Wireless charging intelligent regulation and control method and system

Abstract

The invention discloses a wireless charging intelligent regulation and control method and system, and relates to the technical field of wireless charging regulation and control, and the method specifically comprises the following steps: obtaining the charging demand information of each robot in real time, and generating a task priority coefficient and an electric quantity demand index of each robot; and constructing a wireless charging power distribution evaluation model for the generated task priority coefficient and the electric quantity demand index of each robot, generating a priority distribution coefficient of each robot, and evaluating the wireless charging demand level of each robot. Dividing each robot into a high-demand robot, a normal-demand robot and a low-demand robot according to an evaluation result; and according to the division result of each robot, corresponding power distribution strategies are adopted for the robots with different wireless charging demand levels. According to the method, the problems of wireless charging demand difference identification and dynamic allocation of the robot in the intelligent warehousing system are solved, and an efficient and accurate charging resource optimization configuration effect is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of wireless charging control, and in particular to a wireless charging intelligent control method and system. Background Art

[0002] Wireless charging is a technology that transfers energy through electromagnetic fields to charge devices. It eliminates the tediousness of plugging and unplugging cables in traditional charging methods, making the charging process more convenient. The necessity of intelligent regulation of wireless charging is mainly reflected in improving charging efficiency, extending device battery life, and ensuring safety. Through the intelligent regulation system, the charging status, environmental conditions, and user needs of the device can be monitored in real time, the charging power and frequency can be dynamically adjusted, and the charging process can be optimized, thereby reducing energy loss, avoiding overheating, and effectively preventing battery damage caused by improper charging. In addition, intelligent regulation can also intelligently switch different charging modes according to changes in device type and charging environment, further improving user experience. Therefore, the development of efficient wireless charging regulation methods can not only meet the growing charging needs, but also promote the widespread application of wireless charging technology.

[0003] Existing wireless charging control technology mainly achieves precise control of the charging process through feedback control mechanisms and intelligent algorithms. In this process, energy is transmitted between the charging base station and the receiving device through electromagnetic coupling. The system first uses sensors to monitor the charging status (such as battery power, temperature, etc.) and environmental factors (such as location, obstacles, etc.) of the receiving device in real time. Based on this data, the intelligent control algorithm calculates the optimal charging power and frequency to ensure maximum charging efficiency while avoiding the risk of overheating or overcharging. Specifically, the system may use advanced algorithms such as PID control, fuzzy control or adaptive control to continuously adjust the transmission power and frequency based on real-time feedback. In addition, some systems also integrate intelligent learning functions, which can optimize the control strategy through historical charging data and further improve the intelligence level of the charging process. Therefore, this comprehensive control technology not only improves the safety and efficiency of charging, but also provides users with a more convenient user experience.

[0004] The prior art has the following deficiencies:

[0005] In the intelligent warehousing system, when the mobile robot returns to the wireless charging station for charging after completing the task, especially when the task volume is large or the driving distance is long, the power demand of some robots when returning to the station increases sharply, and the battery's ability to accept charging in a short time may be limited, so it is necessary to dynamically adjust the wireless charging power to ensure the continuous execution of the task. However, the existing wireless charging control system fails to effectively identify the specific power demand and charging acceptance capacity of different robots when returning to the station, resulting in the failure to prioritize the adjustment of wireless charging power distribution according to demand when multiple robots are connected to the charging station at the same time, affecting the rapid charging of high-demand robots. This situation mainly occurs because the system fails to collect key data such as robot task status, remaining power, charging acceptance capacity, etc. in real time, and thus cannot dynamically adjust the wireless charging power according to the needs of each robot. Ultimately, this problem leads to a slowdown in wireless charging speed, affecting the continuity of warehousing tasks. At the same time, due to low charging efficiency, some robots need to frequently return to the station for charging, increasing the system's operation and maintenance pressure and having an adverse impact on the overall scheduling of the warehousing system.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The purpose of the present invention is to provide a wireless charging intelligent control method and system to solve the problems in the above-mentioned background technology.

[0008] In order to achieve the above object, the present invention provides the following technical solution: a wireless charging intelligent control method, specifically comprising the following steps:

[0009] Detect the return time of each robot after completing the task in real time, and obtain the access information of each robot in real time when each robot connects to the wireless charging station. After acquisition, analyze it and establish a wireless charging power monitoring and dynamic control framework for all connected robots.

[0010] Acquire the charging demand information of each robot in real time, analyze it after acquisition, and generate the task priority coefficient and power demand index of each robot respectively;

[0011] A wireless charging power allocation evaluation model is constructed based on the generated task priority coefficients and power demand indexes of each robot, and a priority allocation coefficient of each robot is generated. After the generation, the wireless charging demand level of each robot is evaluated, and each robot is divided into a high-demand robot, a normal-demand robot, and a low-demand robot according to the evaluation results;

[0012] According to the classification results of each robot, corresponding power allocation strategies are adopted for robots with different wireless charging demand levels;

[0013] Continuously monitor the power changes, charging acceptance and charging progress of each robot, dynamically adjust the wireless charging power allocation standard of each robot, regularly update the power allocation evaluation model, and optimize the configuration strategy of power resources of wireless charging stations.

[0014] Preferably, the charging demand information of each robot is acquired in real time, and analyzed after acquisition to generate the task priority coefficient and power demand index of each robot respectively, which specifically includes the following steps:

[0015] Obtain the charging demand information of each robot in real time and perform preprocessing after acquisition;

[0016] Extracting task return information and power demand information from the pre-processed charging demand information of each robot;

[0017] The task return information and power demand information in the extracted charging demand information of each robot are analyzed to generate the task priority coefficient and power demand index of each robot respectively.

[0018] Preferably, the logic for obtaining the task priority coefficient of each robot is as follows:

[0019] The task return information in the preprocessed charging demand information of each robot is extracted, including the distance from the task location to the current wireless charging station, the time spent by each robot on the current task, and the average time for each robot to complete the task in the past period of time, and they are marked as D m 、TW m and TA m , D m represents the distance from the mth robot to the current wireless charging station, TW m Indicates the time spent on the current task, TA m represents the average time to complete the task in the past period of time, m = 1, 2, 3, ..., g, g is a positive integer;

[0020] Calculate the task priority coefficient of each robot. The specific calculation formula is as follows:

[0021]

[0022] Where, TPC m is the task priority coefficient of the mth robot.

[0023] Preferably, the logic for obtaining the power demand index of each robot is as follows:

[0024] The power demand information of each robot in the preprocessed charging demand information is extracted, including the remaining percentage of each robot when it is connected to the current wireless charging station, the estimated total power required for each robot to complete the current task, and the average speed of each robot returning to the wireless charging station, and they are calibrated as E m , H m and VP m , E m It represents the remaining percentage of power of the mth robot when it is connected to the current wireless charging station, H m VP represents the estimated total power required by the mth robot to complete the current task. m represents the average speed of the mth robot returning to the wireless charging station, m = 1, 2, 3, ..., g, where g is a positive integer;

[0025] Calculate the power demand index of each robot. The specific calculation formula is as follows:

[0026]

[0027] Where PDI m is the power demand index of the mth robot.

[0028] Preferably, a wireless charging power allocation evaluation model is constructed based on the generated task priority coefficients and power demand indexes of each robot to generate a priority allocation coefficient for each robot, specifically including the following steps:

[0029] Collect the task priority coefficients, power demand indexes and corresponding priority allocation coefficients of several robots generated in the past period of time, and calibrate them as and x represents the task priority coefficients, power demand indexes and corresponding priority allocation coefficient numbers of several robots generated in the past period of time, x=3, 4, 5, ..., d, d is a positive integer, and the data collected in the past period of time is formed into a historical data set;

[0030] The multivariate regression model is selected as the wireless charging power allocation evaluation model, and is trained through historical data sets to determine the value of the regression coefficient according to the formula:

[0031]

[0032] Where β0, β1 and β2 are regression coefficients;

[0033] By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized, and finally the values ​​of the regression coefficients β0, β1 and β2 are determined;

[0034] Using the finalized regression coefficient, the constructed wireless charging power allocation evaluation model is input with the task priority coefficient TPC of each robot generated in real time. m and Power Demand Index PDI m , generate the priority allocation coefficient PAC of each robot in real time m .

[0035] Preferably, the priority allocation coefficient PAC of each robot is generated m and the preset priority allocation coefficient threshold interval [PAC min , PAC max ] to compare, evaluate the wireless charging demand level of each robot according to the comparison results, and divide each robot into high-demand robot, normal-demand robot and low-demand robot according to the evaluation results. The specific comparison analysis and division are as follows:

[0036] If PAC m <PAC min , the wireless charging requirement level of the robot is a low requirement level, then the robot is classified as a low-requirement robot;

[0037] If PAC min ≤PAC m ≤PAC max , the wireless charging requirement level of the robot is the normal requirement level, then the robot is classified as a normal requirement robot;

[0038] If PAC m >PAC max , the wireless charging requirement level of the robot is a high-demand level, and the robot is classified as a high-demand robot.

[0039] Preferably, according to the division results of each robot, a corresponding power allocation strategy is adopted for robots with different wireless charging demand levels, specifically:

[0040] For low-demand robots with low wireless charging demand levels, the allocation strategy adopted is to reduce the current charging power, prioritize resources to high-demand robots, and only perform routine monitoring;

[0041] For normal demand robots whose wireless charging demand level is normal demand level, the allocation strategy adopted is to maintain the current charging power to ensure that it obtains sufficient power within the time required by the task, and to conduct real-time monitoring to prevent changes in demand;

[0042] For high-demand robots with high wireless charging demand levels, the allocation strategy adopted is to prioritize increasing the charging power to ensure that its charging speed meets the needs of urgent tasks, and to strengthen monitoring and dynamically adjust the power to ensure maximum charging efficiency and prevent mission interruptions.

[0043] Preferably, a wireless charging intelligent control system comprises an access monitoring and control module, a charging demand analysis module, a power allocation evaluation model construction module, a charging power allocation strategy module and a dynamic monitoring and evaluation model update module;

[0044] The access monitoring and control module detects the return time of each robot after completing the task in real time, obtains the access information of each robot in real time when each robot accesses the wireless charging station, and analyzes it after acquisition to establish a wireless charging power monitoring and dynamic control framework for all connected robots;

[0045] The charging demand analysis module obtains the charging demand information of each robot in real time, analyzes it after acquisition, and generates the task priority coefficient and power demand index of each robot respectively;

[0046] The power allocation evaluation model building module builds a wireless charging power allocation evaluation model based on the generated task priority coefficients and power demand indexes of each robot, generates the priority allocation coefficients of each robot, analyzes them after generation, evaluates the wireless charging demand level of each robot, and divides each robot into high-demand robots, normal-demand robots, and low-demand robots according to the evaluation results;

[0047] The charging power allocation strategy module adopts corresponding power allocation strategies for robots with different wireless charging demand levels according to the classification results of each robot;

[0048] The dynamic monitoring and evaluation model update module continuously monitors the power changes, charging acceptance capacity and charging progress of each robot, dynamically adjusts the wireless charging power allocation standard of each robot, regularly updates the power allocation evaluation model, and optimizes the configuration strategy of the power resources of the wireless charging station.

[0049] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0050] 1. The present invention collects and analyzes the task priority coefficient and power demand index of each robot in real time, so that the system can dynamically identify the actual power demand and charging acceptance capacity of each robot on the return trip. This real-time monitoring and quantitative analysis method directly solves the problem of the inability to effectively identify demand differences in the prior art, ensures the system's high-precision assessment of the charging needs of different robots, and enables high-demand robots to obtain charging resources first on the return trip, thereby ensuring the continuous execution of tasks.

[0051] 2. The application of the multivariate regression model proposed in the present invention in power allocation greatly enhances the intelligent control capability of the system. Through historical data training and dynamic generation of priority allocation coefficients, the system can automatically allocate power according to the real-time needs of each robot to ensure the rational allocation of resources. The use of this model optimizes the power allocation efficiency of the charging station, so that when multiple robots are connected at the same time, charging resources can be allocated according to the demand level, thereby effectively alleviating the problem of uneven distribution of traditional systems under high load conditions, improving the overall charging efficiency, and reducing the frequent return to the station for charging.

[0052] 3. The present invention not only makes charging management flexible and real-time, but also improves the scalability and adaptability of the system. Each module (including access monitoring, demand analysis, power allocation strategy, etc.) can work together in the complete process of monitoring, analysis, adjustment and optimization to ensure the dynamic optimization of charging resource allocation. This modular design not only simplifies the maintenance and expansion of the system, but also provides solid support for the reliability and efficiency of the system in complex environments, making the scheduling management of the intelligent warehousing system more flexible and efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0054] Figure 1 The present invention is a flowchart of a wireless charging intelligent control method and system.

[0055] Figure 2 The present invention is a module schematic diagram of a wireless charging intelligent control method and system. DETAILED DESCRIPTION

[0056] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0057] The present invention provides Figure 1 A wireless charging intelligent control method is shown, which specifically includes the following steps:

[0058] Detect the return time of each robot after completing the task in real time, and obtain the access information of each robot in real time when each robot connects to the wireless charging station. After acquisition, analyze it and establish a wireless charging power monitoring and dynamic control framework for all connected robots.

[0059] The return time after completing the task can be detected by setting the real-time task status feedback function in the robot task management system. The specific implementation method is: when performing the task, the robot regularly feeds back the task progress, current position and other data to the task management system through wireless communication (such as Wi-Fi, Bluetooth or 4G / 5G network). When the system detects the task completion signal, it immediately records the task end time and starts timing. At the same time, to ensure accuracy and real-time performance, the task completion signal will be sent to the management system immediately after the robot actually completes the last instruction of the task. In this way, the system can accurately know the return time of each robot after completing the task, so as to arrange the next charging control work.

[0060] The specific information of each robot connected to the charging station can be obtained in real time by setting up a sensing device (such as RFID, infrared sensor or laser sensor) and a communication module on the charging station. The specific implementation method is: when the robot is connected to the wireless charging station and enters the charging position, the sensor of the charging station will detect the physical position or tag of the robot, and bind it with the robot ID, access time and other information and transmit it to the control system. At the same time, the robot will also send real-time information such as current power and expected charging demand to the system. The system receives this access information through the communication module, thereby realizing real-time tracking of each robot, ensuring that the system can immediately obtain charging demand and task status data after access.

[0061] The acquired robot access information can be processed and analyzed through data analysis software combined with real-time evaluation algorithms. The specific implementation method is: the system first pre-processes the access information uploaded by each robot (such as task status, power, charging acceptance, etc.), and uses preset algorithms through analysis software (such as analysis modules based on Python or MATLAB) to generate key indicators for these data, such as task priority coefficients and power demand index. Then, the system establishes a power monitoring framework based on the calculation results, and updates the dynamic control parameters in real time, so as to instantly generate a charging priority evaluation when the robot is connected, and establish dynamic power allocation rules based on real-time monitoring. The framework can be dynamically adjusted as the data changes, thereby effectively realizing power monitoring and control of all connected robots.

[0062] This step is essential because it solves the key problem that existing technologies cannot accurately identify and regulate the wireless charging needs of different robots in real time. In a smart warehousing environment, robot tasks and power requirements vary greatly. Especially under high load, some robots need to be charged first to ensure task continuity. By real-time detection of the return time after the task is completed and obtaining robot access information, the system can accurately grasp the charging needs and status of each robot after returning to the station. Furthermore, through data analysis, a wireless charging power monitoring and dynamic control framework is established, which can flexibly allocate power according to the actual needs of the robot, solve the problem of low charging efficiency caused by uneven power distribution, ensure the efficient operation of the warehousing system and reduce operation and maintenance costs. This real-time analysis and dynamic control solution realizes the optimal allocation of resources and is an important guarantee for meeting the needs of smart warehousing systems.

[0063] Acquire the charging demand information of each robot in real time, analyze it after acquisition, and generate the task priority coefficient and power demand index of each robot respectively;

[0064] In this embodiment, the charging demand information of each robot is obtained in real time, and analyzed after being obtained to generate the task priority coefficient and power demand index of each robot respectively, which specifically includes the following steps:

[0065] Obtain the charging demand information of each robot in real time and perform preprocessing after acquisition;

[0066] The charging demand information of each robot can be obtained in real time through wireless communication modules (such as Wi-Fi, 4G / 5G). The specific implementation method is that when the robot is performing a task, it collects information such as return distance, working time, historical average completion time of the task, remaining power, estimated power consumption of the task, and return speed in real time, and automatically uploads it to the central control system in a timing or event-triggered manner. After receiving the data, the system automatically integrates and stores this data to form a complete charging demand information package for the robot, so that the system can accurately grasp the current tasks and power status of each robot at any time, ensuring comprehensive data support before connecting to the charging station.

[0067] The purpose of preprocessing is to ensure the accuracy, consistency and completeness of charging demand information, so as to facilitate the stability of subsequent analysis and calculation. Specific preprocessing includes data formatting, missing data filling and abnormal data detection. Data formatting converts all information into a standard numerical format with unified units and precision; missing data filling avoids calculation interruptions by finding historical averages or using previously collected data; abnormal data detection identifies abnormal values ​​(such as extreme values ​​of speed or power) and marks or replaces them with values ​​within a reasonable range. Preprocessing is automatically completed through the data cleaning module to ensure accurate calculation of subsequent task priority coefficients and power demand indexes, and more reliable system decisions.

[0068] Extracting task return information and power demand information from the pre-processed charging demand information of each robot;

[0069] Extracting the task return information and power demand information from the preprocessed charging demand information can be achieved through data classification and screening algorithms. The specific extraction method is that the system first performs a hierarchical analysis on the preprocessed charging demand information package, and automatically classifies each data field in the information package (such as return distance, working time, historical average completion time of the task, remaining power, estimated power consumption of the task and return speed, etc.) into two categories of "task return information" and "power demand information" according to predefined classification rules. After the classification is completed, the system extracts the data belonging to the task return information (return distance, working time and historical average completion time of the task) and the data belonging to the power demand information (remaining power, estimated power consumption of the task and return speed) through field mapping and label screening, so as to be used to calculate the task priority coefficient and the power demand index respectively, thereby ensuring that the data corresponds to the correct analysis model in subsequent calculations.

[0070] The task return information and power demand information in the extracted charging demand information of each robot are analyzed to generate the task priority coefficient and power demand index of each robot respectively.

[0071] In this embodiment, the logic for obtaining the task priority coefficient of each robot is as follows:

[0072] The task return information in the preprocessed charging demand information of each robot is extracted, including the distance from the task location to the current wireless charging station, the time spent by each robot on the current task, and the average time for each robot to complete the task in the past period of time, and they are marked as D x 、TW m and TA m , D m represents the distance from the mth robot to the current wireless charging station, TW m Indicates the time spent on the current task, TA m represents the average time to complete the task in the past period of time, m = 1, 2, 3, ..., g, g is a positive integer;

[0073] Extracting the task return information from the preprocessed charging demand information of each robot can be achieved through the data parsing and screening module. Specifically, after the system receives the charging demand information package of each robot, it first uses the data parsing module to decompose the information package into various data fields, including attributes such as distance and time. Subsequently, the screening module identifies the data items required for the task return information, such as the distance from the robot's current position to the charging station, the time spent on the current task, and the average time to complete the same task over a period of time. After screening, these data fields are classified and extracted into the variable group of the task return information for subsequent calculation of the task priority coefficient.

[0074] These quantitative data are automatically acquired through the robot's built-in positioning and task management system. Specifically, the distance data is calculated through the robot's built-in GPS or other positioning systems. The system will update the robot's current position coordinates in real time, and calculate the current straight line or path distance through the fixed position coordinates of the charging station. The elapsed time is recorded by the task management system. The robot starts timing when it starts the task. The system automatically calculates the elapsed time of the task based on the difference between the start time of the task and the current time. The average completion time over the past period of time is calculated by the system based on historical task records, and is obtained by averaging the historical completion time of the same task. All of these data are collected, calculated, and updated in real time through the software to ensure that the task return information obtained by the system is accurate and meets real-time requirements.

[0075] Calculate the task priority coefficient of each robot. The specific calculation formula is as follows:

[0076]

[0077] Where, TPC m is the task priority coefficient of the mth robot.

[0078] The task priority coefficient calculation formula comprehensively evaluates the urgency of the robot's task through two parts of calculation. The first part of the formula Used to measure the distance D between the robot and the charging station m Impact on task priority, where TA m It indicates the average time for the robot to complete the same task in the past period of time. m The square root ratio of the average time increases the priority of tasks that are farther away and have shorter average completion times, giving longer-distance tasks a higher urgency in scheduling. The square root operation effectively reduces the impact of the task's average time on the priority, preventing higher average time values ​​from excessively lowering the priority. Part II The time TW consumed by the current task is taken into account m For the average completion time TAm The introduction of the logarithmic function ensures that when the task takes time TW m Approaching or exceeding the average completion time TA m When the time is up, the priority increases significantly, reflecting that the time-consuming task has a higher urgency. At the same time, through the logarithm and constant term +1, the formula prevents the occurrence of zero or negative values, ensuring that the calculation result is reasonable. Therefore, this formula structure can not only dynamically adapt to the different effects of distance and time, but also ensure that the urgent task obtains the scheduling weight of priority charging.

[0079] Task priority coefficient TPC of the mth robot m The size of directly affects the system's assessment of its wireless charging demand level. The larger the task priority coefficient, the higher the urgency and return demand of the robot in the current task, reflecting that the robot needs to quickly replenish its power to maintain the continuity and completion efficiency of the task. Therefore, when evaluating the wireless charging demand level, the system will give priority to robots with higher task priority coefficients and classify them as high-demand levels to ensure that charging resources are allocated to the most urgent tasks first. A relatively low task priority coefficient indicates that the robot's task is less urgent and may be classified as normal demand or low demand level, with a lower priority in charging resource allocation. Through this relationship, the task priority coefficient effectively supports the system's scientific assessment of the charging demand level of each robot and the optimal allocation of resources.

[0080] In this embodiment, the logic for obtaining the power demand index of each robot is as follows:

[0081] The power demand information of each robot in the preprocessed charging demand information is extracted, including the remaining percentage of each robot when it is connected to the current wireless charging station, the estimated total power required for each robot to complete the current task, and the average speed of each robot returning to the wireless charging station, and they are calibrated as E m , H m and VL,E m It represents the remaining percentage of power of the mth robot when it is connected to the current wireless charging station, H m VP represents the estimated total power required by the mth robot to complete the current task. m represents the average speed of the mth robot returning to the wireless charging station, m = 1, 2, 3, ..., g, where g is a positive integer;

[0082] Extracting the power demand information from the preprocessed charging demand information of each robot can be automatically realized through the data parsing and screening module. Specifically, after the system receives the preprocessed charging demand information package, the data parsing module first separates the various data fields in the information package one by one, and then automatically identifies the data items belonging to the power demand information through the tag recognition module. These data items include the remaining percentage of power when the robot is connected to the charging station, the estimated total power required to complete the current task, and the current average speed of returning to the wireless charging station. The system groups and classifies these data items according to the predefined field identification rules, and classifies them into the power demand information variable group for subsequent calculation of the power demand index.

[0083] These quantitative data are collected in real time through the robot's built-in sensors and task management system and uploaded to the central control system. The remaining percentage of power is monitored in real time through the robot's internal battery management system (BMS), and the BMS transmits the remaining percentage data to the system to ensure that the power data in the charging demand information is accurate. The estimated total power required for the task is generated by the task management system based on the nature of the current task and the power consumption data of similar tasks completed in the past, through historical statistics or model prediction, to ensure that the power consumption demand of each task can be accurately estimated. The return speed is measured in real time by the speed sensor or odometer of the robot's motion control system, and the central control system calculates the average speed based on the distance from the task location to the charging station and the estimated return time. All of these data are automatically collected and calculated by software modules to ensure the accuracy and real-time nature of the data, which is convenient for subsequent control decisions.

[0084] Calculate the power demand index of each robot. The specific calculation formula is as follows:

[0085]

[0086] Where PDI m is the power demand index of the mth robot.

[0087] The calculation formula of the power demand index evaluates the current power urgency of the robot through two calculations. Used to measure the total power consumption of the task H m and remaining power E m The nonlinear relationship amplifies the urgency of low battery conditions through the inverse relationship of the remaining power. The formula puts the product of the difference between power consumption and remaining power in the numerator, so that the lower the remaining power and the greater the power consumption of the task, the higher the urgency. mLocated in the denominator, it means that when the return speed is slow, the urgency increases further. The design of this fractional part ensures that when the remaining power is low and the power demand is high, the power demand index is significantly increased to give priority to charging robots with insufficient power. The ratio of task power consumption to remaining power is further considered, and a logarithmic function is used to smooth the growth rate while avoiding infinite growth. Through this logarithmic term, the formula can enhance the urgency when the remaining power is extremely low and the task power consumption is high, so that the charging priority of the robot with low power is improved. The design of this calculation method combines the influence of task power demand, current power status and return speed, ensures the rationality and sensitivity of the power demand index, and helps the system identify and prioritize the charging needs of robots with high urgency.

[0088] The power demand index PDI of the mth robot m The size of is directly related to the system's assessment of its wireless charging demand level. The larger the power demand index, the lower the current remaining power of the robot, the higher the task power demand and the slower the return speed, reflecting the higher urgency of its charging demand. When evaluating the wireless charging demand level, the system will give priority to robots with a higher power demand index and classify them as high demand levels, thereby ensuring that charging resources are allocated first to robots with urgent power demand. On the contrary, a low power demand index indicates that the robot has relatively sufficient power or a small power demand, so it may be classified as a normal or low demand level, and its priority in resource allocation is correspondingly lower. Through this relationship, the power demand index effectively supports the system's accurate assessment of the robot's charging needs and the rational allocation of resources.

[0089] A wireless charging power allocation evaluation model is constructed based on the generated task priority coefficients and power demand indexes of each robot, and a priority allocation coefficient of each robot is generated. After the generation, the wireless charging demand level of each robot is evaluated, and each robot is divided into a high-demand robot, a normal-demand robot, and a low-demand robot according to the evaluation results;

[0090] In this embodiment, a wireless charging power allocation evaluation model is constructed based on the generated task priority coefficients and power demand indexes of each robot to generate the priority allocation coefficients of each robot, specifically including the following steps:

[0091] Collect the task priority coefficients, power demand indexes and corresponding priority allocation coefficients of several robots generated in the past period of time, and calibrate them as and x represents the task priority coefficients, power demand indexes and corresponding priority allocation coefficient numbers of several robots generated in the past period of time, x=3, 4, 5, ..., d, d is a positive integer, and the data collected in the past period of time is formed into a historical data set;

[0092] The collection of task priority coefficients, power demand indexes, and corresponding priority allocation coefficients of each robot generated in the past period of time can be automatically realized through the data recording and storage module. Specifically, after each calculation of the task priority coefficient, power demand index, and priority allocation coefficient, the system automatically adds a timestamp to these data items and stores them in the system's database. The database can archive data periodically according to a preset time window (such as the past 30 days or 100 calculation results) to form a historical data set. In order to facilitate the training and analysis of subsequent models, the system will automatically summarize these historical records into a specified data table or file through regular tasks or event triggers to ensure that the task priority coefficients, power demand indexes, and priority allocation coefficients generated by all robots within the specified time period are fully collected and backed up. This not only ensures the accuracy of the data, but also provides a reliable data basis for subsequent analysis.

[0093] The range of x is limited to positive integers greater than or equal to 3 to ensure that there are at least three data points to form a system of equations to calculate the three regression coefficients (β0, β1, and β2) in the target equation. If there is only one equation and three unknown regression coefficients need to be determined, then at least three equations are required to form a solvable system of equations to accurately calculate the value of each regression coefficient. In addition, limiting x ≥ 3 is also statistically significant, which can provide basic data support for the regression model, improve fitting accuracy, and avoid model overfitting. A larger data set can further reduce the impact of a single data point on the model, making the estimation of the regression coefficient more stable and reliable, thereby improving the prediction accuracy of the model. Therefore, limiting the value of x to a positive integer greater than or equal to 3 not only meets the mathematical solution requirements, but also helps to improve the robustness of the model.

[0094] The multivariate regression model is selected as the wireless charging power allocation evaluation model, and is trained through historical data sets to determine the value of the regression coefficient according to the formula:

[0095]

[0096] Where β0, β1 and β2 are regression coefficients;

[0097] The multivariate regression model is a statistical method used to analyze the linear relationship between multiple independent variables and dependent variables. It constructs a multivariate equation, uses historical data sets for training, determines the weight of each variable on the dependent variable, and then predicts the value of the dependent variable under new data. In this case, the multivariate regression model is selected as the wireless charging power allocation evaluation model because it can associate the two independent variables of task priority coefficient and power demand index with the dependent variable of priority allocation coefficient, helping the system to automatically evaluate the charging priority according to the real-time tasks and power demand. By training the model with historical data sets, the values ​​of the three regression coefficients can be determined: β0 is a constant term, which indicates the basic value of the priority allocation coefficient when the task priority coefficient and power demand index are zero; β1 is the regression coefficient of the task priority coefficient, which reflects the degree of influence of the task urgency on the priority allocation coefficient; β2 is the regression coefficient of the power demand index, which indicates the relative importance of power demand to priority allocation. By optimizing these three regression coefficients, the model can accurately balance the weights of tasks and power demand in charging allocation decisions, making the allocation of charging resources more scientific and reasonable.

[0098] By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized, and finally the values ​​of the regression coefficients β0, β1 and β2 are determined;

[0099] The purpose of optimizing the regression coefficient by minimizing the error between the predicted value and the actual value is to improve the prediction accuracy of the multivariate regression model for the priority allocation coefficient, so that it can more accurately reflect the actual impact of the task priority coefficient and the power demand index on the charging demand. This optimization process is achieved through the least squares method, that is, when training the model, the system calculates the difference (i.e., error) between the predicted priority allocation coefficient and the historical actual allocation value, and gradually adjusts the values ​​of the regression coefficients (β0, β1, and β2) to minimize the sum of the squares of these errors. Specifically, the system will iteratively calculate based on a large amount of historical data to find a set of optimal regression coefficients so that the predicted priority allocation coefficient is closest to the actual observed value. This method can effectively reduce the deviation of the model and improve the generalization ability of new data, thereby ensuring that in practical applications, the priority allocation coefficients of each robot can accurately guide the reasonable allocation of charging resources.

[0100] Using the finalized regression coefficient, the constructed wireless charging power allocation evaluation model is input with the task priority coefficient TPC of each robot generated in real time. m and Power Demand Index PDI m , generate the priority allocation coefficient PAC of each robot in real time m .

[0101] In this embodiment, the priority allocation coefficient PAC of each robot is generated mand the preset priority allocation coefficient threshold interval [PAC min , PAC max ] to compare, evaluate the wireless charging demand level of each robot according to the comparison results, and divide each robot into high-demand robot, normal-demand robot and low-demand robot according to the evaluation results. The specific comparison analysis and division are as follows:

[0102] If PAC m <PAC min , the wireless charging requirement level of the robot is a low requirement level, then the robot is classified as a low-requirement robot;

[0103] This situation means that the robot's mission urgency and power demand are relatively low, so the need for charging resources is not urgent. Since its mission progress and power status are relatively stable, the system can temporarily delay its charging arrangement and prioritize charging resources for robots with higher demand. Such an allocation strategy effectively avoids resource waste, ensures efficient use of charging station resources, and reduces the pressure of charging queues, which has a positive impact on the overall operation of the system.

[0104] If PAC min ≤PAC m ≤PAC max , the wireless charging requirement level of the robot is the normal requirement level, then the robot is classified as a normal requirement robot;

[0105] This situation indicates that the robot's task priority coefficient and power demand index are at an average level, and its charging demand is at a normal level. In this case, the system can arrange charging for it according to the standard process without special priority or delay. Marking the robot as normal demand will help the system to reasonably regulate the overall charging resources while meeting its charging needs, ensuring that the robot can replenish its power on time under regular task requirements without affecting task continuity.

[0106] If PAC m >PAC max , the wireless charging requirement level of the robot is a high-demand level, and the robot is classified as a high-demand robot.

[0107] This situation indicates that the robot's current mission urgency and power demand are very high, and the charging demand is urgent. After detecting this situation, the system will classify the robot as a high-demand level and prioritize the allocation of charging resources to ensure that its power can be replenished quickly to avoid mission interruptions due to insufficient power. This priority charging strategy can not only ensure the mission continuity of high-demand robots, but also maintain the efficiency and stability of the overall operation of the intelligent warehousing system, and has a direct effect on improving the scheduling effect of the system.

[0108] The preset threshold interval of the priority allocation coefficient can be automatically determined through data analysis and statistical models, and is usually adaptively learned and optimized by the system based on historical data. The specific implementation method is that the system first collects the historical data of the priority allocation coefficient generated by each robot over a period of time to form a data sample set. Then, through the data analysis module, the system performs statistical analysis on these samples and calculates the distribution characteristics of the priority allocation coefficient, such as the mean, standard deviation, percentile, etc. Based on these statistical indicators, the system can set a reasonable interval value, such as [PAC min , PAC max ] is defined as a percentile range in the data set (such as the 25% to 75% percentile) or a range based on the mean plus or minus multiple standard deviations. This method enables the priority allocation coefficient threshold interval to dynamically adapt to different scenarios and needs, and reflects the charging demand distribution of the system under normal conditions through automatic learning and statistical optimization, ensuring the rationality and effectiveness of resource allocation.

[0109] According to the classification results of each robot, corresponding power allocation strategies are adopted for robots with different wireless charging demand levels;

[0110] In this embodiment, according to the classification results of each robot, corresponding power allocation strategies are adopted for robots with different wireless charging demand levels, specifically:

[0111] For low-demand robots with low wireless charging demand levels, the allocation strategy adopted is to reduce the current charging power, prioritize resources to high-demand robots, and only perform routine monitoring;

[0112] For the allocation strategy of low-demand robots, the system can automatically reduce the charging power setting of the robot through the scheduling algorithm and adjust the charging power to a low-power gear. The specific implementation method is that the system first adjusts the charging current and voltage through the charging control module and sets it to the predetermined low-power parameters. At the same time, the system's resource management module will give priority to allocating the remaining charging power to robots with higher demand to ensure optimal resource allocation. In this case, the low-demand robot only requires basic power maintenance, so real-time monitoring is not required. It is only necessary to set regular data feedback to confirm whether the power change is within the expected range. The purpose of this strategy is to give priority to the charging needs of high-demand robots and optimize the overall power allocation efficiency without affecting the normal operation of low-demand robots.

[0113] For normal demand robots whose wireless charging demand level is normal demand level, the allocation strategy adopted is to maintain the current charging power to ensure that it obtains sufficient power within the time required by the task, and to conduct real-time monitoring to prevent changes in demand;

[0114] For the allocation strategy of robots with normal demand, the system can maintain the current charging power setting through the charging management module without making additional adjustments to the current or voltage parameters. The specific implementation method is that the system regularly checks the charging progress and task requirements of robots with normal demand to maintain a stable power output. In addition, the system collects the robot's power and task data in real time through the monitoring module, and uses the conditional judgment algorithm to detect whether there is a change in demand, such as accelerated power consumption or increased task urgency, so as to adjust the charging power in time. The purpose of this strategy is to ensure that robots with normal demand can complete their tasks smoothly and are not affected by insufficient power. At the same time, when the system load changes, it can be flexibly adjusted according to the actual situation to avoid task delays or reduced efficiency due to changes in demand.

[0115] For high-demand robots with high wireless charging demand levels, the allocation strategy adopted is to prioritize increasing the charging power to ensure that its charging speed meets the needs of urgent tasks, and to strengthen monitoring and dynamically adjust the power to ensure maximum charging efficiency and prevent mission interruptions.

[0116] For high-demand robots, the system adopts a priority allocation and dynamic control method, and increases the charging power through the charging management module, that is, increases the charging current and voltage to quickly replenish the power. The specific implementation method is that the system adjusts the charging parameters of the high-demand robot to a high-power gear, and continuously monitors its charging progress and task status through real-time data feedback. The system adopts a dynamic control algorithm to adjust the charging power in real time according to the power sufficiency and task progress, ensuring that the power is gradually reduced after the power is quickly restored to avoid battery overload or overtemperature. The purpose of this strategy is to ensure that the high-demand robot can quickly restore power in emergency tasks to maintain mission continuity. At the same time, through real-time monitoring and dynamic adjustment, the charging efficiency is maximized to ensure that the high-demand robot successfully completes the emergency task.

[0117] Continuously monitor the power changes, charging acceptance and charging progress of each robot, dynamically adjust the wireless charging power allocation standard of each robot, regularly update the power allocation evaluation model, and optimize the configuration strategy of power resources of wireless charging stations.

[0118] The system continuously monitors the power changes, charging acceptance (such as current acceptance rate) and charging progress of each robot through the real-time data acquisition module. The specific implementation method is that the battery management system (BMS) inside the robot regularly sends the current power, instantaneous charging current, voltage and other information to the central control system. The data acquisition module receives and records this data, and performs trend analysis through the monitoring module to identify changes in charging demand in real time. This continuous monitoring ensures that the system maintains full control of the power status and charging status of each robot, and promptly identifies high-demand situations, thereby responding quickly and preventing task delays.

[0119] Based on real-time monitoring data, the system flexibly adjusts the charging power of each robot through a dynamic power control module. Specifically, the system uses a charging control algorithm to adjust the charging power according to the robot's current charging acceptance and power demand. For example, if a robot shows high demand or its charging acceptance increases, the system will increase its charging power; on the contrary, if a robot is close to full charge, the power will be reduced. This dynamic adjustment ensures that the charging speed of each robot meets the task requirements, prevents power waste and optimizes resource utilization.

[0120] In order to maintain the accuracy of the evaluation model, the system regularly uses historical data to retrain the power allocation model. The specific implementation method is that the system collects task priority coefficients, power demand indexes, and charging acceptance data over a period of time to form a new data set, and uses this data to retrain the multivariate regression model, optimize the regression coefficients, and update the model. Through regular updates, the model can reflect the latest working status of the system and the demand characteristics of the robot, so that the power allocation strategy always maintains adaptability and accuracy.

[0121] Through real-time monitoring, dynamic regulation and model updating, the system can optimize the power resource configuration of the wireless charging station. This process ensures that the allocation of charging resources matches the actual needs of the robot, avoids power waste and charging waiting time, and improves the charging efficiency and the overall operating efficiency of the system. This not only ensures the continuity of the robot's mission and reduces the risk of mission interruption, but also improves the working efficiency of the charging station and supports the efficient operation of the intelligent warehousing system.

[0122] like Figure 2 A wireless charging intelligent control system shown includes an access monitoring and control module, a charging demand analysis module, a power allocation evaluation model construction module, a charging power allocation strategy module, and a dynamic monitoring and evaluation model update module;

[0123] The access monitoring and control module detects the return time of each robot after completing the task in real time, obtains the access information of each robot in real time when each robot accesses the wireless charging station, and analyzes it after acquisition to establish a wireless charging power monitoring and dynamic control framework for all connected robots;

[0124] The charging demand analysis module obtains the charging demand information of each robot in real time, analyzes it after acquisition, and generates the task priority coefficient and power demand index of each robot respectively;

[0125] The power allocation evaluation model building module builds a wireless charging power allocation evaluation model based on the generated task priority coefficients and power demand indexes of each robot, generates the priority allocation coefficients of each robot, analyzes them after generation, evaluates the wireless charging demand level of each robot, and divides each robot into high-demand robots, normal-demand robots, and low-demand robots according to the evaluation results;

[0126] The charging power allocation strategy module adopts corresponding power allocation strategies for robots with different wireless charging demand levels according to the classification results of each robot;

[0127] The dynamic monitoring and evaluation model update module continuously monitors the power changes, charging acceptance capacity and charging progress of each robot, dynamically adjusts the wireless charging power allocation standard of each robot, regularly updates the power allocation evaluation model, and optimizes the configuration strategy of the power resources of the wireless charging station.

[0128] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0129] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center containing one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0130] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0131] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0132] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0133] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0134] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0135] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A wireless charging intelligent control method, characterized in that: The specific steps include: Detect the return time of each robot after completing the task in real time, and obtain the access information of each robot in real time when each robot connects to the wireless charging station. After acquisition, analyze it and establish a wireless charging power monitoring and dynamic control framework for all connected robots. Acquire the charging demand information of each robot in real time, analyze it after acquisition, and generate the task priority coefficient and power demand index of each robot respectively; A wireless charging power allocation evaluation model is constructed based on the generated task priority coefficients and power demand indexes of each robot, and a priority allocation coefficient of each robot is generated. After the generation, the wireless charging demand level of each robot is evaluated, and each robot is divided into a high-demand robot, a normal-demand robot, and a low-demand robot according to the evaluation results; According to the classification results of each robot, corresponding power allocation strategies are adopted for robots with different wireless charging demand levels; Continuously monitor the power changes, charging acceptance and charging progress of each robot, dynamically adjust the wireless charging power allocation standard of each robot, regularly update the power allocation evaluation model, and optimize the configuration strategy of power resources of wireless charging stations.

2. A wireless charging intelligent control method according to claim 1, characterized in that: The charging demand information of each robot is obtained in real time, and analyzed after acquisition to generate the task priority coefficient and power demand index of each robot respectively, which specifically includes the following steps: Obtain the charging demand information of each robot in real time and perform preprocessing after acquisition; Extracting task return information and power demand information from the pre-processed charging demand information of each robot; The task return information and power demand information in the extracted charging demand information of each robot are analyzed to generate the task priority coefficient and power demand index of each robot respectively.

3. A wireless charging intelligent control method according to claim 2, characterized in that: The logic for obtaining the task priority coefficients of each robot is as follows: The task return information in the preprocessed charging demand information of each robot is extracted, including the distance from the task location to the current wireless charging station, the time spent by each robot on the current task, and the average time for each robot to complete the task in the past period of time, and they are marked as D m 、TW m and TA m , D m represents the distance from the mth robot to the current wireless charging station, TW m Indicates the time spent on the current task, TA m represents the average time to complete the task in the past period of time, m = 1, 2, 3, ..., g, g is a positive integer; Calculate the task priority coefficient of each robot. The specific calculation formula is as follows: Where, TPC m is the task priority coefficient of the mth robot.

4. A wireless charging intelligent control method according to claim 3, characterized in that: The logic for obtaining the power demand index of each robot is as follows: The power demand information of each robot in the preprocessed charging demand information is extracted, including the remaining percentage of each robot when it is connected to the current wireless charging station, the estimated total power required for each robot to complete the current task, and the average speed of each robot returning to the wireless charging station, and they are calibrated as E m , H m and VP m , E m It represents the remaining percentage of power of the mth robot when it is connected to the current wireless charging station, H m VP represents the estimated total power required by the mth robot to complete the current task. m represents the average speed of the mth robot returning to the wireless charging station, m = 1, 2, 3, ..., g, where g is a positive integer; Calculate the power demand index of each robot. The specific calculation formula is as follows: Where PDI m is the power demand index of the mth robot.

5. A wireless charging intelligent control method according to claim 4, characterized in that: A wireless charging power allocation evaluation model is constructed based on the generated task priority coefficients and power demand indexes of each robot to generate the priority allocation coefficients of each robot, specifically including the following steps: Collect the task priority coefficients, power demand indexes and corresponding priority allocation coefficients of several robots generated in the past period of time, and calibrate them as and x represents the task priority coefficients, power demand indexes and corresponding priority allocation coefficient numbers of several robots generated in the past period of time, x=3, 4, 5, ..., d, d is a positive integer, and the data collected in the past period of time is formed into a historical data set; The multivariate regression model is selected as the wireless charging power allocation evaluation model, and trained through the historical data set to determine the value of the regression coefficient according to the formula: Where β0, β1 and β2 are regression coefficients; By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized, and finally the values ​​of the regression coefficients β0, β1 and β2 are determined; Using the finalized regression coefficient, the constructed wireless charging power allocation evaluation model is input with the task priority coefficient TPC of each robot generated in real time. m and Power Demand Index PDI m , generate the priority allocation coefficient PAC of each robot in real time m .

6. A wireless charging intelligent control method according to claim 5, characterized in that: The priority allocation coefficient PAC of each robot generated m and the preset priority allocation coefficient threshold interval [PAC min , PAC max ] to compare, evaluate the wireless charging demand level of each robot according to the comparison results, and divide each robot into high-demand robot, normal-demand robot and low-demand robot according to the evaluation results. The specific comparison analysis and division are as follows: If PAC m <PAC min , the wireless charging requirement level of the robot is a low requirement level, then the robot is classified as a low-requirement robot; If PAC min ≤PAC m ≤PAC max , the wireless charging requirement level of the robot is the normal requirement level, then the robot is classified as a normal requirement robot; If PAC m >PAC max , the wireless charging requirement level of the robot is a high-demand level, and the robot is classified as a high-demand robot.

7. A wireless charging intelligent control method according to claim 6, characterized in that: According to the classification results of each robot, corresponding power allocation strategies are adopted for robots with different wireless charging demand levels, specifically: For low-demand robots with low wireless charging demand levels, the allocation strategy adopted is to reduce the current charging power, prioritize resources to high-demand robots, and only perform routine monitoring; For normal demand robots whose wireless charging demand level is normal demand level, the allocation strategy adopted is to maintain the current charging power to ensure that it obtains sufficient power within the time required by the task, and to conduct real-time monitoring to prevent changes in demand; For high-demand robots with high wireless charging demand levels, the allocation strategy adopted is to prioritize increasing the charging power to ensure that its charging speed meets the needs of urgent tasks, and to strengthen monitoring and dynamically adjust the power to ensure maximum charging efficiency and prevent mission interruptions.

8. A wireless charging intelligent control system, used to implement a wireless charging intelligent control method as described in any one of claims 1 to 7, characterized in that: It includes access monitoring and control module, charging demand analysis module, power allocation evaluation model construction module, charging power allocation strategy module and dynamic monitoring and evaluation model update module; The access monitoring and control module detects the return time of each robot after completing the task in real time, obtains the access information of each robot in real time when each robot accesses the wireless charging station, and analyzes it after acquisition to establish a wireless charging power monitoring and dynamic control framework for all connected robots; The charging demand analysis module obtains the charging demand information of each robot in real time, analyzes it after acquisition, and generates the task priority coefficient and power demand index of each robot respectively; The power allocation evaluation model building module builds a wireless charging power allocation evaluation model based on the generated task priority coefficients and power demand indexes of each robot, generates the priority allocation coefficients of each robot, analyzes them after generation, evaluates the wireless charging demand level of each robot, and divides each robot into high-demand robots, normal-demand robots, and low-demand robots according to the evaluation results; The charging power allocation strategy module adopts corresponding power allocation strategies for robots with different wireless charging demand levels according to the classification results of each robot; The dynamic monitoring and evaluation model update module continuously monitors the power changes, charging acceptance capacity and charging progress of each robot, dynamically adjusts the wireless charging power allocation standard of each robot, regularly updates the power allocation evaluation model, and optimizes the configuration strategy of the power resources of the wireless charging station.

Images