Cross-level collaborative method for retired power battery order matching and reorganization scheduling based on bi-level programming

Abstract

The application relates to a cross-level coordination method for retired power battery order matching and reorganization scheduling based on double-layer planning, which comprises the following steps: after completing the iteration of the current order matching decision, the determined order matching parameters are sent to a reorganization scheduling planning subsystem; the reorganization scheduling decision parameters returned by the reorganization scheduling planning subsystem in response to the corresponding order matching parameters are received, the order matching decision is updated based on the reorganization scheduling decision parameters and a preset NSGA-II algorithm, and updated order matching parameters are generated; the fitness corresponding to the updated order matching parameters is calculated according to a preset target function, and in the case that the fitness is not greater than a fitness threshold, the order matching decision iteration is repeated based on the reorganization scheduling decision parameters returned by the reorganization scheduling planning subsystem, the fitness and the NSGA-II algorithm until the target order matching parameters are generated, and the received target reorganization scheduling decision parameters and the target order matching parameters are taken as the coordination result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cascade utilization of retired power batteries, and in particular to a cross-level collaborative method for order matching and reorganization scheduling of retired power batteries based on double-layer planning. BACKGROUND

[0002] Power batteries are widely used in electric vehicles and other fields. With the passage of time, their performance will gradually decline, and eventually reach a retired state that cannot meet the vehicle's use requirements. The retired power batteries still have a certain residual capacity and can be used in energy storage scenarios. In related technologies, the recycling and reuse of power batteries include disassembly and recycling and cascade utilization. Cascade utilization is increasingly popular in power battery recycling because it can extend the life cycle value of the battery and achieve full utilization of resources.

[0003] Unlike traditional assembly manufacturing, in the context of retired power battery cascade utilization, the retired battery component matching and reorganization production link presents a significant collaborative decision-making requirement. The parameters of the multi-granularity remanufactured battery components after disassembly and recycling show a high degree of heterogeneity and discreteness (such as capacity, voltage, decay rate, internal resistance value, SOC state, etc.). Under the condition of meeting the voltage-current constraints of reorganization products, the system will generate a multi-dimensional solution space matching combination scheme. Because different matching schemes will derive differentiated process paths, reorganization operation time, and equipment energy consumption costs, a process coupling relationship is formed between the retired battery component matching decision and the reorganization production scheduling, and the matching result directly affects the complexity of the reorganization process and the equipment utilization rate. The efficiency of reorganization production reflects the quality of the matching decision, and both constitute a multi-objective optimization problem with coupled decision variables. However, they are at different decision levels. In related technologies, there is no implementation method that can coordinate the order matching decision at the planning level and the reorganization scheduling at the execution level to find the optimal retired power battery component matching scheme, that is, there is no cross-level collaborative decision-making scheme for battery reorganization and matching.

[0004] In view of the problem that battery reorganization and matching are not cross-level collaborative decision-making in related technologies, an effective solution has not been proposed. SUMMARY

[0005] The embodiments of the present application provide a cross-level collaborative method for order matching and reorganization scheduling of retired power batteries based on double-layer planning, to at least solve the problem that battery reorganization and matching are not cross-level collaborative decision-making in related technologies.

[0006] In a first aspect, the embodiments of the present application provide a cross-level coordination method for retired power battery order matching and reorganization scheduling based on double-layer planning, comprising: after completing the iteration of the current order matching decision, issuing the determined order matching parameters to a reorganization scheduling planning subsystem; receiving the reorganization scheduling decision parameters returned by the reorganization scheduling planning subsystem in response to the corresponding order matching parameters, updating the order matching decision based on the reorganization scheduling decision parameters and a preset NSGA-II algorithm, and generating updated order matching parameters; calculating the fitness corresponding to the updated order matching parameters according to a preset objective function, and determining whether the fitness is greater than a fitness threshold; in the case where it is determined that the fitness is not greater than the fitness threshold, repeating the iteration of the order matching decision based on the reorganization scheduling decision parameters returned by the reorganization scheduling planning subsystem, the fitness, and the NSGA-II algorithm until target order matching parameters are generated, and taking the received target reorganization scheduling decision parameters and the target order matching parameters as the coordination result, wherein the target reorganization scheduling decision parameters are the reorganization scheduling decision parameters used to generate the target order matching parameters.

[0007] Compared with the related art, the cross-level coordination method for retired power battery order matching and reorganization scheduling based on double-layer planning provided by the embodiments of the present application solves the problem that the battery reorganization and matching are not coordinated in the related art by adopting the following measures: after completing the iteration of the current order matching decision, issuing the determined order matching parameters to a reorganization scheduling planning subsystem; receiving the reorganization scheduling decision parameters returned by the reorganization scheduling planning subsystem in response to the corresponding order matching parameters, updating the order matching decision based on the reorganization scheduling decision parameters and a preset NSGA-II algorithm, and generating updated order matching parameters; calculating the fitness corresponding to the updated order matching parameters according to a preset objective function, and determining whether the fitness is greater than a fitness threshold; in the case where it is determined that the fitness is not greater than the fitness threshold, repeating the iteration of the order matching decision based on the reorganization scheduling decision parameters returned by the reorganization scheduling planning subsystem, the fitness, and the NSGA-II algorithm until target order matching parameters are generated, and taking the received target reorganization scheduling decision parameters and the target order matching parameters as the coordination result.

[0008] The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below. Other features, objects, and advantages of the application will be apparent from the description of the embodiments and from the claims. BRIEF DESCRIPTION OF DRAWINGS

[0009] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

[0010] Figure 1 is a hardware structure block diagram of a terminal of a double-layer planning based retired power battery order matching and reorganization scheduling cross-level collaborative method of an embodiment of the application;

[0011] Figure 2 is a flowchart of a double-layer planning based retired power battery order matching and reorganization scheduling cross-level collaborative method according to an embodiment of the application;

[0012] Figure 3 is a schematic diagram of initial encoding individuals and alternative encoding individuals encoding of an embodiment of the application;

[0013] Figure 4 is a crossover operation schematic diagram of an embodiment of the application;

[0014] Figure 5 is a mutation operation schematic diagram of an embodiment of the application;

[0015] Figure 6 is a schematic diagram of encoding and decoding of a reorganization scheduling encoding body of an embodiment of the application;

[0016] Figure 7 is a machProcArray basic corresponding table of an embodiment of the application;

[0017] Figure 8 is a schematic diagram of a pair of parent chromosomes selected by a partial match crossover operation of an embodiment of the application;

[0018] Figure 9 is a schematic diagram of an invalid chromosome obtained by a one-time match crossover operation of an embodiment of the application;

[0019] Figure 10 is a gene mapping table of an embodiment of the application;

[0020] Figure 11 is a schematic diagram of a child chromosome after gene matching of an embodiment of the application;

[0021] Figure 12 is a schematic diagram of an insertion mutation of an embodiment of the application. DETAILED DESCRIPTION

[0022] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be described and explained in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application. Based on the embodiments provided by the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts should fall within the scope of the present application. In addition, it should be understood that, although the efforts made in the development process can be complex and lengthy, some design, manufacture or production changes made on the basis of the technical content disclosed in the present application by those of ordinary skill in the art related to the content disclosed in the present application are only routine technical means and should not be understood as insufficient disclosure of the present application.

[0023] Reference to "embodiments" in this application means that the specific features, structures or characteristics described in connection with the embodiments can be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it mutually exclusive or alternative to other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in the present application can be combined with other embodiments without conflict.

[0024] Unless otherwise defined, the technical terms or scientific terms involved in the present application should be understood as the general meaning understood by those of ordinary skill in the art to which the present application belongs. The terms "one", "a", "an", "the" and the like similar words involved in the present application do not represent quantity limitation, but can represent singular or plural. The terms "include", "contain", "have" and any variations thereof involved in the present application are intended to cover non-exclusive inclusion; for example, the process, method, system, product or device including a series of steps or modules (units) is not limited to the listed steps or units, but can also include steps or units not listed, or can also include other steps or units inherent to the process, method, product or device. The "multiple links" involved in the present application refers to more than or equal to two links. "And / or" describes the association relationship of the associated objects, which means that there can be three relationships, for example, "A and / or B" can represent the existence of A alone, the existence of A and B together, and the existence of B alone. The terms "first", "second", "third" and the like involved in the present application are only to distinguish similar objects, and do not represent a specific order of the objects.

[0025] The related technologies used in the embodiments of the present application are described as follows:

[0026] Aging Electric Vehicle Battery (AEVB) refers to lithium-ion, nickel-hydrogen, and other types of batteries that have been retired from electric vehicles or other electric devices. These batteries typically have a remaining capacity of 70-80% of their initial capacity and cannot meet high power demands, but still have secondary utilization value.

[0027] Cascade Utilization refers to the use of retired power batteries (such as lithium-ion batteries retired from electric vehicles) after testing, screening, and reorganization in other fields with lower performance requirements to extend their service life. Since power batteries are retired from electric vehicles, their capacity is usually still 70-80% of their initial capacity, although they cannot meet high power demands, they can be adapted to energy storage, backup power, and other scenarios to maximize resource utilization.

[0028] Order Matching refers to the reasonable combination and matching of multi-granularity remanufactured battery components obtained through disassembly to meet the capacity and specification requirements of cascade products, similar to the process of developing a product BOM list.

[0029] Battery Reassembly refers to determining the reorganization process route and each process reorganization time for different products according to the matching scheme, and arranging the reorganization production sequence to meet the timely delivery of orders while improving production efficiency.

[0030] NSGA-II (Non-dominated Sorting Genetic Algorithm II) is a multi-objective optimization algorithm (MOEA) proposed by Kalyanmoy Deb et al. in 2002 for efficiently solving optimization problems with multiple conflicting objectives. It is an improved version of the classic NSGA, which significantly improves the convergence and solution distribution of the algorithm by introducing fast non-dominated sorting, crowding distance comparison operator, and elitism.

[0031] Fast Non-dominated Sorting: First, the algorithm sorts the individuals in the population according to the Pareto dominance relationship. If one solution is not worse than another solution in all objectives and at least better in one objective, it is said to dominate the latter. All non-dominated solutions constitute the first layer (Pareto front), then continue to filter the second layer of non-dominated solutions from the remaining solutions, and so on, forming multiple front levels (Front 1, Front 2,...).

[0032] Crowding Distance: To maintain the diversity of the population, NSGA-II calculates the crowding distance of solutions in the same front layer, which measures the distribution density of solutions in the objective space. Solutions with high crowding distance are located in sparse areas, which helps to maintain the uniform distribution of the Pareto front and avoid premature convergence to local optima.

[0033] Elitism: When generating offspring, NSGA-II combines the parent and offspring, then selects the optimal individuals into the next generation through non-dominated sorting and crowding distance comparison, ensuring that excellent solutions are not lost.

[0034] The following describes the embodiments of the present application in detail as follows:

[0035] The method provided by the embodiments of the present application can be executed in a terminal, a computer or a similar computing device. Taking the case of running on a terminal, Figure 1 is a hardware structure block diagram of a terminal based on the double-layer planning-based retired power battery order matching and reorganization scheduling cross-level collaborative method of the embodiments of the present application. As shown in Figure 1 , the terminal can include one or more (only one is shown in Figure 1 ) processor 102 (the processor 102 can include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the above terminal can also include a transmission device 106 for communication function and an input and output device 108. Those skilled in the art can understand that Figure 1 the structure shown is only for illustration, which does not limit the structure of the above terminal. For example, the terminal can include more or fewer components than Figure 1 shown, or have a different configuration than Figure 1 shown.

[0036] The memory 104 can be used to store computer programs, such as software programs of application software and modules, such as the computer program corresponding to the order matching and reorganization scheduling cross-level coordination method based on double-layer planning for retired power battery in the embodiments of the present application. The processor 102 can execute various functional applications and data processing, i.e., implement the above method, by running the computer program stored in the memory 104. The memory 104 can include a high-speed random access memory, and can further include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 104 can further include a memory remotely arranged relative to the processor 102, which can be connected to the terminal through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0037] The transmission device 106 is used to receive or send data via a network. The specific examples of the above network can include a wireless network provided by a communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC) which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, RF) module which is used to communicate with the Internet in a wireless manner.

[0038] The embodiments of the present application provide an order matching and reorganization scheduling cross-level coordination method based on double-layer planning for retired power battery, Figure 2 which is a flowchart of the order matching and reorganization scheduling cross-level coordination method based on double-layer planning for retired power battery according to the embodiments of the present application, as shown in Figure 2 the flowchart includes the following steps:

[0039] In step S201, after completing the iteration of the current matching decision, the matched order matching parameters are issued to the reorganization scheduling planning subsystem.

[0040] In the present embodiment, the AEVB order matching and reorganization scheduling model is established based on a Bilevel Interactive Optimisation (BIO) model framework, the execution subject of the collaborative method of the present application is an order matching (OM) decision system as the upper decision level, and focuses on formulating a retired battery assembly matching scheme for each order and forming an input of the reorganization scheduling planning subsystem to generate an optimal reorganization workshop scheduling scheme with the shortest completion time, and balance between reorganization product performance, reorganization cost and production efficiency; and the reorganization scheduling planning subsystem as the lower decision level and as a follower, after the execution subject generates the retired battery assembly matching scheme, makes a decision on the production sequence according to the corresponding matching scheme, that is, realizes the production target under the constraint of limited resources, and optimizes the reorganization production completion time according to the matching scheme formulated by the upper decision level, and the execution unit of the lower decision level feeds back the workshop scheduling result of the decision to the execution subject for iterative optimization of the matching scheme formulation, after that, the execution subject sends the corresponding order matching result (corresponding to the order matching parameters) to the execution unit of the lower decision level (corresponding to the reorganization scheduling planning subsystem) after the iterative optimization, and the execution unit of the lower decision level plans the workshop scheduling result according to the corresponding order matching parameters, and judges the pros and cons of the order matching scheme decided by the previous decision through the reorganization scheduling decision parameters returned in response to the corresponding order matching parameters; in this way, the double-level interactive optimization is repeated for several times until the optimal order matching parameters and reorganization scheduling decision parameters are obtained, therefore, after the execution subject completes the iteration of the present matching decision, the decided order matching parameters are issued to the reorganization scheduling planning subsystem of the lower decision level.

[0041] In the embodiment, the collaborative result includes the order matching parameter decided by the upper decision level and the reorganization scheduling decision parameter generated by the lower decision level in response to the corresponding order matching parameter, wherein the order matching parameter is a battery product reorganization matching scheme made according to order information (including product type, parameter specification, reorganization product demand, delivery period, delay penalty) under the conditions of meeting the capacity of gradient product orders, energy demand, etc. constraints, meeting the selected battery assembly consistency, long service life, low matching cost and high utilization rate of remanufacturing resources, etc. multi-objective conditions, including the battery type, battery material type, battery assembly type (battery module, battery monomer), specification (quantity) used for reorganization production of each order. It can be understood that in the embodiment, the selection of the battery assembly type by the order matching parameter is based on considering minimizing the specification difference between the reorganization production product and the order demand product, minimizing the battery assembly matching cost (including reorganization cost, storage cost, delay delivery cost), and the storage cost of the battery assembly in the reorganization workshop line side warehouse (excess penalty cost, temporary storage cost). In the embodiment, the reorganization scheduling decision parameter is dependent on the corresponding order matching parameter, and according to the corresponding production resources, including the inventory quantity, parameter specification, reorganization workshop production line resource (including process number, machine number, line side warehouse capacity) of each type of battery assembly, the production order of the reorganization matching scheme corresponding to the battery product reorganization is arranged and planned to generate the optimal scheduling scheme of each flow line in each workshop to meet the timely delivery of reorganization battery orders.

[0042] In step S202, the reorganization scheduling planning subsystem receives the reorganization scheduling decision parameter returned in response to the corresponding order matching parameter, and updates the order matching decision based on the reorganization scheduling decision parameter and the preset NSGA-II algorithm to generate updated order matching parameters, wherein the reorganization scheduling decision parameter at least includes the process unit processing cost parameter, the completion time parameter and the order online time parameter, and is generated based on the improved adaptive catastrophe genetic algorithm and the process path parameter in the corresponding order matching parameter.

[0043] In the embodiment, the OM decision system as the upper decision level executor adopts the reorganization scheduling decision parameters based on the NSGA-II algorithm and the feedback of the reorganization scheduling planning subsystem to make decisions on the optimal battery assembly matching scheme of all current orders; the reorganization scheduling planning subsystem as the lower decision level executor adopts the improved adaptive catastrophe genetic algorithm and the order matching parameters issued by the upper level to make decisions on the optimal scheduling scheme of each pipeline in each workshop; in the embodiment, the OM decision system and the reorganization scheduling planning subsystem will convert the corresponding decision variables and target variables into corresponding mathematical models to describe the order matching and reorganization scheduling process of the battery product before making decisions, wherein the OM decision system will use the corresponding objective function and constraint function of the corresponding upper matching model to mathematically model the order matching of the reorganized battery product, and the reorganization scheduling planning subsystem will use the corresponding objective function and constraint function of the corresponding lower scheduling model to mathematically model the production scheduling of the reorganized battery in the workshop; in the embodiment, the OM decision system establishes a corresponding mathematical model to describe the matching process of the battery to be reorganized based on the collected order information, that is, to describe the process of formulating the matching scheme of the retired power battery assembly for each order, for example: for an order of a battery product demand, a battery assembly matching scheme of matching the same brand of battery module + battery monomer combination is adopted to minimize the specification difference between the reorganization product and the order demand product, minimize the battery assembly matching cost (including reorganization cost, storage cost, delayed delivery cost), and minimize the storage cost (excessive penalty cost, temporary storage cost) of the battery assembly in the reorganization workshop line side warehouse, to formulate the scheme of the retired power battery assembly matching corresponding to each order; in the embodiment, the reorganization scheduling planning subsystem establishes a corresponding lower mathematical model to describe the process of the optimal reorganization workshop scheduling with the shortest completion time (objective function), that is, to describe the process of arranging the production sequence, so as to realize the production of the reorganized battery product required by the corresponding order under the constraint of limited resources.

[0044] In the embodiment, the OM decision system establishes a corresponding mathematical model to describe the matching process of the battery to be reorganized based on the collected order information, which meets the capacity, energy demand and other constraint conditions of the order of the gradient product, and also meets the multiple objectives of high consistency of the selected battery assembly, long service life, low matching cost and high utilization rate of remanufacturing resources, which belongs to the NP-Hard combination optimization problem of multiple objectives, and is solved by using the NSGA-II algorithm; in the embodiment, the reorganization scheduling planning subsystem establishes a corresponding lower mathematical model to describe the process of the optimal reorganization workshop scheduling with the shortest completion time, which belongs to the nonlinear, multiple extreme value and multivariable problem, and is solved by using the improved adaptive catastrophe genetic algorithm.

[0045] It should be noted that after the upper decision level OM decision system makes an iteration of order matching decision and issues the corresponding order decision parameters to the reorganization scheduling planning subsystem, the reorganization scheduling planning subsystem will respond to the received order decision parameters, that is, based on the corresponding order matching parameters (corresponding to the process path parameters) and the production resources it has, the improved adaptive catastrophe genetic algorithm makes multiple decision iterations to generate reorganization scheduling decision parameters that meet the corresponding order matching parameters, and obtains the optimal reorganization workshop scheduling scheme with the shortest completion time. That is, in one cross-level collaborative interaction process, the upper decision level OM decision system makes an iteration of order matching decision, and the lower decision level reorganization scheduling planning subsystem makes multiple corresponding decision iterations.

[0046] In step S203, the fitness corresponding to the updated order matching parameters is calculated according to the preset target function, and it is judged whether the fitness is greater than the fitness threshold, wherein the target function is constructed by coupling the AEVB product deviation parameter, the reorganization cost parameter, the delay penalty cost parameter and the line edge storage cost parameter. The reorganization cost parameter is associated with the process unit processing cost parameter, the delay penalty cost parameter is associated with the completion time parameter, and the line edge storage cost parameter is associated with the order online time parameter.

[0047] In this embodiment, the target function of the mathematical model corresponding to the upper matching model couples the AEVB product deviation parameter (corresponding to the specification difference between the reorganized products and the order demand products), the reorganization cost parameter (including the reorganization cost and the storage cost), the delay penalty cost parameter (including the delay delivery cost) and the line edge storage cost parameter (including the storage cost of the battery assembly in the reorganization workshop line edge warehouse), and the corresponding parameter values are used as the function values of the corresponding target function and used to calculate the corresponding fitness. It can be understood that the function values of the target function of the mathematical model corresponding to the lower scheduling model are also used to calculate the corresponding fitness. In this embodiment, after the upper decision level OM decision system completes an order matching decision, the fitness corresponding to the corresponding order matching scheme is calculated to determine and judge the pros and cons of the order matching scheme decided, so as to guide the OM decision system to decide whether to make decision iteration on the order matching scheme (corresponding to the order matching parameters), until the corresponding order matching scheme meets the set requirement, that is, until the corresponding target order matching parameters are generated.

[0048] Step S204, in the case of judging that the fitness is not greater than the fitness threshold value, the order matching decision iteration is repeated based on the reorganization scheduling decision parameter returned by the reorganization scheduling planning subsystem, the fitness and the NSGA-Ⅱ algorithm, until the target order matching parameter is generated, and the received target reorganization scheduling decision parameter and the target order matching parameter are taken as the collaborative result, and the target reorganization scheduling decision parameter is the reorganization scheduling decision parameter used to generate the target order matching parameter.

[0049] In the embodiment, when it is determined that the fitness corresponding to the corresponding order matching parameter is not greater than the fitness threshold value, it indicates that the order matching scheme of the current OM decision system decision is not the optimal battery assembly matching scheme, and the decision of the battery assembly matching needs to be continued. At this time, the OM decision system will make another order matching decision, and issue the corresponding order matching decision parameter to the reorganization scheduling planning subsystem, so that the reorganization scheduling planning subsystem makes multiple decisions of the optimal scheduling scheme of each flow line in the workshop, generates the optimal production scheduling decision corresponding to the corresponding order matching parameter, that is, the corresponding reorganization scheduling decision parameter.

[0050] In the embodiment, the OM decision system generates the optimal order matching parameter meeting the set requirements by making multiple order matching decision iterations and cross-level collaboration with the reorganization scheduling planning subsystem of the lower decision level. It can be understood that meeting the set requirements includes but is not limited to that the fitness of the optimal order matching parameter is greater than the fitness threshold value, the iteration number reaches the set number, and the difference between the fitnesses corresponding to the order matching parameters before and after is within the preset change value range.

[0051] By the steps S201 to S204, the selected order matching parameters are sent to the reorganization scheduling planning subsystem after completing the current iteration of order matching decision making, the reorganization scheduling decision parameters returned by the reorganization scheduling planning subsystem in response to the corresponding order matching parameters are received, the order matching decision making is updated based on the reorganization scheduling decision parameters and the preset NSGA-Ⅱ algorithm, the updated order matching parameters are generated, the fitness corresponding to the updated order matching parameters is calculated according to the preset objective function, and it is determined whether the fitness is greater than the fitness threshold. In the case where it is determined that the fitness is not greater than the fitness threshold, the order matching decision making iteration is repeated based on the reorganization scheduling decision parameters returned by the reorganization scheduling planning subsystem, the fitness, and the NSGA-Ⅱ algorithm, until the target order matching parameters are generated. The received target reorganization scheduling decision parameters and the target order matching parameters are taken as the collaborative results, the problem that the battery reorganization and matching are not collaboratively decided across levels in the related art is solved, and the joint optimization of the order matching and the reorganization scheduling that exist in different decision levels but are closely related is realized, so that the cascade utilization of the retired power battery is realized in a low-cost, efficient, and sustainable manner.

[0052] It should be noted that the order matching and the reorganization scheduling faced by the embodiments of the present application are in different decision levels, and the order matching decision making at the planning level significantly affects the reorganization scheduling decision making at the scheduling level, and the reorganization scheduling decision result can be used to measure the pros and cons of the order matching. The double-level optimization can be used to create an overall model of the inherent hierarchy between different levels of the supply chain, solve the interrelated decision network, and realize the integration of the planning and scheduling levels. The embodiments of the present application combine the principle of double-level planning (BIO) to construct the two-stage cross-level collaborative decision making of the order matching and the reorganization scheduling. In the embodiments, a nested double-level optimization algorithm is used to solve the corresponding decision parameters, the NSGA-II algorithm is used to solve the mathematical model corresponding to the order matching to obtain the optimal battery component matching scheme of all orders, and an improved adaptive catastrophe genetic algorithm is used to solve the mathematical model corresponding to the reorganization scheduling to obtain the optimal scheduling scheme of each pipeline in each workshop to meet the timely delivery of customer orders.

[0053] In some embodiments, the reorganization scheduling decision parameters at least include the process unit processing cost parameter, the completion time parameter, and the order online time parameter, and the following steps are further implemented:

[0054] Step 21, determine all recombination orders corresponding to the order selection parameters issued before the current upper layer decision is made, and encode and initialize the population according to the upper layer optimization model corresponding to the preset double-layer optimization mathematical model to generate initial coded individuals, wherein the upper layer optimization model includes an AEVB product difference function, a recombination cost function, a delay penalty cost function and a line-edge warehouse cost function, the recombination cost function is associated with the process unit processing cost parameter, the delay penalty cost function is associated with the completion time parameter, the line-edge warehouse cost function is associated with the order online time parameter, and the initial coded individual corresponds to a sub-code for representing a recombination product selection decision.

[0055] In this embodiment, the NSGA-II algorithm is used to solve the order selection, and then the related information corresponding to the decision of selecting the battery assembly needs to be genetically coded, that is, the chromosome gene is coded and the population is initialized according to the preset coding form, forming an initial population corresponding to the upper layer optimization model corresponding to the double-layer optimization mathematical model, that is, an initial population including a plurality of initial coded individuals.

[0056] In this embodiment, one sub-code of the initial coded individual corresponds to one recombination product selection decision, that is, the selection of the battery assembly required for one recombination order, for example: using multiple battery modules for recombination for one order, and the selected multiple battery modules correspond to the selection.

[0057] In this embodiment, when initializing the double-layer optimization mathematical model, the following settings are made for the upper-layer mathematical model that needs to be used: 1. The demand of a customer order is for the same product; 2. The demand of a customer order is for the same product; 3. Each order can only be reorganized with one battery material type, and batteries of the same brand and model are used as much as possible; 4. The battery monomers form a battery module in parallel, and the battery module forms a battery pack in series; 5. The battery type is divided according to the battery material type (such as ternary lithium, lithium iron phosphate, lithium titanate, etc.), the battery component type (module or cell), and the specification (voltage and capacity) in turn; 6. In order to avoid damage to the battery due to violent transportation and other situations during delivery, a certain proportion of redundancy is generally set according to the demand to ensure normal reorganization production; 7. The product categories produced by each workshop are different, and each workshop only produces one product; 8. The number of reorganization lines in each workshop is different; 9. The processes of all reorganization lines in the same workshop are the same; 10. One machine can only process one workpiece at a time; 11. Only one workpiece can be processed on one machine at the same time; 12. Any workpiece has no priority for processing; 13. Once the workpiece starts processing, it cannot be interrupted; 14. The logistics time and logistics resource constraints between processes are not considered; 15. In the reorganization stage, all machines and workpieces are available at zero time, and all machines are in good working condition; 16. It is assumed that all battery components required for order reorganization are transported to the line-side warehouse for temporary storage in the reorganization workshop at the same time; 17. It is assumed that the delivery time of the battery components in the line-side warehouse is equal to the production start time of the order, and the transfer time between the two is ignored.

[0058] In this embodiment, the mathematical model and parameter symbol definitions involved are as follows:

[0059] i represents the order number, i∈{1,2,3,…,n}; G(i) represents the required reorganized battery quantity of the i-th order; T i represents the expected delivery time of the battery product of the i-th order, represents the actual delivery time of the battery product of the i-th order; represents the unit delay penalty cost of the i-th order; s represents the battery material type, s∈{1,2,...,S}; a represents the battery parameter specification, a∈{1,2,…,A}; q s,m,a represents the inventory quantity of the battery module of the a-th parameter specification in the s-th battery material type; q s,c,a represents the inventory quantity of the battery monomer of the a-th parameter specification in the s-th battery material type; ah s,m,a represents the capacity value of the battery module of the a-th parameter specification in the s-th battery material type; V s,m,a represents the voltage value of the battery module of the a-th parameter specification in the s-th battery material type; ah s,c,arepresents the capacity value of the battery cell of the a-th parameter specification in the s-th battery material type; V s,c,a represents the voltage value of the battery cell of the a-th parameter specification in the s-th battery material type; represents the parallel quantity of the selected battery cell reorganized into the battery module in the i-th order; Ah i represents the capacity required for the AEVB of the i-th order; represents the capacity required for the AEVB of the i-th order actually produced; V i represents the voltage required for the AEVB of the i-th order; represents the voltage required for the AEVB of the i-th order actually produced; α represents the redundancy ratio; RT represents the arrival time of the battery assembly required for all orders reorganized to the reorganization workshop; ST i represents the start processing time of the i-th order on the reorganization line; C ot represents the unit temporary storage cost of the reorganization workshop line side warehouse; D r represents the upper limit of the capacity of the reorganization workshop line side warehouse at time r; C oq represents the unit penalty cost of the excess amount of the final assembly workshop line side warehouse; j represents the reorganization process label, j ∈ {1, 2, …, J}; t i,j represents the processing time of the AEVB corresponding to the i-th order in the j-th reorganization process, ; C j represents the unit time production cost of the j-th reorganization process; M j represents the number of machines in the j-th reorganization process; m represents the machine number in the j-th reorganization process, m ∈ {1, 2, …, M j}; T i,j represents the completion time of the i-th order in the j-th reorganization process; E j represents the earliest machine idle time in the j-th reorganization process; represents the line side warehouse delivery time of the battery assembly required for the i-th order; represents the unit processing time of the battery module in the j-th reorganization process; represents the unit processing time of the battery cell in the j-th reorganization process, is a variable of 0 or 1, indicating whether the battery module is processed in the j-th reorganization process, if yes, = 1, otherwise = 0; is a variable of 0 or 1, indicating whether the battery cell is processed in the j-th reorganization process, if yes, = 1, otherwise = 0; represents the number of battery modules of the s-th battery material type required for the AEVB corresponding to the i-th order; This represents the number of battery cells of the s-th battery material type required for the AEBV corresponding to the ith order. The variable is either 0 or 1, indicating whether the AEBV corresponding to the i-th order uses a battery module with parameter specification a from the s-th battery material type for reprocessing. If yes, =1, otherwise, =0; The variable is either 0 or 1, indicating whether the AEBV corresponding to the i-th order uses battery cells of the a-th parameter specification from the s-th battery material type for recombined production. If yes, =1, otherwise, =0; The variable is either 0 or 1, indicating whether the AEBV corresponding to the i-th order uses battery components similar to the s-th battery material for refactoring production. If yes, =1, otherwise, =0; A variable that is either 0 or 1, indicating whether the i-th order on the m-th machine in the j-th reassembly process is the first one. The preceding work for an order, if so. =1, otherwise =0; A variable that is 0 or 1 represents the first... Is the order the first to be produced on the m-th machine in the j-th process? If so, =1, otherwise, =0; A variable that is 0 or 1 represents the first... Is the order the last one produced on the m-th machine in the j-th process? If so, =1, otherwise, =0; The variable is either 0 or 1, indicating whether the AEBY corresponding to the i-th order has undergone the j-th process. If yes, =1, otherwise, =0.

[0060] In this embodiment, for the OM decision-making system at the upper-level decision-making level, the objective function used to calculate the fitness value of a sub-encoder is: minimizing the specification difference between the reorganized product and the product required by the order. and minimize battery component selection costs Where C is the optional cost, C p Indicates restructuring costs, ; Indicates the cost of delayed delivery. C s C represents the storage cost of battery modules in the line-side warehouse of the reprocessing workshop. s=C1+C2, C1 represents the excess penalty cost, , C2 represents the temporary storage cost, ; The objective function of the OM decision system is subject to the constraint functions as follows: 1. The outbound quantity of the battery module cannot exceed the current inventory, and the constraint function is: ; 2. The outbound quantity of the battery monomer cannot exceed the current inventory, and the constraint function is: ; 3. The combined capacity of the battery module and the battery individual selected by each order AEVB must be greater than or equal to the specified capacity required by the AEVB, and the constraint function is: ; 4. The combined voltage of the battery module and the battery individual selected by each order AEVB must be greater than or equal to the specified voltage required by the AEVB, and the constraint function is: .

[0061] In some optional embodiments, according to the upper optimization model corresponding to the preset double-layer optimization mathematical model, all reorganized orders are encoded and population initialized, including the following steps:

[0062] Step 1, obtain the objective function and constraint parameters corresponding to the upper optimization model, and obtain the production order information corresponding to each reorganized order target information, wherein the production order information includes the reorganized power battery target information.

[0063] Step 2, select at least one battery combination matching information for each reorganized power battery target information from the preset battery combination matching information, wherein one battery combination matching information is used to represent the composition of the battery material and the battery component corresponding to one reorganized power battery.

[0064] Step 3, using the objective function and constraint parameters, solving and optimizing the battery combination matching information corresponding to each reorganized power battery target information, generating the intended battery combination matching information corresponding to each reorganized power battery information, and performing two-dimensional integer coding on the intended battery combination matching information according to the preset coding form, obtaining the sub-coding corresponding to the reorganized power battery target information.

[0065] Step 4, after determining the fitness value corresponding to each sub-coding, integrating the sub-coding corresponding to all reorganized orders into an initial coding individual, and initializing the population based on one initial coding individual, generating multiple initial coding individuals.

[0066] In some preferred embodiments, referring to Figure 3 The coding process of the coding individual of the embodiment of the application is described as follows:

[0067] According to the problem characteristics, each initial coding individual is represented by a two-dimensional chromosome, and all use integer coding. An initial coding individual (refer toFigure 3 P1, P2 in FIG. 1) corresponds to the longitudinal order number of the chromosome, and the transverse direction represents the number of battery types Type to be selected, wherein the battery types are divided in turn according to the battery material type (for example: ternary lithium, lithium iron phosphate, lithium titanate), the battery component type (for example: battery module, battery monomer), and the specification (for example: voltage, capacity). In this embodiment, a certain row of the chromosome corresponds to a sub-code of an initial coding individual; with reference to Figure 3 , the ternary lithium battery material type includes M1, C11, and C12, the lithium iron phosphate battery material type includes C2, and the lithium titanate battery material includes M3 and C3. Considering Figure 3 P1 coding individual (corresponding to a chromosome) described in FIG. 1, M1, C11, and C12 belong to the same material type, M1 belongs to a different battery component type under the same material type as C11 and C12, M1 is a battery module, C11 and C12 are battery monomers with different specifications, accordingly, C2 is a battery monomer of a second material type, and M3 and C3 are different battery component types of a third material type; it should be noted that for an order, only battery components of the same material type can be used, for example, in Figure 3 P2 coding individual described in FIG. 1, for order 1 (#1), when the current three columns have data, the 4th-6th columns will be processed as 0, and similarly for order 2, when the 5th-6th columns have data, the first 4 columns will be processed as 0. This coding method can easily satisfy the constraint of using only battery components of the same material type, and can be more flexible and effective for subsequent processing.

[0068] Step 22, based on the NSGA-II algorithm, the upper optimization model, and the fitness of all initial coding individuals, the non-dominated solution sorting of the NSGA-II algorithm is performed on the plurality of initial coding individuals, and the genetic evolution operation is performed on the candidate coding individuals after the non-dominated solution sorting, to generate the current coding individual corresponding to the current upper decision, wherein the fitness is determined according to the sub-code corresponding to the initial coding individual, the sub-individual target value calculated according to the objective functions of the coupling AEVB product difference function, the recombination cost function, the delay penalty cost function, and the line side storage cost function, the genetic evolution operation includes the tournament selection operation, the multi-point crossover operation, and the non-uniform mutation operation.

[0069] In the embodiment, in the order matching decision solving process using the NSGA-II algorithm, the function value of the objective function coupled with the AEVB product deviation parameter (corresponding to the specification difference between the recombined product and the order demand product), the recombination cost parameter (including the recombination cost and the storage cost), the delay penalty cost parameter (including the delay delivery cost), and the line-side warehouse storage cost parameter (including the storage cost of the battery assembly in the recombination workshop line-side warehouse) is taken as the fitness value of a sub-code, and the fitness values of multiple sub-codes are collected as the fitness of an initial coding individual. In the embodiment, the non-dominated solution sorting of the initial coding individual and the genetic evolution operation of the individual after the non-dominated solution sorting are an update of the order matching decision. The order matching decision update includes the battery module and the battery cell quantity, specification (voltage and capacity) of a certain battery material type (for example, ternary lithium and lithium iron phosphate) used for each order matching battery assembly, and the decision target includes the specification difference between the recombined AEVB and the order demand AEVB, the minimum matching cost of the battery assembly, the recombination cost, the delay delivery cost, the storage cost of the battery assembly in the recombination workshop line-side warehouse, and the excess penalty cost and the temporary storage cost.

[0070] It can be understood that the non-dominated solution sorting of the NSGA-II algorithm in the embodiment of the application is a technology known to those skilled in the art and does not constitute a limitation on the unclearness of the technical solution, that is, based on the existing NSGA-II algorithm, the non-dominated solution sorting of the initial coding individual and its sub-codes can be realized, and then the corresponding candidate coding individual is obtained, and then the related genetic evolution operation adopted in the embodiment is performed. Specifically, the tournament selection operation, the multi-point crossover operation, and the non-uniform mutation operation are performed.

[0071] Step 23: taking the order matching parameters generated by decoding the current coding individual as the updated order matching parameters.

[0072] Through the above steps 21 to 23, the order matching decision update of the genetic upper decision level is realized.

[0073] In some embodiments, the genetic evolution operation of the candidate coding individual after the non-dominated solution sorting is realized through the following steps:

[0074] Step 31: randomly selecting any two candidate coding individuals from the multiple candidate coding individuals obtained by the tournament selection operation as an intended coding group, and selecting multiple sub-codes to be operated from all the sub-codes corresponding to the two candidate coding individuals in the intended coding group, and then performing crossover on the selected sub-codes from the corresponding two candidate coding individuals to generate two corresponding first offspring coding individuals.

[0075] In this embodiment, according to the fitness values of the candidate coded individuals, a tournament selection operation is performed to select some individuals (corresponding to a preset number of candidate coded individuals) to be crossed from the parent population (corresponding to all candidate coded individuals of the current iteration), and the individuals with higher fitness values have a higher probability of being selected. In this embodiment, after the candidate coded individuals are selected, a multi-point crossover operation is performed using an order-based multi-point crossover (MPX) method. The offspring C1 and C2 are generated by crossing the parents P1 and P2 (see Figure 3 ) to generate the offspring C1 and C2 (see Figure 4 ). The multi-point crossover process is as follows: (1) first, randomly select multiple points in the longitudinal coding of the chromosome, find the order numbers corresponding to these points, and then select the battery type combinations allocated to these orders in the P1 and P2 chromosome transverse coding according to the obtained order numbers; 3, finally, exchange the battery type combination coding of the corresponding orders selected in P1 and P2 to generate the offspring C1 and C2 obtained by crossing.

[0076] Step 32, from all sub-codes of the two corresponding first offspring coded individuals of each group of intended offspring coded individuals, select a sub-code to be mutated, and determine at least one intended code in the selected sub-code, wherein the intended code is used to represent the coding value of the corresponding code as non-zero.

[0077] Step 33, according to the preset mutation strength control number, randomly increase or decrease the mutation of at least one intended code, and take the mutated code as the new code of the corresponding sub-code, to generate a second offspring coded individual corresponding to each first coded individual, to obtain the coded individuals corresponding to the current iteration of the upper layer decision.

[0078] In this embodiment, non-uniform mutation (corresponding to non-zero position mutation) is used to mutate all sub-codes of the first offspring coded individuals, and the offspring D1 and D2 are generated by mutating the parents C1 and C2 (see Figure 4 ). Figure 5 In this embodiment, the non-zero positions in the chromosome are mutated, and a set of integers controlled by the mutation strength is randomly added or subtracted from the non-zero positions, thereby achieving the effect of mutation.

[0079] Through the above steps 31 to 33, the genetic evolution operation on the candidate coded individuals sorted by non-dominated solutions is realized.

[0080] In some embodiments, before generating the target order matching parameters, the following steps are also implemented:

[0081] Step 41, judging whether the order matching decision iteration after the current upper layer decision satisfies the preset iteration termination condition, wherein the iteration termination condition at least includes one of the following: the difference between the fitness of the current encoding individual corresponding to the current upper layer decision iteration and the fitness of the current encoding individual corresponding to the previous upper layer decision iteration is less than the population fitness variation threshold, and the number of order matching decision iterations exceeds the preset iteration number threshold.

[0082] Step 42, in the case of judging that the iteration termination condition is satisfied, taking the order matching parameter generated by the current upper layer decision as the target order matching parameter.

[0083] Step 43, in the case of judging that the iteration termination condition is not satisfied, performing the next order matching decision iteration based on the reorganization scheduling decision parameter, the fitness returned by the reorganization scheduling planning subsystem, and the NSGA-II algorithm.

[0084] Through the above steps 41 to 43, it is realized to judge whether the target order matching parameter is obtained.

[0085] In some embodiments, for the reorganization scheduling planning subsystem, the following steps are adopted to perform the operation of making the reorganization scheduling decision based on the improved adaptive catastrophe genetic algorithm and the corresponding order matching parameter:

[0086] Step 51, after receiving the corresponding order matching parameter, obtaining all the reorganization orders from the corresponding order matching parameter, and determining the target job process parameters specified by each reorganization order.

[0087] In the present embodiment, the reorganization scheduling workshop sets the target number of target job processes, but because the order matching obtains different battery assembly matching, the case of one or more target job process reordering (not performing) may occur, for example: one order matching parameter 1 corresponds to the target job processes 1, 2, 3, 4, 5, 6, 7, and one order matching parameter 2 corresponds to the target job processes 1, 3, 6, 7. For a certain order matching parameter corresponding to the target job process, it has been determined when the order matching parameter is received, but the order corresponding to the order matching parameter on a certain target job process can be scheduled and decided, for example: the AEVB required to be produced by the order 1 associated with the order matching parameter 1 needs to be worked on the target job process 3, and the AEVB required to be produced by the order 2 associated with the order matching parameter 2 also needs to be worked on the target job process 3. For the target job process 3, the production of order 2 can be arranged first, and then the production of order 1 can be arranged, or the production of order 1 can be arranged first, and then the production of order 2 can be arranged. Therefore, the reorganization scheduling decision based on the improved adaptive catastrophe genetic algorithm and the corresponding order matching parameter can be made.

[0088] In the embodiment, after all the reorganization orders are obtained and the target job process parameters specified by each reorganization order are determined, a decision plan can be made for the target job process corresponding to each reorganization order to produce a corresponding reorganization schedule, that is, the production order of the reorganization order at each job process station is arranged.

[0089] In step 52, based on the lower optimization model corresponding to the double-layer optimization mathematical model, the reorganization orders and the target job process parameters are integer coded and initialized according to a preset coding rule to generate a plurality of reorganization schedule coding bodies, wherein the lower optimization model includes a completion time target function and a plurality of target sub-constraint parameters, the sub-coding corresponding to the reorganization schedule coding body is generated by coding according to the completion time target function and the target sub-constraint parameters, and is used to represent the order of the reorganization order associated with a target job process parameter.

[0090] In the embodiment, the reorganization schedule planning subsystem uses an improved adaptive catastrophe genetic algorithm (IACGA) to solve the reorganization schedule decision, and thus the arrangement of the job process of the battery assembly needs to be genetically coded, that is, the chromosome gene coding and population initialization are performed according to the preset coding form to form an initial population corresponding to the lower optimization model corresponding to the double-layer optimization mathematical model, that is, a plurality of reorganization schedule coding bodies.

[0091] In the embodiment, after the reorganization schedule coding is coded, the reorganization schedule coding body is calculated by calculating the target value of the completion time target function corresponding to the sub-coding body of the reorganization schedule coding body, and the scheduling fitness of the corresponding reorganization schedule coding body is calculated. In the embodiment, the completion time target function is: The constraint functions corresponding to the plurality of target sub-constraint parameters are as follows: 1. The constraint that any order in the same process can only have one immediate preceding order on all machines in the same process is: 2. The constraint that any order in the same process can only be an immediate preceding order of a job on all machines in the same process is: 3. There is no immediate preceding and immediate following relationship between orders in the same position on the same machine, and the function is: 4. The constraint between the completion times of each sequential job of the current machine is: 5. The start processing time of the i-th order is 6. The start processing time of the i-th order is equal to the material delivery time, and the constraint function is: 7. The constraint between the completion times of the preceding and subsequent processes of a specific job is: 8. The start time of the i-th order in the current process is equal to the maximum value of the completion time of the previous process and the earliest machine idle time in the j-th process. The constraint function is: 9. Order delivery date constraints, the function is: .

[0092] In some preferred embodiments, reference Figure 6 and Figure 7 The encoding and decoding process of the recombinant scheduling code in this application embodiment is described below: An operation-based integer encoding method is adopted, where each individual is represented by a one-dimensional chromosome. The encoding length is only related to the number of jobs n and the number of procedures m, so the encoding length is n*m. The encoded content is an integer value between 1, 2, ..., n*m. For example, consider... Figure 6 The L1 entity is described, consisting of 4 operations and 3 processes, thus having a code length of 12 and code content consisting of values ​​between 1, 2, ..., 12; (Reference) Figure 6 After decoding L1, the corresponding workshop scheduling scheme will be obtained (see reference). Figure 6 (Job and Process sections in the text).

[0093] In this embodiment, reference Figure 7 To obtain the scheduling arrangements of the workshops at various times, it is necessary to decode the chromosome code into specific workshop scheduling schemes. The final scheduling scheme array is as follows: The specific decoding steps for L=n*m are as follows:

[0094] Step 1: Obtain the current chromosome nowChrome, with a length of L=n*m.

[0095] Step 2: Define a detailed scheduling scheme array schedule[L][5]. The scheduling scheme consists of five columns of data: jobId, machId, processId, startTime, and endTime.

[0096] Step 3: Let the current process j=1, and traverse (1,2,…,J).

[0097] Step 4: Find all job codes for process j in nowChrome based on the "basic correspondence table", and keep their order in nowChrome, assuming it is procSeq. Find the corresponding job code jobSeq. The corresponding calculation logic is as follows: first find the numbers in nowChrome that are less than or equal to m*i, then find the numbers greater than m*(i-1) from the above sequence, and record them as procSeq. Take the remainder of the above (number-1) divided by m and add 1 to get jobSeq.

[0098] Step 5, arrange the job to the machine according to the job sequence jobSeq of the current process j (priority rule).

[0099] In the embodiment, the number of currently available machines nowMachIds needs to be obtained according to the process, and an array machProcArray can be expressed as follows by assuming that process 1 has 2 machines, process 2 has 3 machines, and process 3 has 2 machines, using a similar "basic correspondence table". Figure 7 .

[0100] Step 53, iteratively perform genetic evolution operation and population catastrophe operation on a plurality of corresponding recombination scheduling codes based on the preset catastrophe adaptive genetic algorithm, the lower-level optimization model, and the scheduling fitness corresponding to the recombination scheduling code participating in each recombination scheduling iteration, until a plurality of intended recombination scheduling codes are generated, wherein the scheduling fitness is determined according to the completion time target function corresponding to the sub-code corresponding to the recombination scheduling code.

[0101] In the embodiment, the process of iteratively performing population on a recombination scheduling code and corresponding sub-codes is a decision update of the production order arrangement of the recombination workshop scheduling. It can be understood that the dynamic selection and adaptive crossover mutation performed by the catastrophe adaptive genetic algorithm belong to the technology known to those skilled in the art and do not constitute a limitation on the unclearness of the technical solution. At the same time, it is also implementable to trigger a catastrophe according to the preset catastrophe rule to guide the adaptive genetic algorithm to perform corresponding genetic evolution operation iteration. In the embodiment, according to the fitness of the population individuals of each iteration, it is determined whether to perform a catastrophe and whether the population individuals after iteration (corresponding to candidate codes) meet the set requirements, that is, whether they are intended recombination scheduling codes. Through multiple catastrophe operations and genetic evolution operations, the fitness of the individuals in the corresponding population meets the set requirements, and then a plurality of intended recombination scheduling codes are obtained.

[0102] Step 54, obtain a target recombination scheduling code from the plurality of intended recombination scheduling codes, and generate a recombination scheduling decision parameter corresponding to the lower-level decision after decoding the target recombination scheduling code.

[0103] In some optional embodiments, the target recombination scheduling code is obtained from the plurality of intended recombination scheduling codes by the following steps:

[0104] Step 54-1, determine the fitness corresponding to each intended recombination scheduling code.

[0105] Step 54-2, selecting the reorganization scheduling encoding body with the highest fitness from the plurality of reorganization scheduling encoding bodies, obtaining a target reorganization scheduling encoding body, and extracting all sub-codes of the target reorganization scheduling encoding body to obtain target sub-codes.

[0106] Step 54-2, selecting the reorganization scheduling encoding body with the highest fitness from the plurality of reorganization scheduling encoding bodies, obtaining a target reorganization scheduling encoding body, and extracting all sub-codes of the target reorganization scheduling encoding body to obtain target sub-codes.

[0107] Through the above steps 51 to 54, the reorganization scheduling planning subsystem realizes the operation of making reorganization scheduling decisions based on the improved adaptive catastrophe genetic algorithm and the corresponding order matching parameters.

[0108] In some embodiments, for the reorganization scheduling planning subsystem, the following steps are adopted to perform the operation of iterating the genetic evolution operation and population catastrophe operation on the plurality of corresponding reorganization scheduling encoding bodies:

[0109] Step 61, according to the fitness of the plurality of reorganization scheduling encoding bodies participating in the current reorganization scheduling iteration, using an elite reservation strategy to select a predetermined number of candidate scheduling encoding bodies from the plurality of reorganization scheduling encoding bodies participating in the current reorganization scheduling iteration.

[0110] In this embodiment, according to the fitness value of the reorganization scheduling encoding body, the elite reservation strategy is adopted to reserve the top 5% of excellent individuals to realize the selection operation.

[0111] Step 62, based on the corresponding adaptive crossover probability and adaptive mutation probability, sequentially performing partial matching crossover operation and insertion mutation operation on all candidate scheduling encoding bodies to generate a plurality of first coding individuals, wherein the reorganization scheduling encoding bodies 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.

[0112] In the embodiment, the selected preset number of candidate scheduling codes are first subjected to a crossover operation based on an adaptively adjusted crossover probability to generate new individuals; in the embodiment, the crossover probability is adaptively and dynamically adjusted according to the fitness values of the population and the evolution 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 used for individuals with lower fitness values to increase the exploration range; in the later stage of evolution, a lower crossover probability is conducive to local optimization, that is, a lower crossover rate is used for individuals with higher fitness values to protect the excellent genes; in the embodiment, after the new individuals are generated through crossover, the genes of the new individuals are subjected to a mutation operation based on an adaptively adjusted mutation probability to generate a plurality of first coding individuals; in the embodiment, the mutation probability can also be adaptively adjusted according to the evolution characteristics of the population and the fitness values of the individuals; in the early stage of evolution, a higher mutation probability helps to explore the entire search space, that is, a higher mutation rate is used for individuals with lower fitness values to increase the exploration range; in the later stage of evolution, a lower mutation probability helps to concentrate on local search to find the optimal solution, that is, a lower mutation rate is used for individuals with higher fitness values to protect the excellent genes; it can be understood that, as the evolution proceeds, the algorithm gradually approaches the optimal solution, at this time, the crossover probability and the mutation probability should be appropriately reduced to protect the obtained excellent genotypes from being destroyed, while allowing subtle search to improve the quality of the solution, therefore, in the embodiment, the crossover probability function and the mutation probability function are set as monotonic decreasing functions, for a minimization problem, the smaller the fitness value of an individual, the smaller the current crossover probability and mutation probability should be, in the embodiment, the crossover probability and the mutation probability are adaptively adjusted by using the set crossover probability function and mutation probability function.

[0113] In the embodiment, the reference Figure 8 to Figure 12 The process of sequentially performing the partial match crossover operation and the insertion mutation operation on all candidate scheduling codes in the embodiment of the application is described as follows:

[0114] The partial match crossover ensures that the genes in each chromosome appear only once, and through the crossover strategy, no repeated genes will appear in a chromosome, by randomly selecting two crossover points to determine the crossover region, after performing the crossover, two invalid chromosomes are generally obtained, and individual genes may appear repeatedly, in order to repair the chromosomes, the matching relationship of each chromosome can be established in the crossover region, and then the matching relationship can be applied to the repeated genes outside the crossover region to eliminate the conflicts.

[0115] For the partial match crossover operation, the following steps are included:

[0116] Step 1, a pair of chromosomes (parents) are randomly selected (for reference Figure 8the start and end positions of several genes in P1 and P2 in FIG. 1 (the same selected positions of two chromosomes), assuming that the fourth position (corresponding to Figure 8 the "2" of P1 and the "7" of P2 indicated by the arrow in FIG. 1) and the eighth position (corresponding to Figure 8 the "1" of P1 and the "8" of P2 indicated by the arrow in FIG. 1).

[0117] Step 2, exchange the positions of the two groups of genes to obtain two invalid chromosomes, and the individual genes appear repeatedly (refer to FIG. 2). Figure 9 P1 and P2 in FIG. 1.

[0118] Step 3, perform conflict detection, and establish a mapping relationship according to the two groups of genes exchanged, such as Figure 10 , taking the mapping relationship of 7-2-12 as an example, the offspring P1 generated in step 2 has two genes 7, which is converted to gene 12 through the mapping relationship, and so on until there is no conflict; finally, all the conflicting genes will be mapped to ensure that the new pair of offspring genes formed have no conflict (refer to FIG. 3). Figure 11

[0119] For the insertion mutation operation, a new chromosome is generated by inserting a gene at a certain locus to other loci of the chromosome, including the following steps:

[0120] Step 1: randomly select a chromosome P1 (refer to FIG. 4). Figure 12

[0121] Step 2: randomly select a gene on the chromosome P1, and randomly move the gene to other loci in the chromosome to generate offspring chromosome C1.

[0122] In this embodiment, first, generate two random numbers pos1 and pos2 between 1:L (for example, "7" indicated by the arrow in FIG. 4), judge the size of pos1 and pos2, if pos1 Figure 12 pos1, pos2, if pos1>pos2, move the genes between pos1 and pos2 by one position, and then assign pos1 to pos2.

[0123] It can be understood that the above-mentioned insertion mutation is clear to those skilled in the art, and the insertion mutation does not constitute a limitation on the technical solutions of the present application.

[0124] ​​Step 63, in all recombination scheduling codes generated by the previous genetic evolution iteration, the recombination scheduling code with the optimal fitness is selected to obtain the first optimal individual corresponding to the previous genetic evolution iteration, and the first coding individual with the optimal fitness is selected from the plurality of first coding individuals to obtain the second optimal individual corresponding to the genetic evolution iteration, and it is judged whether the fitness of the second optimal individual is higher than that of the first optimal individual.

[0125] In the embodiment, the optimal individual (corresponding to the first optimal individual) in the initial population (corresponding to all recombination scheduling codes generated by the previous genetic evolution iteration) is saved as the first local optimal individual; after the population is subjected to several genetic operations, whether the fitness of the second optimal individual is higher than that of the first optimal individual is used as a judgment condition for judging whether a better individual is generated and whether a catastrophe operation is performed, and the catastrophe operation is performed when the catastrophe judgment condition is met.

[0126] Step 64, according to the judgment result, the target optimal individual corresponding to the genetic evolution iteration is selected from the second optimal individual and the first optimal individual, and the catastrophe operation is performed on the plurality of first coding individuals in a preset catastrophe mode to generate a plurality of second coding individuals, wherein the recombination scheduling codes corresponding to the catastrophe operation iteration of the current population include the second coding individuals.

[0127] In some optional embodiments, for the recombination scheduling planning subsystem, the following steps are used to perform the operation of performing the catastrophe operation on the plurality of first coding individuals in a preset catastrophe mode to generate a plurality of second coding individuals.

[0128] Step 641, when it is judged that the fitness of the second optimal individual is higher than that of the first optimal individual, a preset number of first coding individuals are selected in order of fitness from high to low to obtain elite coding individuals, and all the elite coding individuals are initialized based on the lower-level optimization model to generate a plurality of corresponding second coding individuals.

[0129] In the embodiment, if the optimal individual (corresponding to the second optimal individual) in the current population is better than the last updated local optimal individual (corresponding to the first optimal individual), the current local optimal individual is updated, and a type of catastrophe operation is performed, that is, a preset number of first coding individuals are selected in order of fitness from high to low to obtain elite coding individuals, and all the elite coding individuals are initialized to generate a plurality of corresponding second coding individuals; in the embodiment, the individuals (corresponding to the elite coding individuals) in the elite layer of the current population are preferably initialized one by one.

[0130] Step 642, in the case of judging that the fitness of the second optimal individual is not higher than the first optimal individual, selecting the first coding individuals with the set catastrophe scale number in the order of fitness from low to high, obtaining eliminated coding individuals, and after removing all eliminated coding individuals from the plurality of first coding individuals, adding the plurality of newly generated coding individuals to the remaining first coding individuals, obtaining a plurality of second coding individuals corresponding thereto, wherein the number of newly generated coding individuals is equal to the set catastrophe scale number.

[0131] In the embodiment, if the optimal individual in the current population (corresponding to the second optimal individual) is inferior to the locally optimal individual saved last time (corresponding to the first optimal individual), it is considered that the search direction of the current population has deviated, and a second type of 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, thereby improving the diversity of the population. The current catastrophe scale M is not constant, but decreases with the increase of the number of iterations, so as to ensure the stability of the algorithm in the later period. In the embodiment, the current catastrophe scale M is calculated by the following formula:

[0132]

[0133] M is the current catastrophe scale, is a preset catastrophe scale, and λ is a control parameter, is the current iteration number, is the maximum iteration number.

[0134] In some embodiments, for the recombination scheduling planning subsystem, after obtaining the plurality of second coding individuals corresponding thereto, the following steps are further performed:

[0135] Step 71, judging whether the current iteration satisfies a preset iteration termination condition after the iteration of the current population catastrophe operation, wherein the iteration termination condition at least includes one of the following: the fitness difference between the second coding individuals corresponding to the current population catastrophe operation iteration and the previous population catastrophe operation iteration is less than a population fitness change threshold, and the number of the current population catastrophe operation iteration exceeds a preset iteration number threshold.

[0136] Step 72, in the case of judging that the iteration termination condition is satisfied, taking the plurality of second coding individuals as the plurality of intended recombination scheduling coding bodies.

[0137] Step 73, in the case of judging that the iteration termination condition is not satisfied, performing iteration of the genetic evolution operation and the population catastrophe operation on the plurality of second coding individuals, until the plurality of intended recombination scheduling coding bodies are obtained.

[0138] In the embodiment, whether the algorithm is terminated is determined according to preset termination conditions (such as the number of iterations, the change of population fitness), and if the termination conditions are met, the optimal solution (that is, multiple intention reorganization scheduling encoding bodies) is output; if not, the next iteration is entered until the optimal solution is output.

[0139] In some embodiments, for the reorganization scheduling planning subsystem, before the multiple first encoding individuals are generated, the following steps are further implemented:

[0140] In step 81, the average fitness and the minimum fitness corresponding to all the alternative scheduling encoding bodies are determined according to the fitness of the alternative scheduling encoding bodies, and whether the average fitness is less than the minimum fitness is determined.

[0141] In step 82, if it is determined that the average fitness is less than the minimum fitness, the preset maximum crossover probability and the maximum mutation probability are respectively taken as the corresponding adaptive crossover probability and adaptive mutation probability.

[0142] In step 83, if it is determined that the average fitness is greater than the minimum fitness, the maximum crossover probability and the maximum mutation probability are respectively decreased by using the corresponding crossover probability function and mutation probability function, and the first crossover probability and the first mutation probability obtained after the decrease are respectively taken as the corresponding adaptive crossover probability and adaptive mutation probability.

[0143] In the embodiment, the crossover probability function and the mutation probability function are used to adaptively adjust the crossover probability and the mutation probability, and specifically,

[0144] Crossover probability function

[0145]

[0146] Mutation probability function

[0147]

[0148] Wherein, respectively represent the lower bound and the upper bound of the crossover probability, f min represents the minimum value of the fitness in the first encoding individual corresponding to the previous genetic evolution operation iteration, f avg represents the average value of the fitness of the alternative scheduling encoding bodies, represents the minimum value of the fitness of the alternative scheduling encoding bodies, respectively represent the upper bound and the lower bound of the mutation probability, f m represents the fitness value of the mutated individual (the alternative encoding body after the completion of the current crossover operation); based on the sigmoid function The crossover probability function and the mutation probability function are monotonically decreasing functions, and the crossover probability and the mutation probability are monotonically decreasing.

[0149] The embodiment also provides a cross-level collaborative system for AEVB order matching and reorganization scheduling based on double-layer planning, including a memory and a processor, the memory storing a computer program, and the processor being configured to execute the computer program to perform the steps in any of the method embodiments.

[0150] Optionally, the collaborative system can further include a transmission device and an input / output device, wherein the transmission device is connected with the processor, and the input / output device is connected with the processor.

[0151] Optionally, in the embodiment, the processor can be configured to execute the following steps through the computer program:

[0152] S1, after completing the current iteration of order matching decision, the determined order matching parameters are sent to the reorganization scheduling planning subsystem.

[0153] S2, receiving the reorganization scheduling decision parameters returned by the reorganization scheduling planning subsystem in response to the corresponding order matching parameters, updating the order matching decision based on the reorganization scheduling decision parameters and the preset NSGA-Ⅱ algorithm, and generating updated order matching parameters.

[0154] S3, calculating the fitness corresponding to the updated order matching parameters according to the preset objective function, and determining whether the fitness is greater than the fitness threshold.

[0155] S4, in the case where it is determined that the fitness is not greater than the fitness threshold, repeating the order matching decision iteration based on the reorganization scheduling decision parameters returned by the reorganization scheduling planning subsystem, the fitness, and the NSGA-Ⅱ algorithm, until the target order matching parameters are generated, and the received target reorganization scheduling decision parameters and the target order matching parameters are taken as the collaborative result, the target reorganization scheduling decision parameters being the reorganization scheduling decision parameters used to generate the target order matching parameters.

[0156] It should be noted that the specific examples in the embodiment can refer to the examples described in the above embodiments and optional implementation manners, which will not be described here again.

[0157] In addition, in combination with the cross-level collaborative method for retired power battery order matching and reorganization scheduling based on double-layer planning in the above embodiments, the embodiment can provide a storage medium for implementation. The storage medium stores a computer program; when the computer program is executed by a processor, any of the cross-level collaborative methods for retired power battery order matching and reorganization scheduling based on double-layer planning in the above embodiments is implemented.

[0158] Those skilled in the art should understand that each technical feature of the above embodiments can be combined arbitrarily, and for the sake of brevity, each technical feature of the above embodiments is not described in all possible combinations, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the description.

[0159] The above embodiments only express several implementation manners of the application, the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the application, a number of modifications and improvements can be made, which are all within the protection scope of the application. Therefore, the protection scope of the patent of the application should be subject to the appended claims.

Claims

1. A cross-level collaborative method for retired power battery order matching and reorganization scheduling based on bi-level programming, characterized in that, The method comprises the following steps: After completing the current iteration of the order selection decision, the selected order selection parameters are sent to the reorganization scheduling planning subsystem; The reorganization scheduling decision parameters returned by the reorganization scheduling planning subsystem in response to the corresponding order selection parameters are received, and order selection decision updating is performed based on the reorganization scheduling decision parameters and a preset NSGA-II algorithm to generate updated order selection parameters, wherein the reorganization scheduling decision parameters are generated by the reorganization scheduling planning subsystem based on an improved adaptive catastrophe genetic algorithm and the corresponding order selection parameters; According to a preset target function, the fitness of the updated order selection parameters is calculated, and it is determined whether the fitness is greater than a fitness threshold; If it is determined that the fitness is not greater than the fitness threshold, the order selection decision iteration is repeated based on the reorganization scheduling decision parameters returned by the reorganization scheduling planning subsystem, the fitness, and the NSGA-II algorithm until the target order selection parameters are generated, and the received target reorganization scheduling decision parameters and the target order selection parameters are taken as the collaborative results, and the target reorganization scheduling decision parameters are used to generate the target order selection parameters.

2. The method of claim 1, wherein, The reorganization scheduling decision parameters at least include process unit processing cost parameters, completion time parameters, and order online time parameters, and the method further comprises the following steps: Before the current upper-level decision is made, all reorganization orders corresponding to the order selection parameters sent before are determined, and encoding and population initialization are performed on all the reorganization orders according to an upper-level optimization model corresponding to a preset double-layer optimization mathematical model to generate initial encoding individuals, wherein the upper-level optimization model includes an AEVB product difference function, a reorganization cost function, a delay penalty cost function, and a line-edge storage cost function, the reorganization cost function is associated with the process unit processing cost parameters, the delay penalty cost function is associated with the completion time parameters, the line-edge storage cost function is associated with the order online time parameters, and the sub-codes corresponding to the initial encoding individuals are used to represent a reorganization product selection decision; Based on the NSGA-II algorithm, the upper-level optimization model, and the fitness of all the initial encoding individuals, non-dominated solution sorting of the NSGA-II algorithm is performed on a plurality of initial encoding individuals, and genetic evolution operations are performed on candidate encoding individuals that have completed non-dominated solution sorting to generate current encoding individuals corresponding to the current upper-level decision, wherein the fitness is determined according to the sub-code corresponding to the initial encoding individual, and the sub-individual target value calculated according to a target function coupled with the AEVB product difference function, the reorganization cost function, the delay penalty cost function, and the line-edge storage cost function, the genetic evolution operations include tournament selection operations, multi-point crossover operations, and non-uniform mutation operations; The order selection parameters generated by decoding the current encoding individuals are taken as the updated order selection parameters.

3. The method of claim 2, wherein, The genetic evolution operation is performed on the candidate coding individuals of the non-dominated solution sorting, including: two candidate coding individuals are randomly selected from the multiple candidate coding individuals obtained by the tournament selection operation as an intended coding group, and multiple sub-codes to be operated are selected from all the sub-codes corresponding to the two candidate coding individuals in the intended coding group, and then the sub-codes selected from the two candidate coding individuals are crossed to generate two corresponding first offspring coding individuals; from all the sub-codes of the two corresponding first offspring coding individuals in each intended offspring coding group, the sub-codes to be mutated are selected, and at least one intended code in the selected sub-codes is determined, wherein the intended code is used to represent the coding value of the coding; the at least one intended code is randomly increased or decreased according to the preset mutation strength control number, and the mutated code is used as the new code of the corresponding sub-code to generate the second offspring coding individual corresponding to each first offspring coding individual, and the current coding individual corresponding to the current upper decision is obtained.

4. The method of claim 3, wherein, Before generating the target order matching parameter, the method further includes: judging whether the order matching decision iteration after the current upper decision satisfies a preset iteration termination condition, wherein the iteration termination condition at least includes one of the following: the difference between the fitness of the current coding individual corresponding to the current upper decision iteration and the fitness of the current coding individual corresponding to the previous upper decision iteration is less than the population fitness change threshold, and the number of order matching decision iterations exceeds the preset iteration number threshold; in the case of judging that the iteration termination condition is satisfied, the order matching parameter generated by the current upper decision is used as the target order matching parameter; in the case of judging that the iteration termination condition is not satisfied, the next order matching decision iteration is performed based on the reorganization scheduling decision parameter returned by the reorganization scheduling planning subsystem, the fitness and the NSGA-II algorithm.

5. The method of claim 2, wherein, The reorganization scheduling planning subsystem performs reorganization scheduling decision based on the improved adaptive catastrophe genetic algorithm and the corresponding order matching parameter, including: After receiving the corresponding order matching parameter, the reorganization scheduling planning subsystem obtains all the reorganization orders from the corresponding order matching parameter, and determines the target job process parameters specified by each reorganization order; The reorganization scheduling planning subsystem performs integer coding and initialization on the reorganization orders and the target job process parameters according to the preset coding rule based on the lower optimization model corresponding to the double-layer optimization mathematical model, generates multiple reorganization scheduling coding individuals, wherein the lower optimization model includes a completion time objective function and multiple target sub-constraint parameters, the sub-codes of the reorganization scheduling coding individuals are generated according to the completion time objective function and the target sub-constraint parameters, and are used to represent the ordering of the reorganization orders associated with the target job process parameters; The reorganization scheduling planning subsystem iterates genetic evolution operation and population catastrophe operation on multiple corresponding reorganization scheduling codes based on preset catastrophe adaptive genetic algorithm, the lower layer optimization model and scheduling fitness corresponding to the reorganization scheduling codes participating in each reorganization scheduling iteration, until multiple intended reorganization scheduling codes are generated, wherein the scheduling fitness is determined according to the completion time target function corresponding to the sub-codes corresponding to the reorganization scheduling codes; The reorganization scheduling planning subsystem obtains a target reorganization scheduling code from multiple intended reorganization scheduling codes, and generates the reorganization scheduling decision parameters corresponding to the lower layer decision after decoding the target reorganization scheduling code.

6. The method of claim 5, wherein, The reorganization scheduling planning subsystem iterates genetic evolution operation and population catastrophe operation on multiple corresponding reorganization scheduling codes, including: The reorganization scheduling planning subsystem selects a preset number of candidate scheduling codes from multiple reorganization scheduling codes participating in the current reorganization scheduling iteration by using an elite reservation strategy based on the fitness of the reorganization scheduling codes; The reorganization scheduling planning subsystem generates multiple first coding individuals by sequentially performing partial matching crossover operation and insertion mutation operation on all candidate scheduling codes based on corresponding adaptive crossover probability and adaptive mutation probability, wherein the reorganization scheduling codes corresponding to the current genetic evolution 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; The reorganization scheduling planning subsystem selects the reorganization scheduling code with the optimal fitness from all reorganization scheduling codes generated in the previous genetic evolution iteration to obtain a first optimal individual corresponding to the previous genetic evolution iteration, and selects the first coding individual with the optimal fitness from multiple first coding individuals to obtain a second optimal individual corresponding to the current genetic evolution iteration, and determines whether the fitness of the second optimal individual is higher than that of the first optimal individual; The reorganization scheduling planning subsystem selects the target optimal individual corresponding to the current genetic evolution iteration from the second optimal individual and the first optimal individual according to the determination result, and performs catastrophe operation on multiple first coding individuals in a preset catastrophe mode to generate multiple second coding individuals, wherein the reorganization scheduling codes corresponding to the current population catastrophe operation iteration include the second coding individuals.

7. The method of claim 6, wherein, The reorganization scheduling planning subsystem performs catastrophe operation on multiple first coding individuals in a preset catastrophe mode to generate multiple second coding individuals, including: The reorganization scheduling planning subsystem selects a preset number of the first coded individuals in descending order of the fitness in a case where it is judged that the fitness of the second optimal individual is higher than that of the first optimal individual, obtains elite coded individuals, and initializes all the elite coded individuals based on the lower-level optimization model to generate a plurality of corresponding second coded individuals; The reorganization scheduling planning subsystem selects a set number of the first coded individuals in ascending order of the fitness in a case where it is judged that the fitness of the second optimal individual is not higher than that of the first optimal individual, obtains eliminated coded individuals, and after removing all the eliminated coded individuals from the plurality of first coded individuals, adds a plurality of newly generated coded individuals to the remaining first coded individuals to obtain a plurality of corresponding second coded individuals, wherein the number of the newly generated coded individuals is equal to the set number.

8. The method of claim 7, wherein, After obtaining a plurality of corresponding second coded individuals, the method further comprises: The reorganization scheduling planning subsystem judges whether the current iteration of the population catastrophe operation satisfies a preset iteration termination condition, wherein the iteration termination condition at least includes one of the following: a difference between the fitness of the second coded individual corresponding to the current iteration of the population catastrophe operation and the fitness of the second coded individual corresponding to the previous iteration of the population catastrophe operation is less than a population fitness change threshold, and the number of the current iteration of the population catastrophe operation exceeds a preset iteration number threshold; The reorganization scheduling planning subsystem, in a case where it is judged that the iteration termination condition is satisfied, takes the plurality of second coded individuals as a plurality of intended reorganization scheduling coded bodies; The reorganization scheduling planning subsystem, in a case where it is judged that the iteration termination condition is not satisfied, iterates the genetic evolution operation and the population catastrophe operation on the plurality of second coded individuals until a plurality of intended reorganization scheduling coded bodies are obtained.

9. The method of claim 6, wherein, Before generating a plurality of first coded individuals, the method further comprises: The reorganization scheduling planning subsystem determines an average fitness and a minimum fitness corresponding to all the candidate scheduling coded bodies according to the fitness of the candidate scheduling coded bodies, and judges whether the average fitness is less than the minimum fitness; The reorganization scheduling planning subsystem, in a case where it is judged that the average fitness is less than the minimum fitness, takes a preset maximum crossover probability and a preset maximum mutation probability as corresponding adaptive crossover probability and adaptive mutation probability, respectively; The reorganization scheduling planning subsystem, in a case where it is judged that the average fitness is greater than the minimum fitness, respectively decrements the maximum crossover probability and the maximum mutation probability by using a corresponding crossover probability function and a mutation probability function, and takes a first crossover probability and a first mutation probability obtained after the decrementing as corresponding adaptive crossover probability and adaptive mutation probability.

10. The method of claim 5, wherein, The reorganization scheduling planning subsystem obtains a target reorganization scheduling coded body from a plurality of intended reorganization scheduling coded bodies, comprising: The reorganization scheduling planning subsystem determines the fitness corresponding to each of the intention reorganization scheduling encoding; The reorganization scheduling planning subsystem selects the intention reorganization scheduling encoding with the highest fitness from the multiple intention reorganization scheduling encodings, obtains the target reorganization scheduling encoding, and extracts all the sub-codes of the target reorganization scheduling encoding to obtain target sub-codes; The reorganization scheduling planning subsystem decodes the reorganization scheduling decision information corresponding to all the target sub-codes, and returns the reorganization scheduling decision parameters corresponding to the target sub-codes as the response to the corresponding order matching parameters.

Images