Intelligent orbital transfer control system of aerial mobile charging equipment

Abstract

The invention discloses an intelligent orbital transfer control system of air mobile charging equipment, and relates to the related technical field of new energy charging equipment, the intelligent orbital transfer control system comprises a main orbit, a plurality of charging packs, an orbital transfer mechanism, a data processing center, a waiting area, a fault early warning system and an energy management module, the orbital transfer mechanism comprises an intelligent control unit and an orbit switching module, the intelligent control unit is used for transferring the charging pack, and the track switching module is used for controlling the charging pack to be transferred from the waiting area to the main track and the process of returning to the waiting area from the main track after charging is completed. According to the invention, a scheduling decision algorithm is adopted, services are provided for most vehicles in the shortest time according to the state of the charging pack, and the intelligent mobile rail transfer charging equipment control system improves the charging efficiency and the equipment utilization rate through efficient charging equipment switching and rail sharing, reduces the idle time and the charging waiting time of the equipment, and improves the charging efficiency and the equipment utilization rate. The problem of low utilization rate is solved, and equipment investment and space occupation can be reduced through implementation of the system.

Description

Technical Field

[0001] The present invention relates to the technical field related to new energy charging equipment, and in particular to an intelligent track change control system for an aerial mobile charging equipment. Background Art

[0002] With the popularity of electric vehicles, the demand for charging facilities is growing. Traditional charging systems are usually fixed and cannot adjust the position or quantity according to actual needs. 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. However, the number of fuel vehicles still accounts for the majority. In order to solve these problems, aerial mobile charging equipment is needed. As the name suggests, aerial mobile charging means that the charging equipment can be moved in the air, which requires the use of hanging rails to move the charging pack in the air along the hanging rails to charge new energy electric vehicles.

[0003] Currently, there is basically one charging pile for each parking space. However, new energy parking spaces are often occupied by fuel vehicles, causing the charging piles to become a decoration with a low utilization rate. Moreover, when the equipment is put into use for a long time, it is prone to malfunctions or hidden dangers, and sudden failures may cause the system to shut down for maintenance.

[0004] Therefore, it is necessary to propose an intelligent trajectory change control system for aerial mobile charging equipment to solve the above problems. Summary of the invention

[0005] 1. Technical issues to be solved

[0006] In view of the shortcomings of the prior art, the present invention provides an intelligent track change control system for an aerial mobile charging device, which solves the problems that one parking space of the existing charging equipment is equipped with one charging pile, the utilization rate is low, and the equipment is prone to failure or hidden dangers after being put into use for a long time, and sudden failures may cause the system to be shut down for maintenance.

[0007] (II) Technical solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0009] An intelligent track change control system for an aerial mobile charging device, the control system comprising:

[0010] The main track is used to support and guide the movement of the charging pack, and has an interface that matches the charging pack, allowing the charging pack to move along the track to a waiting area or a charging position;

[0011] Multiple charging packs, each of which is an independent mobile charging unit equipped with a charging interface and a status information control unit. The status information control unit is used to count the power, temperature, voltage, charging and discharging status and location information of the charging pack and send the information to the data processing center. The charging pack can drive itself and move along the main track to the designated charging position or return from the charging position;

[0012] The track-changing mechanism is installed outside the charging pack and includes an intelligent control unit and a track switching module. The intelligent control unit is used to mobilize the charging pack, and the track switching module is used to control the transfer of the charging pack from the waiting area to the main track, and the process of returning from the main track to the waiting area after charging is completed;

[0013] The data processing center is connected to the status information control unit of each charging pack, responsible for collecting the status information of the charging pack and making scheduling decisions according to the preset algorithm, responsible for collecting the status information of all charging packs, processing the data, making scheduling decisions, and communicating with the intelligent control unit of the track change mechanism to achieve efficient charging pack scheduling;

[0014] The waiting area is installed outside the charging pack and is used to provide charging services for the charging pack;

[0015] Fault warning system, used to detect the status of the charging pack and issue commands in time to ensure stable operation of the equipment, reduce maintenance costs and prevent unexpected failures;

[0016] Energy management module: The energy storage battery in the charging pack stores energy when the grid load is low and releases energy during peak hours to balance the grid load and improve energy utilization efficiency.

[0017] Optionally, a secondary track is provided on the top of the charging pack, and a driving device and an automatic locking mechanism are provided on the secondary track. The driving device is used to drive the secondary track to move on the main track, and the automatic locking mechanism is used to connect or disconnect the secondary track from the main track. A lifting mechanism is provided at the bottom of the charging pack for supporting the falling of the charging pack and lifting the charging pack from the ground so that the secondary track is connected to the main track.

[0018] Optionally, the data processing center includes a central processing unit, memory, and hard disk storage. The central processing unit is responsible for executing deep reinforcement learning algorithms and processing tasks. The memory is used to store running programs and current data to ensure that the data processing center can quickly read and write data. The hard disk storage is used for long-term storage of system data, log information, and historical records.

[0019] Optionally, the deep reinforcement learning algorithm adopts Q learning method, and the mathematical model is as follows:

[0020]

[0021] Where: Q(s,a) is the state-action value of taking action a in state s, p(s′,r|s,a) is the probability of transferring to state s′ and obtaining reward r after taking action a in state s, r is the immediate reward, γ is the discount factor used to weigh the importance of immediate rewards and future rewards, maxa′Q(s′,a′) is the maximum Q value of all possible actions in the new state s′, Q value (i.e., state-action value function) is used to evaluate the value of taking an action in a specific state, and Q value represents the expected value of the total reward that the agent can obtain after taking a specific action in a given state until the final state;

[0022] For any state s and any action a, its Q value is equal to the expectation over all possible successor states s′ and rewards r. This expectation is weighted by the state transition probability p(s′,r|s,a). The weighted components are the immediate reward r and the discounted future reward (given by γmaxa′Q(s′,a′)), which reflects the consideration of long-term benefits. Calculating Q values ​​is the basis for understanding and applying reinforcement learning. It provides a systematic approach to evaluate the long-term consequences of taking actions in complex environments.

[0023] Optionally, the fault warning system includes a data acquisition module, a fault detection and diagnosis module, a predictive maintenance module, and a safety protection mechanism.

[0024] Optionally, the data acquisition module collects current, voltage, temperature, and power consumption data in real time through sensors and monitoring equipment, converts them into digital signals, and builds a comprehensive equipment operation status database. The fault detection and diagnosis module uses a decision tree algorithm to analyze the collected data to identify possible fault modes or abnormal conditions, establish a fault diagnosis knowledge base, and improve the accuracy and efficiency of fault diagnosis. The predictive maintenance module is used to analyze the usage and maintenance history of the equipment, evaluate the degree of wear and remaining life of the equipment, so as to determine the maintenance strategy and time point, apply regression analysis methods to predict the development trend of equipment failures, formulate maintenance plans in advance, combine prediction results and maintenance strategies, and achieve optimal allocation of maintenance resources, reduce maintenance costs, and extend equipment life. The safety protection mechanism is used to issue a disconnection instruction to the charging pack, disconnect the faulty circuit, and issue an alarm. Faults include battery over-discharge, overcharging, and temperature abnormalities, which are identified through sensor data and fault detection algorithms. Once a fault is detected, the safety protection mechanism will be immediately activated and measures will be taken to ensure the safe operation of the energy storage facility.

[0025] Optionally, the energy management module includes data collection and monitoring elements, data analysis and optimization elements, energy scheduling and control elements, and comprehensive energy management strategy elements.

[0026] Optionally, the data acquisition and monitoring elements include sensors, instrumentation equipment, and a data acquisition system. The instrumentation equipment is used to collect battery charge and discharge status, temperature, voltage, and current data. It is necessary to monitor the generation, storage, and consumption of energy in the energy storage facility in real time. The collected data needs to be summarized and pre-processed by the data acquisition system to ensure the integrity and accuracy of the data, so as to provide a reliable basis for subsequent analysis and decision-making;

[0027] The data analysis and optimization element includes a data processing unit and an optimization decision module. The data processing unit is the core part of the energy management module, which is responsible for performing algorithm processing and analysis on the collected data to understand the real-time working status and performance of the energy system and find out potential problems. The optimization decision module provides suggestions for adjusting the charging and discharging strategy and optimizing the energy utilization efficiency based on the results of data analysis. For example, in a hybrid energy storage system, this module can determine how to optimally allocate power to achieve complementary advantages between lithium-ion batteries and supercapacitors.

[0028] The energy dispatching and control element includes an energy dispatching algorithm module and a control actuator. The energy dispatching algorithm module performs energy dispatching and control, including comprehensive consideration of demand forecasting, electricity price conditions and grid load factors, so as to reasonably arrange the charging and discharging operations of the energy storage facility. The control actuator is used to implement the control instructions calculated by the dispatching algorithm, including bidirectional DC / DC converter hardware devices, which can accurately control the energy flow between the energy storage device and the load;

[0029] The comprehensive energy management strategy element includes an equivalent consumption minimum strategy module and a state machine control strategy module. The equivalent consumption minimum strategy module optimizes energy use by minimizing the system equivalent consumption and is simulated and verified through a Simulink model to ensure its effectiveness and reliability in practical applications. The state machine control strategy module automatically adjusts energy distribution according to preset rules. This strategy is suitable for systems with multiple stable states.

[0030] (III) Beneficial effects

[0031] The present invention provides an intelligent track change control system for an aerial mobile charging device, which has the following beneficial effects:

[0032] 1. The present invention adopts a scheduling decision algorithm to automatically adjust the track according to the status of the charging package to provide services for the most vehicles in the shortest time. Through efficient charging equipment switching and track sharing, the charging efficiency and equipment utilization rate are significantly improved, while the idle time of the equipment and the charging waiting time are reduced, solving the problem of low utilization rate of existing charging piles, and reducing equipment investment and space occupancy. It has broad application prospects.

[0033] 2. The present invention sets up a fault warning system and continuously monitors various indicators of the equipment. Predictive maintenance can help identify and correct problems that may cause early equipment failures. The system's data analysis can evaluate the degree of wear and remaining life of the equipment based on the equipment's usage and maintenance history, making maintenance work more targeted and avoiding unnecessary intervention, thereby extending the overall service life of the equipment. Through early warning and fault prediction, the system downtime for maintenance due to sudden failures can be reduced, thereby improving the equipment's work efficiency.

[0034] 3. The present invention, by setting up an energy management module to monitor the generation, storage and consumption of energy in the energy storage facilities in real time, provides a basis for subsequent analysis and optimization. By conducting in-depth analysis of the collected data, it is possible to identify potential problems and put forward optimization suggestions, and reasonably arrange the charging and discharging operations of the energy storage facilities to achieve efficient utilization and conservation of energy. During the peak load period of the power grid, the energy management module can control the energy storage facilities to release energy to help reduce the pressure on the power grid, and during the off-peak period, it stores excess energy to balance the load of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a module schematic diagram of the intelligent track change control system of the present invention;

[0036] Figure 2 It is a module schematic diagram of the fault warning system of the present invention;

[0037] Figure 3 The figure is a schematic diagram of the principle flow of the intelligent track change control system of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. 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.

[0039] Example 1

[0040] See also Figure 1-3 , an intelligent track change control system for an aerial mobile charging device, the control system includes:

[0041] The main track is used to support and guide the movement of the charging pack, and has an interface that matches the charging pack, allowing the charging pack to move along the track to a waiting area or a charging position;

[0042] Multiple charging packs, each of which is an independent movable charging unit, equipped with a charging interface and a status information control unit. The status information control unit is used to count the power, temperature, voltage, charge and discharge status and location information of the charging pack, and send the information to the data processing center. The charging pack can drive itself and move along the main track to the designated charging position or return from the charging position. A secondary track is provided on the top of the charging pack, and the secondary track is slidably connected to the main track. A driving device and an automatic locking mechanism are provided on the secondary track. The wheels of the driving device are in contact with the main track. The driving device is used to drive the secondary track to move on the main track. The automatic locking mechanism is used to connect or disconnect the secondary track from the main track. A lifting mechanism is provided at the bottom of the charging pack to support the fall of the charging pack and lift the charging pack from the ground so that the secondary track is connected to the main track;

[0043] The track-changing mechanism is installed outside the charging pack and includes an intelligent control unit and a track switching module. The intelligent control unit is used to mobilize the charging pack, and the track switching module is used to control the transfer of the charging pack from the waiting area to the main track, and the process of returning from the main track to the waiting area after charging is completed;

[0044] The data processing center is connected to the status information control unit of each charging pack, responsible for collecting the status information of the charging pack and making scheduling decisions according to the preset algorithm, responsible for collecting the status information of all charging packs, processing the data, making scheduling decisions, and communicating with the intelligent control unit of the track change mechanism to achieve efficient charging pack scheduling;

[0045] The waiting area is installed outside the charging pack and is used to provide charging services for the charging pack;

[0046] The communication system enables the vehicle equipment to establish a connection with the charging station and obtain the vehicle location information and power information;

[0047] Fault warning system, used to detect the status of the charging pack and issue commands in time to ensure stable operation of the equipment, reduce maintenance costs and prevent unexpected failures;

[0048] Energy management module: The energy storage battery in the charging pack stores energy when the grid load is low and releases energy during peak hours to balance the grid load and improve energy utilization efficiency.

[0049] In this embodiment, a scheduling decision algorithm is adopted to automatically adjust the track according to the status of the charging package to provide services for the most vehicles in the shortest time. The intelligent mobile track-changing charging equipment control system significantly improves the charging efficiency and equipment utilization rate through efficient charging equipment switching and track sharing, while reducing the idle time of the equipment and the charging waiting time. The implementation of the system can also reduce equipment investment and space occupancy, and has broad application prospects.

[0050] Example 2

[0051] This embodiment is a further optimization based on the embodiment 1. Specifically, the data processing center includes a central processing unit, a memory, and a hard disk storage. The central processing unit is responsible for executing the deep reinforcement learning algorithm and processing tasks. The memory is used to store the running programs and current data to ensure that the data processing center can quickly read and write data. The hard disk storage is used for long-term storage of system data, log information and historical records.

[0052] The deep reinforcement learning algorithm adopts Q learning method, and the mathematical model is as follows:

[0053]

[0054] Where: Q(s,a) is the state-action value of taking action a in state s, p(s′,r|s,a) is the probability of transferring to state s′ and obtaining reward r after taking action a in state s, r is the immediate reward, γ is the discount factor used to weigh the importance of immediate rewards and future rewards, maxa′Q(s′,a′) is the maximum Q value of all possible actions in the new state s′, Q value (i.e., state-action value function) is used to evaluate the value of taking an action in a specific state, and Q value represents the expected value of the total reward that the agent can obtain after taking a specific action in a given state until the final state;

[0055] For any state s and any action a, its Q value is equal to the expectation over all possible successor states s′ and rewards r. This expectation is weighted by the state transition probability p(s′,r|s,a). The weighted components are the immediate reward r and the discounted future reward (given by γmaxa′Q(s′,a′)), which reflects the consideration of long-term benefits. Calculating Q values ​​is the basis for understanding and applying reinforcement learning. It provides a systematic approach to evaluate the long-term consequences of taking actions in complex environments.

[0056] In this embodiment, the application of the deep reinforcement learning algorithm in charging operations significantly improves the efficiency and intelligence level of energy system management through its high adaptability, optimization capability and efficient decision-making support. The deep reinforcement learning algorithm can autonomously learn and adjust strategies according to different environments and states, which enables the algorithm to effectively cope with various complex situations in charging operations; the deep reinforcement learning algorithm continuously optimizes the charging strategy through a continuous learning process, thereby achieving global optimal or near-optimal charging efficiency. When faced with multiple optimization objectives such as cost, time, and energy consumption, the deep reinforcement learning algorithm can effectively weigh these objectives and output a composite optimal solution; the algorithm can automatically learn and make decisions, reducing the manual intervention required in complex charging management, improving overall operational efficiency, and optimizing the efficiency and cost of charging operations.

[0057] Example 3

[0058] See also Figure 2 , This embodiment is further optimized on the basis of embodiment 1. Specifically, the fault warning system includes a data acquisition module, a fault detection and diagnosis module, a predictive maintenance module, and a safety protection mechanism;

[0059] The data acquisition module collects current, voltage, temperature, and power consumption data in real time through sensors and monitoring equipment, converts them into digital signals, and builds a comprehensive equipment operation status database. The fault detection and diagnosis module uses a decision tree algorithm to analyze the collected data to identify possible fault modes or abnormal conditions, establish a fault diagnosis knowledge base, and improve the accuracy and efficiency of fault diagnosis. The predictive maintenance module is used to analyze the equipment usage and maintenance history based on the data of the equipment operation status database and the fault diagnosis knowledge base, evaluate the degree of wear and remaining life of the equipment, and thus determine the maintenance strategy and time point. The regression analysis method is used to predict the development trend of equipment failures, formulate maintenance plans in advance, and combine the prediction results with the maintenance strategy to achieve optimal allocation of maintenance resources, reduce maintenance costs, and extend equipment life. The safety protection mechanism is used to issue a disconnection command to the charging pack, disconnect the faulty circuit, and issue an alarm. Faults include battery over-discharge, overcharging, and temperature abnormalities, which are identified through sensor data and fault detection algorithms. Once a fault is detected, the safety protection mechanism will be activated immediately and measures will be taken to ensure the safe operation of the energy storage facility.

[0060] In this embodiment, the fault warning system in the charging equipment can bring many benefits. By continuously monitoring various indicators of the equipment, predictive maintenance can help identify and correct problems that may cause early equipment failures, thereby reducing the damage to the equipment caused by sudden failures; the system's data analysis can evaluate the degree of wear and remaining life of the equipment based on the equipment's usage and maintenance history, making maintenance work more targeted and avoiding unnecessary intervention, thereby extending the overall service life of the equipment; using advanced algorithms to analyze data can timely detect potential or existing faults and quickly locate the problem, thereby improving the stability and reliability of the system. The system can conduct risk assessments on factors that may cause failures and take preventive measures in advance to ensure that the system can operate reliably even in harsh environments; through early warning and fault prediction, the system downtime and maintenance time caused by sudden failures can be reduced, thereby improving the equipment's work efficiency and output; through real-time monitoring and fault warning, the system can effectively prevent safety accidents caused by equipment failures and protect the safety of personnel and equipment.

[0061] Example 4

[0062] This embodiment is a further optimization based on the embodiment 1. Specifically, the energy management module is an important component of the intelligent track change control system of the charging equipment. It realizes efficient management and optimization of energy through a series of specific model elements. The energy management module includes data collection and monitoring elements, data analysis and optimization elements, energy scheduling and control elements, and comprehensive energy management strategy elements.

[0063] Data acquisition and monitoring components include sensors, instrumentation equipment, and data acquisition systems. Instrumentation equipment is used to collect battery charge and discharge status, temperature, voltage, and current data. It is necessary to monitor the generation, storage, and consumption of energy in energy storage facilities in real time. The collected data needs to be summarized and pre-processed by the data acquisition system to ensure the integrity and accuracy of the data, providing a reliable basis for subsequent analysis and decision-making;

[0064] The data analysis and optimization components include a data processing unit and an optimization decision module. The data processing unit is the core part of the energy management module. It is responsible for performing algorithm processing and analysis on the collected data to understand the real-time working status and performance of the energy system and identify potential problems. The optimization decision module provides suggestions for adjusting the charging and discharging strategy and optimizing energy utilization efficiency based on the results of data analysis. For example, in a hybrid energy storage system, this module can determine how to optimally allocate power to achieve complementary advantages between lithium-ion batteries and supercapacitors.

[0065] The energy dispatching and control components include an energy dispatching algorithm module and a control actuator. The energy dispatching algorithm module performs energy dispatching and control, including comprehensive consideration of demand forecasting, electricity prices and grid load factors, in order to reasonably arrange the charging and discharging operations of energy storage facilities. The control actuator is used to implement the control instructions calculated by the dispatching algorithm, including bidirectional DC / DC converter hardware devices, which can accurately control the energy flow between energy storage devices and loads.

[0066] The integrated energy management strategy elements include an equivalent consumption minimum strategy module and a state machine control strategy module. The equivalent consumption minimum strategy module optimizes energy usage by minimizing the system equivalent consumption. It is simulated and verified through a Simulink model to ensure its effectiveness and reliability in practical applications. The state machine control strategy module automatically adjusts energy distribution according to preset rules. This strategy is suitable for systems with multiple stable states, such as an electric-hydrogen integrated energy system.

[0067] In this embodiment, the energy management module has multiple benefits in the charging system, which are mainly reflected in improving energy utilization efficiency, optimizing grid operation, protecting equipment performance, etc.; the energy management module monitors the generation, storage and consumption of energy in the energy storage facilities in real time through sensors and instrumentation equipment, providing a basis for subsequent analysis and optimization; through in-depth analysis of the collected data, the energy management module can identify potential problems and put forward optimization suggestions, such as adjusting the charging and discharging strategy and optimizing energy utilization efficiency. This data-based decision support makes energy management more accurate and efficient; the energy management module can intelligently dispatch and control energy according to real-time energy demand and system operation status. It takes into account factors such as demand forecast, electricity price and grid load, and reasonably arranges the charging and discharging operations of energy storage facilities to achieve efficient utilization and conservation of energy. During peak load periods of the grid, the energy management module can control the release of energy from energy storage facilities to help reduce the pressure on the grid, while during low load periods, it stores excess energy to balance the load of the grid. By precisely controlling energy distribution and optimizing charging and discharging strategies, the energy management module can reduce energy waste and improve energy efficiency. In short, the energy management module plays a vital role in the charging system. It not only improves energy utilization efficiency and optimizes grid operation, but also protects equipment performance and reduces operating costs.

[0068] How it works: See Figure 3 a. The owner uses the communication system to establish a connection between the vehicle equipment and the charging station to obtain its charging needs and status information; b. The status information control unit obtains the data of each charging package and transmits the data to the data processing center; c. The data processing center makes scheduling decisions based on the preset algorithm, calculates the optimal scheduling path for each charging package, and transmits the information to the intelligent control unit of the track change mechanism; d. The intelligent control unit mobilizes the appropriate charging package and moves the charging package to the main track through the track switching module; e. The charging package is moved to the corresponding vehicle through the drive device, and then the jacking mechanism is started to support the charging package, and then the automatic locking mechanism is opened to separate the charging package from the main track, and then the jacking mechanism is lowered to drop the charging package to keep the charging package away from the main track, and then the charging interface is inserted into the vehicle charging port; f. After charging is completed, the data processing center optimizes the moving path according to the charging needs and current location of other equipment and prepares for the next charging task.

[0069] In summary: the intelligent track change control system of the present invention can realize efficient scheduling and management of charging packages. It adopts advanced artificial intelligence algorithms to intelligently schedule idle charging piles according to charging needs, electric vehicle types and battery status, and automatically adjusts the tracks to provide services for the most vehicles in the shortest time, reduce charging waiting time, improve the utilization rate of charging facilities and the convenience of electric vehicles, and use data analysis and machine learning to monitor the status of charging equipment, predict potential failures and perform maintenance in advance, reduce downtime and maintenance costs. The system realizes dynamic scheduling and optimized charging path planning of multiple charging devices through an integrated sensor network, a real-time data processing unit, and a high-precision track change control mechanism, thereby improving charging efficiency and equipment utilization. Through efficient charging equipment switching and track sharing, the charging efficiency and equipment utilization are significantly improved, while the idle time and charging waiting time of the equipment are reduced. The charging management module is highly integrated and intelligently designed, which not only improves the quality and efficiency of charging services, but also lays a solid foundation for building a sustainable new energy ecosystem.

[0070] 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. An intelligent track change control system for an aerial mobile charging device, characterized in that ,The intelligent track change control system includes: The main track is used to support and guide the movement of the charging pack, and has an interface that matches the charging pack, allowing the charging pack to move along the track to a waiting area or a charging position; Multiple charging packs, each of which is an independent mobile charging unit equipped with a charging interface and a status information control unit. The status information control unit is used to count the power, temperature, voltage, charging and discharging status and location information of the charging pack and send the information to the data processing center. The charging pack can drive itself and move along the main track to the designated charging position or return from the charging position; The track-changing mechanism is installed outside the charging pack and includes an intelligent control unit and a track switching module. The intelligent control unit is used to mobilize the charging pack, and the track switching module is used to control the transfer of the charging pack from the waiting area to the main track, and the process of returning from the main track to the waiting area after charging is completed; The data processing center is connected to the status information control unit of each charging pack and is responsible for collecting the status information of the charging pack and making scheduling decisions according to the preset algorithm. It is responsible for collecting the status information of all charging packs, processing the data, making scheduling decisions, and communicating with the intelligent control unit of the track change mechanism; The waiting area is installed outside the charging pack and is used to provide charging services for the charging pack; Fault warning system, used to detect the status of the charging pack and issue commands in time; Energy management module: The energy storage battery in the charging pack stores energy when the grid load is low and releases energy during peak hours.

2. According to claim 1, the intelligent track change control system of the aerial mobile charging device is characterized in that: A secondary track is provided on the top of the charging pack, and a driving device and an automatic locking mechanism are provided on the secondary track. The driving device is used to drive the secondary track to move on the main track, and the automatic locking mechanism is used to connect or disconnect the secondary track from the main track. A lifting mechanism is provided at the bottom of the charging pack, which is used to support the falling of the charging pack and lift the charging pack from the ground so that the secondary track is connected to the main track.

3. According to claim 1, the intelligent track change control system of an aerial mobile charging device is characterized in that: The data processing center includes a central processing unit, memory, and hard disk storage. The central processing unit is responsible for executing deep reinforcement learning algorithms and processing tasks. The memory is used to store running programs and current data to ensure that the data processing center can quickly read and write data. The hard disk storage is used for long-term storage of system data, log information, and historical records.

4. The intelligent track change control system of an aerial mobile charging device according to claim 3 is characterized in that: The deep reinforcement learning algorithm adopts Q learning method, and the mathematical model is as follows: Where: Q(s,a) is the state-action value of taking action a in state s, p(s′,r|s,a) is the probability of transferring to state s′ and obtaining reward r after taking action a in state s, r is the immediate reward, γ is the discount factor used to weigh the importance of immediate reward and future reward, maxa′Q(s′,a′) is the maximum Q value of all possible actions in the new state s′; For any state s and any action a, its Q value is equal to the expectation over all possible successor states s′ and rewards r, which is weighted by the state transition probability p(s′,r|s,a), and the weighted components are the immediate reward r and the discounted future reward (given by γmaxa′Q(s′,a′).

5. According to claim 1, the intelligent track change control system of the aerial mobile charging device is characterized in that: The fault warning system includes a data acquisition module, a fault detection and diagnosis module, a predictive maintenance module, and a safety protection mechanism.

6. The intelligent track change control system of an aerial mobile charging device according to claim 5, characterized in that: The data acquisition module collects current, voltage, temperature, and power consumption data in real time through sensors and monitoring equipment, converts them into digital signals, and builds a comprehensive equipment operation status database. The fault detection and diagnosis module uses a decision tree algorithm to analyze the collected data to identify possible fault modes or abnormal conditions and establish a fault diagnosis knowledge base. The predictive maintenance module is used to analyze the usage and maintenance history of the equipment, evaluate the degree of wear and remaining life of the equipment, and thus determine the maintenance strategy and time point. The safety protection mechanism is used to issue a disconnection instruction to the charging pack, disconnect the faulty circuit, and issue an alarm.

7. The intelligent track change control system of an aerial mobile charging device according to claim 1, characterized in that: The energy management module includes data acquisition and monitoring components, data analysis and optimization components, energy scheduling and control components, and comprehensive energy management strategy components.

8. The intelligent track change control system of an aerial mobile charging device according to claim 7, characterized in that: The data acquisition and monitoring elements include sensors, instrumentation equipment, and data acquisition systems. The instrumentation equipment is used to collect battery charge and discharge status, temperature, voltage, and current data. It is necessary to monitor the generation, storage, and consumption of energy in the energy storage facility in real time. The collected data needs to be summarized and pre-processed by the data acquisition system; The data analysis and optimization element includes a data processing unit and an optimization decision module. The data processing unit performs algorithm processing and analysis on the collected data. The optimization decision module provides suggestions for adjusting the charging and discharging strategy and optimizing the energy utilization efficiency based on the results of the data analysis. The energy dispatching and control element includes an energy dispatching algorithm module and a control actuator. The energy dispatching algorithm module performs energy dispatching and control, including comprehensive consideration of demand forecasting, electricity price conditions and grid load factors, so as to reasonably arrange the charging and discharging operations of the energy storage facility. The control actuator is used to implement the control instructions calculated by the dispatching algorithm through the control actuator. The comprehensive energy management strategy element includes an equivalent consumption minimum strategy module and a state machine control strategy module. The equivalent consumption minimum strategy module optimizes energy use by minimizing the system equivalent consumption and is simulated and verified through a Simulink model. The state machine control strategy module automatically adjusts energy distribution according to preset rules.

Images