congestion of the path, and the adjustment formula is:

[0020]

[0021] In formula (1), ρ represents the evaporation rate of pheromone, which is used to simulate the change of pheromone over time, τ ij represents the pheromone strength from node i to node j, Δτ ij represents the total amount of pheromone from node i to node j in the iteration, represents the pheromone residue of ant k moving from node i to node j, m represents the number of ant colonies, k represents the ordinal number of ants in the ant colony, i and j represent the ordinal numbers of nodes in the mobile path graph model, and μ represents the pheromone compensation factor. After multiple iterations, when the pheromone intensity of the path remains stable or reaches the preset maximum number of iterations, the iteration is stopped to obtain the optimal path.

[0022] Furthermore, the charging pack has a built-in track travel motor, a controller, a communication interface, a position sensor and a charging device.

[0023] Furthermore, the track-changing mechanism at least includes a first track, a second track, a third track, an unlocking block, a track-changing motor, a gear set and a screw transmission mechanism, and the screw transmission mechanism includes a screw and a screw nut.

[0024] Furthermore, the aerial mobile charging device performs on-orbit mobile operation including the following steps:

[0025] In the initial state, the first track is connected to the main track, and the first track is connected to the third track through a bilateral locking mechanism. The charging pack moves freely on the main track and waits for charging instructions;

[0026] The charging pack moves. After the user scans the parking space QR code, the control center module sends a control command. After receiving the charging command, the charging pack moves to the designated position on the first track through the track travel motor. After the charging pack reaches the designated position, the charging pack stops and identifies the position sensor signal.

[0027] Unlocking and track changing operation: After the charging pack reaches the designated position, the unlocking block works, the first track and the third track change from double-sided locking to single-sided locking, the track changing motor starts, and the power is transmitted to the lead screw nut through the gear set to drive the charging pack to move along the lead screw to the set position;

[0028] The charging pack works. After the charging pack moves to the set position, the track change motor stops working, the first track and the third track remain unilaterally locked, the charging pack performs charging operations at the set position, and the second track serves as a spare track for other charging packs to use;

[0029] Charging completion and reset. After charging is completed, the charging pack is moved back to the position connected to the main track through the track changing motor, and the first track and the third track are bilaterally locked again to restore the initial state.

[0030] Furthermore, the wireless communication network adopts the TCP protocol as a control protocol for communication network link congestion, and adopts the SSL / TLS encryption transmission protocol to achieve secure data transmission.

[0031] Furthermore, it also includes a fault detection and diagnosis module, which uses a deep learning network model to extract features and train models on the working status information of the charging pack to determine whether there is a fault or abnormal situation. When the monitored data is abnormal or deviates from the normal range, the fault warning mechanism is immediately triggered, and a warning signal is sent to the control center module. The fault type, location and severity are identified by comparing and analyzing historical data and current data. When a severe fault is identified, the charging pack emergency stop response mechanism is automatically started, and all data and information of the fault detection, diagnosis, maintenance and recovery processes are recorded.

[0032] The beneficial effects of the present invention are:

[0033] 1. The present invention significantly increases the number of vehicles that can be charged at the same time by designing multiple charging packs, main tracks and track-changing mechanisms. Each charging pack is an independent charging unit and can be flexibly moved to the vehicle that needs to be charged through the main track and the track-changing mechanism, thereby solving the problem of insufficient number of charging packs. The double-sided locking and unilateral locking mechanisms improve the reliability and safety of switching the charging pack between the main track and the temporary parking track, thereby reducing the risk of system shutdown due to mechanical failure.

[0034] 2. The present invention integrates a state perception module and uses a sensor network to monitor the status information of the charging pack in real time, including location, power, and working status, which helps to detect potential faults in a timely manner and take corresponding preventive measures. At the same time, the data processing and decision-making capabilities of the cloud server can optimize the movement path and charging sequence of the charging pack based on real-time data, reducing faults caused by incorrect operations or improper scheduling.

[0035] 3. The present invention uses the control center module to process data, make decisions and generate instructions, and uses the multi-objective path control model to generate mobile control instructions, making the mobile control of the charging pack more intelligent and efficient. This helps to reduce manual intervention and erroneous operations, and improve the overall operating efficiency and stability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a schematic diagram of the overall system architecture of the present invention;

[0037] Figure 2 Schematic diagram of the workflow of the multi-objective path control model in the present invention;

[0038] Figure 3 A schematic diagram of the workflow of the aerial mobile charging device in the present invention for performing on-orbit mobile operation;

[0039] Figure 4 It is a schematic diagram of the architecture of the aerial mobile charging device in the present invention;

[0040] In the figure: 1, main track; 2, charging pack; 3, track changing mechanism; 301, first track; 302, second track; 303, third track. DETAILED DESCRIPTION

[0041] The following will be combined with the attached embodiment of the present invention Figure 1 To Attachment Figure 4 , the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] The embodiment of the present invention discloses an on-orbit mobile control system of an aerial mobile charging device, which is composed of six modules: a state perception module, a platform management module, a control center module, a mobile operation module, a wireless communication module, and a fault detection and diagnosis module.

[0043] The status perception module monitors the status information of the charging pack in real time through the sensor network, including location information, power information, working status information, etc. The sensor network covers the entire aerial mobile charging system, collects data in real time and transmits it to the cloud server for processing via wired or wireless means.

[0044] The platform management module provides functions such as user information registration, charging parameter setting, and remote charging status viewing based on the mobile phone APP or web platform. Users register an account through the APP or web page, set charging parameters (such as charging time, power demand, etc.), and view the charging status in real time. The platform transmits user information and charging parameters to the cloud server for processing.

[0045] The control center module uses a cloud server for data processing, decision making, and command generation. The cloud server receives data from the state perception module and the platform management module, and makes on-orbit movement decisions for the aerial mobile charging device based on the location and power information of the charging pack and the charging parameters set by the user. The multi-objective path control model is used to generate the optimal mobile control instructions to ensure that the charging pack can be efficiently and accurately docked to the designated vehicle for charging.

[0046] The mobile operation module performs on-orbit mobile operations of the aerial mobile charging device based on the mobile control instructions. The aerial mobile charging device includes multiple charging packs, a main track, and a track-changing mechanism. The charging pack, as an independent charging unit, achieves mobile docking through the main track and the track-changing mechanism. The main track supports the movement of the charging pack, and the track-changing mechanism uses bilateral locking and unilateral locking mechanisms to achieve the switching of the charging pack between the main track and the temporary docking track. The mobile operation module receives control instructions from the control center module and drives the charging pack and the track-changing mechanism to complete the mobile docking task.

[0047] The wireless communication module realizes wireless communication between the user and the control system, including triggering communication requests, transmitting charging package status information, and receiving control instructions. The user triggers the communication request by scanning the QR code corresponding to the parking space. The wireless communication module uses the wireless communication network (such as Wi-Fi, 4G / 5G, etc.) to transmit the charging package status information to the control center module, and transmits the control instructions generated by the control center module to the aerial mobile charging device.

[0048] The fault detection and diagnosis module uses a deep learning network model to extract features and train models of the working status information of the charging pack, determine whether there is a fault or abnormality, and take corresponding countermeasures. This module receives data from the state perception module in real time and uses a deep learning algorithm to process and analyze the data. When the data is detected to be abnormal or deviates from the normal range, the fault warning mechanism is immediately triggered and a warning signal is sent to the control center module. The type, location and severity of the fault are identified by comparing and analyzing historical data and current data. When a severe fault is identified, the emergency stop response mechanism is automatically started to protect the safety of equipment and personnel, and all data and information of the fault detection, diagnosis, maintenance and recovery process are recorded for subsequent analysis.

[0049] Specific implementation steps: Start each module and perform self-check to ensure the normal operation of the system. Users register an account and set charging parameters through the APP or web platform. The status perception module collects the status information of the charging package in real time and transmits it to the cloud server. The cloud server processes the received data and generates mobile control instructions. The mobile operation module receives the control instructions and executes the mobile docking task of the charging package. The fault detection and diagnosis module monitors the status of the charging package in real time and performs fault warning and diagnosis. Users view the charging status and fault information in real time through the APP or web platform.

[0050] Through the implementation of the above steps, the on-orbit mobile control system of the aerial mobile charging equipment can achieve efficient and accurate charging services, and has powerful fault detection and diagnosis capabilities, ensuring the stable operation of the system and a good user experience.

[0051] The multi-objective path control model uses the A-star algorithm and the ant colony optimization algorithm to achieve optimal mobile control of the charging package, and introduces a pheromone compensation factor to adjust the priority of path selection. The following are the specific implementation steps of the multi-objective path control model:

[0052] S1. Set the initial parameters of the A-star algorithm and the ant colony optimization algorithm;

[0053] A-star algorithm parameters: including the weight of the heuristic function, which is used to evaluate the priority of the node. Common heuristic functions can be Euclidean distance or Manhattan distance.

[0054] Ant Colony Optimization Algorithm Parameters: Pheromone Initial Value: The initial pheromone concentration on all paths is set to the same value so that the algorithm has a fair chance to search at the beginning. Pheromone Evaporation Rate: Controls the rate at which pheromones decrease over time, which helps to avoid infinite accumulation of pheromones on certain paths.

[0055] Number of ant colonies: The number of ants affects the search breadth and depth of the algorithm and needs to be adjusted according to the specific problem.

[0056] S2, constructing a mobile path diagram model of the aerial mobile charging device;

[0057] According to the status information of the charging package (such as location and power), the charging parameters set by the user (such as charging time and power requirement), and the layout of the main track and the track change mechanism, a mobile path graph model of the aerial mobile charging device is constructed. The model consists of nodes and edges. Nodes represent key locations such as charging points and temporary stops, and edges represent the tracks where the charging package may move.

[0058] S3, obtaining a set of paths from the current charging package location to the target charging location;

[0059] The A-star algorithm is used to perform a preliminary path search, starting from the current charging package location, evaluating the priority of the node through the heuristic function, and gradually expanding to the target charging location. The selection of the heuristic function should take into account factors such as the movement cost of the charging package (such as time and energy consumption) and the feasibility of the path (such as track restrictions and obstacles).

[0060] S4, perform path optimization to obtain the best path;

[0061] The path set obtained by the A-star algorithm is used as the initial search space of the ant colony algorithm to reduce the blindness of the search. Set the starting point of the ant colony to the current location of the charging package, and the target point to the location of the charging station. The pheromone concentration of each path in the initial path set is the initial value of the pheromone. Introduce the pheromone compensation factor to dynamically adjust the distribution of pheromones according to the distance, charging efficiency and congestion of the path. For example, shorter paths, paths with high charging efficiency or paths with low congestion can obtain higher pheromone compensation. Through iterative calculation, ants select paths based on pheromone concentration and heuristic information, and release pheromones on the paths they pass through, and the pheromones evaporate over time. Finally, through multiple rounds of iterations, the ant colony algorithm can find one or more optimal paths as the movement plan for the charging package.

[0062] S5, dynamically update the best path and generate new movement control instructions;

[0063] The optimal path is dynamically updated based on the real-time status information of the charging pack and the charging parameters set by the user. When congestion on the path is detected, the charging pack is low on power, or the user changes the charging parameters, steps S3 and S4 are re-executed to search and optimize the path. A new mobile control instruction is generated based on the latest optimal path and sent to the mobile operation module for execution.

[0064] Through the implementation of the above steps, the multi-objective path control model can comprehensively consider multiple factors and provide the optimal or near-optimal mobility control solution for the charging package to ensure the efficiency and accuracy of the charging service.

[0065] In S4, the pheromone compensation factor adjusts the distribution of pheromones according to the distance, charging efficiency and congestion of the path. The adjustment formula is:

[0066]

[0067] In formula (1), ρ represents the evaporation rate of pheromone, which is used to simulate the change of pheromone over time, τ ij represents the pheromone strength from node i to node j, Δτ ij represents the total amount of pheromone from node i to node j in the iteration, represents the pheromone residue of ant k moving from node i to node j, m represents the number of ant colonies, k represents the ordinal number of ants in the ant colony, i and j represent the ordinal numbers of nodes in the mobile path graph model, and μ represents the pheromone compensation factor. After multiple iterations, when the pheromone intensity of the path remains stable or reaches the preset maximum number of iterations, the iteration is stopped to obtain the optimal path.

[0068] The laboratory configuration uses a Core i9 64+128G memory computer, and the simulation environment is established using simulation software. The on-site experimental environment is set up, the simulation data accuracy is 95%, and the algorithm operation error does not exceed 2.5%. The multi-objective path control model (Group A), ant colony optimization algorithm (Group B) and A-star algorithm (Group C) are used for comparative experiments. Five charging packs are set at different positions on the track for charging. The same charging requirements and charging parameters are set for the experiment. The experiment is repeated five times. Before each experiment, the starting position of the charging pack is manually changed. The matching accuracy and time consumption are used to evaluate the effect of the algorithm, which is recorded in Table 1.

[0069] Table 1 Results Statistics

[0070]

[0071] As can be seen from the table, the multi-objective path control model (Group A) has shown excellent results in both matching accuracy and average time consumption. Compared with the A-star algorithm and the ant colony optimization algorithm, the multi-objective path control model has higher matching accuracy, lower average time consumption, and has shown stable performance in multiple experiments.

[0072] The laboratory configuration uses a Core i964+128G memory computer, and the simulation environment is established using simulation software. The on-site experimental environment is set up, the simulation data accuracy is 95%, and the algorithm operation error does not exceed 2.5%. The multi-objective path control model (Group A), ant colony optimization algorithm (Group B) and A-star algorithm (Group C) are used for comparative experiments. Five charging packs are set at different positions on the track for charging. The test is repeated five times. Different charging requirements and charging parameters are manually set before each test for experiment. The matching accuracy and time consumption are used to evaluate the effect of the algorithm, which is recorded in Table 2.

[0073] Table 2 Results Statistics

[0074]

[0075]

[0076] As can be seen from Table 1, the multi-objective path control model (Group A) shows the best performance in both matching accuracy and average time consumption. In particular, in terms of matching accuracy, the multi-objective path control model performs significantly better than the other two algorithms. This shows that under different charging requirements and charging parameters, the multi-objective path control model can perform path planning more accurately and improve the charging efficiency of rail charging equipment.

[0077] Manually set different charging requirements and charging parameters, such as power, charging time, etc.

[0078] The charging pack has built-in track travel motor, controller, communication interface, position sensor and charging device.

[0079] The track-changing mechanism at least comprises a first track, a second track, a third track, an unlocking block, a track-changing motor, a gear set and a screw transmission mechanism, wherein the screw transmission mechanism comprises a screw and a screw nut.

[0080] The on-orbit mobile operation of the aerial mobile charging device includes the following steps:

[0081] Step 1: In the initial state, the first track is connected to the main track, and the first track is connected to the third track through a bilateral locking mechanism. The charging pack moves freely on the main track and waits for charging instructions.

[0082] Step 2: The charging pack moves. After the user scans the parking space QR code, the control center module issues a control command. After receiving the charging command, the charging pack moves to the designated position on the first track through the track travel motor. After the charging pack reaches the designated position, the charging pack stops and identifies the position sensor signal.

[0083] Step 3: Unlock and change track. After the charging pack reaches the designated position, the unlocking block works, and the first track and the third track change from bilateral locking to unilateral locking. The track change motor starts, and transmits power to the lead screw nut through the gear set to drive the charging pack to move along the lead screw to the set position.

[0084] Step 4: The charging pack works. After the charging pack moves to the set position, the track change motor stops working, the first track and the third track remain unilaterally locked, and the charging pack performs charging operations at the set position. At the same time, the second track serves as a spare track for other charging packs to use;

[0085] Step 5, charging completion and reset. After charging is completed, the charging pack is moved back to the position connected to the main track through the track change motor, and the first track and the third track are bilaterally locked again to restore the initial state.

[0086] The wireless communication module selects the appropriate wireless communication network according to the actual application scenario. For example, in areas covered by Wi-Fi, you can choose the Wi-Fi network for communication; in scenarios where remote communication or strong mobility is required, you can choose the 4G / 5G network. After the user triggers a communication request by scanning the QR code corresponding to the parking space, the wireless communication module will automatically connect to the selected wireless communication network. This process may involve steps such as network authentication and authorization to ensure that only legitimate users can access the network. A TCP connection is established between the wireless communication module and the control center module. The TCP protocol establishes a connection through a three-way handshake process to ensure that the data transmission channel between the communicating parties is reliable. At the same time, the TCP protocol also has a congestion control mechanism that can dynamically adjust the data transmission rate according to the network conditions to avoid network congestion.

[0087] The wireless communication module encapsulates the status information of the charging package (such as power, location, fault status, etc.) into a data packet and transmits it to the control center module through a TCP connection. During the transmission process, the SSL / TLS encryption transmission protocol is used to encrypt the data to ensure the security and confidentiality of the data during transmission. The control center module generates corresponding control instructions based on the received charging package status information and sends them to the wireless communication module through a TCP connection. After receiving the control instructions, the wireless communication module forwards them to the aerial mobile charging device through internal logic processing to achieve remote control of the charging device.

[0088] The TCP protocol has an error detection mechanism that can detect and discard erroneous data packets. For lost or damaged data packets, the TCP protocol triggers a retransmission mechanism to ensure data integrity and reliability. When the wireless communication network is interrupted or the signal is unstable, the wireless communication module should have an automatic reconnection mechanism. By regularly detecting the network connection status and trying to reestablish the connection, ensure that the communication between the user and the control system is always smooth.

[0089] The SSL / TLS encryption transmission protocol is used to encrypt data to ensure the security and confidentiality of data transmission. At the same time, the identity and authority of both parties in communication are verified through mechanisms such as digital certificates to prevent unauthorized access and data tampering. The stability and reliability of the wireless communication network are improved by optimizing network configuration, adding redundant equipment and implementing load balancing. At the same time, the wireless communication module is regularly maintained and upgraded to ensure that its performance is always kept in the best condition.

[0090] In summary, in the process of realizing wireless communication between users and control systems, wireless communication modules need to select appropriate modules, configure network parameters, establish TCP connections, encrypt transmission data, and handle errors and communication interruptions. Through the implementation of these measures, it can be ensured that the communication between users and control systems is safe, reliable and efficient.

[0091] The implementation of the fault detection and diagnosis module in the charging pack system mainly relies on the feature extraction, model training and real-time monitoring of the charging pack working status information by the deep learning network model.

[0092] First, it is necessary to collect working status data in real time from various sensors and monitoring systems of the charging pack, including but not limited to key parameters such as current, voltage, temperature, power factor, etc. The collected raw data is cleaned, denoised, and normalized to improve the efficiency and accuracy of subsequent feature extraction and model training.

[0093] Use deep learning network models (such as convolutional neural network CNN, recurrent neural network RNN ​​or its variant LSTM, etc.) to extract features from the preprocessed data. These features should be able to reflect the working status of the charging pack and its potential failure mode. In the feature extraction process, domain knowledge and expert experience can be combined to design a reasonable network structure and parameters to better capture key information.

[0094] Use the annotated historical fault data and normal working data as training sets to train the deep learning model. During the training process, the recognition accuracy and generalization ability of the model can be improved by adjusting model parameters and optimizing algorithms. At the same time, regularization, dropout and other technologies can be introduced to prevent overfitting and ensure the stability of the model in practical applications.

[0095] The trained model is deployed to the charging pack system to monitor the real-time collected working status data in real time. When the monitored data is abnormal or deviates from the normal range, the fault warning mechanism is immediately triggered and a warning signal is sent to the control center module. The warning signal should include key information such as fault type, location, severity, etc., so that the control center module can respond and process quickly.

[0096] By comparing and analyzing historical data and current data, the classification and regression capabilities of the deep learning model are used to identify the type, location and severity of the fault. When a high-severity fault is identified, the charging pack emergency stop response mechanism is automatically activated to cut off the power supply and isolate the fault area to prevent the situation from escalating. At the same time, all data and information of the fault detection, diagnosis, maintenance and recovery process are recorded to provide a basis for subsequent analysis and improvement.

[0097] Regularly evaluate and adjust the performance of the deep learning model to adapt to changes in the working status of the charging pack system and the emergence of new failure modes. Combined with user feedback and actual on-site conditions, the functions and performance of the fault detection and diagnosis module are continuously optimized to improve the reliability and stability of the system.

[0098] In summary, the implementation of the fault detection and diagnosis module in the charging pack system requires the comprehensive use of technical means and methods in multiple links such as data collection, preprocessing, feature extraction, model training, real-time monitoring and fault warning, fault diagnosis and response, and continuous optimization and improvement. Through these measures, comprehensive monitoring and rapid response to the working status of the charging pack can be achieved to ensure the safe and stable operation of the system.

[0099] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A mobile control system for an aerial mobile charging device on track, characterized in that: include: A state sensing module, wherein the state sensing module monitors the charging package state information in real time through a sensor network, and transmits the acquired charging package state information to a cloud server for processing, wherein the charging package state information includes at least location information, power information, and working state information; A platform management module, which performs user information registration, charging parameter setting, and remote charging status checking based on a mobile phone APP or web platform, and transmits user registration information and charging parameters set by the user to a cloud server for processing; A control center module, which uses a cloud server for data processing, decision making and instruction generation. The cloud server makes on-orbit movement decisions of the aerial mobile charging device based on the location information and power information of the charging package and the charging parameters set by the user, and generates movement control instructions based on a multi-objective path control model; A mobile operation module, wherein the mobile operation module performs on-track mobile operation of the aerial mobile charging device based on the mobile control instruction, wherein the aerial mobile charging device comprises a plurality of charging packs, a main track and a track-changing mechanism, wherein the charging pack is an independent charging unit, and the charging pack is moved and docked to a designated vehicle for charging via the main track and the track-changing mechanism, wherein the main track is used to support the movement of the charging pack, and the track-changing mechanism is used for temporary parking and movement of the charging pack, and the track-changing mechanism adopts a bilateral locking mechanism and a unilateral locking mechanism to realize the switching of the charging pack between the main track and the temporary parking track; Wireless communication module, the user triggers a communication request by scanning the QR code corresponding to the parking space. The wireless communication module uses the wireless communication network to transmit the charging package status information to the control center module, and transmits the control instructions generated by the control center module to the aerial mobile charging device.

2. According to claim 1, a mobile control system for an aerial mobile charging device on track is characterized in that: The multi-objective path control model adopts the combination of the A-star algorithm and the ant colony optimization algorithm to realize the optimal mobile control of the charging package, and introduces the pheromone compensation factor to adjust the priority of path selection. The working method of the multi-objective path control model includes the following steps: Setting initial parameters of the A-star algorithm and the ant colony optimization algorithm, wherein the initial parameters at least include a heuristic function weight, a pheromone initial value, a pheromone evaporation rate, and an ant colony number; A mobile path graph model of the aerial mobile charging device is constructed according to the charging package status information, the charging parameters set by the user, and the layout of the main track and the track change mechanism. The mobile path graph model consists of nodes and edges. The nodes represent charging points and temporary parking points, and the edges represent the moving tracks of the charging package. The A-star algorithm is used for preliminary path search to obtain a set of paths from the current charging package location to the target charging location, and the priority of the node is evaluated through the heuristic function; The ant colony optimization algorithm is used for path optimization. The obtained path set is used as the initial search space of the ant colony algorithm. The starting point of the ant colony is set as the charging package location, and the target point is set as the charging station location. The pheromone concentration of each path in the path set is set as the pheromone initial value. The pheromone compensation factor adjusts the distribution of pheromones according to the distance, charging efficiency and congestion of the path, and the optimal path is obtained through iterative calculation. According to the real-time status information of the charging package and the charging parameters set by the user, the optimal path is dynamically updated and new mobile control instructions are generated.

3. The on-orbit mobile control system of an aerial mobile charging device according to claim 2, characterized in that: The pheromone compensation factor adjusts the distribution of pheromones according to the distance, charging efficiency and congestion of the path. The adjustment formula is: In formula (1), ρ represents the evaporation rate of pheromone, which is used to simulate the change of pheromone over time, τ ij represents the pheromone strength from node i to node j, Δτ ij represents the total amount of pheromone from node i to node j in the iteration, represents the pheromone residue of ant k moving from node i to node j, m represents the number of ant colonies, k represents the ordinal number of ants in the ant colony, i and j represent the ordinal numbers of nodes in the mobile path graph model, and μ represents the pheromone compensation factor. After multiple iterations, when the pheromone intensity of the path remains stable or reaches the preset maximum number of iterations, the iteration is stopped to obtain the optimal path.

4. The on-orbit mobile control system of an aerial mobile charging device according to claim 1, characterized in that: The charging pack has a built-in track travel motor, a controller, a communication interface, a position sensor and a charging device.

5. The on-orbit mobile control system of an aerial mobile charging device according to claim 4, characterized in that: The track-changing mechanism at least comprises a first track, a second track, a third track, an unlocking block, a track-changing motor, a gear set and a screw transmission mechanism, and the screw transmission mechanism comprises a screw and a screw nut.

6. The on-orbit mobile control system of an aerial mobile charging device according to claim 5, characterized in that: The on-orbit mobile operation of the aerial mobile charging device includes the following steps: In the initial state, the first track is connected to the main track, and the first track is connected to the third track through a bilateral locking mechanism. The charging pack moves freely on the main track and waits for charging instructions; The charging pack moves. After the user scans the parking space QR code, the control center module sends a control command. After receiving the charging command, the charging pack moves to the designated position on the first track through the track travel motor. After the charging pack reaches the designated position, the charging pack stops and identifies the position sensor signal. Unlocking and track changing operation: After the charging pack reaches the designated position, the unlocking block works, the first track and the third track change from double-sided locking to single-sided locking, the track changing motor starts, and the power is transmitted to the lead screw nut through the gear set to drive the charging pack to move along the lead screw to the set position; The charging pack works. After the charging pack moves to the set position, the track change motor stops working, the first track and the third track remain unilaterally locked, the charging pack performs charging operations at the set position, and the second track serves as a spare track for other charging packs to use; Charging completion and reset. After charging is completed, the charging pack is moved back to the position connected to the main track through the track changing motor, and the first track and the third track are re-bilaterally locked to restore the initial state.

7. The on-orbit mobile control system of an aerial mobile charging device according to claim 1, characterized in that: The wireless communication network adopts the TCP protocol as the control protocol for communication network link congestion, and adopts the SSL / TLS encryption transmission protocol to achieve data security transmission.

8. The on-orbit mobile control system of an aerial mobile charging device according to claim 1, characterized in that: It also includes a fault detection and diagnosis module, which uses a deep learning network model to extract features and train models on the working status information of the charging pack to determine whether there is a fault or abnormality. When the monitored data is abnormal or deviates from the normal range, the fault warning mechanism is immediately triggered, and a warning signal is sent to the control center module. The fault type, location and Severity: When a serious fault is detected, the emergency stop response mechanism of the charging pack is automatically activated. And record all fault detection, diagnosis, repair and recovery process data and information.

Images