Retired power battery matching and recombining method, service system and storage medium

Abstract

The invention relates to a decommissioned power battery matching and recombining method, a service system and a storage medium, and the method comprises the steps: carrying out the preprocessing of a plurality of target index parameters corresponding to the target information of each to-be-recombined target decommissioned power cell, and generating a plurality of corresponding standard characteristic parameters; processing the various standard characteristic parameters corresponding to each target retired power cell by using a consistency sorting model to obtain classification label data corresponding to a plurality of sorted retired power cell sets; based on pre-acquired battery demand parameters, the plurality of retired power battery cell sets and the corresponding classification label data, utilizing an improved artificial bee colony algorithm to carry out battery recombination configuration planning iteration, and generating corresponding recombination configuration information; and after production order demand information corresponding to the battery demand parameters is determined, carrying out production scheduling planning on the production order demand information and the recombination configuration information by using a preset heuristic algorithm, and carrying out power battery recombination according to generated target production scheduling planning information.

Description

Technical Field

[0001] The present application relates to the technical field of cascade utilization of retired power batteries, in particular to a matching and reorganization method, service system and storage medium for retired power batteries. Background Art

[0002] Power batteries are widely used in electric vehicles and other fields. As time goes by, their performance will gradually decline, and eventually they will be retired and can no longer meet the needs of vehicle use. Retired power batteries still have a certain residual capacity and can be used in energy storage and other scenarios. In related technologies, the ways of recycling and reusing power batteries include disassembly and recycling and cascade utilization. Cascade utilization is becoming more and more popular in power battery recycling because it can extend the life cycle value of the battery and make full use of resources.

[0003] In the related technology, when retired power batteries are recycled, due to the significant differences in parameters such as capacity, internal resistance, and health status of retired power batteries, the performance consistency of different batteries is poor. The existing sorting methods are mainly based on static indicators, which cannot comprehensively measure the overall performance of the battery, making it difficult to balance sorting accuracy and timeliness, resulting in low matching efficiency and difficult inventory management for the reorganization and production of retired power cells.

[0004] At present, no effective solution has been proposed for the problems of insufficient sorting accuracy, low reorganization and matching efficiency, and difficult inventory management when reorganizing and matching retired power cells in related technologies. Summary of the invention

[0005] The embodiments of the present application provide a retired power battery matching and reorganization method, service system and storage medium, so as to at least solve the problems in the related art of insufficient sorting accuracy, low recombination and matching efficiency and difficult inventory management when reorganizing and matching retired power cells.

[0006] In a first aspect, an embodiment of the present application provides a method for matching and reorganizing retired power batteries, comprising: obtaining target information of multiple target retired power cells to be reorganized, wherein each of the target information comprises multiple target indicator parameters, and the target indicator parameters are used to characterize a characteristic parameter of the corresponding target retired power cell, and the characteristic parameter is at least used to characterize the current storage state of the target retired power cell; after preprocessing the multiple target indicator parameters corresponding to each of the target retired power cells to generate the corresponding multiple standard characteristic parameters, using a trained consistency sorting model to process the multiple standard characteristic parameters corresponding to each of the target retired power cells to obtain classification label data corresponding to the sorted multiple retired power cell sets, wherein the classification label data includes a method for characterizing the application of the retired power cell set in a tiered scenario during the reorganization process. The priority reorganization adaptation level, the consistency sorting model is a machine learning model trained based on the fuzzy c-means clustering algorithm, and is trained to generate classification label data corresponding to the corresponding retired power cell set according to the input battery characteristic parameters; based on the pre-acquired battery demand parameters, multiple retired power cell sets and the corresponding classification label data, the improved artificial bee colony algorithm is used to iterate the battery reorganization configuration planning to generate corresponding reorganization configuration information, wherein the reorganization configuration information includes the target information corresponding to the retired power cell corresponding to the reorganized power battery group; after determining the production order demand information corresponding to the battery demand parameters, the production order demand information and the reorganization configuration information are scheduled using a preset heuristic algorithm, and the power batteries are reorganized according to the generated target production scheduling information to obtain multiple reorganized power batteries.

[0007] In a second aspect, an embodiment of the present application provides a service system, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the retired power battery matching and reorganization method described in the first aspect.

[0008] In a third aspect, an embodiment of the present application provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the retired power battery matching and reorganization method as described in the first aspect above.

[0009] Compared with the related art, the retired power battery matching and reorganization method, service system and storage medium provided in the embodiments of the present application adopt the method of obtaining target information of multiple target retired power cells to be reorganized, each of the target information includes multiple target indicator parameters, and the target indicator parameters are used to characterize a characteristic parameter of the corresponding target retired power cell, and the characteristic parameters are at least used to characterize the current storage state of the target retired power cell; after pre-processing the multiple target indicator parameters corresponding to each of the target retired power cells to generate the corresponding multiple standard characteristic parameters, the multiple standard characteristic parameters corresponding to each of the target retired power cells are processed by using the trained consistency sorting model to obtain the classification label data corresponding to the sorted multiple retired power cell sets; based on the pre-acquired battery demand parameters, the multiple retired power cell sets and the corresponding classification label data, an improved artificial bee colony is used. The algorithm iterates the battery reorganization configuration planning to generate corresponding reorganization configuration information, wherein the reorganization configuration information includes the target information corresponding to the retired power cell corresponding to the reorganized power battery pack; after determining the production order demand information corresponding to the battery demand parameters, the production order demand information and the reorganization configuration information are scheduled using a preset heuristic algorithm, and the power battery is reorganized according to the generated target production scheduling information to obtain a plurality of reorganized power batteries, so as to solve the problems of insufficient sorting accuracy, low reorganization matching efficiency and difficult inventory management when reorganizing and matching retired power cells in related technologies, and adopt fuzzy clustering sorting, multi-objective optimization matching and heuristic algorithm scheduling and reorganization arrangement to achieve high-precision consistency sorting, efficient order demand matching, optimized production scheduling and lean inventory management of retired power batteries, thereby improving the utilization efficiency of retired battery resources and reducing the pollution of waste batteries to the environment.

[0010] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 It is a hardware structure block diagram of a terminal of the retired power battery matching and reorganization method according to an embodiment of the present application; Figure 2 is a flow chart of a method for matching and reorganizing retired power batteries according to an embodiment of the present application; Figure 3 It is a structural block diagram of a retired power battery matching and reorganization device according to an embodiment of the present application. DETAILED DESCRIPTION

[0012] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for ordinary technicians in the field related to the contents disclosed in the present application, some changes such as design, manufacturing or production based on the technical contents disclosed in the present application are only conventional technical means, and should not be understood as insufficient contents disclosed in the present application.

[0013] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0014] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation and may represent the singular or plural. The terms "including", "comprising", "having" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include unlisted steps or units, or may also include other steps or units inherent to these processes, methods, products or devices. The "multiple links" involved in this application refer to links greater than or equal to two. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" may represent: A exists alone, A and B exist at the same time, and B exists alone. The terms "first", "second", "third" and the like involved in this application are only used to distinguish similar objects and do not represent a specific ordering of objects.

[0015] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. Taking running on a terminal as an example, Figure 11 is a hardware structure block diagram of a terminal of a retired power battery matching and reorganization method according to an embodiment of the present application. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0016] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the retired power battery matching and reorganization method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0017] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0018] This embodiment provides a retired power battery matching and reorganization method running on the above terminal, Figure 2 is a flow chart of a method for matching and reorganizing retired power batteries according to an embodiment of the present application, such as Figure 2 As shown, the process includes the following steps: Step S201, obtaining target information of multiple target retired power cells to be reassembled, wherein each target information includes multiple target indicator parameters, and the target indicator parameter is used to characterize a characteristic parameter of the corresponding target retired power cell, and the characteristic parameter is at least used to characterize the current storage state of the target retired power cell.

[0019] In this embodiment, before reorganizing the retired power cells, it is necessary to sort the target retired power cells to be reorganized for consistency, so that the reorganized power batteries meet the corresponding order requirements; and in order to sort the target retired power cells for consistency, it is necessary to use the relevant parameters corresponding to each target retired power cell, and the relevant parameters include static parameters and dynamic parameters. In this embodiment, the static parameters include the internal resistance of the cell, the remaining capacity of the cell, and the open circuit voltage of the cell. The static parameters are used to reflect the current state of the battery and are necessary parameters. The dynamic parameters include the charge and discharge rate, the depth of discharge and the state of health (SOH). The dynamic parameters are used to evaluate the actual performance and remaining life of the cell.

[0020] Step S202, after preprocessing the multiple target indicator parameters corresponding to each target retired power cell and generating the corresponding multiple standard feature parameters, use the trained consistency sorting model to process the multiple standard feature parameters corresponding to each target retired power cell to obtain classification label data corresponding to the sorted multiple retired power cell sets, wherein the classification label data includes a reorganization adaptation level for characterizing the priority of the retired power cell set applied to the tiered scenario during the reorganization process, and the consistency sorting model is a machine learning model trained based on the fuzzy c-means clustering algorithm, and is trained to generate classification label data corresponding to the corresponding retired power cell set according to the input battery feature parameters.

[0021] In this embodiment, before inputting a variety of target indicator parameters into a trained consistency sorting model, it is necessary to first preprocess the multiple target indicator parameters, that is, to process the multiple target indicator parameters into a data format that can be recognized by the consistency sorting model, and to provide accurate data support for the consistency sorting model to sort the target retired power cells, and the consistency sorting model is trained using a sample data set of the corresponding data format; in this embodiment, after the preprocessing conversion generates the corresponding standard feature parameters, the multiple standard feature parameters are input into the consistency sorting model, and the multiple standard feature parameters corresponding to each target retired power cell group are clustered, and retired power cells with similar performance are clustered into one category, and a certain degree of ambiguity is allowed, that is, each retired power cell can partially belong to multiple categories. This ambiguity helps to achieve flexible grouping when the performance of retired power cells varies greatly, thereby ensuring the robustness of clustering.

[0022] In this embodiment, a consistency sorting model of machine learning is used to cluster and sort multiple target retired power cells. Clustering is performed through the consistency sorting model to classify retired power cells with similar performance into the same category to facilitate subsequent reorganization and matching. In this embodiment, the classification label data of each target retired power cell marks the target retired power battery as a certain category, and the cells in this category have high performance consistency in terms of capacity, internal resistance, discharge rate and health status. The classification label data is used as the sorting result for subsequent cell reorganization and matching processes to ensure that the reorganized battery pack maintains a high degree of similarity in performance, thereby providing protection for the stability and life of the battery pack. Step S203, based on the pre-acquired battery demand parameters, multiple retired power cell sets and corresponding classification label data, the improved artificial bee colony algorithm is used to iterate the battery reorganization configuration planning to generate corresponding reorganization configuration information, wherein the reorganization configuration information includes target information corresponding to the retired power cells corresponding to the reorganized power battery pack.

[0023] In this embodiment, after determining the classification label data corresponding to the target retired power cell, the battery reorganization configuration planning is iterated according to the pre-acquired battery demand parameters (corresponding to the order demand data), and then according to the order demand parameters and the sorting results represented by the classification label data, so as to reorganize and match the appropriate battery pack; in some optional implementation modes, the battery demand parameters are obtained by demand forecasting based on the analysis of historical order data, current market trends and application scenario requirements; in this embodiment, during the iterative process of battery reorganization configuration planning, the following target matching is also performed: capacity matching, which is used to ensure that the capacity of the allocated reorganized battery pack is as close as possible to the capacity requirement of the order to avoid waste or insufficient capacity; discharge rate matching, which ensures the performance stability of the battery during application by selecting batteries that meet the discharge rate requirements of the order; life matching, which satisfies the order requirements for battery life and improves the long-term reliability of the configuration scheme by preferentially selecting battery packs with a higher state of health (SOH); internal resistance matching According to the requirements of the order for the internal resistance of the battery pack, batteries with appropriate internal resistance are selected to reduce the internal resistance difference, so as to achieve internal resistance balance of the battery pack and improve the overall efficiency and safety; in this embodiment, the battery reorganization configuration planning iteration is based on the sorting results of the retired power cells in stock, and comprehensively analyzes the standard characteristic parameters of the retired power cells in stock (including capacity, internal resistance, discharge rate and health state (SOH)) to perform accurate screening and intelligent matching configuration; in this embodiment, by screening the standard characteristic parameters, it is ensured that the reorganized battery pack can meet the order requirements and improve the utilization efficiency of the retired power cells, that is, the battery reorganization configuration planning iteration is through the detailed classification of the capacity, internal resistance and other indicators of each retired power cell, and based on the order requirements for capacity, life, and discharge rate to select battery packs that meet the performance standards, so as to meet the application scenario of cascade utilization; and the embodiment of the present application adopts the introduction of artificial bee colony algorithm to iteratively optimize and generate reorganization configuration information by simulating the behavior of bees collecting honey.

[0024] Step S204, after determining the production order demand information corresponding to the battery demand parameters, use a preset heuristic algorithm to perform production scheduling on the production order demand information and the reorganization configuration information, and reorganize the power batteries according to the generated target production scheduling information to obtain multiple reorganized power batteries.

[0025] In this embodiment, after the reorganization configuration information is generated, a heuristic algorithm is used to perform production scheduling. The production scheduling is based on the reorganization production requirements of the battery pack, the allocation of equipment resources, and the time requirements of the order. By reasonably arranging production resources and optimizing the task sequence, the efficiency and stability of the production process are guaranteed.

[0026] Through the above steps S201 to S204, target information of multiple target retired power cells to be reorganized is obtained, each target information includes multiple target indicator parameters, and the target indicator parameters are used to characterize a characteristic parameter of the corresponding target retired power cell, and the characteristic parameters are at least used to characterize the current storage state of the target retired power cell; after pre-processing the multiple target indicator parameters corresponding to each target retired power cell to generate the corresponding multiple standard characteristic parameters, the multiple standard characteristic parameters corresponding to each target retired power cell are processed by using the trained consistency sorting model to obtain the classification label data corresponding to the sorted multiple retired power cell sets; based on the pre-acquired battery demand parameters, the multiple retired power cell sets and the corresponding classification label data, the improved artificial bee colony algorithm is used to iterate the battery reorganization configuration planning to generate the battery demand parameters, the multiple retired power cell sets and the corresponding classification label data. The corresponding reorganization configuration information is obtained, and the reorganization configuration information includes the target information corresponding to the retired power cells corresponding to the reorganized power battery pack; after determining the production order demand information corresponding to the battery demand parameters, the production order demand information and the reorganization configuration information are scheduled by using a preset heuristic algorithm, and the power batteries are reorganized according to the generated target production scheduling information to obtain multiple reorganized power batteries, so as to solve the problems of insufficient sorting accuracy, low reorganization matching efficiency and difficult inventory management when reorganizing and matching retired power cells in related technologies, and adopt fuzzy clustering sorting, multi-objective optimization matching and heuristic algorithm scheduling and reorganization arrangement to achieve high-precision and consistent sorting of retired power batteries, efficient order demand matching, optimized production scheduling and lean inventory management, so as to improve the utilization efficiency of retired battery resources and reduce the pollution of waste batteries to the environment.

[0027] It should be noted that the retired power battery matching and reorganization method of the embodiment of the present application performs fuzzy clustering sorting, multi-objective optimization matching and heuristic algorithm production planning to achieve high-precision consistency sorting of retired power cells, efficient demand matching, optimized production scheduling, and lean inventory management.

[0028] It should be further explained that, in this embodiment, when performing production scheduling, the current production resources are reasonably allocated, including resources such as assembly equipment, testing equipment, storage space and personnel, and the reorganization production requirements of each battery pack are matched with the available resources to ensure that the equipment utilization is maximized; specifically, different production steps (such as charge and discharge tests, internal resistance tests, battery assembly, etc.) will be arranged according to production requirements and equipment conditions to ensure that the equipment requirements of each step are reasonably met; at the same time, in task scheduling, heuristic algorithms are used to optimize production scheduling to ensure that the order of tasks is reasonable. The heuristic algorithm quickly calculates the optimal task scheduling sequence by simulating human experience and judgment; in the initialization stage, the initial scheduling sequence generated by the production scheduling plan gives priority to orders with urgent delivery time and ensures the continuity of production tasks; then, the orders are arranged Tasks are prioritized according to urgency, complexity and equipment availability to determine the order in which each order is scheduled during the production process. At the same time, the heuristic algorithm will fine-tune the task sequence during the local optimization phase to ensure that the production steps on which the task depends are smoothly connected to avoid production interruptions due to resource conflicts or task waiting. During multiple iterative improvements, production arrangements are dynamically adjusted based on task priority and resource utilization to improve overall production efficiency and resource utilization. Furthermore, during the scheduling process, emphasis will be placed on ensuring the timeliness of order delivery, with priority given to urgent orders to ensure on-time delivery. For orders with longer cycles, the allocation of production tasks will be balanced to ensure that resources in each production link are evenly utilized. If production resources are insufficient or equipment fails, tasks will be automatically adjusted or the production sequence will be rearranged to ensure production continuity and on-time delivery of orders.

[0029] In some embodiments, based on the pre-acquired battery demand parameters, the plurality of retired power cell sets and the corresponding classification label data, an improved artificial bee colony algorithm is used to iterate the battery reorganization configuration planning to generate corresponding reorganization configuration information, including the following steps: Step 21, according to the classification label data corresponding to multiple retired power cell sets, use the improved artificial bee colony algorithm to perform battery reorganization configuration to generate first reorganization configuration information, wherein the first reorganization configuration information includes target retired power cells selected for the first power battery group, and the first power battery group is used to represent the power battery group currently reorganized and configured.

[0030] Step 22: Obtain a first fitness corresponding to each first power battery pack from the first reorganization configuration information, wherein the first fitness is calculated based on an adaptation function constructed based on classification label data corresponding to target retired power cells assigned to each first power battery pack, and is used to characterize the performance excellence of the first power battery pack.

[0031] Step 23, determine the target fitness corresponding to the demand battery group corresponding to the battery demand parameter, and according to the difference between the first fitness and the target fitness, perform local search, neighborhood optimization and global search iterations based on the improved artificial bee colony algorithm on the first reorganization configuration information until the difference is no more than a preset threshold, and generate the reorganization configuration information, wherein in the global search stage, the improved artificial bee colony algorithm introduces dynamic neighborhood adjustment and local optimal escape mechanism.

[0032] In this embodiment, generating the first reorganization configuration information corresponds to the initialization stage of battery reorganization configuration using the improved artificial bee colony algorithm. In the initialization stage, a number of retired power cells are randomly selected from the retired power cell set to be reorganized into a first power battery group, and the configuration scheme corresponding to the first power battery group is used as the initial solution. Before configuring the initial solution, a fitness value is assigned to the initial solution to be configured according to the degree of matching between its cell capacity, discharge rate, life and internal resistance and the order requirements. The higher the fitness value, the better the matching degree. That is, when the initial solution is randomly generated, it needs to be matched with the assigned fitness value. After the corresponding fitness value is assigned, a configuration scheme that is close to or equal to the assigned fitness value is randomly selected, that is, multiple retired power cells with similar performance consistency are selected. It should be understood that the first fitness value of the configured initial solution is not the assigned fitness value. The first fitness value is the value of the assigned fitness value. The fitness value needs to be calculated based on the adaptation function constructed based on the classification label data corresponding to the configured multiple retired power cells. It may be equal to the assigned fitness value or close to it. The corresponding fitness value is solved for the allocation scheme, and the solution corresponding to the power battery pack is adjusted according to the difference between the assigned fitness value and the solved fitness value. That is, local search, neighborhood optimization and global search based on the improved artificial bee colony algorithm are iterated until a power battery pack that meets the order requirements and has excellent performance is obtained. At this time, the difference between the fitness value corresponding to the power battery pack and the preset target fitness is not greater than the preset threshold. It should be noted that in this embodiment, when the initial solution is generated using the improved artificial bee colony algorithm, a dynamic fitness value update mechanism is introduced, and the order prediction results are considered during initialization. For parameters that may have greater demand in the future, higher fitness values ​​will be assigned.

[0033] Through step 21 to step 23, the improved artificial bee colony algorithm is adopted to find the optimal solution corresponding to the optimal combination of power battery packs by simulating the process of bees collecting honey, and then generate the reorganization configuration information corresponding to the power battery packs containing multiple optimal combinations.

[0034] In some of the embodiments, according to the classification label data corresponding to the plurality of retired power cell sets, the improved artificial bee colony algorithm is used to perform battery reconfiguration and generate the first reconfiguration configuration information, which is achieved by the following steps: Step 31 : obtaining coding information and classification label data corresponding to all retired power cells in a plurality of retired power cell sets, wherein the coding information is generated according to target information of the retired power cells.

[0035] Step 32 : randomly assign codes to each of the plurality of coding information to obtain a plurality of coding bodies corresponding to the plurality of first power battery packs, wherein one coding body corresponds to a reconfiguration result of one first power battery pack.

[0036] Step 33, determine the battery capacity, discharge rate, life span and battery internal resistance corresponding to the classification label data corresponding to each target retired power cell, and calculate the first fitness corresponding to each encoding body based on the adaptation function constructed based on the battery capacity, discharge rate, life span and battery internal resistance, wherein when constructing the adaptation function, the weights corresponding to the battery capacity, discharge rate, life span and battery internal resistance are dynamically updated based on the battery demand parameters.

[0037] In this embodiment, the adaptation function is constructed based on the capacity, discharge rate, life, internal resistance of the battery pack, order demand constraints and reorganized battery constraints, where the capacity matching function is: CapacityMatch=|C order -C group |,C order is the required capacity of the battery pack in the order, C group For the capacity of the reorganized power battery pack, through capacity matching, ensure that the allocated battery pack capacity is close to the required capacity of the order, to avoid affecting the order performance due to insufficient capacity, or causing resource waste due to excess capacity; the discharge rate matching function is: DischargeRateMatch=|D order -D group |,D order is the discharge rate requirement of the battery pack in the order, D group The discharge rate of the reorganized power battery pack is matched by the discharge rate, so as to ensure that the output power in the actual application of the order meets the requirements; the life matching function is: LifeMatch=|L order -SOH group |, L order For the life requirements of the battery pack in the order, SOH group To measure the health of the reorganized power battery pack, life matching is used to ensure that the battery pack maintains stable performance during its use cycle to meet the service life requirements of the order. Battery packs with high life matching are given priority to orders with higher life requirements; the built-in matching function is: ResistanceMatch=|R order -R group |,Rorder is the internal resistance requirement of the battery pack in the order, R group It is the built-in average value of the reorganized power battery pack. By controlling the built-in range of the battery pack, the balance within the battery pack is ensured to improve the discharge efficiency and safety of use. In this embodiment, the corresponding order demand constraint is set to ensure that the capacity, discharge rate, life and internal resistance of each allocated power battery pack meet the minimum requirements of the order; the reorganized battery constraint is set to that all batteries entering the reorganization process must come from the retired power cell set of the same group in the consistency sorting module, ensuring that the batteries in the same group are highly close in performance parameters.

[0038] It should be noted that different target weights are set according to different application scenarios and order requirements. For orders requiring high power output, the weight of discharge rate matching is increased, thereby giving priority to ensuring the discharge capacity of the reorganized battery pack; for orders with higher life requirements, the weight of life matching is increased, and battery cells in better health are allocated first, thereby reorganizing a power battery pack with a long service life.

[0039] Step 34: Generate first recombinant configuration information from a plurality of encoding bodies and a first fitness corresponding to each encoding body.

[0040] Through step 31 to step 34, the initial solution is generated by using the improved artificial bee colony algorithm, providing a data basis for solving the optimal power battery pack.

[0041] In some of the embodiments, according to the difference between the first fitness and the target fitness, the first reorganization configuration information is iterated by performing local search, neighborhood optimization and global search based on the improved artificial bee colony algorithm, which is achieved by the following steps: Step 41, based on the artificial bee colony algorithm, a first neighborhood solution is generated for all the coding bodies in the first reorganization configuration information, and the target retired power cells corresponding to the randomly selected first neighborhood solutions are randomly replaced to generate multiple second coding bodies, wherein the randomly replaced target retired power cells are target retired power cells in the same retired power cell set, and the second coding bodies are used to characterize the configuration results of the power battery group reorganized in the local search phase.

[0042] In this embodiment, an artificial bee colony algorithm is used to simulate bees collecting honey, and it is defined as the employed bee stage, so as to generate a new configuration scheme in the neighborhood of the encoding body corresponding to each initial solution, that is, to generate a first neighborhood solution, and improve the fitness value corresponding to the first neighborhood solution by fine-tuning the battery cell combination in the configuration scheme (first neighborhood solution) and dynamically adjusting the neighborhood range; in this embodiment, the neighborhood size is adaptively adjusted to avoid the local optimal problem caused by a too small neighborhood range, and at the same time expand the search range of high-quality solutions; in this embodiment, when fine-tuning the first neighborhood solution, it can be a partial target retirement dynamic of a first neighborhood solution. For example, for a first neighborhood solution, the cells of a power battery pack are cell 1, cell 2, cell 3, cell 4, cell 5 and cell 6. After fine-tuning, cell 1 and cell 6 are replaced by cell 7 and cell 9 respectively to form a new power battery pack. It can also be a replacement of part of the first neighborhood solution, for example, the first neighborhood solution a and the first neighborhood solution b are replaced by the first neighborhood solution f and the first neighborhood solution g respectively. It can be understood that the replacement of the neighborhood solution is the replacement of the relevant power battery pack; in this embodiment, after fine-tuning the first neighborhood solution, the power battery pack corresponding to the second coding body is generated.

[0043] Step 42, after selecting a second coding body having a fitness value greater than a fitness threshold from multiple second coding bodies according to the fitness corresponding to the second coding body, determine the candidate coding body that does not belong to the preset optimal coding body pool among the selected multiple candidate coding bodies, generate a second neighborhood solution for the determined candidate coding body, and use all the second neighborhood solutions and the candidate coding bodies that belong to the optimal coding body pool among the multiple candidate coding bodies as the third coding body, wherein all the coding bodies stored in the optimal coding body pool are optimal coding bodies obtained based on the memory mechanism, and the third coding body is used to characterize the configuration result of the power battery pack reorganized in the neighborhood optimization stage.

[0044] In this embodiment, the observation bee stage is simulated, and according to the fitness value of each second encoding body, the observation bee selects a solution with higher fitness (corresponding to a second encoding body with a fitness value greater than a fitness threshold), and conducts a deeper search of its neighborhood; in this embodiment, a fitness threshold judgment mechanism is added to the observation bee stage, and the second encoding bodies with a fitness value lower than the fitness threshold are directly excluded, and the neighborhood of the high fitness solution is optimized intensively; at the same time, a memory pool mechanism is introduced in the neighborhood search, and the encoding bodies with excellent performance in the history are stored in the optimal encoding body pool, so as to prevent good encoding bodies from being mistakenly eliminated in the neighborhood search, so as to improve the accuracy of the matching scheme.

[0045] Step 43, a random global search is performed on the target retired power cell corresponding to the randomly selected third code body within the set global search range to generate a candidate code body that satisfies the local optimal escape mechanism, and the generated multiple candidate code bodies are used as the candidate reorganization configuration information corresponding to the current iteration, wherein the global search range is determined by introducing random factors and a large-scale search mechanism, and the local optimal escape mechanism is used to characterize that when the generated candidate code body is the optimal solution, the global search range is stopped from being expanded.

[0046] In this embodiment, the scout bee stage is simulated, and after the code bodies with smaller fitness values ​​are eliminated, the scout bee dynamically generates new code bodies for global search to maintain the diversity of the solution space and prevent the algorithm from falling into the local optimum; in this embodiment, by introducing an escape mechanism based on adaptive control, the global search range of the scout bee can be adaptively adjusted according to the distribution of the current solution, and a large-scale search is performed when it deviates from the global optimum, gradually approaching the code body corresponding to the optimal power battery pack; it can be understood that the local optimal escape mechanism adopted in this embodiment is that when the generated candidate code body falls into the local optimal solution, it will change part of the current solution to help the algorithm jump out of the local optimal solution and explore a wider solution space (that is, expand the global search range).

[0047] Step 44, repeatedly executing the step of generating corresponding candidate recombination configuration information until the difference between the fitness of the candidate recombination configuration information and the target fitness is not greater than a preset threshold, and taking the candidate recombination configuration information whose difference is not greater than the preset threshold as the recombination configuration information.

[0048] In this embodiment, multiple iterative optimizations are performed to continuously update the fitness value of the corresponding encoding body, and gradually converge to the optimal encoding body through alternating optimization in each stage; it can be understood that the improved artificial bee colony algorithm adopted in the embodiment of the present application improves the convergence speed and global search capability through the local optimal escape mechanism, adaptive neighborhood and memory pool mechanism, and finally outputs the optimal matching solution that meets the order requirements.

[0049] In some embodiments, the heuristic algorithm includes a parthenogenetic algorithm based on simulated annealing, and the production order demand information and the reorganization configuration information are subjected to production scheduling using a preset heuristic algorithm, which is implemented by the following steps: Step 51, from the reorganization configuration information, obtain the battery pack number corresponding to the target power battery pack of the reorganization configuration, and randomly linearly encode multiple battery pack numbers to obtain an initial linear code body set, wherein each first linear code individual in the initial linear code body set is used to represent a production planning information for reorganizing all target power battery packs, and the production planning information includes the production line and assembly time allocated to each target power battery pack.

[0050] Step 52, obtain the first production scheduling information corresponding to each first linear coding individual obtained by decoding the initial linear coding set, and calculate the reorganization fitness corresponding to each first linear coding individual according to the assembly time of each target power battery pack extracted from the first production scheduling information, and the reorganization fitness is used to characterize the processing time length for reorganizing the target power battery pack.

[0051] Step 53, determining whether the recombination fitness values ​​corresponding to all current linear coding individuals generated by completing the current iteration are less than a preset recombination fitness threshold, wherein the current linear coding individual includes one of the first linear coding individual and the linear coding individual generated by completing the previous iteration.

[0052] Step 54, when it is determined that the recombination fitness values ​​of all current linear coding individuals are not less than the recombination fitness threshold, a simulated annealing operation is iterated based on all current linear coding individuals and a parthenogenetic algorithm based on simulated annealing until the recombination fitness value of the generated target linear coding individual is less than the recombination fitness threshold, and the production scheduling information obtained by decoding all target linear coding individuals is used as the target production scheduling information, wherein the simulated annealing operation includes selection, mutation, receiving a new solution based on the Metropolis criterion, and cooling.

[0053] In this embodiment, the goal of production scheduling is to complete the production of the reorganization plans of the same order at the same time as much as possible, maximize the benefits of the reorganization plans, and minimize the remanufacturing cost. The constraints of production scheduling include that each reorganization plan must be remanufactured according to a fixed process flow, and there is a close relationship between the process flows. There are professional machines for each process, and there are corresponding buffers in front of the machines. A machine can only process one reorganization plan at the same time. Different reorganization plans have different processing times on different machines. Different reorganization plans generally have different delivery times, and different reorganization plans have different benefits.

[0054] In this embodiment, a parthenogenetic algorithm based on simulated annealing is used for production scheduling, and the specific process is as follows: Step 1. Initialization In this embodiment, an initial linear encoding body set, namely, an initial population, is generated, and an initial temperature T_0 and a cooling rate α are set. Each first linear encoding individual represents a recombination scheme, and its allocation to different production lines and the production start time are determined.

[0055] Step 2: Fitness evaluation In this embodiment, the fitness value of each first linear encoding individual is calculated, wherein the fitness value reflects the length of the machine processing time, and the goal is to minimize the machine processing time.

[0056] Step 3. Select.

[0057] In this embodiment, the first linear coding individual with a higher fitness value is selected as the parent individual to ensure that the individual with a higher fitness value has a greater chance of entering the next generation.

[0058] Step 4: Mutation operation In this embodiment, the mutation operation is performed on the selected first linear coding individual, and the simulated annealing algorithm controls the range and probability of mutation through temperature. When the temperature is high, a larger mutation range is allowed, and the production line allocation and production start time of the individual are randomly changed. As the temperature gradually decreases, the mutation range narrows, so that the algorithm gradually converges and avoids excessive search.

[0059] Step 5: Acceptance criteria In this embodiment, whether the solution corresponding to the new encoding body generated by the mutation operation is accepted depends on its fitness value and the current temperature; in this embodiment, the Metropolis criterion is adopted to accept new solutions, and poor solutions can be accepted when the temperature is high to avoid falling into the local optimum. If the new solution is better than the current solution, the new solution is directly accepted. If the new solution is worse than the current solution, the new solution is accepted with probability P=e^(-∆f / T), where ∆f is the fitness difference and T is the current temperature.

[0060] Step 6: Cooling After each iteration, the temperature is updated according to the cooling rate T = αT to gradually reduce the temperature so that the search range gradually converges.

[0061] Step 7: Repeat steps 1 to 6 until the preset stop condition (such as number of iterations, temperature threshold, fitness threshold, etc.) is reached.

[0062] In some embodiments, preprocessing is performed on a plurality of target indicator parameters corresponding to each target retired power cell to generate a plurality of corresponding standard characteristic parameters, which is achieved by the following steps: Step 61, acquiring characteristic parameters corresponding to each target retired power cell in the acquired target information of each target retired power cell, wherein the characteristic parameters include at least one of the following: cell capacity, cell internal resistance, open circuit voltage, depth of discharge and state of charge.

[0063] In this embodiment, professional testing equipment is used to perform detailed performance tests on each retired power cell, and key parameters are collected, including original data such as capacity, internal resistance, open circuit voltage, depth of discharge (DOD) and state of charge (SOC). Capacity reflects the ability of the battery to store energy, internal resistance reflects the conductivity of the battery, open circuit voltage is used to preliminarily judge the electrochemical performance of the battery, and DOD and SOC reflect the dynamic performance of the battery under different discharge conditions. The data of each retired power cell is stored in the form of a record file to form a complete battery characteristic data set for subsequent processing and analysis.

[0064] Step 62, after filtering, denoising, adding and deleting missing values, and removing outliers on the characteristic parameters, multi-dimensional indicator parameters are generated, wherein adding and deleting missing values ​​includes filling missing values ​​and removing missing values, and filling missing values ​​includes filling using one of the average method, median method and interpolation method, and removing outliers uses one of the following methods to detect the deleted outliers: mean method, standard deviation method, box plot method, outlier detection method.

[0065] In this embodiment, after data collection is completed, the data set needs to be preprocessed. Due to the different usage histories and statuses of different retired power cells, the collected data may have missing values ​​and outliers. The noise in the collected data will affect the accuracy of sorting. Data preprocessing is used to improve data quality and ensure the accuracy of sorting. In this embodiment, the method for processing missing values ​​will choose to fill or eliminate according to the situation. Among them, the missing value filling method includes using the mean, median or interpolation method to estimate the missing value to ensure the integrity of the data set. If there are many missing data and it is impossible to fill them reasonably, you can choose to eliminate data samples with more missing values. In this way, the integrity of the data is ensured, and the parameter data of each retired power cell is complete. In this embodiment, the method for processing outliers includes the mean method, standard deviation method, box plot method or other outlier detection methods based on statistics, and the obviously abnormal values ​​are eliminated or appropriately adjusted to avoid misleading the grouping results and ensure the accuracy of the data.

[0066] Step 63, normalizing the multi-dimensional index parameters and extracting key features to obtain standard feature parameters corresponding to the characteristic parameters.

[0067] In this embodiment, the indicator parameters of different dimensions are normalized, and all data are standardized to a unified scale range to facilitate the processing of the fuzzy clustering algorithm. The purpose of normalization is to unify the numerical range of different parameters into a standardized interval to eliminate the influence between different dimensions. The normalized data is more suitable for the processing of the fuzzy clustering algorithm, which can improve the stability and accuracy of the clustering effect. In this embodiment, after the indicator parameters are normalized, feature extraction is performed, that is, after the indicator parameters are normalized, the key features of each battery cell are extracted from the corresponding indicator parameters, including indicators such as capacity, internal resistance, DOD and SOC. By directly inputting the key feature indicators into the fuzzy clustering algorithm, it is used to characterize the health status, discharge capacity and consistency of the battery.

[0068] Through the above steps 61 to 63, preprocessing of multiple target indicator parameters corresponding to the target retired power cells is achieved, which can improve the accuracy of sorting retired power cells.

[0069] In some embodiments, the training of the consistency sorting model includes the following steps: Step 71, obtaining a preset training sample set, wherein the training sample set includes characteristic parameters corresponding to a plurality of sample retired power cells.

[0070] Step 72 , pre-process the characteristic parameters in the training sample set accordingly to generate standard characteristic parameters corresponding to each sample retired power cell.

[0071] Step 73, after selecting the initial cluster center from the standard characteristic parameters corresponding to all sample retired power cells, based on the initial cluster center and the standard characteristic parameters corresponding to all sample retired power cells, perform iterations of membership matrix calculation and cluster center update corresponding to the fuzzy c-means clustering algorithm until the membership matrix converges to generate a consistency sorting model.

[0072] In this embodiment, after preprocessing, normalizing and feature extraction of characteristic parameters corresponding to a preset training sample set, the extracted standard characteristic parameters corresponding to the sample retired power cells are input into a fuzzy c-means clustering algorithm (FCM) for sorting. Based on the FCM algorithm and the standard characteristic parameters of each sample retired power cell, cells with similar performance are clustered into one category, and a certain degree of fuzziness is allowed; in this embodiment, at the beginning of training, an initial clustering center is first set. The setting method of the initial clustering center can be randomly selected or based on a preset position of the characteristic mean. The initial clustering center provides a reference point for the subsequent clustering process. With the iteration of the algorithm, the clustering center will gradually adjust to a more reasonable position, thereby improving the clustering effect; thereafter, the membership matrix is ​​calculated. In this embodiment, the distance from each standard characteristic parameter to the clustering center is used to calculate its membership in each category. The membership matrix records the degree of membership of all cells in each category. The distance between each standard characteristic parameter and the clustering center is calculated. The degree of membership in each category; it can be understood that the membership matrix records the degree of membership of all battery cells in each category, and the corresponding value is between 0 and 1, indicating the strength of the battery cell's membership to a certain cluster. The membership matrix allows each corresponding battery cell to belong to multiple categories with different membership values, thereby being able to more accurately reflect the performance differences between battery cells; during the training and sorting process, after calculating the membership matrix, the cluster center will be updated according to the membership. The updating method is to weightedly calculate the average value of all standard feature parameters in each category to generate a new cluster center. The continuous adjustment of the cluster center makes the battery cell distribution gradually approach the location of the cluster center, thereby achieving a gradually refined clustering result; thereafter, an iterative update will be performed, that is, repeating the steps of calculating the membership matrix and updating the cluster center until the change in the membership matrix is ​​less than the preset convergence threshold or the maximum number of iterations is reached. At this time, the clustering result is considered to be converged, and the final grouping result is obtained. Through the above-mentioned repeated iterations, the stability and accuracy of the clustering are guaranteed, so that the sorting result is optimized.

[0073] In some embodiments, obtaining the battery requirement parameter is achieved by the following steps: Step 81, obtaining historical battery demand order data, wherein the historical battery demand order data includes order parameters and time parameters, the order parameters include battery demand order quantity, required battery pack capacity, battery pack discharge rate, battery pack life span, and the time parameters include at least the order timestamp.

[0074] Step 82, performing data cleaning on the order parameters and time parameters corresponding to the historical battery demand order data to generate first order data, wherein the data cleaning includes at least one of the following: processing missing values ​​of the order parameters and time parameters by using mean filling, interpolation or elimination methods; detecting outliers of the order parameters and time parameters by using one of the mean method, standard deviation method and box plot method, and deleting the detected outliers.

[0075] Step 83, use feature engineering to process the first order data to generate order feature data, and use the trained order demand prediction model to process the order feature data to predict and output battery demand parameters, wherein the order demand prediction model is a classification prediction model trained based on the CART algorithm, and is trained to predict and output the order demand corresponding to the first feature data based on the input first feature data.

[0076] In some optional implementations, the order demand prediction model is trained using the following steps: Step 1: Collect historical battery demand order data In this embodiment, battery demand orders over a period of time in the past are collected, and the data of the battery demand orders include order parameters such as the battery demand order quantity, the required battery pack capacity, the battery pack discharge rate, and the battery pack life, as well as time parameters including the timestamp of the order and other associated time features (such as season, month, week, etc.).

[0077] Step 2: Data cleaning In this embodiment, the battery demand order data is preprocessed to process missing values, outliers and duplicate values ​​to ensure the integrity and consistency of the data. For missing values, mean filling, interpolation or elimination can be used; for outliers, statistical methods or box plot methods are used for detection and processing.

[0078] Step 3: Feature Engineering In this embodiment, feature engineering is used to extract features and create new features for the first order data to improve the prediction effect of order demand forecasting. For example, new time features are generated according to time (such as the beginning of the month, the middle of the month, the end of the month, etc.), and information such as the order type and application scenario can also be extracted as corresponding input features.

[0079] Step 4: Data segmentation In this study, the order feature data generated by feature engineering is divided into training set, validation set and test set.

[0080] Step 5: Model training In this embodiment, the model training process is to train the decision tree model by inputting features and historical battery demand order data, so as to learn the relationship between features and order demand.

[0081] Step 6: Feature Selection In this embodiment, according to the division criteria of the CART algorithm, the feature that can best reduce the mean square error is selected as the segmentation point, and a tree structure is constructed layer by layer, wherein the feature selection process finds the most important feature combination in the training data so that the model can generate accurate prediction values.

[0082] Step 7: Initial node segmentation In this embodiment, starting from the root node, the best features and split points are selected by minimizing the mean square error, and the data set is split into two subsets. Each subset forms a new node, which will become the branches of the tree.

[0083] Step 8: Recursive node splitting In this embodiment, the above process is repeated for each new node, and the best segmentation features and segmentation points are continuously searched to minimize the mean square error of each subset. The CART algorithm continuously segments each node until the stopping condition is reached.

[0084] Step 9: Node stops splitting In this embodiment, the recursive process of the CART regression tree ends when a stopping condition is met: the reduction in the mean square error after the node split is less than a preset threshold.

[0085] Step 10: Calculate the mean square error of the node In this embodiment, for each segmented subset, its mean square error is calculated, and the mean square errors of all nodes are weighted averaged to obtain the overall mean square error of the segmentation.

[0086] Step 11: Generate leaf nodes In this embodiment, when the stopping condition is reached, the decision tree stops further splitting. It can be understood that in the regression task, the output value of each leaf node is usually the average order demand of the node data, which also represents the predicted value of the node.

[0087] Step 12: Post-pruning It is understandable that decision trees are prone to overfitting, especially when the data is noisy. After the tree is built, pruning is used to simplify the tree structure. Post-pruning is usually based on cost-complexity pruning, which calculates the cost complexity on the leaf nodes and selects the pruning scheme with the lowest cost to reduce overfitting. The node complexity cost is the mean square error of the node plus the complexity penalty term. After training, the performance of the decision tree model is evaluated to ensure that its prediction of order demand is accurate and has generalization capabilities.

[0088] Step 13: Model evaluation: Use the validation set to evaluate the model’s prediction performance and calculate the R² score of the validation set. Step 14, hyperparameter tuning, after model evaluation, further improves model performance through hyperparameter tuning. Decision tree hyperparameters include: maximum depth, minimum number of sample splits, minimum number of leaf node samples, etc. The best parameter combination is selected through random search.

[0089] Step 15, cross validation, cross validation is performed on the training set, the data is divided into multiple subsets, multiple training and validation are performed, and the average performance index is taken as the final result.

[0090] Step 16: Model testing: Use the test set data to perform a final test on the decision tree model and calculate the R² evaluation index.

[0091] After the order demand prediction model is trained, the trained decision tree model will be deployed and combined with real-time order data to predict order demand. It is understandable that the trained order demand prediction model will also be monitored, that is, the prediction error of the decision tree model will be regularly monitored, and the changes in model performance will be analyzed. If the prediction error increases significantly, it means that the market environment has changed and the existing order demand prediction model is no longer suitable and needs to be updated. It is updated by incremental learning or retraining. For scenarios with slight changes, the incremental learning method is used to update the model parameters with a small amount of new data. For situations with significant changes, the model is retrained using new historical order data to ensure the accuracy of the model. In the process of using the order demand prediction model, a feedback learning mechanism is also used, that is, by collecting the difference between the actual order demand and the model prediction value, the model is continuously optimized through the feedback mechanism. Data feature optimization processing is also used, and input features are continuously optimized through feature selection and feature importance evaluation to improve the prediction effect of the model.

[0092] In this embodiment, for the target indicator parameters corresponding to the external characteristic parameters (for example: type of retired power battery pack, brand name of retired power battery pack, type of retired power battery pack), it means that after the power battery is retired and determined to be used for reorganization, more important indicator parameters are screened out from the preset indicator parameters and assigned to the corresponding target retired power battery cell group. When the target retired power battery cell group to be stored is received, the target information of each target retired power battery cell group already has the target indicator parameters corresponding to the external characteristic parameters; and the target indicator parameters characterizing the internal characteristic parameters can be measured when the power battery is retired as a target retired power battery cell group, or can be measured when it is stored in the warehouse.

[0093] This embodiment also provides a retired power battery matching and reorganization device, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the terms "module", "unit", "subunit", etc. can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0094] Figure 3 is a structural block diagram of a retired power battery matching and recombination device according to an embodiment of the present application, such as Figure 3 As shown, the device includes an acquisition module 31, a sorting module 32, a planning module 33 and a processing module 34, wherein: The acquisition module 31 is used to obtain target information of multiple target retired power cells to be reassembled, wherein each target information includes multiple target indicator parameters, and the target indicator parameter is used to characterize a characteristic parameter of the corresponding target retired power cell, and the characteristic parameter is at least used to characterize the current storage state of the target retired power cell.

[0095] The sorting module 32 is coupled to the acquisition module 31, and is used to pre-process the multiple target indicator parameters corresponding to each target retired power cell to generate the corresponding multiple standard feature parameters, and then use the trained consistency sorting model to process the multiple standard feature parameters corresponding to each target retired power cell to obtain the classification label data corresponding to the sorted multiple retired power cell sets, wherein the classification label data includes a reorganization adaptation level for characterizing the priority of the retired power cell set applied to the tiered scenario during the reorganization process, and the consistency sorting model is a machine learning model trained based on the fuzzy c-means clustering algorithm, and is trained to generate classification label data corresponding to the corresponding retired power cell set according to the input battery feature parameters.

[0096] The planning module 33 is coupled to the sorting module 32, and is used to perform battery reorganization configuration planning iterations based on pre-acquired battery demand parameters, multiple retired power cell sets and corresponding classification label data using an improved artificial bee colony algorithm to generate corresponding reorganization configuration information, wherein the reorganization configuration information includes target information corresponding to the retired power cells corresponding to the reorganized power battery pack.

[0097] The processing module 34 is coupled to the planning module 33, and is used to perform production scheduling for the production order demand information and the reorganization configuration information using a preset heuristic algorithm after determining the production order demand information corresponding to the battery demand parameters, and to reorganize the power batteries according to the generated target production scheduling information to obtain multiple reorganized power batteries.

[0098] In some embodiments, the planning module 33 further includes: A configuration unit, configured to perform battery reconfiguration configuration using an improved artificial bee colony algorithm according to the classification label data corresponding to the plurality of retired power cell sets, and generate first reconfiguration configuration information, wherein the first reconfiguration configuration information includes target retired power cells selected for a first power battery group, and the first power battery group is used to represent a power battery group currently reconfigured; an acquisition unit coupled to the configuration unit, and configured to acquire a first fitness corresponding to each first power battery pack from the first reorganization configuration information, wherein the first fitness is calculated based on an adaptation function constructed based on classification label data corresponding to target retired power cells allocated to each first power battery pack, and is used to characterize the performance excellence of the first power battery pack; The determination unit is coupled to the acquisition unit and is used to determine the target fitness corresponding to the demand battery group corresponding to the battery demand parameter, and according to the difference between the first fitness and the target fitness, iterate the local search, neighborhood optimization and global search based on the improved artificial bee colony algorithm for the first reorganization configuration information until the difference is no more than a preset threshold, and generate the reorganization configuration information, wherein in the global search stage, the improved artificial bee colony algorithm introduces dynamic neighborhood adjustment and local optimal escape mechanism.

[0099] In some of the embodiments, the configuration unit is also used to obtain coding information and classification label data corresponding to all retired power cells in a set of multiple retired power cells, wherein the coding information is generated based on the target information of the retired power cells; randomly assign codes to each of the multiple coding information to obtain multiple coding bodies corresponding to multiple first power battery groups, wherein one coding body corresponds to the reorganization configuration result of one first power battery group; determine the battery capacity, discharge rate, life span and battery internal resistance corresponding to the classification label data corresponding to each target retired power cell, and calculate the first fitness corresponding to each coding body based on the adaptation function constructed based on the battery capacity, discharge rate, life span and battery internal resistance, wherein when constructing the adaptation function, the weights corresponding to the battery capacity, discharge rate, life span and battery internal resistance are dynamically updated based on the battery demand parameters; and generate multiple coding bodies and the first fitness corresponding to each coding body as the first reorganization configuration information.

[0100] In some of the embodiments, the determination unit is further used to generate a first neighborhood solution for all coding bodies in the first reorganization configuration information based on an artificial bee colony algorithm, and to randomly permute the target retired power cells corresponding to the randomly selected first neighborhood solutions to generate multiple second coding bodies, wherein the randomly permuted target retired power cells are target retired power cells in the same retired power cell set, and the second coding body is used to characterize the configuration result of the power battery pack reorganized in the local search phase; after selecting a second coding body having a fitness value greater than a fitness threshold from multiple second coding bodies according to the fitness corresponding to the second coding body, determine a candidate coding body that does not belong to a preset optimal coding body pool among the selected multiple candidate coding bodies, generate a second neighborhood solution for the determined candidate coding body, and use all second neighborhood solutions and candidate coding bodies belonging to the optimal coding body pool among the multiple candidate coding bodies as a third coding body, wherein , all the code bodies stored in the optimal code body pool are the optimal code bodies obtained based on the memory mechanism, and the third code body is used to characterize the configuration result of the power battery group reorganized in the neighborhood optimization stage; for the target retired power cell corresponding to the randomly selected third code body, a random global search is performed within the set global search range to generate a candidate code body that satisfies the local optimal escape mechanism, and the generated multiple candidate code bodies are used as the candidate reorganization configuration information corresponding to the iteration, wherein the global search range is determined by introducing random factors and a large-scale search mechanism, and the local optimal escape mechanism is used to characterize that when the generated candidate code body is the optimal solution, the global search range is stopped from being expanded; the steps of generating the corresponding candidate reorganization configuration information are repeated until the difference between the fitness of the candidate reorganization configuration information and the target fitness is not greater than the preset threshold, and the candidate reorganization configuration information with a difference not greater than the preset threshold is used as the reorganization configuration information.

[0101] In some embodiments, the heuristic algorithm includes a parthenogenetic algorithm based on simulated annealing, and the processing module 34 further includes: An encoding unit, used to obtain a battery pack number corresponding to a target power battery pack of the reorganization configuration from the reorganization configuration information, and to perform random linear encoding on multiple battery pack numbers to obtain an initial linear encoding body set, wherein each first linear encoding individual in the initial linear encoding body set is used to represent a production scheduling information for reorganizing all target power battery packs, and the production scheduling information includes a production line and assembly time allocated to each target power battery pack; A calculation unit is coupled to the encoding unit and is used to obtain first production scheduling information corresponding to each first linear coding individual obtained by decoding the initial linear coding set, and calculate the reorganization fitness corresponding to each first linear coding individual according to the assembly time of each target power battery pack extracted from the first production scheduling information, wherein the reorganization fitness is used to characterize the processing time length of the reorganization of the target power battery pack; a judgment unit, coupled to the calculation unit, for judging whether the recombination fitness values ​​corresponding to all current linear coding individuals generated by completing the current iteration are less than a preset recombination fitness threshold, wherein the current linear coding individual includes one of the first linear coding individual and the linear coding individual generated by completing the previous iteration; The operation unit is coupled to the judgment unit and is used to perform simulated annealing operation iterations based on all current linear coding individuals and a parthenogenetic algorithm based on simulated annealing when it is judged that the recombination fitness values ​​of all current linear coding individuals are not less than the recombination fitness threshold, until the recombination fitness value of the generated target linear coding individual is less than the recombination fitness threshold, and use the production scheduling information obtained by decoding all target linear coding individuals as the target production scheduling information, wherein the simulated annealing operation includes selection, mutation, receiving a new solution based on the Metropolis criterion, and cooling.

[0102] In some embodiments, the sorting module 32 further comprises: An extraction unit, used to obtain characteristic parameters corresponding to each target retired power cell in the obtained target information of each target retired power cell, wherein the characteristic parameters include at least one of the following: cell capacity, cell internal resistance, open circuit voltage, depth of discharge and state of charge; The generating unit is coupled with the extracting unit and is used to filter, reduce noise, add or delete missing values, and delete outliers on the characteristic parameters to generate multi-dimensional indicator parameters, wherein the adding or deleting of missing values ​​includes filling missing values ​​and removing missing values, and the filling of missing values ​​includes filling by using one of the average method, the median method, and the interpolation method, and the outlier deletion uses one of the following methods to detect the deleted outliers: the mean method, the standard deviation method, the box plot method, and the outlier detection method; The processing unit is coupled to the generating unit and is used for normalizing the multi-dimensional index parameters and extracting key features to obtain standard feature parameters corresponding to the characteristic parameters.

[0103] In some of the embodiments, the retired power battery matching and reorganization device also obtains a preset training sample set, wherein the training sample set includes characteristic parameters corresponding to multiple sample retired power cells; performs corresponding preprocessing on the characteristic parameters in the training sample set to generate standard characteristic parameters corresponding to each sample retired power cell; after selecting an initial clustering center from the standard characteristic parameters corresponding to all sample retired power cells, based on the initial clustering center and the standard characteristic parameters corresponding to all sample retired power cells, performs iterations of membership matrix calculation and clustering center update corresponding to the fuzzy c-means clustering algorithm until the membership matrix converges to generate a consistency sorting model.

[0104] In some embodiments, the planning module 33 is also used to obtain historical battery demand order data, wherein the historical battery demand order data includes order parameters and time parameters, the order parameters include the number of battery demand orders, the required battery pack capacity, the battery pack discharge rate, and the battery pack life, and the time parameters include at least the order timestamp; the order parameters and time parameters corresponding to the historical battery demand order data are cleaned to generate first order data, wherein the data cleaning includes at least one of the following: using mean filling, interpolation or elimination methods to process missing values ​​of order parameters and time parameters; using one of the mean method, standard deviation method and box plot method to detect outliers of order parameters and time parameters, and deleting the detected outliers; using feature engineering to process the first order data to generate order feature data, and using the trained order demand prediction model to process the order feature data to predict and output battery demand parameters, wherein the order demand prediction model is a classification prediction model trained based on the CART algorithm, and is trained to predict and output order demand corresponding to the first feature data based on the input first feature data.

[0105] This embodiment further provides a service system, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0106] Optionally, the above-mentioned reorganization and configuration system may further include a transmission device and an input-output device, wherein the transmission device is connected to the above-mentioned processor, and the input-output device is connected to the above-mentioned processor.

[0107] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program: S1, obtaining target information of multiple target retired power cells to be reassembled, wherein each target information includes multiple target indicator parameters, and the target indicator parameter is used to characterize a characteristic parameter of the corresponding target retired power cell, and the characteristic parameter is at least used to characterize the current storage state of the target retired power cell.

[0108] S2, after preprocessing the multiple target indicator parameters corresponding to each target retired power cell and generating the corresponding multiple standard feature parameters, use the trained consistency sorting model to process the multiple standard feature parameters corresponding to each target retired power cell to obtain classification label data corresponding to the sorted multiple retired power cell sets, wherein the classification label data includes a reorganization adaptation level for characterizing the priority of the retired power cell set applied to the tiered scenario during the reorganization process, and the consistency sorting model is a machine learning model trained based on the fuzzy c-means clustering algorithm, and is trained to generate classification label data corresponding to the corresponding retired power cell set according to the input battery feature parameters.

[0109] S3, based on the pre-acquired battery demand parameters, multiple retired power cell sets and corresponding classification label data, use the improved artificial bee colony algorithm to iterate the battery reorganization configuration planning and generate corresponding reorganization configuration information, wherein the reorganization configuration information includes target information corresponding to the retired power cells corresponding to the reorganized power battery pack.

[0110] S4, after determining the production order demand information corresponding to the battery demand parameters, use a preset heuristic algorithm to perform production scheduling on the production order demand information and the reorganization configuration information, and reorganize the power batteries according to the generated target production scheduling information to obtain multiple reorganized power batteries.

[0111] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0112] In addition, in combination with the retired power battery matching and reorganization method in the above embodiments, the present application embodiment can provide a storage medium for implementation. The storage medium stores a computer program; when the computer program is executed by a processor, any retired power battery matching and reorganization method in the above embodiments is implemented.

[0113] Those skilled in the art should understand that the technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0114] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for reorganizing retired power batteries, characterized in that: include: Obtaining target information of a plurality of target retired power cells to be reassembled, wherein each of the target information includes a plurality of target indicator parameters, the target indicator parameters are used to characterize a characteristic parameter of the corresponding target retired power cell, and the characteristic parameter is at least used to characterize a current storage state of the target retired power cell; After preprocessing the multiple target indicator parameters corresponding to each of the target retired power cells to generate the corresponding multiple standard feature parameters, the multiple standard feature parameters corresponding to each of the target retired power cells are processed using the trained consistency sorting model to obtain classification label data corresponding to the selected multiple retired power cell sets, wherein the classification label data includes a reorganization adaptation level for characterizing the priority of the retired power cell set in the echelon scenario during the reorganization process, and the consistency sorting model is a machine learning model trained based on a fuzzy c-means clustering algorithm, and is trained to generate classification label data corresponding to the corresponding retired power cell set according to the input battery feature parameters; Based on the pre-acquired battery demand parameters, the multiple retired power cell sets and the corresponding classification label data, the improved artificial bee colony algorithm is used to iterate the battery reorganization configuration planning to generate corresponding reorganization configuration information, wherein the reorganization configuration information includes the target information corresponding to the retired power cell corresponding to the reorganized power battery group; After determining the production order demand information corresponding to the battery demand parameters, a preset heuristic algorithm is used to perform production scheduling on the production order demand information and the reorganization configuration information, and the power batteries are reorganized according to the generated target production scheduling information to obtain multiple reorganized power batteries.

2. The method according to claim 1, characterized in that Based on the pre-acquired battery demand parameters, the plurality of retired power cell sets and the corresponding classification label data, the improved artificial bee colony algorithm is used to iterate the battery reorganization configuration planning to generate corresponding reorganization configuration information, including: According to the classification label data corresponding to the plurality of retired power cell sets, the improved artificial bee colony algorithm is used to perform battery reorganization configuration to generate first reorganization configuration information, wherein the first reorganization configuration information includes the target retired power cells selected for the first power battery group, and the first power battery group is used to represent the power battery group currently reorganized and configured; Acquire a first fitness corresponding to each of the first power battery packs from the first reorganization configuration information, wherein the first fitness is calculated based on an adaptation function constructed based on the classification label data corresponding to the target retired power cells allocated to each of the first power battery packs, and is used to characterize the performance excellence of the first power battery packs; Determine the target fitness corresponding to the demand battery group corresponding to the battery demand parameter, and according to the difference between the first fitness and the target fitness, perform local search, neighborhood optimization and global search iterations based on the improved artificial bee colony algorithm on the first reorganization configuration information until the difference is no more than a preset threshold, and generate the reorganization configuration information, wherein, in the global search stage, the improved artificial bee colony algorithm introduces dynamic neighborhood adjustment and local optimal escape mechanism.

3. The method according to claim 2, characterized in that According to the classification label data corresponding to the plurality of retired power cell sets, the improved artificial bee colony algorithm is used to perform battery reconfiguration to generate first reconfiguration configuration information, including: Acquire the coding information and the classification label data corresponding to all the retired power cells in the plurality of retired power cell sets, wherein the coding information is generated according to the target information of the retired power cells; Randomly assigning codes to each of the plurality of coding information to obtain a plurality of coding bodies corresponding to the plurality of the first power battery packs, wherein one coding body corresponds to a reorganization configuration result of one of the first power battery packs; Determine the battery capacity, discharge rate, life span and battery internal resistance corresponding to the classification label data corresponding to each of the target retired power cells, and calculate the first fitness corresponding to each of the encoded bodies based on the adaptation function constructed based on the battery capacity, the discharge rate, the life span and the battery internal resistance, wherein when constructing the adaptation function, the weights corresponding to the battery capacity, the discharge rate, the life span and the battery internal resistance are dynamically updated based on the battery demand parameters; The plurality of encoding bodies and the first fitness corresponding to each encoding body are generated as the first recombinant configuration information.

4. The method according to claim 3, characterized in that According to the difference between the first fitness and the target fitness, the first reorganization configuration information is iterated by local search, neighborhood optimization and global search based on the improved artificial bee colony algorithm, including: Based on the artificial bee colony algorithm, a first neighborhood solution is generated for all the code bodies in the first reorganization configuration information, and the target retired power cells corresponding to the randomly selected first neighborhood solutions are randomly replaced to generate multiple second code bodies, wherein the randomly replaced target retired power cells are the target retired power cells in the same set of retired power cells, and the second code bodies are used to characterize the configuration results of the power battery group reorganized in the local search phase; After selecting the second coding body whose fitness value is greater than the fitness threshold from the plurality of second coding bodies according to the fitness corresponding to the second coding body, determining the candidate coding body that does not belong to the preset optimal coding body pool among the selected plurality of candidate coding bodies, and performing second neighborhood solution generation on the determined candidate coding body, and using all the second neighborhood solutions and the candidate coding body that belongs to the optimal coding body pool among the plurality of candidate coding bodies as the third coding body, wherein all the coding bodies stored in the optimal coding body pool are optimal coding bodies obtained based on the memory mechanism, and the third coding body is used to characterize the configuration result of the power battery pack reorganized in the neighborhood optimization stage; For the target retired power cell corresponding to the randomly selected third code body, a random global search is performed within a set global search range to generate a candidate code body that satisfies the local optimal escape mechanism, and the generated multiple candidate code bodies are used as candidate reorganization configuration information corresponding to the current iteration, wherein the global search range is determined by introducing random factors and a large-scale search mechanism, and the local optimal escape mechanism is used to indicate that when the generated candidate code body is the optimal solution, the global search range is stopped from being expanded; Repeat the step of generating the corresponding candidate recombination configuration information until the difference between the fitness of the candidate recombination configuration information and the target fitness is not greater than a preset threshold, and use the candidate recombination configuration information whose difference is not greater than the preset threshold as the recombination configuration information.

5. The method according to claim 1, characterized in that The heuristic algorithm includes a parthenogenetic algorithm based on simulated annealing, and the production order demand information and the reorganization configuration information are subjected to production scheduling using a preset heuristic algorithm, including: From the reorganization configuration information, obtain the battery pack number corresponding to the target power battery pack of the reorganization configuration, perform random linear coding on the multiple battery pack numbers, and obtain an initial linear coding body set, wherein each first linear coding individual in the initial linear coding body set is used to represent a production scheduling information for reorganizing all the target power battery packs, and the production scheduling information includes the production line and assembly time allocated to each target power battery pack; Obtaining first production scheduling information corresponding to each first linear code individual obtained by decoding the initial linear code set, and calculating the reorganization fitness corresponding to each first linear code individual according to the assembly time of each target power battery pack extracted from the first production scheduling information, wherein the reorganization fitness is used to characterize the processing time length for reorganizing the target power battery pack; Determine whether the recombination fitness values ​​corresponding to all current linear coding individuals generated by completing the current iteration are less than a preset recombination fitness threshold, wherein the current linear coding individual includes one of the first linear coding individual and the linear coding individual generated by completing the previous iteration; In the case where it is determined that the recombination fitness values ​​of all the current linear coding individuals are not less than the recombination fitness threshold, a simulated annealing operation is iterated based on all the current linear coding individuals and the parthenogenetic algorithm based on simulated annealing until the recombination fitness value of the generated target linear coding individual is less than the recombination fitness threshold, and the production scheduling information obtained by decoding all the target linear coding individuals is used as the target production scheduling information, wherein the simulated annealing operation includes selection, mutation, receiving a new solution based on the Metropolis criterion, and cooling.

6. The method according to claim 1, characterized in that Preprocessing the multiple target indicator parameters corresponding to each of the target retired power cells to generate corresponding multiple standard feature parameters, including: In the target information of each of the target retired power cells obtained, characteristic parameters corresponding to each of the target retired power cells are obtained, wherein the characteristic parameters include at least one of the following: cell capacity, cell internal resistance, open circuit voltage, depth of discharge, and state of charge; The characteristic parameters are filtered, denoised, missing values ​​are added and deleted, and outliers are deleted to generate multi-dimensional indicator parameters, wherein the missing value addition and deletion include missing value filling and missing value removal, the missing value filling includes filling by using one of the average method, the median method and the interpolation method, and the outlier deletion uses one of the following methods to detect the deleted outliers: mean method, standard deviation method, box plot method, outlier detection method; The multi-dimensional index parameters are normalized and key features are extracted to obtain the standard feature parameters corresponding to the characteristic parameters.

7. The method according to claim 1, characterized in that Training of the consistency sorting model includes: Obtaining a preset training sample set, wherein the training sample set includes the characteristic parameters corresponding to a plurality of sample retired power cells; Preprocess the characteristic parameters in the training sample set accordingly to generate the standard characteristic parameters corresponding to each of the sample retired power cells; After selecting the initial cluster center from the standard characteristic parameters corresponding to all the sample retired power cells, based on the initial cluster center and the standard characteristic parameters corresponding to all the sample retired power cells, the membership matrix calculation and cluster center update corresponding to the fuzzy c-means clustering algorithm are iterated until the membership matrix converges to generate the consistency sorting model.

8. The method according to claim 1, characterized in that Get battery requirement parameters, including: Acquire historical battery demand order data, wherein the historical battery demand order data includes order parameters and time parameters, the order parameters include battery demand order quantity, required battery pack capacity, battery pack discharge rate, and battery pack life span, and the time parameters include at least an order timestamp; Performing data cleaning on the order parameters and the time parameters corresponding to the historical battery demand order data to generate first order data, wherein the data cleaning includes at least one of the following: processing missing values ​​of the order parameters and the time parameters by using a mean filling, interpolation or elimination method; detecting abnormal values ​​of the order parameters and the time parameters by using one of a mean method, a standard deviation method and a box plot method, and deleting the detected abnormal values; The first order data is processed by feature engineering to generate order feature data, and the order feature data is processed by a trained order demand prediction model to predict and output the battery demand parameters, wherein the order demand prediction model is a classification prediction model trained based on the CART algorithm, and is trained to predict and output the order demand corresponding to the first feature data based on the input first feature data.

9. A service system, comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps of the retired power battery recombination method according to any one of claims 1 to 8.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the retired power battery recombination method according to any one of claims 1 to 8 is implemented.

Images