Battery capacity grading capacity correction method and system based on artificial intelligence

Abstract

The invention provides a battery capacity grading capacity correction method and system based on artificial intelligence, and belongs to the technical field of battery management. The artificial intelligence-based battery capacity grading capacity correction method comprises the following steps of: obtaining battery monitoring data and historical monitoring data; the battery monitoring data comprises temperature data and time data; the historical monitoring data comprises historical temperature data and historical time data; calculating estimated correction time of each single battery in the battery pack according to the battery monitoring data and the historical monitoring data; the estimated correction time is associated with the temperature data and the time data; calling task data of each work task in the work task pool; the task data comprises task duration; determining the capacity correction time of the battery pack according to the estimated correction time and the task data; by adopting the scheme, the working efficiency of the battery pack is improved on the premise of not influencing the correction of the battery pack.

Description

Technical Field

[0001] The present application relates to the technical field of battery management, and in particular to a battery capacity correction method and system based on artificial intelligence. Background Art

[0002] Battery capacity test is a conventional test method for testing the capacity of single cells in a battery pack. After the battery pack has been working for a period of time, the temperature and humidity in the working environment, the different currents of each single cell in the battery pack caused by the power supply task, etc. will cause the capacity of each single cell to change, thus affecting the working stability of the battery pack. At this time, it is necessary to perform capacity test on the battery pack and perform capacity correction after the test to make the performance and capacity of each elevator battery in the battery pack converge. Generally speaking, there will be multiple battery packs to perform work tasks in the work task pool, and the capacity test and capacity correction of the battery pack will be performed periodically. However, as the working time increases, the life consumption caused by the aging of each single cell in the battery pack makes the aging state and capacity consumption of each single cell in the initial battery pack state no longer similar, which in turn causes the battery pack to have a greater impact on the completion of the work task. Therefore, it is very important to complete the capacity test and capacity correction of the battery pack while reducing the impact on the work task. Summary of the invention

[0003] The present application provides a battery capacity correction method and system based on artificial intelligence, which can be beneficial.

[0004] In a first aspect, the present application provides a battery capacity correction method based on artificial intelligence. The method comprises: Acquire battery monitoring data and historical monitoring data; the battery monitoring data includes temperature data and time data; the historical monitoring data includes historical temperature data and historical time data; Calculating an estimated correction time for each single battery in the battery pack according to the battery monitoring data and the historical monitoring data; the estimated correction time is associated with the temperature data and the time data; Retrieving task data of each work task in the work task pool; the task data includes task duration; The capacity correction time of the battery pack is determined according to the estimated correction time and the task data.

[0005] Further, determining the capacity correction time of the battery pack according to the estimated correction time and the task data includes: Determine a task completion node for each work task according to the task data; the task completion node is the time node when the work task is completed; Determine the normal working time of the battery pack according to the estimated correction time; the normal working time is the time when the battery pack meets the working condition of at least one working task; the working condition is that the number of normal single cells in the battery pack is not less than the preset number of batteries required for the working task; the normal single cell is a single cell with an estimated correction time before the task completion node; Determine a plurality of task allocation schemes based on the task data and the normal working time; the task allocation scheme is to select at least one work task from the work task pool to the battery pack; Based on the preset task screening conditions, multiple task allocation schemes are screened and integrated to obtain a target task scheme group; the target task scheme group includes multiple target task schemes; the target task scheme is a task allocation scheme after being screened by the preset task screening conditions; Calculating the cost performance data of each target task solution in the target task solution group, and determining a final task solution based on the cost performance data; the final task solution is the target task solution with the highest cost performance data; The capacity correction time of the battery pack is determined according to the final mission plan.

[0006] Furthermore, the screening and integration of multiple task allocation schemes based on the preset task screening conditions to obtain a target task scheme group includes: Integrate multiple task allocation schemes to obtain a task allocation scheme group; Determine the continuous working time of the battery pack according to the estimated correction time; the continuous working time is the working time of the battery pack from the current node to the forced correction node; Determine the total working time of each task allocation scheme in the task allocation scheme group; Based on the preset task screening condition, the task allocation schemes whose total working time is not greater than the continuous working time are screened out from the task allocation scheme group and integrated to obtain a first task scheme group; Determine the first number of single cells of each task allocation scheme in the first task scheme group, and determine the second number of single cells of the battery group; the first number of single cells is the number of preset required batteries in the working conditions of the task allocation scheme; the second number of single cells is the number of normal single cells in the battery group when the node is forced to be corrected; Based on a preset task screening condition, task allocation schemes in which the number of the first single battery cells is not greater than the number of the second single battery cells are screened out from the first task scheme group and integrated to obtain a target task scheme group.

[0007] Further, the calculating the cost performance data of each target task solution in the target task solution group, and determining the final task solution based on the cost performance data includes: Determine the number of work tasks for each target task plan and the task submission node for each work task; Calculate the urgency data of each target task solution according to the task submission node and the task duration; Assume that there are n tasks in any target task plan, then the urgency data of the i-th task is , the urgency data of the target task plan is ; The method for calculating the cost performance data of the solution includes: ; In the formula, The cost performance data of the solution is: is the number of work tasks; are respectively a first preset conversion coefficient and a second preset conversion coefficient; are respectively a first preset weight and a second preset weight; The preset urgency weight.

[0008] Further, ; .

[0009] In a second aspect, the present application provides a battery capacity correction system based on artificial intelligence, the system comprising: An acquisition module, used to acquire battery monitoring data and historical monitoring data; the battery monitoring data includes temperature data and time data; the historical monitoring data includes historical temperature data and historical time data; A calculation module, used for calculating an estimated correction time of each single battery in the battery pack according to the battery monitoring data and the historical monitoring data; the estimated correction time is associated with the temperature data and the time data; A calling module, used to call task data of each work task in the work task pool; the task data includes task duration; A determination module is used to determine the capacity correction time of the battery pack according to the estimated correction time and the task data.

[0010] Furthermore, the determination module is further configured to determine the capacity correction time of the battery pack according to the estimated correction time and the task data, including: Determine a task completion node for each work task according to the task data; the task completion node is the time node when the work task is completed; Determine the normal working time of the battery pack according to the estimated correction time; the normal working time is the time when the battery pack meets the working condition of at least one working task; the working condition is that the number of normal single cells in the battery pack is not less than the preset number of batteries required for the working task; the normal single cell is a single cell with an estimated correction time before the task completion node; Determine a plurality of task allocation schemes based on the task data and the normal working time; the task allocation scheme is to select at least one work task from the work task pool to the battery pack; Based on the preset task screening conditions, multiple task allocation schemes are screened and integrated to obtain a target task scheme group; the target task scheme group includes multiple target task schemes; the target task scheme is a task allocation scheme after being screened by the preset task screening conditions; Calculating the cost performance data of each target task solution in the target task solution group, and determining a final task solution based on the cost performance data; the final task solution is the target task solution with the highest cost performance data; The capacity correction time of the battery pack is determined according to the final mission plan.

[0011] Furthermore, the determination module is further configured to screen and integrate multiple task allocation solutions based on the preset task screening conditions to obtain a target task solution group, including: Integrate multiple task allocation schemes to obtain a task allocation scheme group; Determine the continuous working time of the battery pack according to the estimated correction time; the continuous working time is the working time of the battery pack from the current node to the forced correction node; Determine the total working time of each task allocation scheme in the task allocation scheme group; Based on the preset task screening condition, the task allocation schemes whose total working time is not greater than the continuous working time are screened out from the task allocation scheme group and integrated to obtain a first task scheme group; Determine the first number of single cells of each task allocation scheme in the first task scheme group, and determine the second number of single cells of the battery group; the first number of single cells is the number of preset required batteries in the working conditions of the task allocation scheme; the second number of single cells is the number of normal single cells in the battery group when the node is forced to be corrected; Based on a preset task screening condition, task allocation schemes in which the number of the first single battery cells is not greater than the number of the second single battery cells are screened out from the first task scheme group and integrated to obtain a target task scheme group.

[0012] Further, the determination module is further configured to calculate the solution cost performance data of each target task solution in the target task solution group, and determine the final task solution based on the solution cost performance data, including: Determine the number of work tasks for each target task plan and the task submission node for each work task; Calculate the urgency data of each target task solution according to the task submission node and the task duration; Assume that there are n tasks in any target task plan, then the urgency data of the i-th task is , the urgency data of the target task plan is ; The method for calculating the cost performance data of the solution includes: ; In the formula, The cost performance data of the solution is: is the number of work tasks; are respectively a first preset conversion coefficient and a second preset conversion coefficient; are respectively a first preset weight and a second preset weight; The preset urgency weight.

[0013] Furthermore, the determining module is further configured to: ; .

[0014] It should be understood that the contents described in the Summary of the Invention are not intended to limit the key or important features of the embodiments of the present application, nor are they intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein: Figure 1 A flow chart of a method in an embodiment of the present application is shown; Figure 2 A block diagram of a system in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0017] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0018] In the first aspect, the present application provides a battery capacity correction method based on artificial intelligence, referring to Figure 1 The specific steps included in the method are as follows.

[0019] Step S110: Acquire battery monitoring data and historical monitoring data; the battery monitoring data includes temperature data and time data; the historical monitoring data includes historical temperature data and historical time data.

[0020] In an embodiment of the present application, the working environment of the battery pack is fixed, and monitoring equipment such as temperature and humidity sensors are provided in the working environment of the battery pack, and the monitoring and recording of the temperature of the working environment of the battery pack can be realized through monitoring equipment such as temperature and humidity sensors; it can be understood that for each single cell in the battery pack, under the premise that the battery pack itself is not replaced, its position in the battery pack is fixed, and the working environment of the battery pack is also fixed, so the position of each single cell in the working environment is also fixed; therefore, the temperature change of each single cell during operation can be analyzed based on the battery monitoring data and historical monitoring data; it can be understood that the time data here includes the working time of the battery pack, and the working time of the battery pack represents all working time from the last correction to the current node.

[0021] Step S120: Calculate the estimated correction time of each single battery in the battery pack according to the battery monitoring data and the historical monitoring data; the estimated correction time is associated with the temperature data and the time data.

[0022] Calculate the normal working time of each single battery in the battery pack according to the battery monitoring data and the historical monitoring data; obtain the estimated correction time according to the current time node and the normal working time; In the embodiment of the present application, the method for calculating the normal working time includes: ; In the formula, For normal working hours, is the standard duration, is the temperature effect data, For time-influenced data, is the preset temperature weight, is the preset time weight; wherein, the temperature impact data and the time impact data are both time values, and the time impact data is the working time value; the temperature impact data is obtained from the preset temperature impact comparison table; the preset temperature impact comparison table contains the correspondence between the temperature data and the temperature impact data; generally, the preset temperature weight and the preset time weight are both 0.5; it can be understood that the normal working time here refers to the time between the current time node and the estimated correction time that represents the need to correct the battery; the standard time here refers to the time between the current time node and the standard correction time of the battery pack under ideal conditions; the estimated correction time and the standard correction time here both represent a time node.

[0023] It can be understood that in the scheme of the present application, it is assumed that the working state of each single cell in each work task is fixed, that is, based on the historical temperature data, the impact on the life of the single cell under different temperature conditions can be analyzed. The life impact here refers to the remaining working life of the single cell before the next correction, that is, the working time.

[0024] Specifically, the historical correction time of the single cell can be obtained based on the historical correction data; the historical temperature situation of the single cell can be obtained based on the historical temperature data; the total working time of the single cell can be obtained based on the historical correction time and the preset factory time of the single cell; it can be understood that the historical correction time here also represents a time node, and the normal working time corresponding to different historical temperatures under different total working times can be obtained by calculating the time between two adjacent historical correction times, and the normal working time here is the temperature impact data; in the scheme of the present application, in order to facilitate subsequent calculations, the total working time and the historical temperature here are set as multi-segment functions, that is, after obtaining the temperature data and time data, first match which stage the total working time belongs to, and then match the temperature under this stage, find the stage to which the temperature belongs, and then determine the corresponding temperature impact data; for example, the total working time of battery A is 6 months, which belongs to the total working time stage of 5-7 months; then match the temperature, the temperature of battery A is 25 degrees Celsius, which belongs to the temperature stage of 20-35 degrees Celsius, and the corresponding temperature impact data of battery A is 1 month; it can be understood that the above is only an exemplary description.

[0025] Step S130: Retrieve the task data of each work task in the work task pool; the task data includes task duration.

[0026] Step S140: Determine the capacity correction time of the battery pack according to the estimated correction time and the task data.

[0027] In an embodiment of the present application, determining the capacity correction time of the battery pack according to the estimated correction time and the task data specifically includes determining a task completion node for each work task according to the task data; the task completion node is a time node at which the work task is completed; determining the normal working time of the battery pack according to the estimated correction time; the normal working time is the time when the battery pack meets the working conditions of at least one work task; the working condition is that the number of normal single cells in the battery pack is not less than the preset number of batteries required for the work task; the normal single cell is a single cell whose estimated correction time is before the task completion node; based on the task data and the normal Determine multiple task allocation plans during working hours; the task allocation plan is to select at least one work task from the work task pool to the battery pack; based on preset task screening conditions, multiple task allocation plans are screened and integrated to obtain a target task plan group; the target task plan group contains multiple target task plans; the target task plan is the task allocation plan after being screened by the preset task screening conditions; calculate the cost performance data of each target task plan in the target task plan group, and determine the final task plan based on the cost performance data; the final task plan is the target task plan with the highest cost performance data; determine the capacity correction time of the battery pack according to the final task plan.

[0028] It can be understood that the task data includes the duration and end node of the task; the duration indicates how long the battery pack is required to work for the task; and the end node indicates that the task needs to be completed before this node; it should be noted that there are multiple battery packs in the solution of the present application, and the specifications, working environment, volume and other parameters of the battery packs are the same, and all work tasks in the work task pool also match this type of battery pack, so each work task is bound to task data that represents the task information.

[0029] It can be understood that although the work tasks in the work task pool are all executed by the battery pack in the present application, when the single cells in the battery pack need to be corrected, the stability of the battery pack in completing the work tasks will be reduced; and the task data also pre-sets a limit on the number of normal single cells in the battery pack, that is, the working conditions; the working conditions indicate that if the battery pack wants to complete the work task, it must have a specified number of normal single cells to work, and the single cells that have reached the estimated correction time are not normal single cells.

[0030] Among them, based on the preset task screening conditions, screening and integrating multiple task allocation schemes to obtain a target task scheme group specifically includes: integrating multiple task allocation schemes to obtain a task allocation scheme group; determining the continuous working time of the battery group according to the estimated correction time; the continuous working time is the working time of the battery group from the current node to the forced correction node; determining the total working time of each task allocation scheme in the task allocation scheme group; based on the preset task screening conditions, screening out the task allocation schemes whose total working time is not greater than the continuous working time from the task allocation scheme group and integrating them to obtain a first task scheme group; determining the number of first single cells for each task allocation scheme in the first task scheme group, and determining the number of second single cells of the battery group; the number of the first single cells is the number of preset required batteries in the working conditions of the task allocation scheme; the number of the second single cells is the number of normal single cells in the battery group at the forced correction node; based on the preset task screening conditions, screening out the task allocation schemes whose first number of single cells is not greater than the second number of single cells from the first task scheme group and integrating them to obtain a target task scheme group.

[0031] Among them, calculating the cost performance data of each target task solution in the target task solution group, and determining the final task solution based on the cost performance data specifically includes: determining the number of work tasks of each target task solution and the task submission node of each work task; calculating the urgency data of each target task solution according to the task submission node and the task duration; assuming that there are n work tasks in any target task solution, the urgency data of the i-th work task is , the urgency data of the target task plan is ; The method for calculating the cost performance data of the solution includes: ; In the formula, The cost performance data of the solution is: is the number of work tasks; are respectively a first preset conversion coefficient and a second preset conversion coefficient; are respectively a first preset weight and a second preset weight; is a preset urgency weight; and ; .

[0032] It can be understood that the first preset conversion coefficient and the second preset conversion coefficient here are only used as parameters involved in the calculation of balancing in the calculation formula, and are set to ensure that the calculation result is more in line with the actual situation.

[0033] Specifically, in the present application, the method for calculating the urgency data of the work task includes: ; Among them, the remaining submission time is the time between the current time node and the task submission node; All are preset weights.

[0034] By adopting the solution of the present application, a final task solution with the highest cost-performance ratio is finally obtained, so that the battery pack can complete higher-value work tasks without affecting the correction and improve work efficiency.

[0035] In the present application scheme, the conventional battery pack capacity matching method is used to correct the capacitance capacity, that is, during the discharge process, when the total voltage of the battery pack or the voltage of any single cell drops to the discharge protection state voltage, the discharge is stopped; then, the single cells that have not reached the discharge protection state voltage are discharged until the voltages of all single cells are consistent; during the charging process, when the total voltage of the battery pack or the voltage of any single cell rises to the charge protection state voltage, the charging is stopped; then, the single cells that have not reached the charge protection state voltage are charged until the voltages of all single cells are consistent; the capacity of the battery pack can be corrected by using this method.

[0036] It should be noted that the method of the present application is essentially a machine learning model. In the process of continuously calculating the cost-effectiveness data of the solution, the relevant calculation parameters are continuously trained. The parameters that can be trained include preset temperature weight, preset time weight, preset temperature impact comparison table, first preset conversion coefficient, second preset conversion coefficient, first preset weight, second preset weight, preset urgency weight, After continuous training of the above parameters, the cost-effectiveness data of the solution is more in line with reality, so that the battery pack can complete higher-value tasks before correction, thereby improving work efficiency.

[0037] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the embodiments of the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0038] In the second aspect, the present application provides an artificial intelligence battery capacity correction system. Figure 2As shown, the system includes an acquisition module 210, which is used to acquire battery monitoring data and historical monitoring data; the battery monitoring data includes temperature data and time data; the historical monitoring data includes historical temperature data and historical time data; a calculation module 220, which is used to calculate the estimated correction time of each single cell in the battery pack according to the battery monitoring data and the historical monitoring data; the estimated correction time is associated with the temperature data and the time data; a retrieval module 230, which is used to retrieve the task data of each work task in the work task pool; the task data includes task duration; a determination module 240, which is used to determine the capacity correction time of the battery pack according to the estimated correction time and the task data.

[0039] Furthermore, the determination module 240 is further configured such that the determination of the capacity correction time of the battery pack according to the estimated correction time and the task data includes: determining a task completion node of each work task according to the task data; the task completion node is a time node when the work task is completed; determining the normal working time of the battery pack according to the estimated correction time; the normal working time is the time when the battery pack meets the working conditions of at least one work task; the working condition is that the number of normal single cells in the battery pack is not less than the preset number of batteries required for the work task; the normal single cell is a single cell with an estimated correction time before the task completion node; based on the task number According to the normal working time, multiple task allocation schemes are determined; the task allocation scheme is to select at least one work task from the work task pool to the battery pack; based on the preset task screening conditions, multiple task allocation schemes are screened and integrated to obtain a target task scheme group; the target task scheme group contains multiple target task schemes; the target task scheme is the task allocation scheme after being screened by the preset task screening conditions; the cost performance data of each target task scheme in the target task scheme group is calculated, and the final task scheme is determined based on the cost performance data; the final task scheme is the target task scheme with the highest cost performance data; the capacity correction time of the battery pack is determined according to the final task scheme.

[0040] Among them, based on the preset task screening conditions, screening and integrating multiple task allocation schemes to obtain a target task scheme group includes: integrating multiple task allocation schemes to obtain a task allocation scheme group; determining the continuous working time of the battery group according to the estimated correction time; the continuous working time is the working time of the battery group from the current node to the forced correction node; determining the total working time of each task allocation scheme in the task allocation scheme group; based on the preset task screening conditions, screening out the task allocation schemes whose total working time is not greater than the continuous working time from the task allocation scheme group and integrating them to obtain a first task scheme group; determining the number of first single cells for each task allocation scheme in the first task scheme group, and determining the number of second single cells of the battery group; the number of the first single cells is the number of preset required batteries in the working conditions of the task allocation scheme; the number of the second single cells is the number of normal single cells in the battery group at the forced correction node; based on the preset task screening conditions, screening out the task allocation schemes whose first number of single cells is not greater than the second number of single cells from the first task scheme group and integrating them to obtain a target task scheme group.

[0041] Among them, calculating the cost performance data of each target task solution in the target task solution group, and determining the final task solution based on the cost performance data includes: determining the number of work tasks of each target task solution and the task submission node of each work task; calculating the urgency data of each target task solution according to the task submission node and the task duration; assuming that there are n work tasks in any target task solution, the urgency data of the i-th work task is , the urgency data of the target task plan is ; The method for calculating the cost performance data of the solution includes: ; In the formula, The cost performance data of the solution is: is the number of work tasks; are respectively a first preset conversion coefficient and a second preset conversion coefficient; are respectively a first preset weight and a second preset weight; is the preset urgency weight; ; .

[0042] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described device can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0043] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

Claims

1. A battery capacity correction method based on artificial intelligence, characterized in that: include: Acquire battery monitoring data and historical monitoring data; the battery monitoring data includes temperature data and time data; The historical monitoring data includes historical temperature data and historical time data; Calculating an estimated correction time for each single battery in the battery pack according to the battery monitoring data and the historical monitoring data; The estimated correction time is associated with the temperature data and the time data; Retrieving task data of each work task in the work task pool; the task data includes task duration; The capacity correction time of the battery pack is determined according to the estimated correction time and the task data.

2. The battery capacity correction method based on artificial intelligence according to claim 1 is characterized in that: Determining the capacity correction time of the battery pack according to the estimated correction time and the task data includes: Determine a task completion node for each work task according to the task data; the task completion node is a time node when the work task is completed; Determine the normal working time of the battery pack according to the estimated correction time; the normal working time is the time when the battery pack meets the working condition of at least one working task; the working condition is that the number of normal single cells in the battery pack is not less than the preset number of batteries required for the working task; the normal single cell is a single cell with an estimated correction time before the task completion node; Determine a plurality of task allocation schemes based on the task data and the normal working time; the task allocation scheme is to select at least one work task from the work task pool to the battery pack; Based on the preset task screening conditions, multiple task allocation schemes are screened and integrated to obtain a target task scheme group; the target task scheme group includes multiple target task schemes; the target task scheme is a task allocation scheme after being screened by the preset task screening conditions; Calculating the cost performance data of each target task solution in the target task solution group, and determining a final task solution based on the cost performance data; the final task solution is the target task solution with the highest cost performance data; The capacity correction time of the battery pack is determined according to the final mission plan.

3. The battery capacity correction method based on artificial intelligence according to claim 2 is characterized in that: The method of screening and integrating multiple task allocation schemes based on preset task screening conditions to obtain a target task scheme group includes: Integrate multiple task allocation schemes to obtain a task allocation scheme group; Determine the continuous working time of the battery pack according to the estimated correction time; the continuous working time is the working time of the battery pack from the current node to the forced correction node; Determine the total working time of each task allocation scheme in the task allocation scheme group; Based on the preset task screening condition, the task allocation schemes whose total working time is not greater than the continuous working time are screened out from the task allocation scheme group and integrated to obtain a first task scheme group; Determine the first number of single cells of each task allocation scheme in the first task scheme group, and determine the second number of single cells of the battery group; the first number of single cells is the number of preset required batteries in the working conditions of the task allocation scheme; the second number of single cells is the number of normal single cells in the battery group when the node is forced to be corrected; Based on a preset task screening condition, task allocation schemes in which the number of the first single battery cells is not greater than the number of the second single battery cells are screened out from the first task scheme group and integrated to obtain a target task scheme group.

4. The battery capacity correction method based on artificial intelligence according to claim 3 is characterized in that: The calculating the cost performance data of each target task solution in the target task solution group, and determining the final task solution based on the cost performance data includes: Determine the number of work tasks for each target task plan and the task submission node for each work task; Calculate the urgency data of each target task solution according to the task submission node and the task duration; Assume that there are n tasks in any target task plan, then the urgency data of the i-th task is , the urgency data of the target task plan is ; The method for calculating the cost performance data of the solution includes: ； In the formula, The cost performance data of the solution is: is the number of work tasks; are respectively a first preset conversion coefficient and a second preset conversion coefficient; are respectively a first preset weight and a second preset weight; The preset urgency weight.

5. The method for correcting battery capacity based on artificial intelligence according to claim 4, characterized in that: ； 。 6. A battery capacity correction system based on artificial intelligence, characterized in that: include: An acquisition module (210), used to acquire battery monitoring data and historical monitoring data; the battery monitoring data includes temperature data and time data; The historical monitoring data includes historical temperature data and historical time data; A calculation module (220), used for calculating an estimated correction time of each single cell in the battery pack according to the battery monitoring data and the historical monitoring data; The estimated correction time is associated with the temperature data and the time data; A calling module (230) is used to call task data of each work task in the work task pool; the task data includes task duration; A determination module (240) is used to determine the capacity correction time of the battery pack according to the estimated correction time and the task data.

7. The artificial intelligence-based battery capacity correction system according to claim 6 is characterized in that: The determination module (240) is further configured to determine the capacity correction time of the battery pack according to the estimated correction time and the task data, including: Determine a task completion node for each work task according to the task data; the task completion node is the time node when the work task is completed; Determine the normal working time of the battery pack according to the estimated correction time; the normal working time is the time when the battery pack meets the working condition of at least one working task; the working condition is that the number of normal single cells in the battery pack is not less than the preset number of batteries required for the working task; the normal single cell is a single cell with an estimated correction time before the task completion node; Determine a plurality of task allocation schemes based on the task data and the normal working time; the task allocation scheme is to select at least one work task from the work task pool to the battery pack; Based on the preset task screening conditions, multiple task allocation schemes are screened and integrated to obtain a target task scheme group; the target task scheme group includes multiple target task schemes; the target task scheme is a task allocation scheme after being screened by the preset task screening conditions; Calculating the cost performance data of each target task solution in the target task solution group, and determining a final task solution based on the cost performance data; the final task solution is the target task solution with the highest cost performance data; The capacity correction time of the battery pack is determined according to the final mission plan.

8. The artificial intelligence-based battery capacity correction system according to claim 7 is characterized in that: The determination module (240) is further configured to filter and integrate multiple task allocation solutions based on the preset task screening condition to obtain a target task solution group, including: Integrate multiple task allocation schemes to obtain a task allocation scheme group; Determine the continuous working time of the battery pack according to the estimated correction time; the continuous working time is the working time of the battery pack from the current node to the forced correction node; Determine the total working time of each task allocation scheme in the task allocation scheme group; Based on the preset task screening condition, the task allocation schemes whose total working time is not greater than the continuous working time are screened out from the task allocation scheme group and integrated to obtain a first task scheme group; Determine the first number of single cells of each task allocation scheme in the first task scheme group, and determine the second number of single cells of the battery group; the first number of single cells is the number of preset required batteries in the working conditions of the task allocation scheme; the second number of single cells is the number of normal single cells in the battery group when the node is forced to be corrected; Based on a preset task screening condition, task allocation schemes in which the number of the first single battery cells is not greater than the number of the second single battery cells are screened out from the first task scheme group and integrated to obtain a target task scheme group.

9. The artificial intelligence-based battery capacity correction system according to claim 8, characterized in that: The determining module (240) is further configured to calculate the solution cost performance data of each target task solution in the target task solution group, and determine the final task solution based on the solution cost performance data, including: Determine the number of work tasks for each target task plan and the task submission node for each work task; Calculate the urgency data of each target task solution according to the task submission node and the task duration; Assume that there are n tasks in any target task plan, then the urgency data of the i-th task is , the urgency data of the target task plan is ; The method for calculating the cost performance data of the solution includes: ； In the formula, The cost performance data of the solution is: is the number of work tasks; are respectively a first preset conversion coefficient and a second preset conversion coefficient; are respectively a first preset weight and a second preset weight; The preset urgency weight.

10. The artificial intelligence-based battery capacity correction system according to claim 9, characterized in that: The determination module (240) is further configured to: ; .

Images