Matching decision method and system for storage and reorganization linkage management of retired power batteries

Abstract

The present application relates to a matching decision method and system for storage and reorganization linkage management of retired power batteries, the method comprising: after receiving reorganization correction information, detecting at least one reorganization decision information to be executed from first reorganization matching decision information, and associating one reorganization decision information with one first reorganization order; combining the dynamic reorganization order corresponding to the reorganization correction information with all first reorganization orders into a second reorganization order, encoding and population initialization of all second reorganization orders according to a preset mixed integer programming, and generating multiple candidate coding individuals; based on a preset catastrophe adaptive genetic algorithm, mixed integer programming, and the fitness corresponding to the candidate coding individuals participating in each iteration, iterating genetic evolution operations and population catastrophe operations on multiple corresponding candidate coding individuals until multiple intended coding individuals are generated; obtaining a target coding individual from the multiple intended coding individuals, and obtaining a decision result including the target coding individual.

Description

Technical Field

[0001] The present application relates to the technical field of cascade utilization of retired power batteries, and in particular to a matching decision method and system for storage and reorganization linkage management of 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 reach a retired state where they can no longer meet the needs of vehicle use. Retired power batteries still have a certain residual capacity and can be used in scenarios such as energy storage. In related technologies, the methods of power battery recycling and reuse include disassembly recycling and cascade utilization. Cascade utilization is becoming increasingly popular in power battery recycling because it can extend the life cycle value of the battery and achieve full utilization of resources.

[0003] In the process of cascade utilization of retired power batteries, how to efficiently match and reorganize the disassembled batteries is the key to ensuring their benefits. Reorganized power batteries require that each single cell or module battery has high consistency in parameters such as health state (SOH), internal resistance, and capacity to ensure the performance stability and service life of the reorganized battery pack.

[0004] In the related technologies, since the disassembled battery raw materials include battery modules and battery cells, these materials have significant differences in parameters and are stored mixed in the warehouse, and due to the complexity of the reorganization and matching methods of tiered products, the warehouse management and production workshop scheduling efficiency are facing great pressure; at the same time, in the related technologies, there are also difficulties in matching order demand with production, that is, under the premise of meeting battery consistency, it is impossible to complete the selection and reorganization of battery raw materials efficiently and timely.

[0005] In the related technology, the cascade utilization of retired power batteries is complicated, resulting in low efficiency in warehouse management and production workshop scheduling, and no effective solution has been proposed yet. Summary of the Invention

[0006] The embodiments of the present application provide a matching decision method and system for the storage and reorganization linkage management of retired power batteries, so as to at least solve the problem of low efficiency in warehouse management and production workshop scheduling caused by the complexity of the reorganization matching method in the cascade utilization of retired power batteries in the related art.

[0007] In the first aspect, an embodiment of the present application provides a matching decision method for storage and reorganization linkage management of retired power batteries, comprising: after receiving reorganization correction information, detecting at least one reorganization decision information to be executed from the first reorganization matching decision information generated by the current decision, wherein the reorganization decision information is used to characterize the matching decision of the reorganized power battery corresponding to a production order demand information, and one reorganization decision information is associated with a first reorganization order; combining the dynamic reorganization order corresponding to the reorganization correction information with all the first reorganization orders into a second reorganization order, and encoding and population initialization of all the second reorganization orders according to a preset mixed integer programming to generate multiple candidate coding individuals, wherein the mixed integer programming includes multiple target sub- function and multiple target sub-constraint parameters, the sub-code corresponding to the candidate coding individual is encoded and generated according to the corresponding target sub-function and the target sub-constraint parameters, and is used to represent the reorganization decision information; based on the preset catastrophe adaptive genetic algorithm, the mixed integer programming and the fitness corresponding to the candidate coding individual participating in each iteration, the multiple corresponding candidate coding individuals are iterated by genetic evolution operations and population catastrophe operations until multiple intention coding individuals are generated, wherein the fitness is determined according to the collaborative operation cost parameter associated with the target sub-function corresponding to the sub-code corresponding to the candidate coding individual; a target coding individual is obtained from the multiple intention coding individuals to obtain a decision result including the target coding individual.

[0008] In a second aspect, an embodiment of the present application provides a service system comprising 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 matching decision method for storage and reorganization linkage management of retired power batteries as described in the first aspect.

[0009] Compared with the related art, the matching decision method and system for the storage and reorganization linkage management of retired power batteries provided in the embodiment of the present application adopts the method of detecting at least one reorganization decision information to be executed from the first reorganization matching decision information generated by the current decision after receiving the reorganization correction information, wherein the reorganization decision information is used to characterize the matching decision of the reorganized power battery corresponding to a production order demand information, and one reorganization decision information is associated with a first reorganization order; the dynamic reorganization order corresponding to the reorganization correction information is combined with all the first reorganization orders into a second reorganization order, and all the second reorganization orders are encoded and the population is initialized according to the preset mixed integer programming to generate multiple candidate coding individuals, wherein the mixed integer programming includes multiple objective sub-functions and multiple objective sub-constraint parameters, and the sub-code corresponding to the candidate coding individual is encoded and generated according to the corresponding objective sub-function and the target sub-constraint parameter, and is used to characterize one reorganization decision information. Information; based on the preset catastrophe adaptive genetic algorithm, the mixed integer programming and the fitness corresponding to the candidate coding individuals participating in each iteration, the genetic evolution operation and the population catastrophe operation are iterated on the multiple corresponding candidate coding individuals until a plurality of intention coding individuals are generated, wherein the fitness is determined according to the collaborative operation cost parameter associated with the target sub-function corresponding to the sub-coding corresponding to the candidate coding individual; the target coding individual is obtained from the multiple intention coding individuals, and the decision result including the target coding individual is obtained, which solves the problem of low efficiency in warehouse management and production workshop scheduling caused by the complexity of the reorganization matching method in the cascade utilization of retired power batteries in the related technology. Through the matching decision method of the present application, the cascade utilization enterprise reduces the complexity of reorganization production, strengthens the effective management of warehouses, improves warehouse turnover, reduces inventory costs, optimizes the cascade utilization process of retired power batteries, improves the operational efficiency of the enterprise, and ensures the timely delivery of orders.

[0010] The 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:

[0012] Figure 1 This is a hardware structure block diagram of a terminal for a matching decision method for storage and reorganization linkage management of retired power batteries according to an embodiment of the present application;

[0013] Figure 2This is a flowchart of a matching decision method for storage and reorganization linkage management of retired power batteries according to an embodiment of the present application;

[0014] Figure 3 is a schematic diagram of a chromosome according to an embodiment of the present application;

[0015] Figure 4 is a schematic diagram of a combination of battery raw materials according to a preferred embodiment of the present application;

[0016] Figure 5 This is a structural block diagram of a matching decision device for storage and reorganization linkage management of retired power batteries according to an embodiment of the present application. DETAILED DESCRIPTION

[0017] 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 examples. 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 the contents disclosed in the present application being insufficient.

[0018] References to "embodiments" in this application mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it refer to independent or alternative embodiments that are mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described in this application may be combined with other embodiments unless there is a conflict.

[0019] Unless otherwise defined, technical or scientific terms used in this application shall have the ordinary meaning as understood by persons of ordinary skill in the art to which this application belongs. The use of "a," "an," "an," "the," and similar expressions in this application does not denote a limitation of quantity and may refer to either the singular or the plural. The terms "comprise," "include," "have," and any variations thereof, as used in this application, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device comprising a series of steps or modules (units) is not limited to the listed steps or units but may also include steps or units not listed, or may include other steps or units inherent to the process, method, product, or device. As used in this application, "multiple steps" means two or more steps. "And / or" describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" may mean: A exists alone, A and B exist simultaneously, or B exists alone. The terms "first," "second," and "third," etc., as used in this application, simply distinguish similar objects and do not imply a specific ordering of the objects.

[0020] Before describing the matching decision method according to the embodiment of the present application, the technical problem to be solved by the present application and the background of the present application are described as follows:

[0021] The following describes the related technologies used in the embodiments of this application:

[0022] Genetic algorithms (GAs) are heuristic search algorithms inspired by natural selection and evolution. Traditional GAs mimic the biological processes of genetic mutation, crossover, and survival of the fittest to find optimal solutions. However, for certain types of problems, particularly those with high dimensionality, nonlinearity, or multimodal characteristics, standard GAs can suffer from slow convergence and a tendency to get stuck in local optima. Consequently, related technologies are exploring improved GAs, such as adaptive GAs.

[0023] Adaptive Genetic Algorithm (AGA) dynamically adjusts algorithm parameters (such as mutation probability and crossover probability) to respond to different problem characteristics and the needs of the evolution stage, thereby improving the robustness and optimization efficiency of the algorithm.

[0024] The new Catastrophe Adaptive Genetic Algorithm (CAGA) builds upon the foundation of the AGA by further incorporating the principles of catastrophe theory, a mathematical theory that studies sudden changes in systems. It helps us understand the behavior of systems approaching critical points. By detecting declining population diversity or other signals that indicate the algorithm may be trapped in a local optimum, the CAGA applies timely catastrophic operations (such as large-scale perturbations or reinitialization of some individuals) to disrupt the existing state and promote the emergence of new, superior solutions. This advanced genetic algorithm combines adaptive capabilities with catastrophe theory. Its key feature is its ability to dynamically adjust algorithm parameters based on the characteristics of the problem and the state of algorithm evolution. It can also take aggressive measures, when necessary, to prevent premature convergence, thereby improving the efficiency and effectiveness of problem solving.

[0025] Mixed Integer Programming (MIP) is an optimization problem that combines features of linear programming and integer programming. In a MIP problem, some decision variables are continuous (can take any real value), while others are discrete (can only take integer values).

[0026] 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 1 This is a hardware structure block diagram of a terminal for a matching decision method for storage and reorganization linkage management of retired power batteries 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) a processor 102 (the processor 102 may include but is not limited to 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 will 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 than shown, or with Figure 1 Different configurations shown.

[0027] 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 matching decision method for the storage and reorganization linkage management of retired power batteries 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, implementing the above-mentioned 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 located 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 combinations thereof.

[0028] Transmission device 106 is used to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by the terminal's communications provider. In one embodiment, transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0029] This embodiment provides a matching decision method for storage and reorganization linkage management of retired power batteries, which runs on the above-mentioned terminal. Figure 2 Flowchart of a matching decision method for storage and reorganization linkage management of retired power batteries according to an embodiment of the present application, such as Figure 2 As shown, the process includes the following steps:

[0030] Step S201, after receiving the reorganization correction information, detect at least one reorganization decision information to be executed from the first reorganization matching decision information that has been previously generated, wherein the reorganization decision information is used to represent the matching decision of the reorganized power battery corresponding to a production order demand information, and one reorganization decision information is associated with one first reorganization order.

[0031] In this embodiment, the execution subject of the matching decision method of the embodiment of the present application is a digital twin system deployed in a recycling enterprise, and based on the macro perspective of the manager of the recycling enterprise, it realizes the accurate tracking and efficient allocation of battery raw material resources in the warehouse, ensuring that each retired power battery can be maximized, reasonably allocating raw material resources, and completing more customer orders; in this embodiment, the decision result is a battery product reorganization matching plan made according to the order demand information, which does not include the system layout design and picking path of the warehouse, but includes the material outbound plan, that is, the decision-making plan of the reorganization decision information of the reorganized battery that meets the order demand information. The reorganization decision information includes the battery type, battery material type, battery component type (battery module, battery cell), and specifications (quantity) used for the reorganized production of each order. At the same time, after the reorganization decision information is determined, it will also map or manage the start of reorganization of each order in each process of each reorganization workshop. time, and the time when all materials in the warehouse are shipped out; it can be understood that, in this embodiment, the selection of the battery component type by the reorganization decision information is based on the storage cost, turnover cost and safety maintenance cost of the warehouse, that is, the decision result is based on the coordination of warehousing and reorganization, and the warehousing and reorganization coordination of the embodiment of the present application means that when making matching decisions, it is necessary to consider the benefits of each reorganization workshop (for example: reorganization production time, reorganization production cost) and the penalty cost caused by order delays, and the benefits of the warehouse (for example: the turnover rate of different battery raw materials, the storage cost of all raw materials) also need to be considered. For example: when making decisions, if only the use of battery modules for reorganization is considered, although the reorganization time and cost can be reduced, it will cause a large backlog of battery cells in the warehouse, which is not conducive to the turnover of the warehouse and increases the safety maintenance cost of the warehouse for the battery cells.

[0032] In this embodiment, before the current moment, the reorganization workshop will carry out the reorganization production of retired power batteries according to all the reorganization decision information corresponding to the first reorganization matching decision information, including picking up battery raw materials in the warehouse, temporarily storing the battery raw materials in the warehouse buffer area, transporting the buffered battery raw materials to the reorganization workshop, and transporting the battery cost reorganization production to the finished product warehouse after the reorganization workshop completes the battery cost reorganization production; at the current moment, the execution subject detects that a dynamic event has occurred (for example, an emergency insertion order has been generated). At this time, it is necessary to adjust and re-plan the first reorganization matching decision information. It can be understood that at the current moment, there will be unfinished reorganization orders, that is, there will be unexecuted reorganization decision information. When re-planning the corresponding reorganization matching decision information, it is necessary to first determine the reorganization order corresponding to the unexecuted reorganization decision information, that is, the first reorganization order (corresponding to the production order that has not been reorganized), and then match the first reorganization order and the dynamically added reorganization order (that is, the dynamic reorganization order). The first reorganization matching decision information is combined into a reorganization order corresponding to the current one, and then the reorganization matching decision information is re-planned in combination with the current production capacity of the reorganization workshop and the warehouse; in this embodiment, the first reorganization matching decision information determines its corresponding content according to the dynamic attributes generated at the current moment. When the dynamic occurs in the first decision, the first reorganization matching decision information and the reorganization decision information to be executed are empty; when the dynamic occurs in a non-first decision, the first reorganization matching decision information is generated by the previous decision planning, for example: the first reorganization matching decision information includes but is not limited to the reorganization matching decision information generated by planning according to the decision steps of this embodiment based on the full-factor data collected in real time for the first time. At the current moment, there is corresponding reorganization decision information to be executed; for example: when the dynamic occurs, two matching decisions have been completed, and the first reorganization matching decision information is the reorganization matching decision information generated by the second matching decision.

[0033] In step S202, the dynamic reorganization order corresponding to the reorganization correction information is combined with all the first reorganization orders into a second reorganization order, and all the second reorganization orders are encoded and population initialized according to a preset mixed integer programming to generate multiple candidate coding individuals, wherein the mixed integer programming includes multiple target sub-functions and multiple target sub-constraint parameters, and the sub-code corresponding to the candidate coding individual is generated by encoding according to the corresponding target sub-function and target sub-constraint parameters, and is used to represent a reorganization decision information.

[0034] In this embodiment, for all second reorganization orders corresponding to retired power batteries to be reorganized, before generating reorganization decision information, it is necessary to convert the decision variables and target variables in the reorganization decision information corresponding to the second reorganization order into corresponding mathematical models to describe the reorganization process of the battery products, that is, to use the target sub-function and target sub-constraint parameters corresponding to the preset mixed integer programming to mathematically model the reorganization of all second reorganization orders; in this embodiment, based on the collected production demand data corresponding to the second reorganization order, a mathematical model is established to describe the reorganization process of the battery products, including cost calculation, resource allocation, and reorganization production planning, with the goal of minimizing the overall operating cost of the warehouse and the reorganization workshop; at the same time, according to constraints such as order demand, complete material delivery, and reorganization production capacity, a reorganization matching plan for the battery products is formulated to ensure that the model can fully reflect the various target sub-constraint parameters and target sub-functions in actual operations; in the target sub-function of the mathematical model in this embodiment, costs of multiple dimensions are associated, for example: reorganization production Production cost, warehouse storage cost, and delivery delay penalty cost are calculated, and the corresponding costs are used as the objective function values ​​of the corresponding objective sub-functions and used to calculate the corresponding fitness. At the same time, in this embodiment, inequalities representing relevant sub-constraint parameters are designed. For example, the various types of battery components used in all orders cannot exceed the inventory. For each order product, the combined capacity and energy of the selected modules and cells must be greater than or equal to the specified capacity and energy required by the product. In this embodiment, based on the collected production demand data corresponding to the second reorganization order, a mathematical model is established to describe the reorganization process of battery products. This is a non-deterministic polynomial problem (NP-Hard). Therefore, a related genetic algorithm is used for solution. Furthermore, it is necessary to genetically encode the relevant information corresponding to the battery reorganization decision, that is, to encode the chromosome genes and initialize the population according to a preset encoding form, forming an initial population corresponding to the collaborative decision matching after dynamic occurrence, that is, an initial population including multiple candidate encoding individuals.

[0035] Step S203, based on the preset catastrophe adaptive genetic algorithm, mixed integer programming and the fitness corresponding to the candidate coding individuals participating in each iteration, the genetic evolution operation and the population catastrophe operation are iterated on multiple corresponding candidate coding individuals until multiple intention coding individuals are generated, wherein the fitness is determined according to the collaborative operation cost parameter associated with the target sub-function corresponding to the sub-coding corresponding to the candidate coding individual.

[0036] In this embodiment, after generating the corresponding initial population, the sub-encoding bodies of the encoding individuals in the initial population are encoded according to mixed integer programming and are NP-Hard problems, which require a genetic algorithm to solve. However, traditional genetic algorithms are prone to falling into local optimal solutions. Therefore, an adaptive genetic algorithm with a catastrophic operation is used to solve the problem that traditional genetic algorithms are prone to falling into local optimal solutions when facing nonlinear, multi-extreme value, and multi-variable problems. It is understandable that the dynamic selection and dynamic crossover mutation performed by the adaptive genetic algorithm are well known to those skilled in the art and do not constitute an unclear limitation of the present technical solution. At the same time, it is also feasible to trigger a catastrophic operation according to a preset catastrophic rule to guide the adaptive genetic algorithm to perform corresponding genetic evolution operation iterations. In this embodiment, based on the fitness of the population individuals in each iteration, it is determined whether to perform a catastrophic operation and whether the population individuals after the iteration (corresponding to the candidate encoding bodies) meet the set requirements, that is, whether they are intended encoding individuals. Through multiple catastrophic operations and genetic evolution operations, the fitness of the individuals in the corresponding population meets the set requirements, thereby obtaining multiple intended encoding bodies.

[0037] In this embodiment, the target sub-functions corresponding to the warehousing subsystem and the recombination subsystem are converted into corresponding fitness functions respectively. The target sub-functions corresponding to the warehousing subsystem and the recombination subsystem are the target sub-functions of the mathematical model in this embodiment. The target function values ​​of multiple target sub-functions (for example: the recombination production cost, warehouse storage cost, and delivery delay penalty cost corresponding to the collaborative operations of the two stages of warehousing and recombination) will be used to calculate the fitness of the corresponding coding individuals; in this embodiment, the higher the fitness, the smaller the corresponding cost, and the better the effect of the candidate coding individuals after the iteration of genetic evolution operations and catastrophe operations.

[0038] Step S204: obtaining a target coding individual from a plurality of intended coding individuals, and obtaining a decision result including the target coding individual.

[0039] In this embodiment, genetic evolution operations and population catastrophe operations are iterated on multiple corresponding candidate coding individuals to generate intentional coding individuals that meet the set requirements (the fitness of the corresponding candidate coding individuals is higher than the set fitness threshold), and target coding individuals are selected from the intentional coding individuals to obtain a decision result including the target coding individual; in this embodiment, although the decision result is the target coding individual, it is actually the reorganization decision information corresponding to all target sub-codes of the target coding individual, that is, the battery product reorganization matching plan made to meet the corresponding order demand information.

[0040] Through the above steps S201 to S204, after receiving the reorganization correction information, at least one reorganization decision information to be executed is detected from the first reorganization matching decision information that has been decided and generated before, wherein the reorganization decision information is used to represent the matching decision of the reorganized power battery corresponding to a production order demand information, and one reorganization decision information is associated with a first reorganization order; the dynamic reorganization order corresponding to the reorganization correction information is combined with all the first reorganization orders into a second reorganization order, and all the second reorganization orders are encoded and the population is initialized according to the preset mixed integer programming to generate multiple candidate coding individuals, wherein the mixed integer programming includes multiple target sub-functions and multiple target sub-constraint parameters, and the sub-code corresponding to the candidate coding individual is encoded and generated according to the corresponding target sub-function and target sub-constraint parameters, and is used to represent a reorganization decision information; based on the preset catastrophe adaptive genetic algorithm Method, mixed integer programming and the fitness corresponding to the candidate coding individuals participating in each iteration, and iterate the genetic evolution operation and population catastrophe operation on multiple corresponding candidate coding individuals until multiple intention coding individuals are generated, wherein the fitness is determined according to the collaborative operation cost parameter associated with the target sub-function corresponding to the sub-code corresponding to the candidate coding individual; obtain the target coding individual from the multiple intention coding individuals, and obtain the decision result including the target coding individual, which solves the problem of low efficiency of warehouse management and production workshop scheduling caused by the complexity of the reorganization matching method in the cascade utilization of retired power batteries in the related technology. Through the matching decision method of this application, the cascade utilization enterprise reduces the complexity of reorganization production, strengthens the effective management of warehouses, improves warehouse turnover, reduces inventory costs, optimizes the cascade utilization process of retired power batteries, improves the operational efficiency of the enterprise, and ensures the timely delivery of orders.

[0041] It should be noted that in order to solve the decision-making problem of the warehousing and reorganization coordination of retired power batteries (corresponding to the reorganization matching of remanufacturing), it is necessary to conduct real-time perception and dynamic interaction of the multi-scale data generated by each operation link of warehousing and reorganization. In the embodiment of the present application, a digital twin (DT) image is used to embody the DT system that is expanded to meet the dynamic decision-making needs of the "warehousing and reorganization" two-stage system of the retired power battery remanufacturing system, and to construct a dynamic matching decision-making information architecture for the two-stage coordination of "warehousing and reorganization" based on the digital twin. The full-factor data of the physical entity is obtained through the physical object warehouse of the DT information architecture (including order information, such as: order arrival time, delivery time, quantity, required specifications, price; specification information, inventory quantity, storage time, storage cost of various types of battery raw materials in the warehouse, real-time production capacity of the reorganization workshop production line, battery material set time, order production online time; according to the vehicle The unit processing time and cost of battery modules and battery cells in different processes obtained from the experience of workers in the remanufacturing workshop are used). DT-related technologies are used to model and instantiate the physical execution units of the remanufacturing system's production logistics process at the virtual image layer of the DT system, mapping them into virtual execution units that can reflect the real-time operating status of the system. In other words, the physical entity is converted into a virtual image in the form of a model (corresponding mathematical function). Finally, the decision control layer of the DT system receives the corresponding data. By comprehensively considering the coordination between the warehouse's material outbound plan and the production plan of the remanufacturing workshop, real-time decisions are made on the matching plan between retired power battery raw materials and battery product demand, guiding on-site operations and achieving intelligent management and control with the lowest operating cost for the entire remanufacturing production logistics system. In other words, by embedding the models and algorithms proposed below, real-time decisions can be made on the matching plan between retired power battery raw materials and battery product demand, and the decision results can guide real-time on-site operations. In this embodiment, digital twin technology is used to solve the problem of information sharing between the remanufacturing workshop and the warehouse. It helps the remanufacturing workshop formulate a reasonable order matching plan based on the inventory status of various types of battery raw materials in the warehouse, its own resources, and order delivery time, and issues a material collection plan to the warehouse. While meeting the order delivery time, it also optimizes the warehouse cycle. Conversion rate and reorganization production cost; in this embodiment, by establishing mixed integer programming, a quantitative optimization of the battery raw material and battery product demand matching decision considering the "warehousing-reorganization" two-stage collaboration with the goal of minimizing the overall operating cost is established, considering the respective constraints of the multi-partition battery raw material complete set outbound and multi-category product reorganization workshop multi-production line production scenarios, solving the challenges faced in the systematic modeling of the battery raw material and battery product demand matching decision problem considering the "multi-partition battery raw material warehouse material outbound plan-multi-category battery product reorganization workshop production plan" collaboration in the remanufacturing production logistics operation system consisting of the two stages of "warehousing-reorganization";In this embodiment, mixed integer programming is an NP-Hard problem, making exact solutions difficult to obtain. Therefore, a genetic algorithm is employed for the solution. However, traditional genetic algorithms are prone to falling into local optimal solutions. In this embodiment, an adaptive genetic algorithm with a catastrophic operation is employed for the solution. It is understood and necessary to understand that the new catastrophic adaptive genetic algorithm is a genetic algorithm that combines catastrophic operation with an adaptive adjustment mechanism. It aims to address the problem of traditional genetic algorithms easily falling into local optimal solutions when faced with nonlinear, multi-extreme value, and multi-variable problems. In this embodiment, the corresponding mathematical models and algorithms are embedded in the decision-making control layer of the digital twin system. The decision-making control layer receives dynamic simulation data, completes the solution by matching the decision model, and transmits the results to the physical object layer, guiding the coordinated operation of the warehouse and the reorganization production workshop, achieving the lowest-cost intelligent management and control of the entire remanufacturing "warehousing-reorganization" operation system.

[0042] It should be further explained that the warehousing and reorganization coordination matching decision method provided in the embodiment of the present application is used to make matching decisions on battery raw materials and battery product demands in the two-stage coordination of warehousing and reorganization, so as to help the reorganization workshop of the retired power battery recycling enterprise to formulate a reasonable material requirement plan (MRP). On the premise of ensuring timely completion of orders, it can not only reduce the complexity of reorganization production, but also strengthen the effective management of warehouses, improve warehouse turnover, and reduce inventory costs, thereby optimizing the retired power battery recycling process and improving the enterprise's operational efficiency.

[0043] In some embodiments, the reorganization decision information includes a reorganization online time, and detecting at least one reorganization decision information to be executed from the first reorganization matching decision information generated by the decision before the current one is implemented by the following steps:

[0044] Step 21: Obtain all the reorganization decision information corresponding to the first reorganization matching decision information, and determine the reorganization online time corresponding to each reorganization decision information, wherein the first reorganization matching decision information is generated by iterating the genetic evolution operation and the population catastrophe operation based on the corresponding fitness of the historical coding body, and the historical coding body is generated by encoding and population initialization according to mixed integer programming based on all the first reorganization orders received before the current time.

[0045] In this embodiment, when the reorganization decision information corresponding to the current decision result is used to operate the reorganization order that matches the production order demand information, when a certain link becomes dynamic (for example, urgently inserting a reorganization order), the reorganization decision information that was already executed before the dynamic (corresponding to dynamic interference) occurs and the associated first reorganization order continue to be executed. At the moment of the dynamic occurrence, the DT system will adjust the reorganization order based on the current production capacity corresponding to the current warehousing subsystem and the reorganization workshop subsystem, the reorganization order corresponding to the unexecuted reorganization decision information (corresponding to the reorganization decision information to be executed), and the reorganization order added by the dynamic interference. The decision result, that is, the need to detect the reorganization decision information to be executed from the first reorganization matching decision information generated before the current decision, is specifically set to correspond to reorganization orders 1, 2, 3, 4, 5, and 6, and the corresponding production sequence is 3, 5, 6, 2, 1, and 4. When reorganization order 6 is executed, dynamics are generated (for example, there is an emergency insertion order 7). At this time, reorganization orders 3, 5, and 6 are executed according to the normal existing reorganization decision information, and the reorganization orders 7, 2, 1, and 4 to be executed are replanned. The reorganization orders to be executed that are detected are reorganization orders 2, 1, and 4.

[0046] It can be understood that in this embodiment, the first reorganization matching decision information determines its corresponding content based on the dynamic attributes generated at the current moment. When the dynamic occurs in the first decision, the first reorganization matching decision information and the reorganization decision information to be executed are empty; when the dynamic occurs in a non-first decision, the first reorganization matching decision information is generated by the previous decision plan. For example: the first reorganization matching decision information includes but is not limited to the reorganization matching decision information generated by planning according to the decision steps of this embodiment based on the full-factor data collected in real time for the first time. At the current moment, there is corresponding reorganization decision information to be executed; for example: when the dynamic occurs, two matching decisions have been completed, and the first reorganization matching decision information is the reorganization matching decision information generated by the second matching decision.

[0047] Step 22: Select the reorganization decision information whose reorganization online time is later than the current time from among all the reorganization decision information to obtain at least one reorganization decision information to be executed.

[0048] In this embodiment, when the DT system establishes a mathematical model based on the corresponding production demand data to describe the reorganization process of retired power batteries, the time element corresponding to the production demand data will be taken into account to at least meet the timely delivery of orders. In this embodiment, the production demand data obtained by the DT system is full-factor data obtained based on the physical object layer of the DT system, including order information, warehousing information and reorganization workshop information, among which the order information includes the arrival time, delivery time, quantity, demand specifications, and price of the order; the warehousing information includes the specification information, inventory quantity, storage time, and storage cost of various types of battery raw materials in the warehouse; the reorganization workshop information includes the real-time production capacity of the reorganization workshop production line, the time when the battery materials are complete, and the storage cost of the reorganization workshop. time, order production launch time, unit processing time and cost of battery modules and battery cells in different processes; it can be understood that the order production launch time in the reorganization workshop information is a factor that affects whether the reorganization order has been executed. Therefore, by determining the order production launch time, that is, the reorganization launch time, it can be determined whether the corresponding reorganization order is in an executed state, thereby detecting the reorganization decision information to be executed, and determining the unexecuted reorganization production orders, and then realizing the adjustment of decision results according to the current production capacity corresponding to the current warehousing subsystem and the reorganization workshop subsystem respectively, the reorganization orders corresponding to the unexecuted reorganization decision information (corresponding to the reorganization decision information to be executed), and the reorganization orders added by dynamic interference.

[0049] In some embodiments, based on a preset catastrophic adaptive genetic algorithm, mixed integer programming, and the fitness of the candidate coding individuals participating in each iteration, iterative genetic evolution operations and population catastrophic operations are performed on a plurality of corresponding candidate coding individuals, which is achieved through the following steps:

[0050] Step 31, according to the target sub-function corresponding to the mixed integer programming, calculate the collaborative operation cost parameter for the sub-codes corresponding to the candidate code individuals participating in the current iteration, and determine the fitness corresponding to each candidate code individual in the current iteration based on the collaborative operation cost parameters corresponding to all sub-codes, wherein the collaborative operation cost parameter is calculated based on the warehousing cost and the reorganization production cost, and the warehousing cost and the reorganization production cost are calculated based on the corresponding target sub-function.

[0051] In this embodiment, a sub-code encoded based on the catastrophe adaptive genetic algorithm corresponds to a reorganization decision information, that is, a matching reorganization plan for retired power batteries corresponding to a reorganization production order, and a matching reorganization plan involves a warehousing subsystem (warehouse) and a reorganization subsystem (reorganization workshop). In the process of solving using the catastrophe adaptive genetic algorithm, the objective functions of the warehousing subsystem and the reorganization subsystem are converted into corresponding fitness functions, that is, the corresponding warehousing cost and reorganization production cost are calculated respectively by the objective sub-functions corresponding to the warehousing subsystem and the reorganization subsystem, so as to determine the target cost corresponding to the planned reorganization decision information, that is, determine the collaborative operation cost parameters corresponding to each sub-code, and determine the fitness of a candidate code individual based on the collaborative operation cost parameters corresponding to all the sub-codes of the candidate code individual.

[0052] In this embodiment, the objective subfunctions corresponding to the warehousing subsystem and the reorganization subsystem are respectively converted into corresponding fitness functions. The corresponding objective subfunctions in the warehousing subsystem and the reorganization subsystem are the objective subfunctions of the mathematical model in this embodiment. The objective function values ​​of multiple objective subfunctions (for example, the reorganization production cost, warehouse storage cost, and delivery delay penalty cost corresponding to the collaborative operation of the warehousing and reorganization stages) are used to calculate the fitness of the corresponding coded individuals. In this embodiment, the process of encoding a coded individual and the corresponding sub-code and population iteration is an update of the reorganization decision information corresponding to the reorganization order. The decision on the reorganization decision information includes outputting decision variables and decision target values, wherein the decision variables include the number of modules and battery cells of a certain type (such as ternary lithium or lithium iron phosphate) used in the reorganization production of each reorganization order, the start time of each process of each reorganization order in each reorganization workshop, and the time when all materials in the warehouse are shipped out. The decision target values ​​include the reorganization completion time of each reorganization order in each reorganization workshop, the total reorganization cost, the order delay time, the order delay cost; and the storage cost of each type of battery component with unit storage cost difference in the warehouse affected by storage time.

[0053] In this embodiment, when initializing the model, the following settings are made for the mathematical model to be used: 1. The demand for a customer order is for the same type of reconstituted battery product; 2. One customer order constitutes one production batch and cannot be split; 3. The battery product categories of each reconstitution workshop are different, and each reconstitution workshop only produces one type of battery product; 4. The number of reconstitution lines in each reconstitution workshop is different; 5. The processes of all reconstitution lines in the same reconstitution workshop are the same.

[0054] In this embodiment, the mathematical models and parameter symbols involved are defined as follows:

[0055] i represents the production order number, i∈{1,2,3,…,n}, all battery products of production order i belong to one production batch; G(i) represents the number of reassembled batteries required for the i-th production order; Ah i E represents the capacity requirement of the reassembled battery required for the i-th production order; i represents the energy demand of the battery product required for the i-th production order; f represents the reorganization workshop number, f∈{1,2,…,F}, l f Indicates the reorganization line number in the reorganization workshop f, l f ∈{1,2,…,L};j f represents the process number of the reorganized workshop f, j f ∈{1,2,…,J}; t i,j Indicates the battery product of the i-th production order in process j f Processing time, C i,j Indicates the battery product of the i-th production order in process j f Unit production cost of processing; T i represents the expected exchange time of the battery product of the i-th production order, represents the actual exchange time of the battery product of the i-th production order; represents the unit delay penalty cost of the i-th production order of the reorganized workshop; ω i，lf A variable of 0 or 1, indicating whether the battery product of the i-th production order is in the reorganization line l of the reorganization workshop f f On production, then ω i，lf =1, otherwise 0;m j,f Indicates the jth f The machine number in the process, m j,f ∈{1,2,...,M}; A variable of 0 or 1, indicating the jth f The mth process j,f The i-th production order on the machine is the i-th ’ The immediate predecessor; β i,j A variable of 0 or 1, indicating whether the battery product of the i-th production order has passed the j-th f process; R lf Indicates the first f The production capacity of the reorganization line was put online; Indicates the time it takes for all battery raw materials required for the i-th production order to be shipped out; Indicates the start time of the battery product of the i-th production order in the reorganization workshop; represents the penalty cost of excess units in the line warehouse of the f-th reorganized workshop; represents the temporary storage cost per unit of the line warehouse of the f-th reorganized workshop; Q f,carepresents the upper limit of the capacity of the line warehouse of the f-th reorganization workshop at time t; p represents the batch of battery raw materials entering the warehouse, p∈{1,2,…,P}; Indicates the storage time of the pth batch of battery raw materials; Indicates the delivery time of the pth batch of battery raw materials; Indicates the number of battery modules in the pth batch of battery raw materials; Indicates the number of battery cells in the pth batch of battery raw materials; A variable of 0 or 1, indicating whether the battery raw materials required for the battery product of the i-th production order are stored in the aisle a of the buffer zone. =1, otherwise, =0; Indicates the actual number of S-type battery modules shipped for the i-th production order; Indicates the actual number of S-type batteries shipped out for the i-th production order; Indicates the jth battery module assembly f Unit processing time of each process; Indicates the jth time when the battery cell is assembled f The unit processing time of each process; v represents the warehouse location number, v∈{1,2,...,V}; a represents the aisle number, a=1,2,...,N; s represents the battery model in the warehouse, s∈{1,2,...,S}; ah s,m Indicates the capacity of s-type battery module m; ah s,c Indicates the capacity of s-type battery cell c; e s,m represents the energy of the s-type battery module m; e s,c represents the energy of s-type battery cell c; q s,m represents the current inventory of s-type battery modules m in the warehouse; q s,c represents the current inventory of s-type battery cell c in the warehouse; represents the number of s-type battery modules m required for the battery product of the i-th production order; represents the number of s-type battery cells c required for the battery product of the i-th production order; represents the fixed storage cost of battery module m; represents the fixed storage cost of battery cell c; represents the unit time storage cost of battery module m; represents the unit time storage cost of battery cell c; represents the loss cost of battery module m; represents the loss cost of battery cell c; represents the initial value of the s-type battery module m; represents the initial value of the s-type battery cell c; represents the initial performance of the s-type battery module m; represents the initial performance of the s-type battery cell c; p s,m represents the performance of the s-type battery module m at time t; p s,c represents the performance of the s-type battery cell c at time t; f(t) m represents the attenuation function of battery module m, f(t) c represents the attenuation function of battery cell c; A variable of 0 or 1, indicating whether the s-type battery module m is stored in the v-th storage location. If so, =1, otherwise =0; A variable of 0 or 1, indicating whether the s-type battery cell c is stored in the v-th storage location. If so, =1, otherwise =0; α represents the safe delivery ratio; represents the picking completion time of battery module m required for the i-th production order; represents the completion time of picking the battery cell c required for the i-th production order; σ represents the ratio of the number of battery cells and battery modules of the same model.

[0056] In this embodiment, the objective function corresponding to the fitness of each coding individual is to minimize the total cost of warehousing and reorganization coordination, and Z is set as the total cost of the system, C ware represents the storage cost, C recom Represents the restructuring cost, and minZ=C ware +C recom .

[0057] In this embodiment, the storage cost C direc is the direct cost C direct and indirect costs C undire The sum of which,

[0058] Direct warehousing cost C direct = C fix + C var， C fix Represents the fixed cost of battery modules and battery cell storage, fixed cost C fix Mainly related to equipment depreciation, which is a fixed value; unit time variable cost C var It is mainly related to the storage time. Raw materials are put into storage in batches. Each batch of battery raw materials put into storage includes a certain number of battery modules and battery cells. The unit time variable cost .

[0059] Warehousing indirect costs C undire Mainly the loss cost of battery raw materials, among which C undire = + ; Warehousing indirect cost C undire Including the loss cost of battery module placement and the loss cost of battery cell placement , = , = .

[0060] In this embodiment, the restructuring cost C recom By reorganization production cost C pro , Reorganize the storage cost of the workshop line warehouse C sto , Delay penalty cost C delay Composition, C recom =C pro +C sto +C delay ,in,

[0061] Restructuring production costs ;

[0062] Reorganize the storage costs of workshop line warehouses ;

[0063] Delay penalty costs .

[0064] In this embodiment, the relevant constraints of the mathematical model, that is, multiple target sub-constraint parameters, include: multi-partition warehouse storage and outbound constraints, multi-category reorganization workshop multi-line production constraints, among which,

[0065] The storage and outbound constraints of a multi-partition warehouse include: a battery module can only be stored in one location, the constraint type is: ; A battery cell can only be stored in one cargo space, constrained: The outbound quantity of battery modules cannot exceed the current inventory quantity. The constraint is: ; The quantity of battery cells shipped out cannot exceed the current inventory constraint: The time required for the production order to complete the material set is less than the start time of the reorganized production. The constraint formula is: To avoid accidents such as collisions of battery modules that result in the actual shipment quantity exceeding the actual demand, the constraint formula is: To avoid accidents such as collisions of battery cells that result in the actual shipment quantity exceeding the actual demand, the constraint formula is: The buffer area can only store the battery modules / battery cells required for 2 production orders at a time, constraint type: ; Battery modules / battery cells of the same production order can only be stored in one cache area, constraint: The material set-up time for the i-th production order is the maximum picking time of the battery module / battery cell, and the constraint formula is: .

[0066] The production constraints of a multi-product reorganized workshop with multiple production lines include:

[0067] The combined capacity of the battery modules and battery cells selected for each production order must be greater than or equal to the specified capacity required for the recombinant battery product. The constraint formula is: ;

[0068] The combined energy of the battery modules and battery cells selected for each production order must be greater than or equal to the specified energy required for the recombinant battery product. The constraint formula is: ;

[0069] Each production order product can only be processed and produced on one reorganization line, with the following constraints: ;

[0070] The start time of a production order on the reorganization line in the reorganization workshop should be equal to the material set-up time minus the factory transportation time. The constraint formula is: ;

[0071] The completion time of a production order is equal to the start time plus the processing time of each process. The constraint formula is: ;

[0072] The i-th production order is placed at the j-th f The processing time of each process is constrained by: ;

[0073] Indicator function: ;

[0074] The capacity limit constraint is that the number of products produced by each reorganized production line cannot exceed the maximum capacity. The constraint formula is: ;

[0075] The capacity constraints of the line warehouses of each reorganization workshop are as follows: the delivery time T of the raw materials required for the production of the reorganization workshop needs to comprehensively consider the capacity of the line warehouse at time T. The constraint formula is: .

[0076] Step 32: Select a preset number of candidate coding individuals from all candidate coding individuals in the current iteration based on the fitness and a preset selection operation, wherein the selection operation includes one of the following: roulette wheel selection, selection based on elite retention strategy, and league selection method, and the selection probability corresponding to the selection operation is determined based on the fitness of the corresponding candidate coding individual.

[0077] In this embodiment, according to the fitness value of the candidate coding individual, one of the roulette wheel selection, elite retention strategy or league selection method is adopted to select some individuals to be crossed (corresponding to a preset number of alternative coding individuals) from the parent group (corresponding to all candidate coding individuals in the current iteration). Individuals with high fitness are more likely to be selected. It can be understood that the collaborative operation cost corresponding to the high fitness in the embodiment of the present application is the lowest; in this embodiment, it is preferred to adopt the elite retention strategy to retain the top 5% of excellent individuals to realize the selection operation.

[0078] Step 33, based on the corresponding adaptive crossover probability and adaptive mutation probability, perform crossover operations and mutation operations on all candidate coding individuals in sequence to generate multiple first coding individuals, wherein the candidate coding individuals corresponding to the current genetic evolution operation iteration include the first coding individuals, the adaptive crossover probability is determined based on the crossover probability function corresponding to the catastrophe adaptive genetic algorithm, and the adaptive mutation probability is determined based on the mutation probability function corresponding to the catastrophe adaptive genetic algorithm.

[0079] In this embodiment, a crossover operation is first performed on a preset number of selected candidate coding individuals based on an adaptively adjusted crossover probability to generate new individuals; in this embodiment, the crossover probability is adaptively and dynamically adjusted according to the fitness value of the population and the evolutionary stage. In the early stage of evolution, a higher crossover probability helps to maintain the diversity of the population, that is, a higher crossover rate is adopted for individuals with poor fitness to increase the exploration range; in the late stage of evolution, a lower crossover probability is conducive to local optimization, that is, a lower crossover rate is adopted for individuals with higher fitness to protect excellent genes; in this embodiment, after the crossover generates new individuals, the genes of the new individuals are mutated based on the adaptively adjusted mutation probability to generate multiple first coded individuals. In this embodiment, the mutation probability can also be adaptively adjusted according to the evolutionary characteristics of the population and the fitness value of the individual. In the early stage of evolution, In the early stage, a higher mutation probability helps to explore the entire search space, that is, a higher mutation rate is adopted for individuals with poor fitness to increase the exploration range; in the late evolutionary stage, a lower mutation probability helps to concentrate on local search to find the optimal solution, that is, individuals with higher fitness adopt a lower mutation rate to protect excellent genes; it is understandable that as evolution proceeds, the algorithm gradually approaches the optimal solution. At this time, the crossover probability and mutation probability should be appropriately reduced to protect the obtained excellent genotypes from being destroyed, while allowing subtle searches to improve the quality of the solution. Therefore, in this embodiment, the crossover probability function and the mutation probability function are set to monotonically decreasing functions. For the minimization problem, the smaller the individual fitness value, the smaller the current crossover probability and mutation probability should be. In this embodiment, the set crossover probability function and mutation probability function are used to adaptively adjust the crossover probability and mutation probability.

[0080] In some embodiments, after generating a plurality of first coding entities, the following steps are further performed:

[0081] Step 41 : Select the candidate coding individual with the best fitness from all candidate coding individuals generated by the previous genetic evolution iteration to obtain the first best individual corresponding to the previous genetic evolution iteration.

[0082] Step 42: Select the first coding individual with the best fitness from the multiple first coding individuals, obtain the second best individual corresponding to the current genetic evolution iteration, and determine whether the fitness of the second best individual is higher than that of the first best individual.

[0083] In this embodiment, the best individual (corresponding to the first best individual) in the initial population (corresponding to all candidate coding individuals generated by the previous genetic evolution iteration) is saved as the first local best individual; after several genetic operations, whether the fitness of the second best individual is higher than that of the first best individual is used as a judgment condition for determining whether a better individual is generated and whether a catastrophic operation is performed; if the catastrophic judgment condition is met, the catastrophic operation is performed.

[0084] Step 43, based on the judgment result, select the target optimal individual corresponding to the current genetic evolution iteration from the second optimal individual and the first optimal individual, and perform a catastrophic operation on all multiple first coding individuals according to a preset catastrophic method to generate multiple second coding individuals, wherein the candidate coding individuals corresponding to the current catastrophic operation iteration include the second coding individuals.

[0085] In some optional implementations, a catastrophic operation is performed on all first coded individuals according to a preset catastrophic method to generate a plurality of second coded individuals, which is achieved by the following steps:

[0086] Step 431: When it is determined that the fitness of the second best individual is higher than that of the first best individual, a preset number of first coding individuals are selected in descending order of fitness to obtain elite coding individuals, and all elite coding individuals are initialized based on mixed integer programming to generate a corresponding plurality of second coding individuals.

[0087] In this embodiment, if the best individual in the current population (corresponding to the second best individual) is better than the last updated local best individual (corresponding to the first best individual), the current local best individual is updated, and a type of catastrophic operation is performed, that is, a preset number of first coded individuals are selected in order of fitness from high to low to obtain elite coded individuals, and all elite coded individuals are initialized based on mixed integer programming to generate corresponding multiple second coded individuals; in this embodiment, it is preferred to initialize the individuals in the elite class of the current population (corresponding to the elite coded individuals) one by one according to preset rules.

[0088] Step 432: When it is determined that the fitness of the second best individual is not higher than that of the first best individual, first coding individuals of the set disaster scale are selected in order of fitness from low to high to obtain eliminated coding individuals. After removing all eliminated coding individuals from the multiple first coding individuals, multiple randomly generated new coding individuals are added to the remaining first coding individuals to obtain corresponding multiple second coding individuals, where the number of new coding individuals is equal to the set disaster scale.

[0089] In this embodiment, if the best individual in the current population (corresponding to the second best individual) is inferior to the local best individual (corresponding to the first best individual) saved in the previous catastrophe, it is considered that the search direction of the current population has deviated, and a second-type catastrophe operation is performed, that is, M individuals with poor fitness in the population are eliminated, and M new individuals are randomly generated to join the current population to improve the diversity of the population; the current catastrophe scale M is not constant, but decreases with the increase in the number of iterations to ensure the stability of the algorithm in the later stage. In this embodiment, the current catastrophe scale M is calculated using the following formula:

[0090]

[0091] M is the current disaster scale, is the preset disaster scale, λ is the control parameter, is the current iteration number, is the maximum number of iterations.

[0092] In some embodiments, after obtaining the corresponding plurality of second code entities, the following steps are further performed:

[0093] Step 51, determine whether the iteration satisfies the preset iteration termination condition after the catastrophe operation iteration, wherein the iteration termination condition includes at least one of the following: the fitness difference between the second coding individual corresponding to the catastrophe operation iteration and the previous catastrophe operation iteration is less than the population fitness change threshold, and the number of iterations exceeds the preset iteration number threshold.

[0094] Step 52: When it is determined that the iteration termination condition is satisfied, the plurality of second coding individuals are used as a plurality of intended coding individuals.

[0095] Step 53, when it is determined that the iteration termination condition is not met, iterative genetic evolution operation and population catastrophe operation are performed on the plurality of second coding individuals until a plurality of intended coding individuals are obtained.

[0096] In this embodiment, whether the algorithm is terminated is determined based on preset termination conditions (such as the number of iterations and the change in population fitness). If the termination conditions are met, the optimal solution is output (that is, multiple intention-coded individuals are output); if not, the algorithm enters the next iteration until the optimal solution is output.

[0097] In some embodiments, before generating a plurality of first coding individuals, the following steps are further performed:

[0098] Step 61: Determine the average fitness and minimum fitness corresponding to all candidate coding individuals based on the fitness of the candidate coding individuals, and judge whether the average fitness is less than the minimum fitness.

[0099] Step 62: When it is determined that the average fitness is less than the minimum fitness, the preset maximum crossover probability and maximum mutation probability are used as the corresponding adaptive crossover probability and adaptive mutation probability respectively.

[0100] Step 63, when it is determined that the average fitness is greater than the minimum fitness, the corresponding crossover probability function and mutation probability function are used to reduce the maximum crossover probability and the maximum mutation probability respectively, and the first crossover probability and the first mutation probability distribution obtained after the reduction are used as the corresponding adaptive crossover probability and adaptive mutation probability.

[0101] In this embodiment, the following crossover probability function and mutation probability function are used to adaptively adjust the crossover probability and mutation probability. Specifically,

[0102] Crossover probability function

[0103]

[0104] Mutation probability function

[0105]

[0106] Among them, Respectively represent the lower bound and upper bound of the crossover probability, f min represents the minimum fitness value of the first coded individual corresponding to the previous iteration of the genetic evolution operation, f avg represents the average fitness of the candidate coding individuals, represents the minimum fitness value among the candidate coding individuals, They represent the upper and lower bounds of the mutation probability, respectively, and f m Represents the fitness value of the mutant individual (the alternative coding individual that completes the crossover operation); based on the sigmoid function ( ) characteristics, the crossover probability function and the mutation probability function are monotonically decreasing functions, and the crossover probability and the mutation probability are monotonically decreasing.

[0107] In some embodiments, obtaining a target coding individual from a plurality of intended coding individuals and obtaining a decision result including the target coding individual is achieved by the following steps:

[0108] Step 71: Determine the fitness corresponding to each intention coding individual.

[0109] Step 72: Select the intended coding individual with the highest fitness from multiple intended coding individuals to obtain a target coding individual, and extract all sub-codes of the target coding individual to obtain a target sub-code.

[0110] Step 73: Decode the reorganization decision information corresponding to all target sub-codes, and use the reorganization decision information corresponding to all target sub-codes as the decision result.

[0111] In some embodiments, encoding and population initialization are performed on all second reorganization orders according to a preset mixed integer programming to generate multiple candidate encoding individuals, which is achieved by the following steps:

[0112] Step 81 : Obtain the objective sub-function and objective sub-constraint parameters corresponding to the mixed integer programming, and obtain the production order information corresponding to each second reorganization order, wherein the production order information includes the reorganized power battery target information.

[0113] Step 82 : Match at least one type of battery combination matching information to each recombinant power battery target information from the preset battery combination matching information, wherein one type of battery combination matching information is used to characterize the composition of battery materials and battery components corresponding to a recombinant power battery.

[0114] Step 83, using the target sub-function and the target sub-constraint parameters, solve and optimize the battery combination matching information corresponding to each reorganized power battery target information, generate the intended battery combination matching information corresponding to each reorganized power battery information, and perform two-dimensional integer encoding on the intended battery combination matching information according to a preset encoding format to obtain the sub-code corresponding to the reorganized power battery target information.

[0115] Step 84 , after determining the collaborative operation cost parameter mapped to each sub-code, integrate the sub-codes corresponding to all second reorganized orders into a candidate code individual, and perform population initialization based on the candidate code individual to generate multiple candidate code individuals.

[0116] In some preferred embodiments, reference Figure 3 The following describes the encoding process of the encoding individual in the embodiment of the present application:

[0117] According to the characteristics of the problem, each candidate coding individual is represented by a two-dimensional chromosome and all are encoded in integer format. Figure 3 The vertical direction of the chromosome corresponding to P1 and P2 in the figure represents the number of orders, and the horizontal direction represents the number of battery types to be selected. The battery types are divided according to the battery material type (for example, ternary lithium, lithium iron phosphate, lithium titanate), battery component type (for example, battery module, battery cell), and specification (for example, voltage, capacity). In this embodiment, a row of the chromosome corresponds to a sub-code of a candidate coding individual; refer to Figure 3 , ternary lithium battery material types include M1, C11, C12, lithium iron phosphate battery material types include C2, lithium titanate battery materials include M3, C3, considering Figure 3 The P1 coding individual described in (corresponding to a chromosome), M1, C11, C12 belong to the same material type, M1 and C11, C12 belong to different battery component types under the same material type, M1 is a battery module, C11, C12 are battery cells with different specifications, correspondingly, C2 belongs to a battery cell of the second material type, M3, C3 belong to different battery component types of the third material type; it should be noted that for a production order, only battery components of the same material type can be used, for example, in Figure 3 In the coded individual describing P2, for order 1 (#1), when the first three columns contain data, columns 4-6 will all be processed as 0. Similarly, for production order 2, when columns 5-6 contain data, the first four columns will all be processed as 0. This encoding method encodes the chromosomes of the population and initializes the population, which can easily meet the constraint of using only battery components of the same material type and can be used more flexibly and effectively for subsequent processing.

[0118] In some optional implementations, the following steps are also performed:

[0119] Step 1: The execution entity receives the customer order and converts it into a production order through the company's ERP system, and issues it to each reorganization workshop. The customer order list includes the following table 1

[0120] Table 1

[0121]

[0122] In this embodiment, the reassembly workshop includes three categories: (1) Home backup battery (1-10kwh) reassembly workshop: used for home emergency power supply or outdoor activities; (2) Residential energy storage battery (10-50kWh) reassembly workshop: mainly used in combination with rooftop solar photovoltaic panels to achieve self-sufficient energy supply, and can also provide power support when the grid is out of power; (3) Industrial and commercial energy storage battery (100-1000kwh) reassembly workshop: used in commercial buildings, data centers and other scenarios to optimize electricity bills and improve energy use flexibility.

[0123] Step 2: After receiving the production order, the reorganization workshop retrieves the inventory information from the warehouse management system (WMS) and decides on the type and quantity of battery raw materials required.

[0124] In this embodiment, each reorganization workshop has independent decision-making capabilities, and the main goal of decision-making is to reduce reorganization costs while completing order delivery in a timely manner.

[0125] Step 3: After receiving the material requisitions from the various reorganization workshops, the warehouse picks the materials in the various storage areas of the battery raw material warehouse. The picked battery raw materials are temporarily stored in the buffer area and then transported to the various reorganization workshops by transport vehicles. The finished batteries produced by the reorganization workshops are also transported to the finished product warehouse to wait for delivery.

[0126] In this embodiment, the warehouse is partitioned into three levels: first, storage is performed according to modules and battery cells; second, the areas of each battery module and battery cell are further refined into storage areas according to the model. For example, Yiwei Lithium Energy's square lithium iron phosphate battery cell models are LF304 and LF160, which are partitioned and stored separately; finally, storage is continued in each area according to parameters such as 80% and 90% of the remaining capacity.

[0127] Step 4: Based on the operation of the reorganization workshop, the reorganization workshop selects battery raw materials according to the fineness and cost of the products produced by the reorganization workshop while meeting the order requirements and delivery date.

[0128] In this embodiment, the battery raw materials of the battery product are combined in various ways. A 51.2V-200Ah residential energy storage battery has a variety of combination matching methods. For details, refer to Figure 4 .

[0129] In this embodiment, the precision is determined by the difference between the capacity of the battery pack actually reorganized and produced and the capacity required by the customer order, and the difference between the voltage of the battery pack actually reorganized and produced and the voltage required by the customer order. It is understandable that, during reorganization production, the higher the precision of the battery cell reorganization, the longer it takes and the higher the cost. Although the selection of battery modules sometimes cannot accurately meet the order requirements, it can greatly reduce the time and cost of reorganization. It should be noted that the decision of the reorganization workshop only focuses on the precision of the battery products produced by the reorganization workshop and the cost of matching battery raw materials. However, the matching plan will also have a certain impact on the battery raw material warehouse. First, the storage costs of battery modules and battery cells are different: the storage cost of battery cells is higher. First, the equipment used during storage. Battery cells also need to be tested individually, which requires more testing equipment. Second, the storage of battery cells requires a certain interval. A pallet can store a battery module consisting of 10 battery cells, but can only store 5 battery cells of the same model. Therefore, battery modules and battery cells with the same power occupy different numbers of storage spaces, resulting in further increase in warehouse costs; third, due to the special properties of batteries, when the battery is stored for too long, it will lead to accelerated attenuation of performance such as capacity, which will not bring economic benefits to the enterprise. Therefore, when selecting battery raw materials for reorganization, the reorganization workshop must also consider the status of raw materials in the warehouse: the storage cost and storage time of different battery raw materials.

[0130] This embodiment also provides a matching decision device for the storage and reorganization linkage management of retired power batteries, which is used to implement the above-mentioned embodiments and preferred implementation methods, and will not be repeated here. As used below, the terms "module", "unit", "sub-unit", etc. can be a combination of software and / or hardware that implements the predetermined functions. 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.

[0131] Figure 5 This is a structural block diagram of a matching decision device for storage and reorganization linkage management of retired power batteries according to an embodiment of the present application, such as Figure 5 As shown, the device includes a detection module 51, an encoding module 52, a decision module 53 and a processing module 54, wherein:

[0132] The detection module 51 is used to detect at least one reorganization decision information to be executed from the first reorganization matching decision information generated before the current decision after receiving the reorganization correction information, wherein the reorganization decision information is used to represent the matching decision of the reorganized power battery corresponding to the production order demand information, and one reorganization decision information is associated with a first reorganization order.

[0133] The encoding module 52 is coupled to the detection module 51 and is used to combine the dynamic reorganization order corresponding to the reorganization correction information with all the first reorganization orders into a second reorganization order, and encode and initialize the population of all the second reorganization orders according to a preset mixed integer programming to generate multiple candidate encoding individuals, wherein the mixed integer programming includes multiple target sub-functions and multiple target sub-constraint parameters, and the sub-code corresponding to the candidate encoding individual is encoded and generated according to the corresponding target sub-functions and target sub-constraint parameters, and is used to represent a reorganization decision information.

[0134] The decision module 53 is coupled to the coding module 53 and is used to iterate the genetic evolution operation and the population catastrophe operation on multiple corresponding candidate coding individuals based on the preset catastrophe adaptive genetic algorithm, mixed integer programming and the fitness corresponding to the candidate coding individuals participating in each iteration until multiple intention coding individuals are generated, wherein the fitness is determined according to the collaborative operation cost parameter associated with the target sub-function corresponding to the sub-coding corresponding to the candidate coding individual.

[0135] The processing module 54 is coupled to the decision module 53 and is configured to obtain a target coding individual from a plurality of intended coding individuals and obtain a decision result including the target coding individual.

[0136] In some embodiments, the reorganization decision information includes the reorganization online time, and the detection module 51 further includes:

[0137] The first acquisition unit is used to obtain all recombinant decision information corresponding to the first recombinant matching decision information, and determine the recombinant online time corresponding to each recombinant decision information, wherein the first recombinant matching decision information is generated by iterating genetic evolution operations and population catastrophe operations based on corresponding fitness on the historical coding body, and the historical coding body is generated by encoding and population initialization according to mixed integer programming based on all first recombinant orders received before the current time.

[0138] The selection unit is coupled to the first acquisition unit and is used to select, from all the reorganization decision information, the reorganization decision information whose reorganization online time is later than the current time, to obtain at least one reorganization decision information to be executed.

[0139] In some embodiments, the decision module 53 further includes:

[0140] The computing unit is configured to calculate the collaborative operation cost parameter for the sub-codes corresponding to the candidate coding individuals participating in the current iteration according to the target sub-function corresponding to the mixed integer programming, and determine the fitness corresponding to each candidate coding individual in the current iteration based on the collaborative operation cost parameters corresponding to all sub-codes, wherein the collaborative operation cost parameter is calculated based on the warehousing cost and the reorganization production cost, and the warehousing cost and the reorganization production cost are calculated based on the corresponding target sub-function.

[0141] The selection unit is coupled to the calculation unit and is used to select a preset number of candidate coding individuals from all candidate coding individuals in the current iteration according to fitness and a preset selection operation, wherein the selection operation includes one of the following: roulette wheel selection, selection based on elite retention strategy, and league selection method, and the selection probability corresponding to the selection operation is determined based on the fitness of the corresponding candidate coding individual.

[0142] The operation unit is coupled to the selection unit and is used to perform crossover operations and mutation operations on all candidate coding individuals in sequence based on corresponding adaptive crossover probabilities and adaptive mutation probabilities to generate multiple first coding individuals, wherein the candidate coding individuals corresponding to the current genetic evolution operation iteration include the first coding individuals, the adaptive crossover probability is determined based on a crossover probability function corresponding to the catastrophe adaptive genetic algorithm, and the adaptive mutation probability is determined based on a mutation probability function corresponding to the catastrophe adaptive genetic algorithm.

[0143] In some embodiments, after generating multiple first coded individuals, the matching decision device for the storage and reorganization linkage management of retired power batteries is also used to select the candidate coded individual with the best fitness from all candidate coded individuals generated by the previous genetic evolution iteration, and obtain the first optimal individual corresponding to the previous genetic evolution iteration; select the first coded individual with the best fitness from multiple first coded individuals, obtain the second optimal individual corresponding to the current genetic evolution iteration, and judge whether the fitness of the second optimal individual is higher than that of the first optimal individual; according to the judgment result, select the target optimal individual corresponding to the current genetic evolution iteration from the second optimal individual and the first optimal individual, and perform a catastrophe operation on all multiple first coded individuals according to a preset catastrophe method to generate multiple second coded individuals, wherein the candidate coded individuals corresponding to the current catastrophe operation iteration include the second coded individuals.

[0144] In some embodiments, the matching decision device for the coordinated management and control of storage and reorganization of retired power batteries is also used to select a preset number of first coded individuals in order of fitness from high to low when it is judged that the fitness of the second optimal individual is higher than that of the first optimal individual, to obtain elite coded individuals, and initialize all elite coded individuals based on mixed integer programming to generate corresponding multiple second coded individuals; when it is judged that the fitness of the second optimal individual is not higher than that of the first optimal individual, select first coded individuals with a set disaster scale in order of fitness from low to high to obtain eliminated coded individuals, and after removing all eliminated coded individuals from the multiple first coded individuals, add the randomly generated multiple new coded individuals to the remaining first coded individuals to obtain corresponding multiple second coded individuals, wherein the number of new coded individuals is equal to the set disaster scale number.

[0145] In some embodiments, after obtaining the corresponding multiple second-coded individuals, the matching decision device for the storage and reorganization linkage management of retired power batteries is also used to determine whether the iteration meets the preset iteration termination condition after the current catastrophe operation iteration, wherein the iteration termination condition includes at least one of the following: the fitness difference between the second-coded individuals corresponding to the current catastrophe operation iteration and the previous catastrophe operation iteration is less than the population fitness change threshold, and the number of iterations exceeds the preset iteration number threshold; when it is judged that the iteration termination condition is met, the multiple second-coded individuals are used as multiple intended coding individuals; when it is judged that the iteration termination condition is not met, the multiple second-coded individuals are iterated with genetic evolution operations and population catastrophe operations until multiple intended coding individuals are obtained.

[0146] In some embodiments, before generating multiple first coded individuals, the matching decision device for the storage and reorganization linkage management of retired power batteries is also used to determine the average fitness and minimum fitness corresponding to all alternative coded individuals based on the fitness of the alternative coded individuals, and judge whether the average fitness is less than the minimum fitness; when it is judged that the average fitness is less than the minimum fitness, the preset maximum crossover probability and maximum mutation probability are used as the corresponding adaptive crossover probability and adaptive mutation probability respectively; when it is judged that the average fitness is greater than the minimum fitness, the corresponding crossover probability function and mutation probability function are used to reduce the maximum crossover probability and the maximum mutation probability respectively, and the first crossover probability and the first mutation probability distribution obtained after the reduction are used as the corresponding adaptive crossover probability and the adaptive mutation probability.

[0147] In some embodiments, the processing module 54 further includes:

[0148] The determination unit is used to determine the fitness corresponding to each intention coding individual.

[0149] The extraction unit is coupled to the determination unit and is used to select the intention coding individual with the highest fitness from multiple intention coding individuals to obtain a target coding individual, and extract all sub-codes of the target coding individual to obtain a target sub-code.

[0150] The decoding unit is coupled to the extraction unit and is used to decode the reorganization decision information corresponding to all target sub-codes and use the reorganization decision information corresponding to all target sub-codes as a decision result.

[0151] In some embodiments, the decision module 53 further includes:

[0152] The second acquisition unit is used to obtain the objective sub-function and objective sub-constraint parameters corresponding to the mixed integer programming, and obtain the production order information corresponding to each second reorganization order, wherein the production order information includes the reorganized power battery target information.

[0153] The matching unit is coupled to the second acquisition unit and is used to match at least one battery combination matching information from the preset battery combination matching information to each recombinant power battery target information, wherein one type of battery combination matching information is used to characterize the composition of battery materials and battery components corresponding to a recombinant power battery.

[0154] The generation unit is coupled to the matching unit and is used to use the target sub-function and the target sub-constraint parameters to solve and optimize the battery combination matching information corresponding to each reorganized power battery target information, generate the intended battery combination matching information corresponding to each reorganized power battery information, and perform two-dimensional integer encoding on the intended battery combination matching information according to a preset encoding form to obtain a sub-code corresponding to the reorganized power battery target information.

[0155] The encoding unit is coupled to the generation unit and is used to determine the collaborative operation cost parameters mapped by each sub-code, integrate the sub-codes corresponding to all second reorganization orders into a candidate encoding individual, and initialize the population based on a candidate encoding individual of the encoding to generate multiple candidate encoding individuals.

[0156] This embodiment also provides a matching decision system for the storage and reorganization linkage management of retired power batteries, 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 of the above method embodiments.

[0157] Optionally, the reconfiguration system may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0158] Optionally, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0159] S1. After receiving the reorganization correction information, detect at least one reorganization decision information to be executed from the first reorganization matching decision information that has been previously generated, wherein the reorganization decision information is used to represent the matching decision of the reorganized power battery corresponding to a production order demand information, and one reorganization decision information is associated with one first reorganization order.

[0160] S2, combines the dynamic reorganization order corresponding to the reorganization correction information with all the first reorganization orders into a second reorganization order, and encodes and initializes the population of all the second reorganization orders according to the preset mixed integer programming to generate multiple candidate coding individuals, wherein the mixed integer programming includes multiple target sub-functions and multiple target sub-constraint parameters, and the sub-code corresponding to the candidate coding individual is encoded and generated according to the corresponding target sub-function and target sub-constraint parameters, and is used to represent a reorganization decision information.

[0161] S3, based on the preset catastrophe adaptive genetic algorithm, mixed integer programming and the fitness corresponding to the candidate coding individuals participating in each iteration, iterate the genetic evolution operation and population catastrophe operation on multiple corresponding candidate coding individuals until multiple intention coding individuals are generated, wherein the fitness is determined according to the collaborative operation cost parameter associated with the target sub-function corresponding to the sub-coding corresponding to the candidate coding individual.

[0162] S4, obtaining a target coding individual from multiple intention coding individuals, and obtaining a decision result including the target coding individual.

[0163] 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 repeated here.

[0164] In addition, in conjunction with the matching decision-making method for the coordinated management and control of retired power battery storage and reorganization in the above-mentioned embodiments, the present application can provide a storage medium for implementation. The storage medium stores a computer program; when the computer program is executed by a processor, it implements any of the matching decision-making methods for the coordinated management and control of retired power battery storage and reorganization in the above-mentioned embodiments.

[0165] Those skilled in the art should understand that the technical features of the above embodiments can be combined arbitrarily. In order 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.

[0166] The above embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A matching decision method for storage and reorganization linkage management of retired power batteries, characterized in that: include: After receiving the reorganization correction information, detecting at least one reorganization decision information to be executed from the first reorganization matching decision information generated previously, wherein the reorganization decision information is used to represent a matching decision for a reorganized power battery corresponding to a production order requirement information, and one reorganization decision information is associated with one first reorganization order; Combining the dynamic reorganization order corresponding to the reorganization correction information with all the first reorganization orders into a second reorganization order, and encoding and population initializing all the second reorganization orders according to a preset mixed integer programming to generate a plurality of candidate coding individuals, wherein the mixed integer programming includes a plurality of objective sub-functions and a plurality of objective sub-constraint parameters, and the sub-codes corresponding to the candidate coding individuals are generated by encoding according to the corresponding objective sub-functions and the objective sub-constraint parameters, and are used to represent the one reorganization decision information; Based on a preset catastrophic adaptive genetic algorithm, the mixed integer programming, and the fitness corresponding to the candidate coding individuals participating in each iteration, iterative genetic evolution operations and population catastrophic operations are performed on a plurality of corresponding candidate coding individuals until a plurality of intended coding individuals are generated, wherein the fitness is determined based on a collaborative operation cost parameter associated with the objective sub-function corresponding to the sub-coding corresponding to the candidate coding individuals; A target coding individual is obtained from the plurality of intended coding individuals, and a decision result including the target coding individual is obtained.

2. The method according to claim 1, characterized in that The reorganization decision information includes the reorganization online time, and detecting at least one reorganization decision information to be executed from the first reorganization matching decision information generated by the decision before the current one, including: Obtaining all the reorganization decision information corresponding to the first reorganization matching decision information, and determining the reorganization online time corresponding to each reorganization decision information, wherein the first reorganization matching decision information is generated by iteratively performing a genetic evolution operation and a population catastrophe operation on a historical coding body based on the corresponding fitness, and the historical coding body is generated by encoding and population initialization according to the mixed integer programming based on all the first reorganization orders received before the current time; Among all the reorganization decision information, the reorganization decision information whose reorganization online time is later than the current time is selected to obtain at least one reorganization decision information to be executed.

3. The method according to claim 1, characterized in that Based on the preset catastrophic adaptive genetic algorithm, the mixed integer programming, and the fitness corresponding to the candidate coding individuals participating in each iteration, iterating the genetic evolution operation and the population catastrophic operation on a plurality of corresponding candidate coding individuals, including: Calculating the collaborative operation cost parameter for the sub-codes corresponding to the candidate code individuals participating in the current iteration according to the objective sub-function corresponding to the mixed integer programming, and determining the fitness corresponding to each candidate code individual in the current iteration based on the collaborative operation cost parameters corresponding to all the sub-codes, wherein the collaborative operation cost parameter is calculated based on warehousing cost and reorganization production cost, and the warehousing cost and the reorganization production cost are calculated based on the corresponding objective sub-function; selecting a preset number of candidate coding individuals from all the candidate coding individuals in the current iteration according to the fitness and a preset selection operation, wherein the selection operation includes one of the following: roulette wheel selection, selection based on an elite retention strategy, and a league selection method, and the selection probability corresponding to the selection operation is determined based on the fitness of the corresponding candidate coding individual; Based on the corresponding adaptive crossover probability and adaptive mutation probability, crossover operations and mutation operations are performed on all the alternative coding individuals in sequence to generate multiple first coding individuals, wherein the candidate coding individuals corresponding to the current genetic evolution operation iteration include the first coding individuals, the adaptive crossover probability is determined based on the crossover probability function corresponding to the catastrophe adaptive genetic algorithm, and the adaptive mutation probability is determined based on the mutation probability function corresponding to the catastrophe adaptive genetic algorithm.

4. The method according to claim 3, characterized in that After generating a plurality of the first coding individuals, the method further includes: Among all the candidate coding individuals generated by the previous genetic evolution iteration, the candidate coding individual with the best fitness is selected to obtain the first best individual corresponding to the previous genetic evolution iteration; Selecting the first coding individual with the best fitness from the plurality of first coding individuals, obtaining a second best individual corresponding to the current genetic evolution iteration, and determining whether the fitness of the second best individual is higher than that of the first best individual; According to the judgment result, the target optimal individual corresponding to the current genetic evolution iteration is selected from the second optimal individual and the first optimal individual, and a catastrophe operation is performed on all the first coding individuals according to a preset catastrophe method to generate multiple second coding individuals, among which the candidate coding individuals corresponding to the current catastrophe operation iteration include the second coding individual.

5. The method according to claim 4, characterized in that Performing a catastrophic operation on all of the first coding individuals according to a preset catastrophic method to generate a plurality of second coding individuals includes: When it is determined that the fitness of the second best individual is higher than that of the first best individual, a preset number of the first coding individuals are selected in descending order of the fitness to obtain elite coding individuals, and all the elite coding individuals are initialized based on the mixed integer programming to generate a corresponding plurality of second coding individuals; When it is determined that the fitness of the second optimal individual is not higher than that of the first optimal individual, the first coded individuals of the set disaster scale are selected in order of the fitness from low to high to obtain eliminated coded individuals, and after all the eliminated coded individuals are removed from the multiple first coded individuals, the randomly generated multiple new coded individuals are added to the remaining first coded individuals to obtain the corresponding multiple second coded individuals, wherein the number of the new coded individuals is equal to the set disaster scale number.

6. The method according to claim 5, characterized in that After obtaining the corresponding plurality of second coding individuals, the method further includes: After the catastrophe operation iteration, whether the iteration satisfies a preset iteration termination condition, wherein the iteration termination condition includes at least one of the following: when the fitness difference between the second coding individual corresponding to the catastrophe operation iteration and the previous catastrophe operation iteration is less than a population fitness change threshold, or when the number of iterations exceeds a preset iteration number threshold; When it is determined that the iteration termination condition is satisfied, taking the plurality of the second coding individuals as the plurality of the intended coding individuals; When it is determined that the iteration termination condition is not met, the genetic evolution operation and the population catastrophe operation are iterated on the plurality of the second coding individuals until a plurality of the intended coding individuals are obtained.

7. The method according to claim 3, characterized in that Before generating a plurality of first coding individuals, the method further includes: Determining, based on the fitness of the candidate coding individuals, an average fitness and a minimum fitness corresponding to all the candidate coding individuals, and judging whether the average fitness is less than the minimum fitness; When it is determined that the average fitness is less than the minimum fitness, the preset maximum crossover probability and the maximum mutation probability are used as the corresponding adaptive crossover probability and the adaptive mutation probability respectively; When it is determined that the average fitness is greater than the minimum fitness, the corresponding crossover probability function and the mutation probability function are used to decrease the maximum crossover probability and the maximum mutation probability respectively, and the first crossover probability and the first mutation probability distribution obtained after the decrease are used as the corresponding adaptive crossover probability and the adaptive mutation probability.

8. The method according to claim 1, characterized in that Obtaining a target coding individual from the plurality of intended coding individuals and obtaining a decision result including the target coding individual, including: Determining the fitness corresponding to each of the intention coding individuals; Selecting the intended coding individual with the highest fitness from the plurality of intended coding individuals to obtain the target coding individual, and extracting all the sub-codes of the target coding individual to obtain a target sub-code; The reorganization decision information corresponding to all the target sub-codes is decoded, and the reorganization decision information corresponding to all the target sub-codes is used as the decision result.

9. The method according to claim 1, characterized in that According to the preset mixed integer programming, all the second reorganization orders are coded and the population is initialized to generate multiple candidate coding individuals, including: Obtaining the objective sub-function and the objective sub-constraint parameters corresponding to the mixed integer programming, and obtaining production order information corresponding to each second reorganization order, wherein the production order information includes reorganized power battery target information; Matching at least one of the battery combination matching information to each of the recombined power battery target information from the preset battery combination matching information, wherein one of the battery combination matching information is used to characterize the composition of battery materials and battery components corresponding to a recombined power battery; Using the target sub-function and the target sub-constraint parameter, the battery combination matching information corresponding to each of the reorganized power battery target information is solved and optimized to generate the intended battery combination matching information corresponding to each of the reorganized power battery information, and the intended battery combination matching information is two-dimensionally integer-encoded according to a preset coding format to obtain the sub-code corresponding to the reorganized power battery target information; After determining the collaborative operation cost parameter mapped by each sub-code, the sub-codes corresponding to all the second reorganization orders are integrated into one candidate code individual, and a population is initialized based on one candidate code individual to generate multiple candidate code individuals.

10. A matching decision system for storage and reorganization linkage management of retired power batteries, 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 matching decision method for the storage and reorganization linkage management of retired power batteries according to any one of claims 1 to 9.

Images