An intelligent portable image and digital integrated remote control system for special robots

Abstract

The invention relates to the technical field of special robot control, and provides an intelligent special robot portable integrated image and data remote control system; the system comprises a data acquisition module, a data preprocessing module, a control module, a robot and a battery management module; data is acquired in real time by the data acquisition module, and filtered, denoised and normalized by the data preprocessing module; the control module adopts an SRO control strategy algorithm, combines MDPD k-means to cluster and enhance classification scenes, optimizes the control strategy to generate an adaptive control signal, and ensures the high-precision operation of the robot in a complex environment; the battery management module introduces a Sin Cos HM FDO algorithm, optimizes the management of the charging and discharging strategy, and effectively improves the battery use efficiency and life; the invention improves the adaptability and operation accuracy of the robot in complex tasks, and enhances the stability and energy efficiency management of the system.

Description

Technical Field

[0001] The invention relates to the technical field of robot control, in particular to an intelligent special robot portable integrated image and digital remote control system. Background Art

[0002] With the rapid development of intelligent technology, the application demand of special robots in various complex environments is increasing; however, existing robot control systems often face many challenges, especially in real-time operation and environmental adaptability; traditional remote control systems often ignore the complexity and dynamic changes of the environment due to the relatively simple control strategies adopted, resulting in insufficient response capabilities and decision-making accuracy in specific scenarios; current remote control systems usually adopt fixed control algorithms and lack in-depth analysis and processing of real-time data, resulting in low sensitivity to environmental changes; this limitation makes the robot show greater instability and low efficiency when performing high-precision tasks, and cannot meet the accuracy and reliability requirements of modern special robots; in addition, traditional battery management strategies have also failed to fully consider the battery utilization efficiency in different operating scenarios, often resulting in energy loss and shortened service life; in order to solve these problems, there is an urgent need for a new type of portable integrated image and digital remote control system that can integrate advanced control algorithms and intelligent battery management strategies. Summary of the invention

[0003] The present invention provides an intelligent special robot portable integrated image and data remote control system, aiming to overcome the problems of insufficient environmental adaptability, low control accuracy and poor energy management efficiency existing in the prior art; the present invention adopts the SRO-control strategy algorithm, and uses MDPD-k-means to cluster and enhance the classified scenes, which significantly improves the accuracy of the control signal, can capture environmental changes in real time, and automatically adjust the control strategy, so as to effectively cope with complex operation scenarios; in terms of battery management, the present invention introduces a sine-cosine hybrid mechanism to improve the FDO algorithm, and by optimizing the charging and discharging strategy, improves the battery utilization efficiency and life cycle, reduces unnecessary energy loss, and ensures that the robot still maintains high performance under long-term operation.

[0004] The present invention provides an intelligent special robot portable image and data integrated remote control system, the system comprises a data acquisition module, a data preprocessing module, a control module, a robot and a battery management module;

[0005] The data acquisition module collects real-time data of the environment and the robot status to obtain original sensor data;

[0006] The data preprocessing module performs filtering, denoising and normalization on the original sensor data to obtain preprocessed sensor feature data;

[0007] The control module improves the clustering algorithm by minimum density deviation and k-means, constructs MDPD-k-means, clusters and enhances the classification scene by MDPD-k-means, constructs an SRO-control strategy algorithm, uses the SRO-control strategy algorithm to process the pre-processed sensor feature data, and generates adaptive control signal data. The SRO-control strategy algorithm includes an environment modeling and state estimation layer, a task planning and path planning layer, a control strategy generation layer, and a strategy optimization layer;

[0008] The robot executes adaptive control signal data, performs search and rescue, environmental monitoring and industrial inspection, and generates real-time feedback data;

[0009] The battery management module improves the FDO algorithm by combining the sine-cosine hybrid mechanism to obtain the Sin-CosHM-FDO algorithm, and uses the Sin-CosHM-FDO algorithm to optimize the charging and discharging strategy of the robot battery.

[0010] Furthermore, the environment modeling and state estimation layer specifically includes: establishing a SLAM algorithm model, using the SLAM algorithm model to perform environment modeling based on preprocessed sensor feature data, generating an environment map, and performing robot state estimation through sensor fusion technology to obtain map data and robot state estimation data.

[0011] Furthermore, the task planning and path planning layer specifically includes: setting the task goal and decomposing it into multiple subtasks according to the map data and the robot state estimation data, generating the target task plan, and obtaining the task planning data; establishing the RRT path planning algorithm model, and based on the task planning data, using the RRT path planning algorithm model to perform path search, find the optimal path from the current position of the robot to the target position, and obtain the planned path data.

[0012] Furthermore, the generation of the control strategy layer specifically includes: generating a smooth motion trajectory according to the planned path data, and obtaining motion trajectory data; using the motion trajectory data, calculating the control signal through the PID control algorithm, generating the motor speed and steering angle, and obtaining the control signal data.

[0013] Furthermore, the strategy optimization layer uses an SRO algorithm to optimize the control signal data and generate adaptive control signal data.

[0014] Furthermore, the process of using the SRO algorithm to optimize the control signal data and generate the adaptive control signal data specifically includes the following steps:

[0015] Step S1: Data modeling: According to the robot motion data in the real-time data of the robot state, a robot motion model is established, and control variables are defined to obtain control variable data;

[0016] Step S2: scene generation and reduction: classify the motion scenes according to different tasks in the target task plan to obtain classified scenes, and use MDPD-k-means to cluster the classified scenes to obtain typical scene data;

[0017] Step S3: Model optimization: establish a particle swarm optimization algorithm model, optimize the typical scene data through the particle swarm optimization algorithm model, adjust the control variable data, and obtain the optimized control strategy data;

[0018] Step S4: Strategy optimization and execution: The optimized control strategy data is stored in a lookup table, and the real-time scenario is matched through the lookup table to apply the optimized control strategy data; the optimized control strategy data is adaptively adjusted according to the real-time feedback data to obtain the adaptive control strategy data, and then the adaptive control signal data is calculated through the PID control algorithm.

[0019] Further, step S2 specifically includes the following steps:

[0020] Step S21: normalizing the robot motion data, scaling the data to the interval [0, 1], and obtaining standardized motion data;

[0021] Step S22: mapping the standardized motion data as the overall data points into the coordinate system, dividing it into equal-proportional grids, calculating the density of data points in each grid in the equal-proportional grid, and selecting the densest grid as the first initial cluster center to obtain initial cluster center data;

[0022] Step S23: Set the target number of initial cluster centers, calculate the distance from the overall data points to the initial cluster center data, sort them from small to large, select the 80th percentile of the distance as the next initial cluster center, repeat this step until the set target number of initial cluster centers is reached, and output typical scene data.

[0023] Furthermore, the process of optimizing the charging and discharging strategy of the robot battery using the Sin-CosHM-FDO algorithm includes the following steps:

[0024] Step M1: Population initialization: Based on the charge and discharge strategy, a scout bee population in the search space is randomly generated. Each scout bee position in the scout bee population represents a solution. The parameters of each scout bee are initialized, including power loss, voltage deviation, battery health status, and battery charge status, to obtain the initial scout bee population;

[0025] Step M2: Fitness evaluation: Perform fitness evaluation on the initial scout bee population, use battery life, power loss, and load demand as evaluation indicators, judge the quality of each solution in the initial scout bee population based on the evaluation indicators, and obtain fitness evaluation data. The formula used is as follows:

[0026] ;

[0027] in, Represents the scout bee index, represents the fitness function, Indicates The location of the scout bees, Indicates the battery life. represents the power loss, Indicates load demand; , and are weight coefficients respectively;

[0028] Initial stage weight coefficient: , and ;

[0029] Step M3: Movement and position update of scout bees: Based on the fitness evaluation data, the position of each scout bee in the initial scout bee population is adjusted through the update mechanism and the pace standard to obtain the current global optimal solution; the pace standard is controlled by the lambda parameter. Through iterative processing, the position of the scout bee is gradually adjusted according to the current global optimal solution. After multiple iterations, it gradually approaches the global optimal solution. The formula used is as follows:

[0030] ;

[0031] in, Represents the iteration index, Indicates Scout bees in the current iteration The position at Indicates Scout bees in the current iteration The position at the time; represents the pace factor, represents the current global optimal solution, represents the distance vector, Represents a random number between 0 and 1;

[0032] Step M4: Sine-cosine hybrid mechanism: While adjusting the position, the sine-cosine algorithm is mixed to optimize the pace standard and obtain the pace optimization data; according to the pace optimization data, the current global optimal solution is updated again in real time; if a new optimal solution is found, the current global optimal solution is updated and recorded as the global optimal solution. The formula used is as follows:

[0033] ;

[0034] in, Pace optimization data, Represents the scaling factor, controlling the size of the step standard. represents a random factor that controls the direction of the step standard, Represents a random factor, and determines whether to use the sine or cosine function;

[0035] Step M5: Check the termination condition: Iterate steps M2-M5, reach the convergence standard, that is, the fitness change is no longer significant, and output the optimal charging and discharging strategy.

[0036] By adopting the above scheme, the beneficial effects achieved by the present invention are as follows:

[0037] The present invention provides an intelligent special robot portable integrated image and data remote control system. The intelligent upgrade of the control strategy is realized. The present invention uses the SRO-control strategy algorithm and combines MDPD-k-means to cluster and enhance the classification scenes, which significantly improves the robot's operating accuracy and response speed; specifically, the system uses MDPD-k-means to intelligently analyze and classify complex environmental data, effectively reducing the delay and uncertainty of the control signal, so that the robot can quickly adapt to the dynamically changing environment; this technical means solves the shortcomings of traditional remote control systems in real-time and accuracy, and ensures that the robot performs more stably and reliably when performing complex tasks;

[0038] In addition, the present invention introduces an improved FDO algorithm with a sine-cosine hybrid mechanism in the battery management module. Based on the FDO algorithm, the algorithm effectively improves the battery efficiency and life by introducing a sine-cosine hybrid mechanism. In the management of charging and discharging strategies, traditional systems often fail to fully consider the changes in energy consumption under different working conditions, resulting in high energy loss and poor performance in terms of battery life. The present invention can achieve more precise real-time monitoring and dynamic adjustment of battery usage status by introducing a sine-cosine hybrid mechanism and a Sin-CosHM-FDO algorithm. This optimization management technology intelligently adjusts the charging and discharging strategy according to the operating requirements of the robot, which not only significantly reduces energy loss, but also extends the effective working time of the battery. The introduction of the sine-cosine hybrid mechanism makes the adjustment in the charging and discharging process more flexible and more adaptable, thereby ensuring that the robot can still maintain high efficiency during long-term operation, meet the needs of various special operations, and solve the problems of high energy consumption and short service life in battery management of traditional systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a module schematic diagram of an intelligent special robot portable integrated graphics and digital remote control system proposed by the present invention;

[0040] Figure 2 This is a flow chart of the battery management module proposed in the ninth embodiment. DETAILED DESCRIPTION

[0041] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0042] Embodiment 1, according to Figure 1 , the present invention provides an intelligent special robot portable image and data integrated remote control system, the system includes a data acquisition module, a data preprocessing module, a control module, a robot and a battery management module;

[0043] The data acquisition module collects real-time data of the environment and the robot status to obtain original sensor data;

[0044] The data preprocessing module performs filtering, denoising and normalization on the original sensor data to obtain preprocessed sensor feature data;

[0045] The control module improves the clustering algorithm by minimum density deviation and k-means, constructs MDPD-k-means, clusters and enhances the classification scene by MDPD-k-means, constructs an SRO-control strategy algorithm, uses the SRO-control strategy algorithm to process the pre-processed sensor feature data, and generates adaptive control signal data. The SRO-control strategy algorithm includes an environment modeling and state estimation layer, a task planning and path planning layer, a control strategy generation layer, and a strategy optimization layer;

[0046] The robot executes adaptive control signal data, performs search and rescue, environmental monitoring and industrial inspection, and generates real-time feedback data;

[0047] The battery management module improves the FDO algorithm by combining the sine-cosine hybrid mechanism to obtain the Sin-CosHM-FDO algorithm, and uses the Sin-CosHM-FDO algorithm to optimize the charging and discharging strategy of the robot battery.

[0048] Embodiment 2: This embodiment is based on the above embodiment, wherein the data acquisition module collects real-time data of the environment and the real-time data of the robot status to obtain original sensor data;

[0049] Real-time environmental data includes: temperature, humidity, air pressure, light intensity, sound level, gas concentration, obstacle detection, terrain information, GPS location and tilt angle;

[0050] The real-time data of the robot status include: speed, direction, battery status, motion status, joint angle, load condition, fault status, control command status, real-time feedback data and state estimation.

[0051] Embodiment three, this embodiment is based on the above embodiment, and the environment modeling and state estimation layer specifically includes: establishing a SLAM algorithm model, using the SLAM algorithm model to perform environment modeling based on preprocessed sensor feature data, generating an environment map, and performing robot state estimation through sensor fusion technology to obtain map data and robot state estimation data.

[0052] Embodiment 4, this embodiment is based on the above embodiment, and the task planning and path planning layer specifically includes: according to the map data and the robot state estimation data, setting the task goal and decomposing it into multiple subtasks, generating the target task plan, and obtaining the task planning data; establishing the RRT path planning algorithm model, based on the task planning data, using the RRT path planning algorithm model to perform path search, find the optimal path from the current position of the robot to the target position, and obtain the planned path data.

[0053] Embodiment 5: This embodiment is based on the above embodiment, and the generation of the control strategy layer specifically includes: generating a smooth motion trajectory according to the planned path data, and obtaining the motion trajectory data; using the motion trajectory data, calculating the control signal through the PID control algorithm, generating the motor speed and steering angle, and obtaining the control signal data.

[0054] Embodiment 6: This embodiment is based on the above embodiment, and the strategy optimization layer uses the SRO algorithm to optimize the control signal data to generate adaptive control signal data.

[0055] Embodiment 7, based on the above embodiment, the process of using the SRO algorithm to optimize the control signal data and generate the adaptive control signal data specifically includes the following steps:

[0056] Step S1: Data modeling: According to the robot motion data in the real-time data of the robot state, a robot motion model is established, and control variables are defined to obtain control variable data;

[0057] Step S2: scene generation and reduction: classify the motion scenes according to different tasks in the target task plan to obtain classified scenes, and use MDPD-k-means to cluster the classified scenes to obtain typical scene data;

[0058] Step S3: Model optimization: establish a particle swarm optimization algorithm model, optimize the typical scene data through the particle swarm optimization algorithm model, adjust the control variable data, and obtain the optimized control strategy data;

[0059] Step S4: Strategy optimization and execution: The optimized control strategy data is stored in a lookup table, and the real-time scenario is matched through the lookup table to apply the optimized control strategy data; the optimized control strategy data is adaptively adjusted according to the real-time feedback data to obtain the adaptive control strategy data, and then the adaptive control signal data is calculated through the PID control algorithm.

[0060] Embodiment 8, based on the above embodiment, step S2 specifically includes the following steps:

[0061] Step S21: normalizing the robot motion data, scaling the data to the interval [0, 1], and obtaining standardized motion data;

[0062] Step S22: mapping the standardized motion data as the overall data points into the coordinate system, dividing it into equal-proportional grids, calculating the density of data points in each grid in the equal-proportional grid, and selecting the densest grid as the first initial cluster center to obtain initial cluster center data;

[0063] Step S23: Set the target number of initial cluster centers, calculate the distance from the overall data points to the initial cluster center data, sort them from small to large, select the 80th percentile of the distance as the next initial cluster center, repeat this step until the set target number of initial cluster centers is reached, and output typical scene data.

[0064] Embodiment 9, according to Figure 2 This embodiment is based on the above embodiment and uses the Sin-CosHM-FDO algorithm to optimize the charging and discharging strategy of the robot battery. The specific steps include:

[0065] Step M1: Population initialization: Based on the charge and discharge strategy, a scout bee population in the search space is randomly generated. Each scout bee position in the scout bee population represents a solution. The parameters of each scout bee are initialized, including power loss, voltage deviation, battery health status, and battery charge status, to obtain the initial scout bee population;

[0066] Step M2: Fitness evaluation: Perform fitness evaluation on the initial scout bee population, use battery life, power loss, and load demand as evaluation indicators, judge the quality of each solution in the initial scout bee population based on the evaluation indicators, and obtain fitness evaluation data. The formula used is as follows:

[0067] ;

[0068] in, Represents the scout bee index, represents the fitness function, Indicates The location of the scout bees, Indicates the battery life. represents the power loss, Indicates load demand; , and are weight coefficients respectively;

[0069] Initial stage weight coefficient: , and ;

[0070] Step M3: Movement and position update of scout bees: Based on the fitness evaluation data, the position of each scout bee in the initial scout bee population is adjusted through the update mechanism and the pace standard to obtain the current global optimal solution; the pace standard is controlled by the lambda parameter. Through iterative processing, the position of the scout bee is gradually adjusted according to the current global optimal solution. After multiple iterations, the formula used to gradually approach the global optimal solution is as follows:

[0071] ;

[0072] in, Represents the iteration index, Indicates Scout bees in the current iteration The position at Indicates Scout bees in the current iteration The position at the time; represents the pace factor, represents the current global optimal solution, represents the distance vector, Represents a random number between 0 and 1;

[0073] Step M4: Sine-cosine hybrid mechanism: While adjusting the position, the sine-cosine algorithm is mixed to optimize the pace standard and obtain the pace optimization data; according to the pace optimization data, the current global optimal solution is updated again in real time; if a new optimal solution is found, the current global optimal solution is updated and recorded as the global optimal solution. The formula used is as follows:

[0074] ;

[0075] in, Pace optimization data, Represents the scaling factor, controlling the size of the step standard. represents a random factor that controls the direction of the step standard, Represents a random factor, and determines whether to use the sine or cosine function;

[0076] Step M5: Check the termination condition: Iterate steps M2-M5, reach the convergence standard, that is, the fitness change is no longer significant, and output the optimal charging and discharging strategy.

[0077] Embodiment 10, based on the above embodiment, the robot executes adaptive control signal data, performs search and rescue, environmental monitoring and industrial inspection, and generates real-time feedback data;

[0078] In embodiment 10:

[0079] Building fire scenario: During a building fire, the robot is deployed to the fire scene;

[0080] Determine the weight coefficients: In the building fire scenario, the weight coefficients after training in Example 9 are , and ;

[0081] Environmental real-time data:

[0082] 100m ahead, the temperature sensor showed a high temperature area of ​​600°C, indicating a large fire;

[0083] 100m ahead, the smoke sensor detected thick smoke, limiting the visibility;

[0084] Real-time data of robot status:

[0085] The robot moves at a speed of 0.5 m / s;

[0086] The battery level is 75%, which is normal.

[0087] The joints are in normal condition and all sensors are working properly;

[0088] Arriving near the trapped people, the robot sends real-time data to the command center:

[0089] Trapped person, location coordinates (x: 125m, y: 158m, z: 0m);

[0090] The on-site temperature near the trapped persons (750°C, the fire is very large, the risk factor is high), and the smoke concentration environmental data (450mg / m³);

[0091] Its own status data, battery power (65%), exercise status (normal).

[0092] The present invention and its embodiments are described above, which is not restrictive. What is shown in the accompanying drawings is only one of the embodiments of the present invention, and the actual structure is not limited to this. In short, if ordinary technicians in this field are inspired by it and do not deviate from the purpose of the invention, they can creatively design structural methods and embodiments similar to the technical solution, which should all fall within the scope of protection of the present invention.

Claims

1. An intelligent special robot portable integrated image and data remote control system, comprising a data acquisition module and a data preprocessing module, wherein the data acquisition module collects real-time environmental data and real-time robot status data to obtain raw sensor data; the data preprocessing module preprocesses the raw sensor data to obtain preprocessed sensor feature data; the characteristics are: The system also includes a control module, a robot and a battery management module; The control module improves the clustering algorithm by minimum density deviation and k-means, constructs MDPD-k-means, clusters and enhances the classification scene by MDPD-k-means, constructs an SRO-control strategy algorithm, uses the SRO-control strategy algorithm to process the pre-processed sensor feature data, and generates adaptive control signal data. The SRO-control strategy algorithm includes an environment modeling and state estimation layer, a task planning and path planning layer, a control strategy generation layer, and a strategy optimization layer; The robot executes adaptive control signal data, performs search and rescue, environmental monitoring and industrial inspection, and generates real-time feedback data; The battery management module improves the FDO algorithm by combining the sine-cosine hybrid mechanism to obtain the Sin-CosHM-FDO algorithm, and uses the Sin-CosHM-FDO algorithm to optimize the charging and discharging strategy of the robot battery; The process of using the Sin-CosHM-FDO algorithm to optimize the charging and discharging strategy of the robot battery specifically includes step M2: Fitness evaluation: Perform fitness evaluation on the initial scout bee population, use the battery life, power loss, and load demand as evaluation indicators, judge the pros and cons of each solution in the initial scout bee population based on the evaluation indicators, and obtain fitness evaluation data.

2. According to claim 1, the portable integrated image and digital remote control system for intelligent special robots is characterized by: The environment modeling and state estimation layer specifically includes: establishing a SLAM algorithm model, using the SLAM algorithm model to perform environment modeling based on preprocessed sensor feature data, generating an environment map, and performing robot state estimation through sensor fusion technology to obtain map data and robot state estimation data.

3. The portable integrated image and digital remote control system for intelligent special robots according to claim 2 is characterized by: The task planning and path planning layer specifically includes: setting the task goal and decomposing it into multiple subtasks according to the map data and the robot state estimation data, generating the target task plan, and obtaining the task planning data; establishing the RRT path planning algorithm model, and based on the task planning data, using the RRT path planning algorithm model to perform path search, find the optimal path from the current position of the robot to the target position, and obtain the planned path data.

4. The portable integrated image and digital remote control system for intelligent special robots according to claim 3 is characterized by: The generation of the control strategy layer specifically includes: generating a smooth motion trajectory according to the planned path data to obtain motion trajectory data; using the motion trajectory data to calculate a control signal through a PID control algorithm, generating a motor speed and a steering angle, and obtaining control signal data.

5. The portable integrated image and digital remote control system for intelligent special robots according to claim 4 is characterized by: The strategy optimization layer uses the SRO algorithm to optimize the control signal data and generate adaptive control signal data.

6. The portable integrated image and digital remote control system for intelligent special robots according to claim 5, characterized in that: The process of generating adaptive control signal data at the strategy optimization layer specifically includes the following steps: Step S1: Data modeling: According to the robot motion data in the real-time data of the robot state, a robot motion model is established, and control variables are defined to obtain control variable data; Step S2: scene generation and reduction: classify the motion scenes according to different tasks in the target task plan to obtain classified scenes, and use MDPD-k-means to cluster the classified scenes to obtain typical scene data; Step S3: Model optimization: establish a particle swarm optimization algorithm model, optimize the typical scene data through the particle swarm optimization algorithm model, adjust the control variable data, and obtain the optimized control strategy data; Step S4: Strategy optimization and execution: The optimized control strategy data is stored in a lookup table, and the real-time scenario is matched through the lookup table to apply the optimized control strategy data; the optimized control strategy data is adaptively adjusted according to the real-time feedback data to obtain the adaptive control strategy data, and then the adaptive control signal data is calculated through the PID control algorithm.

7. The portable integrated image and digital remote control system for intelligent special robots according to claim 6 is characterized by: Step S2 specifically includes the following steps: Step S21: normalizing the robot motion data, scaling the data to the interval [0, 1], and obtaining standardized motion data; Step S22: mapping the standardized motion data as the overall data points into the coordinate system, dividing it into equal-proportional grids, calculating the density of data points in each grid in the equal-proportional grid, and selecting the densest grid as the first initial cluster center to obtain initial cluster center data; Step S23: Set the target number of initial cluster centers, calculate the distance from the overall data points to the initial cluster center data, sort them from small to large, select the 80th percentile of the distance as the next initial cluster center, repeat this step until the set target number of initial cluster centers is reached, and output typical scene data.

8. The portable integrated image and digital remote control system for intelligent special robots according to claim 1 is characterized by: The process of optimizing the charging and discharging strategy of the robot battery using the Sin-CosHM-FDO algorithm includes the following steps: The step M2 includes the step M1 before: Step M1: Population initialization: randomly generate a charge-discharge strategy, and based on the charge-discharge strategy, randomly generate a scout bee population in the search space. Each scout bee position in the scout bee population represents a solution. Initialize the parameters of each scout bee to obtain the initial scout bee population. The step M2 includes steps M3 to M5: Step M3: Scout bee movement and position update: Based on the fitness evaluation data, adjust the position of each scout bee in the initial scout bee population through the update mechanism and pace standard to obtain the current global optimal solution; the pace standard is controlled by the lambda parameter, and through iterative processing, the position of the scout bee is gradually adjusted according to the current global optimal solution. After multiple iterations, it gradually approaches the global optimal solution; Step M4: Sine-cosine hybrid mechanism: While adjusting the position, the sine-cosine algorithm is mixed to optimize the pace standard and obtain the pace optimization data; according to the pace optimization data, the current global optimal solution is updated again in real time; if a new optimal solution is found, the current global optimal solution is updated and recorded as the global optimal solution; Step M5: Check termination conditions: set convergence criteria, reach convergence criteria, and output optimal charge and discharge strategy.

Images