CN118536910B

CN118536910B - Intelligent storage method, device, intelligent storage system and storage medium for retired power batteries

Info

Publication number: CN118536910B
Application number: CN202410887922.2A
Authority: CN
Inventors: 屈挺; 潘威; 张凯; 郑湃; 李昭; 黄国全
Original assignee: Jinan University
Current assignee: Jinan University
Priority date: 2024-07-03
Filing date: 2024-07-03
Publication date: 2025-01-21
Anticipated expiration: 2044-07-03
Also published as: CN118536910A

Abstract

The present application relates to a method, device, intelligent storage system and storage medium for intelligent storage of retired power batteries, the method comprising: obtaining a plurality of target indicator parameters corresponding to each target AEVB to be stored; after preprocessing the target indicator parameters to generate standard feature parameters, using an evaluation classification model to process the standard feature parameters to obtain classification label data corresponding to each target AEVB; based on the layout parameter information corresponding to the storage area and multiple target AEVBs, using the NSGA‑II algorithm to perform storage allocation planning to generate initial storage allocation information; determining the first storage fitness corresponding to all candidate storage areas in the initial storage allocation information, and performing storage planning iterations on the initial storage allocation information according to the difference between the target storage fitness corresponding to the target reorganization heat classification and the target reorganization heat score value in the classification label data and the first storage fitness, until the difference is no greater than a preset threshold, and generating the corresponding target storage allocation information.

Description

Retired power battery intelligent storage method and device, intelligent storage system and storage medium

Technical Field

The application relates to the technical field of echelon utilization of retired power batteries, in particular to an intelligent storage method and device for retired power batteries, an intelligent storage system and a storage medium.

Background

The power battery is widely used in the fields of electric automobiles and the like, the performance of the power battery is gradually attenuated along with the lapse of the use time, the power battery after retirement still has certain residual capacity and can be used for energy storage and other scenes, in the related technology, the mode of recycling the power battery comprises disassembly recycling and echelon utilization, the echelon utilization is more and more popular in the power battery recycling because the life cycle value of the battery can be prolonged and the full utilization of resources is realized.

In the related art, in the recycling and storing stage, due to the fact that the efficiency of a recombination link is not considered, when a product is sent to a recombination workshop for recombination, the quality of the recombined product is uneven, meanwhile, due to the fact that the internal characteristic parameters of the parts corresponding to different retired power batteries are not available, the retired power batteries are sorted by obtaining limited measurable internal characteristic parameters, then the sorted power batteries are recombined, the retired power batteries cannot be effectively sorted in the storage process, further the quality of the recombined batteries cannot be effectively controlled, the recycling efficiency of the retired power batteries is reduced, the storage disorder and the sorting efficiency of the power batteries to be recombined are also reduced when the power batteries are stored in storage, and due to the fact that the retired power batteries are not available in sorting, the retired power batteries are difficult to store in a standardized mode, and safety risks exist.

At present, an effective solution is not provided for solving the problems that retired power batteries in the related art cannot be effectively sorted in the storage process, the recovery utilization rate of the power batteries is reduced, and the intelligent storage effect is reduced.

Disclosure of Invention

The embodiment of the application provides an intelligent storage method, an intelligent storage device, an intelligent storage system and a storage medium for retired power batteries, which at least solve the problems that retired power batteries in the related art cannot be effectively sorted in the storage process, the recycling rate of the power batteries is reduced, and the intelligent storage effect is reduced.

In a first aspect, an embodiment of the present application provides an intelligent warehousing method for retired power batteries, including obtaining target information of a plurality of target power batteries AEVB to be warehoused, where each target information includes a plurality of target index parameters, the target index parameters are used to characterize a corresponding one of characteristic parameters of the target AEVB, the characteristic parameters include an internal characteristic parameter and an external characteristic parameter, preprocessing the plurality of target index parameters corresponding to each target AEVB to generate a plurality of standard characteristic parameters corresponding to each target AEVB, processing a plurality of standard characteristic parameters corresponding to each target AEVB by using a trained evaluation classification model to obtain classification label data corresponding to each target AEVB, where the classification label data includes a target recombination heat classification corresponding to the target AEVB and a target recombination heat score value, the target recombination heat classification is used to characterize a priority used by the target AEVB during recombination, the evaluation model is based on a machine learning of a very gradient lifting decision tree algorithm XGBoost, generating a plurality of standard characteristic parameters corresponding to the batteries, generating a plurality of initial allocation information corresponding to a plurality of initial allocation information of storage areas corresponding to a plurality of storage areas by using a trained evaluation classification model, generating a plurality of initial allocation information corresponding to a plurality of storage areas corresponding to the target AEVB, and generating a plurality of initial allocation information corresponding to a storage area corresponding to the initial allocation information corresponding to the target storage areas, and performing non-dominant sorting iteration and genetic evolution operation iteration based on the NSGA-II algorithm on the initial warehouse allocation information according to the target warehouse fitness corresponding to the target recombination heat classification and the target recombination heat scoring value and the difference value of the first warehouse fitness until the difference value is not greater than a preset threshold value, and generating corresponding target warehouse allocation information, wherein the target warehouse allocation information comprises target warehouse areas allocated for each target AEVB.

In a second aspect, an embodiment of the present application provides an intelligent storage apparatus for retired power batteries, including:

The storage system comprises an acquisition module, a storage module and a storage module, wherein the acquisition module is used for acquiring target information of a plurality of target power storage batteries AEVB to be stored, each piece of target information comprises a plurality of target index parameters, the target index parameters are used for representing one characteristic parameter of the corresponding target AEVB, and the characteristic parameters comprise an inner characteristic parameter and an outer characteristic parameter;

The prediction module is configured to pre-process the multiple target index parameters corresponding to each target AEVB to generate multiple corresponding standard feature parameters, and then process the multiple standard feature parameters corresponding to each target AEVB by using a trained evaluation classification model to obtain classification tag data corresponding to each target AEVB, where the classification tag data includes a target recombination heat classification corresponding to the target AEVB and a target recombination heat score value, the target recombination heat classification is used to characterize a priority of the target AEVB used during recombination, and the evaluation classification model is a machine learning model trained based on an extreme gradient lifting decision tree algorithm XGBoost and is trained to generate classification tag data corresponding to a corresponding battery according to the input recombination battery feature parameters;

the planning module is used for carrying out warehouse allocation planning by utilizing a multi-target genetic algorithm NSGA-II based on the layout parameter information corresponding to the preset warehouse areas and a plurality of target AEVB, and generating corresponding initial warehouse allocation information, wherein the initial warehouse allocation information comprises an alternative warehouse area allocated to each target AEVB;

The processing module is configured to determine a first storage fitness corresponding to all the candidate storage warehouse areas in the initial storage allocation information, and perform non-dominant sorting iteration and genetic evolution iteration based on the NSGA-II on the initial storage allocation information according to a difference value between the target storage fitness determined by the target recombination heat classification and the target recombination heat scoring value and the first storage fitness until the difference value is not greater than a preset threshold, so as to generate corresponding target storage allocation information, where the target storage allocation information includes a target storage warehouse area allocated for each target AEVB.

In a third aspect, an embodiment of the present application provides an intelligent warehousing system, including a memory and a processor, where the memory stores a computer program, and the processor is configured to run the computer program to perform the intelligent warehousing method of retired power batteries according to the first aspect.

In a fourth aspect, an embodiment of the present application provides a storage medium having stored thereon a computer program which, when executed by a processor, implements the retired power battery intelligent warehousing method according to the first aspect described above.

Compared with the related art, the intelligent warehousing method, the intelligent warehousing system and the storage medium for the retired power battery provided by the embodiment of the application are characterized in that the target information of a plurality of target power storage batteries AEVB to be warehoused is obtained by obtaining the target information of the target power storage batteries AEVB, wherein each target information comprises a plurality of target index parameters, each target index parameter is used for representing one characteristic parameter of the corresponding target AEVB, each characteristic parameter comprises an internal characteristic parameter and an external characteristic parameter, after preprocessing the plurality of target index parameters corresponding to each target AEVB to generate a plurality of corresponding standard characteristic parameters, a trained evaluation classification model is utilized to process the plurality of standard characteristic parameters corresponding to each target AEVB to obtain classification label data corresponding to each target AEVB, wherein the target classification label data comprises a target recombination heat degree classification corresponding to the target AEVB and a target recombination heat degree score value, the target recombination heat degree classification is used for representing a priority level applied to the target AEVB when the target AEVB is recombined, the evaluation decision model is based on an extreme gradient lifting tree XGBoost, a pre-trained battery is used for generating a corresponding training area based on a plurality of preset battery characteristics, the initial storage area is determined based on the initial allocation information of the corresponding to the initial allocation of the storage area, the storage area is determined by utilizing the initial allocation of the storage area of the initial allocation information, and the storage area is determined by utilizing the initial allocation of the initial allocation information of the storage area, and according to the target storage fitness corresponding to the target recombination heat classification and the target recombination heat scoring value and the difference value of the first storage fitness, carrying out non-dominant sorting iteration and genetic evolution operation iteration based on the NSGA-II algorithm on the initial storage allocation information until the difference value is not more than a preset threshold value to generate corresponding target storage allocation information, wherein the target storage allocation information comprises a target storage warehouse area allocated to each target AEVB, the problems that retired power batteries cannot be effectively sorted, the power battery recycling rate is reduced and the intelligent storage effect is reduced in the storage process in the related technology are solved, the retired power batteries are managed and sorted by adopting the available external characteristic parameter data combining part measurable internal characteristic parameters, the intelligent storage and management of the power batteries are realized, the retired power batteries can be effectively classified according to different scenes to determine the reorganization consistency index and the storage rule of the retired power batteries under the condition that part of internal characteristic data is absent, and the reorganized power batteries can be applied to the energy storage scene in time, and the power utilization rate of the retired power batteries is improved.

The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the other features, objects, and advantages of the application.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:

FIG. 1 is a hardware block diagram of a terminal of an intelligent warehousing method for retired power batteries according to an embodiment of the application;

FIG. 2 is a flow chart of a retired power battery intelligent warehousing approach according to an embodiment of the application;

fig. 3 is a block diagram of a retired power battery intelligent warehousing unit according to an embodiment of the application.

Detailed Description

The present application will be described and illustrated with reference to the accompanying drawings and examples in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application. All other embodiments, which can be made by a person of ordinary skill in the art based on the embodiments provided by the present application without making any inventive effort, are intended to fall within the scope of the present application. Moreover, it should be appreciated that while such a development effort might be complex and lengthy, it would nevertheless be a routine undertaking of design, fabrication, or manufacture for those of ordinary skill having the benefit of this disclosure, and thus should not be construed as having the benefit of this disclosure.

Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is to be expressly and implicitly understood by those of ordinary skill in the art that the described embodiments of the application can be combined with other embodiments without conflict.

Unless defined otherwise, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this application belongs. The terms "a," "an," "the," and similar referents in the context of the application are not to be construed as limiting the quantity, but rather as singular or plural. The terms "comprises," "comprising," "includes," "including," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to only those steps or elements but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. The term "multi-link" as used herein refers to a number of links greater than or equal to two. "and/or" describes the association relationship of the association object, and indicates that three relationships may exist, for example, "a and/or B" may indicate that a exists alone, a and B exist simultaneously, and B exists alone. The terms "first," "second," "third," and the like, as used herein, are merely distinguishing between similar objects and not representing a particular ordering of objects.

Before describing specific embodiments of the present application, the related art of the present application will be described as follows:

The gradient lifting framework is used based on an extreme gradient lifting decision tree algorithm (eXtreme Gradient Boosting, XGBoost for short), and the aim is to provide an efficient, flexible and portable gradient lifting library, and XGBoost belongs to a Boosting type integrated learning method.

Non-dominant ordered genetic algorithm II (Non-dominated Sorting Genetic Algorithm II, NSGA-II for short) is a genetic algorithm for solving the multi-objective optimization problem, is an improved version of NSGA, and solves the problems of the original NSGA in terms of computational complexity, convergence and parameter setting.

Non-dominant ordering

The method comprises the steps of non-dominated sorting of individuals in a population, sorting the individuals into different grades, wherein the higher the grade is, the higher the priority is, sorting and selecting solutions which are not dominated by other solutions at the same time on a plurality of targets, one solution is non-dominated (or not inferior) if the solution is not exceeded by the other solution on all targets, in multi-target optimization, the condition that the solution A dominates the solution B is that the solution A is not worse than the solution B on all targets, the solution A is superior to the solution B on at least one target, comparing each candidate solution with other solutions, finding solutions which are not dominated by other solutions, the solutions form a first layer non-dominated front (Pareto front or layer), repeating the process on the rest of solutions after the found first layer non-dominated solution is removed, finding a second layer non-dominated solution, and continuing the process until all solutions are sorted into a certain layer, comparing two fitness values of each solution until the solutions are found, the solutions which are not dominated by any other solutions, and the solutions A, B, C and C are assumed to be non-dominated by any other solutions. The second layer is non-dominant solution, the population after the first layer is removed, comparison is carried out again, a solution which is not dominant by any other solution is found to form the second layer, the solution D and the solution E are assumed to belong to the second layer, and the subsequent layer is that the previous step is continued until all solutions are distributed in a certain layer.

Genetic evolution of non-dominant ranking genetic algorithm II

Once the non-dominant ranking is complete, these ranking layers can be used to perform selection, crossover and mutation operations to generate next generation populations, with lower numbers of layers giving higher priority to solutions meaning that the solutions are better balanced in multi-objective optimization, selection, crossover and mutation by generating new populations with selection, crossover and mutation operations in genetic algorithms, ensuring population diversity and accelerating the optimization process, iterative solution by multiple iterations, continually generating new populations and selecting, successive approximation of optimal solutions, each generation including- -computing fitness functions, non-dominant ranking and crowding distance computation, selection, crossover and mutation operations, with the final optimization result being a Pareto front containing a set of non-inferior solutions.

The following describes the reasons for the technical problems solved by the intelligent warehouse and the corresponding technical means principles as follows:

The power battery is recycled and reused for generation, and the retired power battery can be applied to energy storage facilities in an electric power system and used as an energy storage device of renewable energy sources to improve the energy utilization efficiency, and can also be used for constructing an electric power frequency modulation and standby power supply system to provide auxiliary services for a power grid. By detecting and reclassifying the retired batteries by means of the intelligent storage system, after the batteries conforming to the standard are recombined, the recombined batteries are distributed and then reused, so that new economic value is created.

In the prior art, because different brands of retired power batteries have special Battery Management Systems (BMS), the states of the batteries are monitored and managed by the respective BMS, for example, one or more of the following internal characteristic parameters, such as voltage, temperature, charge and discharge, and Battery balancing, because the BMS of each brand of retired power Battery are different and the corresponding authorization rights are different, it is not feasible to obtain all Battery information of the retired power Battery of different brands, for example, for a brand-a power Battery, because of the rights problem, the corresponding Battery balancing parameter and charge and discharge parameter of the power Battery of brand-a cannot be acquired or obtained after the power Battery is retired, at this time, the whole Battery information of the power Battery of brand-a is required to be acquired at a huge cost, and for an enterprise using the recycled power Battery gradient, it is not desirable, and thus the problem that the retired power Battery cannot be effectively sorted is generated, that is the technical problem that is required by the embodiment of the present application is solved.

For the technical problems to be solved by the embodiment of the application, the means adopted by the embodiment of the application is that the retired power battery is managed by applying the acquired external characteristic parameter data (namely, according to the transaction platform data of the retired power battery, the battery heat degree in a network and the measurable structured data, a large amount of acquired external characteristic parameter data of consistency indexes of the power battery, such as the battery name, the battery type and the battery supply quantity parameter) and the partial measurable internal characteristic parameter (for the partial data which can be measured by the disassembled battery, such as the residual capacity, the voltage and the current), the retired power battery is sorted according to the external characteristic parameter and the internal characteristic parameter, namely, when the partial internal characteristic parameter of the retired power battery is not acquired or is lost, the retired power battery is replaced by the external characteristic parameter which can be used for representing the related characteristics of the retired power battery and is acquired based on the existing data, and the partial unoccupied internal characteristic parameter is combined with the consistency of the power battery to be recombined, so that the retired power battery is effectively sorted, and the recombined battery can be used for the energy storage scene to improve the utilization rate of the retired power battery.

Specific examples of the present application are described below:

The method embodiment provided in this embodiment may be executed in a terminal, a computer or a similar computing device. Taking the operation on the terminal as an example, fig. 1 is a hardware structure block diagram of the terminal of the retired power battery intelligent storage method according to the embodiment of the application. As shown in fig. 1, the terminal may include one or more processors 102 (only one is shown in fig. 1) (the processor 102 may include, but is not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA) and a memory 104 for storing data, and optionally, a transmission device 106 for communication functions and an input-output device 108. It will be appreciated by those skilled in the art that the structure shown in fig. 1 is merely illustrative and not limiting on the structure of the terminal described above. For example, the terminal may also include more or fewer components than shown in fig. 1, or have a different configuration than shown in fig. 1.

The memory 104 may be used to store a computer program, for example, a software program of an application software and a module, such as a computer program corresponding to the intelligent warehousing method of the retired power battery in the embodiment of the present invention, and the processor 102 executes the computer program stored in the memory 104 to perform various functional applications and data processing, that is, implement the method described above. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, which may be connected to the terminal via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission device 106 is used to receive or transmit data via a network. The specific example of the network described above may include a wireless network provided by a communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, simply referred to as a NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is configured to communicate with the internet wirelessly.

The embodiment provides an intelligent storage method of retired power battery operating on the terminal, fig. 2 is a flowchart of the intelligent storage method of retired power battery according to the embodiment of the application, as shown in fig. 2, the flowchart includes the following steps:

Step S201, obtaining target information of a plurality of target power storage batteries AEVB to be stored, where each target information includes a plurality of target index parameters, and the target index parameters are used to represent a characteristic parameter of the corresponding target AEVB, and the characteristic parameters include an inner characteristic parameter and an outer characteristic parameter.

In this embodiment, in order to sort the target AEVB (corresponding to the retired power battery), it is necessary to use the internal characteristic parameter and the external characteristic parameter corresponding to the AEVB, and after the target AEVB to be stored is received, the measurable internal characteristic parameter in the target information may be collected after the power battery is retired, or may be collected after the target AEVB is obtained, where the measurable internal characteristic parameter includes voltage, temperature, and residual capacity, and the internal characteristic is a parameter that must be provided, and for the corresponding external characteristic parameter (for example, a battery brand and a date of generation), it is meant that when the power battery is retired and determined to be used for reorganization, the important (for example, the index parameter is sorted, the index parameter sorted before) is selected from the preset index parameters (related to the external characteristic parameter), and is given to the corresponding target AEVB, that is, after the target AEVB to be stored is received, the target index parameter related to the external characteristic parameter in the target information of each target AEVB is already existing.

Step S202, after preprocessing the multiple target index parameters corresponding to each target AEVB to generate multiple corresponding standard characteristic parameters, processing the multiple standard characteristic parameters corresponding to each target AEVB by using a trained evaluation classification model to obtain classification tag data corresponding to each target AEVB, wherein the classification tag data comprises target recombination heat classification corresponding to the target AEVB and a target recombination heat grading value, the target recombination heat classification is used for representing the priority of the target AEVB used in recombination, and the evaluation classification model is a machine learning model trained based on an extreme gradient lifting decision tree algorithm XGBoost and is trained to generate classification tag data corresponding to a corresponding battery according to the input recombination battery characteristic parameters.

In this embodiment, after the preprocessing is converted into the corresponding standard characteristic parameters, the standard characteristic parameters are input into the evaluation classification model, the various standard characteristic parameters corresponding to each target AEVB are ranked, and then the important standard characteristic parameters are selected based on the ranking to perform AEVB classification and AEVB demand prediction, wherein the AEVB classification refers to whether the AEVB to be stored is classified into a better-recombined battery classification, that is, whether the corresponding AEVB is preferentially used for recombination, the AEVB demand prediction refers to evaluating the corresponding AEVB to be stored according to the evaluation result (corresponding score value), and whether the AEVB is a recombined battery product required in the future or not is determined according to the evaluation result (corresponding score value), for example, when the corresponding two values of the AEVB are 8.555 and 9.122 respectively, the high score value and the low score value of the corresponding battery are high-class and the high score value of the corresponding battery are used as the recombined product in the future.

In this embodiment, a machine learning assessment classification model is used to perform consistency index ranking, AEVB classification, and AEVB demand prediction, and then corresponding indexes and corresponding weights are determined at different nodes to obtain a target reorganization heat classification and a target reorganization heat score value, where the corresponding target reorganization heat classification is used to determine a storage bin region (i.e. a region approximately where the AEVB to be stored is represented), and the target reorganization heat score value is used to determine the specific storage bin region of the AEVB to be stored; in this embodiment, the actual space of the warehouse is divided into a plurality of independent areas, and the areas can be distributed according to heat levels (corresponding to consistent recombination heat classifications), for example, a high-heat (extremely hot and hot) warehouse area is arranged at the core position of the warehouse or in an area convenient to access, the high-heat warehouse area is provided with a better environment control system (such as temperature and humidity control) and a higher safety standard, a medium-heat (temperature) warehouse area is distributed to a secondary center area, the area environment control and safety measure of the medium-heat warehouse area are moderate, the battery with moderate storage and access frequency is suitable, a low-heat (cool and cold) warehouse area is distributed to the edge of the warehouse or an area less frequently accessed, the environment control and safety measure of the low-heat warehouse area are relatively low, and therefore, the recombination heat classification and the target recombination heat score value can be utilized to reasonably distribute the recovery warehouse of the battery VB, and the safety and high efficiency of battery storage are ensured.

In the embodiment, the target reorganization heat classification and target reorganization heat score value are expected targets of the corresponding target AEVB when the corresponding target AEVB is distributed in the warehouse area, namely the most ideal warehouse position of the target AEVB to be stored currently, for example, the warehouse area with high heat (the corresponding heat score value interval is 8.000-10.000) is provided with a warehouse area 1, a warehouse area 2, a warehouse area 3, a warehouse area 4 and a warehouse area 5, the corresponding reorganization heat score values are respectively 8.25, 8.5, 8.75, 9.0 and 9.5, the target reorganization heat classification in the classification label data corresponding to one target AEVB is high heat, and the target warehouse area corresponding to the target AEVB is 8.5, and the target reorganization heat classification and target reorganization heat score value in the classification label data is used for guiding the warehouse area allocated to the target VB to be gradually reorganized from the initial randomly distributed target heat classification heat score value to the corresponding target heat score and the corresponding target heat score value of the corresponding to the warehouse area in the warehouse allocation planning process.

Step S203, based on the layout parameter information corresponding to the preset warehouse area and a plurality of target AEVB, warehouse allocation planning is performed by utilizing a multi-target genetic NSGA-II algorithm, and corresponding initial warehouse allocation information is generated, wherein the initial warehouse allocation information comprises alternative warehouse areas allocated to each target AEVB.

In the embodiment, after determining the classification label data corresponding to the target AEVB, warehouse allocation planning is performed according to the layout parameter information of the current warehouse area, that is, the corresponding optimal warehouse allocation is solved by using an NSGA-II algorithm, in the solving process, a random initialization population is performed firstly, that is, a warehouse allocation scheme is generated randomly, individuals in the random initialization population (corresponding to the initial warehouse allocation information) represent the possible AEVB warehouse area configuration scheme, that is, the alternative warehouse area allocated to each target AEVB, and the alternative warehouse area is one currently idle in the preset warehouse area, and it can be understood that the initial warehouse allocation information is a scheme generated by random initialization, the corresponding warehouse fitness is greatly deviated from the target warehouse fitness, so that non-dominant ordering iteration and genetic evolution operation iteration based on the NSGA-II algorithm are required to be performed on the initial warehouse allocation information.

Step S204, determining first storage fitness corresponding to all the alternative storage warehouse areas in the initial storage allocation information, and carrying out non-dominant sorting iteration and genetic evolution operation iteration based on an NSGA-II algorithm on the initial storage allocation information according to the difference value between the target storage fitness corresponding to the target reorganization heat classification and the target reorganization heat scoring value and the first storage fitness until the difference value is not greater than a preset threshold value, so as to generate corresponding target storage allocation information, wherein the target storage allocation information comprises target storage warehouse areas allocated for each target AEVB.

In this embodiment, the fitness function is used to measure the merits of the individual (corresponding to the warehouse area allocated by one target AEVB) corresponding to the warehouse allocation information generated in the warehouse allocation planning process, that is, the first warehouse fitness of the corresponding warehouse area in the warehouse allocation information solved based on the NSGA-II algorithm is calculated to measure the merits of the warehouse allocation scheme solved at the present time, and by comparing the first warehouse fitness corresponding to the warehouse area allocated at the present time with the target warehouse fitness corresponding to the corresponding target AEVB of all the target AEVB, the non-dominant sorting iteration and genetic evolution operation iteration based on the NSGA-II algorithm are further directed to the currently generated warehouse allocation information until the target warehouse allocation information is generated, it can be understood that the target reorganization heat classification and the target reorganization heat score value in the classification label data are used to guide the warehouse area allocated for the corresponding target AEVB to the corresponding target warehouse area gradually until the corresponding target warehouse area is allocated to the corresponding target warehouse area and the corresponding to the target reorganization heat classification value and the target reorganization heat score value are allocated to the corresponding target heat classification value and the target reorganization heat score value, respectively, and the target heat classification heat score and the genetic evolution value are generated.

It should be noted that, in this embodiment, the steps of the non-dominant ranking and the corresponding genetic evolution operation are corresponding operations in the related art, and those skilled in the art will understand that the steps of the non-dominant ranking and the corresponding genetic evolution operation do not constitute an unclear limitation of the present application.

Through the steps S201 to S204, target information of a plurality of target power storage batteries AEVB to be stored is obtained, each target information comprises a plurality of target index parameters, the target index parameters are used for representing one characteristic parameter of the corresponding target AEVB, the characteristic parameters comprise internal characteristic parameters and external characteristic parameters, after preprocessing the plurality of target index parameters corresponding to each target AEVB to generate a plurality of corresponding standard characteristic parameters, the plurality of standard characteristic parameters corresponding to each target AEVB are processed by using a trained evaluation classification model, classification label data corresponding to each target AEVB are obtained, the classification label data comprise target recombination heat classification corresponding to the target AEVB and target recombination heat scoring value, the target recombination heat classification is used for representing the priority of the target AEVB when being recombined, storage allocation information is generated by using a multi-target genetic NSGA-II algorithm based on the preset storage library region, the initial allocation information comprises candidate storage allocation information corresponding to each target AEVB, the initial storage allocation information is determined by using a trained evaluation classification model, the first storage area is determined to be a first storage area, the target heat classification value corresponding to the target AEVB is not required to be recombined, the first storage area is not matched with the target heat classification value is not required to be matched with the target heat scoring value, and the first storage area is not matched with the target heat classification value is not required to be matched with the target heat classification value, and the first storage area is not matched with the target heat classification value is required to be matched with the target heat classification value, and the first storage area is expanded, and the storage area is expanded, and the storage area is expanded to the storage information, the problems of the recovery utilization rate of the power battery and the intelligent storage effect are reduced, the available external characteristic parameter data is combined with the part of the measurable internal characteristic parameter to manage and sort the retired power battery, so that the intelligent power battery storage and management is realized, the reorganization consistency index and the storage rule of the retired power battery can be determined according to different scenes under the condition that the part of the internal characteristic data is absent, the warehousing battery is effectively classified, the reorganized battery can be timely applied to the energy storage scene, the utilization rate of the retired power battery is further improved, and the reasonable library position planning and arrangement are performed on the in-library battery according to the library position optimization rule, so that the method meets certain safety and high storage efficiency.

In some embodiments, preprocessing is performed on multiple target index parameters corresponding to each target AEVB to generate multiple corresponding standard characteristic parameters, and the method is implemented through the following steps:

And step 21, extracting a plurality of target index parameters corresponding to each target AEVB from target information of each target AEVB, wherein the target index parameters comprise one of the AEVB type, AEVB product name, AEVB type and AEVB electrical parameters.

In this embodiment, the target index parameters (for example, AEVB type, AEVB product name and AEVB type) corresponding to the external characteristic parameters refer to that important index parameters are screened out from preset index parameters and are given to corresponding target AEVB after the power battery is retired and determined to be used for recombination, and when the target AEVB to be stored is received, the target information of each target AEVB already has the target index parameter corresponding to the external characteristic parameters, and the target index parameter representing the internal characteristic parameters can be measured when the power battery is retired as the target AEVB or can be measured when the power battery is stored and stored.

And 22, filtering, denoising and cleaning the target index parameters corresponding to all the target AEVB to generate standard index parameters.

In this embodiment, filtering, that is, performing deduplication processing, removing repeated items in the target index parameter, ensuring that each piece of data is unique, performing format conversion, normalizing different measurement units, for example, uniformly converting the working voltage into volts (V), uniformly converting the battery capacity into kilowatt-hours (kWh), denoising the target index parameter, that is, detecting abnormal values, detecting and removing obviously abnormal data points, for example, obviously higher or lower power supply amount of the target AEVB, uniformly processing the missing values in the target index parameter, filling the missing values or removing severely incomplete data lines of information, cleaning the target index parameter, that is, performing format uniform processing on the target index parameter, ensuring that all text fields are normalized, removing redundant information, and retaining core data.

And step 23, carrying out normalization processing on the standard index parameters corresponding to all the target AEVB to generate standard characteristic parameters.

In this embodiment, the standard index parameters are normalized so that all standard characteristic parameters input to the evaluation classification model are of the same order of magnitude.

Through the steps, multiple target index parameters corresponding to each target AEVB are extracted from target information of each target AEVB, wherein the target index parameters comprise one of the AEVB type, the AEVB product name, the AEVB type and the AEVB electrical parameters, the target index parameters corresponding to all the targets AEVB are filtered, noise reduced and cleaned to generate standard index parameters, the standard index parameters corresponding to all the targets AEVB are normalized to generate standard characteristic parameters, the target index parameters in target information of all the targets AEVB are preprocessed, and the formed standard characteristic parameters have high quality, high consistency and high analyzability so as to evaluate a classification model to classify the AEVB and predict requirements.

In some of these embodiments, before acquiring the target information of the plurality of target power storage batteries AEVB to be stocked, the following steps are further implemented:

Step 31, acquiring corresponding hypertext markup language HTML page data from the target network platform by using a preset data collector.

In this embodiment, before collecting data, the target network platform is also identified to identify the network platform that is performing the retired power battery transaction, and then, for different network platforms, different data collectors (for example, beautifulSoup and Scrapy of Python) are configured, and the data collectors periodically and automatically access the target network platform to obtain dynamic data, and extract HTML page data.

And step 32, extracting transaction data corresponding to the AEVB from the HTML page data, and analyzing a first index parameter corresponding to the external characteristic parameter from the transaction data.

In the embodiment, transaction data corresponding to AEVB is further extracted by analyzing HTML page data, the corresponding transaction data comprises AEVB names, brands, AEVB types, supply amounts, application scenes and supply amounts, the AEVB names comprise vehicle batteries, industrial batteries and energy storage batteries, the brands comprise corresponding battery suppliers, the AEVB types comprise battery packs (Pack), modules (Module) and cells (Cell), the supply amounts provide data such as batch numbers and total amounts, the unit is kWh or group numbers, the application scenes comprise corresponding usage scene specifications such as electric vehicles, electric tools and energy storage systems, and the supply amounts comprise voltages (V), capacities (Ah or kWh).

And step 33, taking the second index parameter and the first index parameter corresponding to the acquired internal characteristic parameters as target index parameters.

In this embodiment, after the first index parameter is obtained, the first index parameter is used as an index parameter library, when the AEVB is retired and used for reorganization, the corresponding first index parameter is selected from the parameter library to be given to the corresponding AEVB, so that the target information of the AEVB has the target index parameter representing the external characteristic parameter, meanwhile, the partial internal characteristic parameter can be obtained through measurement, and then the second index parameter corresponding to the measured internal characteristic parameter is associated with the AEVB, so that the target information of the AEVB has the complete target index parameter.

The method comprises the steps of acquiring corresponding hypertext markup language (HTML) page data from a target network platform by using a preset data acquisition device in the steps, extracting transaction data corresponding to AEVB from the HTML page data, analyzing first index parameters corresponding to external characteristic parameters from the transaction data, and taking second index parameters and first index parameters corresponding to the acquired internal characteristic parameters as target index parameters, so that the construction and the preset of the target index parameters are realized, further, the target index parameters of retired AEVB of a recombinant battery can be quickly determined, and further, the target AEVB is quickly sorted and stored.

In some embodiments, based on the layout parameter information corresponding to the preset warehouse area and a plurality of target AEVB, the warehouse allocation planning is performed by using a multi-target genetic NSGA-II algorithm, and corresponding initial warehouse allocation information is generated, which is realized through the following steps:

Step 41, obtaining coding information corresponding to a plurality of target AEVB and layout parameter information of each warehouse area, wherein the layout parameter information comprises a reorganization picking efficiency parameter, a warehouse safety parameter and a warehouse status parameter corresponding to each warehouse area, the reorganization picking efficiency parameter is determined according to the position information of the warehouse area, and the warehouse safety parameter is determined according to the storage environment and the position information corresponding to the warehouse area.

And 42, after determining the currently idle warehouse area according to the warehouse status parameters, carrying out random allocation coding on the currently idle warehouse area and each piece of coding information to obtain a plurality of coding bodies corresponding to a plurality of target AEVB, and taking the warehouse area corresponding to each coding body as a corresponding alternative warehouse area.

Step 43, determining a first warehouse fitness corresponding to each alternative warehouse area, and generating initial warehouse allocation information based on the alternative warehouse areas and the first warehouse fitness corresponding to all the target AEVB, wherein the first warehouse fitness is generated by weighting according to the recombination picking efficiency parameters and the warehouse safety parameters corresponding to the corresponding warehouse areas.

In the embodiment, the quality degree corresponding to each warehouse allocation scheme is determined based on two indexes of the reorganization and picking efficiency and the warehouse safety parameter, namely, the first warehouse fitness corresponding to the alternative warehouse area allocated for each target AEVB at the time is calculated to measure the excellence of the allocation scheme, wherein the reorganization and picking efficiency is calculated according to stored record data, the picking path length and the time corresponding to each warehouse area are calculated, and further the corresponding reorganization and picking efficiency is calculated, the reorganization and safety parameter is the heat degree grade determined based on the storage environment and the position of the corresponding warehouse area, and the corresponding safety score is, for example, the warehouse area provided with an environment control system and safety protection measures is high in the corresponding safety score.

Through the steps 41 to 43, a random storage allocation scheme is realized, and data is provided for determining target storage allocation information.

In some embodiments, according to the difference value between the target storage fitness and the first storage fitness corresponding to the target reorganization heat classification and the target reorganization heat scoring value, performing non-dominant sorting iteration and genetic evolution operation iteration based on NSGA-II algorithm on the initial storage allocation information, including the following steps:

step 51, determining an fitness interval corresponding to the target recombination heat classification corresponding to each target AEVB, and determining whether the first storage fitness corresponding to each alternative storage bin is in the corresponding fitness interval.

And step 52, under the condition that the first warehouse fitness corresponding to at least one alternative warehouse area is not in a fitness interval, carrying out non-dominant sorting iteration and genetic evolution operation iteration based on an NSGA-II algorithm on the initial warehouse allocation information for a plurality of times until the first warehouse fitness corresponding to the current warehouse area allocated to each target AEVB in the generated current warehouse allocation information is in the corresponding fitness interval, wherein the genetic evolution operation comprises a coding body selection operation, a coding body crossing operation and a coding body mutation operation.

Step 53, judging whether the difference between the first storage fitness corresponding to the current storage bin and the target storage fitness corresponding to the target recombination heat score value is greater than a preset threshold, and taking the current storage bin as the target storage bin corresponding to the target AEVB and generating target storage allocation information under the condition that the difference between the first storage fitness corresponding to the current storage bin and the target storage fitness is not greater than the preset threshold.

And step 54, under the condition that the difference value between the first warehouse fitness corresponding to the current warehouse area and the target warehouse fitness corresponding to the target recombination heat scoring value is larger than a preset threshold value, performing non-dominant sorting iteration and genetic evolution operation iteration based on NSGA-II algorithm on the current warehouse allocation information.

In some embodiments, before the first warehouse fitness corresponding to the at least one current warehouse region is not within the corresponding fitness interval, the steps of repeatedly performing non-dominant ranking iteration and genetic evolution operation iteration based on NSGA-II algorithm on the currently generated warehouse allocation information are further implemented.

In some of these embodiments, the training to evaluate the classification model includes:

Step 61, a preset data set is obtained, wherein the data set comprises a plurality of target index parameters corresponding to AEVB.

Step 62, after preprocessing the target index parameter corresponding to each AEVB in the data set to generate a feature parameter set, dividing all standard feature parameters corresponding to each AEVB in the feature parameter set into recombined battery feature sets, and labeling the recombined battery feature sets corresponding to each AEVB with corresponding classification label data to generate recombined battery feature parameter sets.

And 63, cutting the recombinant battery characteristic parameter set into a recombinant battery characteristic parameter training set and a recombinant battery characteristic parameter test set according to a preset proportion, and training the initially constructed XGBoost machine learning model by utilizing the recombinant battery characteristic parameter training set until regression fitting is performed to obtain a trained XGBoost machine learning model.

In the embodiment, a machine learning model is initially built XGBoost, relevant parameters and objective functions of the XGBoost model are configured, all standard characteristic parameters in a battery characteristic parameter training set are used as input, corresponding classification label data are used as supervision for training, parameters such as tree number, depth and learning rate are set, and cross verification is carried out to select optimal parameters.

And step 64, testing and evaluating the trained XGBoost machine learning model by utilizing the recombinant battery characteristic parameter testing set so as to train and generate an evaluation classification model.

In the embodiment, when the recombinant battery characteristic parameter test set is used for evaluating and testing the model, all standard characteristic parameters in the recombinant battery characteristic parameter test set are used as input, deviation of classification label data output by the model and classification label data marked by the recombinant battery characteristic parameter test set is compared, and then the effect of evaluating the classification model is evaluated, and in the embodiment, the effect of evaluating the classification model is evaluated by using indexes such as accuracy, precision, recall rate, F1-score and the like.

The embodiment also provides an intelligent storage device for retired power batteries, which is used for realizing the embodiment and the preferred embodiment, and is not described again. As used below, the terms "module," "unit," "sub-unit," and the like may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

Fig. 3 is a block diagram of a retired power battery intelligent warehousing unit according to an embodiment of the present application, as shown in fig. 3, including an acquisition module 31, a prediction module 32, a planning module 33, and a processing module 34, wherein,

The obtaining module 31 is configured to obtain target information of a plurality of target power storage batteries AEVB to be stored, where each target information includes a plurality of target index parameters, and the target index parameters are used to represent one characteristic parameter of the corresponding target AEVB, and the characteristic parameters include an inner characteristic parameter and an outer characteristic parameter;

The prediction module 32 is coupled to the acquisition module 31, and is configured to perform preprocessing on multiple target index parameters corresponding to each target AEVB, and then process multiple standard feature parameters corresponding to each target AEVB by using a trained evaluation classification model to obtain classification tag data corresponding to each target AEVB, where the classification tag data includes a target recombination heat classification corresponding to the target AEVB and a target recombination heat score value, the target recombination heat classification is used to characterize a priority of the target AEVB used during recombination, and the evaluation classification model is a machine learning model trained based on an extreme gradient lifting decision tree algorithm XGBoost, and is trained to generate classification tag data corresponding to a corresponding battery according to the input feature parameters of the recombined battery;

The planning module 33 is coupled to the prediction module 32, and is configured to perform warehouse allocation planning by using a multi-objective genetic algorithm NSGA-II based on layout parameter information corresponding to a preset warehouse area and a plurality of objective AEVB, so as to generate corresponding initial warehouse allocation information, where the initial warehouse allocation information includes an alternative warehouse area allocated for each objective AEVB;

The processing module 34 is coupled to the planning module 33, and is configured to determine a first storage fitness corresponding to all the candidate storage areas in the initial storage allocation information, and perform non-dominant sorting iteration and genetic evolution iteration based on NSGA-II on the initial storage allocation information according to a difference between the target storage fitness and the first storage fitness determined by the target recombination heat classification and the target recombination heat scoring value until the difference is not greater than a preset threshold, so as to generate corresponding target storage allocation information, where the target storage allocation information includes a target storage area allocated for each target AEVB.

The intelligent storage device for the retired power battery is adopted.

In some of these embodiments, the prediction module 32 further includes:

the extracting unit is used for extracting various target index parameters corresponding to each target AEVB from target information of each target AEVB, wherein the target index parameters comprise one of AEVB type, AEVB product name, AEVB type and AEVB electrical parameters;

The processing unit is coupled with the extraction unit and is used for filtering, reducing noise and cleaning target index parameters corresponding to all target AEVB, so as to generate standard index parameters;

The generating unit is coupled with the processing unit and is used for carrying out normalization processing on the standard index parameters corresponding to all the target AEVB and generating standard characteristic parameters.

In some embodiments, the retired power battery intelligent storage device is further configured to, before acquiring target information of a plurality of target power batteries AEVB to be stored, acquire corresponding hypertext markup language HTML page data from a target network platform by using a preset data collector, extract transaction data corresponding to the AEVB from the HTML page data, and analyze a first index parameter corresponding to an external characteristic parameter from the transaction data, and take a second index parameter and the first index parameter corresponding to the acquired internal characteristic parameter as target index parameters.

In some of these embodiments, the planning module 33 further includes:

The storage system comprises an acquisition unit, a storage unit and a storage unit, wherein the acquisition unit is used for acquiring coding information corresponding to a plurality of target AEVB and layout parameter information of each storage area, the layout parameter information comprises a reorganization picking efficiency parameter, a storage safety parameter and a storage state parameter corresponding to each storage area, the reorganization picking efficiency parameter is determined according to the position information of the storage area, and the storage safety parameter is determined according to the storage environment and the position information corresponding to the storage area;

The coding unit is coupled with the acquisition unit and is used for carrying out random distribution coding on the current idle warehouse area and each piece of coding information after determining the current idle warehouse area according to the warehouse status parameters to obtain a plurality of coding bodies corresponding to a plurality of target AEVB, and taking the warehouse area corresponding to each coding body as a corresponding alternative warehouse area;

The determining unit is coupled with the encoding unit and used for determining first warehousing fitness corresponding to each alternative warehousing warehouse area and generating initial warehousing distribution information based on the alternative warehousing warehouse areas and the first warehousing fitness corresponding to all the target AEVB, wherein the first warehousing fitness is generated by weighting according to the recombination picking efficiency parameters and the warehousing safety parameters corresponding to the corresponding warehousing warehouse areas.

In some of these embodiments, the processing module 34 further includes:

The processing unit is used for determining an adaptability interval corresponding to the target recombination heat classification corresponding to each target AEVB and determining whether the first storage adaptability corresponding to each alternative storage area is in the corresponding adaptability interval;

The iteration unit is coupled with the processing unit and is used for carrying out non-dominant sorting iteration and genetic evolution operation iteration on the initial warehouse allocation information for a plurality of times based on the NSGA-II algorithm under the condition that the first warehouse fitness corresponding to at least one alternative warehouse area is not in a fitness interval, until the first warehouse fitness corresponding to the current warehouse area allocated to each target AEVB in the generated current warehouse allocation information is in the corresponding fitness interval, wherein the genetic evolution operation comprises a coder selection operation, a coder crossing operation and a coder variation operation;

The judging unit is coupled with the iteration unit and is used for judging whether the difference value between the first storage fitness corresponding to the current storage bin and the target storage fitness corresponding to the target recombination heat scoring value is larger than a preset threshold value or not, and taking the current storage bin as the target storage bin corresponding to the target AEVB and generating target storage allocation information under the condition that the difference value between the first storage fitness corresponding to the current storage bin and the target storage fitness is not larger than the preset threshold value.

In some embodiments, the processing module 34 is further configured to repeatedly perform non-dominant sorting iteration and genetic evolution operation iteration based on the NSGA-II algorithm on the currently generated warehouse allocation information before the iteration unit determines that the first warehouse fitness corresponding to the at least one current warehouse area is not in the corresponding fitness interval, and if the determination unit determines that the difference between the first warehouse fitness corresponding to the current warehouse area and the target warehouse fitness corresponding to the target recombination heat score value is greater than the preset threshold, the processing module 34 is further configured to perform non-dominant sorting iteration and genetic evolution operation iteration based on the NSGA-II algorithm on the current warehouse allocation information.

In some embodiments, the retired power battery intelligent storage device is further configured to obtain a preset data set, wherein the data set includes a plurality of target index parameters corresponding to AEVB, after preprocessing each target index parameter corresponding to AEVB in the data set to generate a feature parameter set, dividing all standard feature parameters corresponding to each AEVB in the feature parameter set into a recombined battery feature set, labeling the recombined battery feature set corresponding to each AEVB with corresponding classification label data to generate a recombined battery feature parameter set, cutting the recombined battery feature parameter set into a recombined battery feature parameter training set and a recombined battery feature parameter testing set according to a preset proportion, training an initially constructed XGBoost machine learning model by using the recombined battery feature parameter training set until regression fitting is performed to obtain a trained XGBoost machine learning model, and performing test evaluation on the trained XGBoost machine learning model by using the recombined battery feature parameter testing set to train to generate an evaluation classification model.

The present embodiment also provides a smart warehousing system comprising a memory having a computer program stored therein and a processor configured to run the computer program to perform the steps of any of the method embodiments described above.

Optionally, the intelligent warehousing system may further include a transmission device and an input/output device, where the transmission device is connected to the processor, and the input/output device is connected to the processor.

Alternatively, in the present embodiment, the above-described processor may be configured to execute the following steps by a computer program:

s1, obtaining target information of a plurality of target power storage batteries AEVB to be stored, wherein each target information comprises a plurality of target index parameters, the target index parameters are used for representing one characteristic parameter of the corresponding target AEVB, and the characteristic parameters comprise an inner characteristic parameter and an outer characteristic parameter.

S2, preprocessing various target index parameters corresponding to each target AEVB to generate various corresponding standard characteristic parameters, and then processing the various standard characteristic parameters corresponding to each target AEVB by using a trained evaluation classification model to obtain classification label data corresponding to each target AEVB, wherein the classification label data comprises target recombination heat classification corresponding to the target AEVB and target recombination heat scoring values, the target recombination heat classification is used for representing the priority of the target AEVB used in recombination, and the evaluation classification model is a machine learning model trained based on an extreme gradient lifting decision tree algorithm XGBoost and is trained to generate classification label data corresponding to a corresponding battery according to the input recombination battery characteristic parameters.

S3, based on the layout parameter information corresponding to the preset warehouse area and a plurality of target AEVB, carrying out warehouse allocation planning by utilizing a multi-target genetic NSGA-II algorithm, and generating corresponding initial warehouse allocation information, wherein the initial warehouse allocation information comprises alternative warehouse areas allocated for each target AEVB.

S4, determining first storage fitness corresponding to all the alternative storage warehouse areas in the initial storage allocation information, and carrying out non-dominant sorting iteration and genetic evolution operation iteration based on an NSGA-II algorithm on the initial storage allocation information according to the difference value between the target storage fitness corresponding to the target reorganization heat classification and the target reorganization heat scoring value and the first storage fitness until the difference value is not greater than a preset threshold value, so as to generate corresponding target storage allocation information, wherein the target storage allocation information comprises target storage warehouse areas allocated for each target AEVB.

It should be noted that, specific examples in this embodiment may refer to examples described in the foregoing embodiments and alternative implementations, and this embodiment is not repeated herein.

In addition, in combination with the retired power battery intelligent storage method in the above embodiment, the embodiment of the application can be realized by providing a storage medium. The storage medium is stored with a computer program which when executed by a processor implements any of the retired power battery intelligent warehousing methods of the embodiments described above.

It should be understood by those skilled in the art that the technical features of the above embodiments may be combined in any manner, and for brevity, all of the possible combinations of the technical features of the above embodiments are not described, however, they should be considered as being within the scope of the description provided herein, as long as there is no contradiction between the combinations of the technical features.

The foregoing examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.

Claims

1. A method for intelligent storage of retired power batteries, characterized by comprising:

Obtaining target information of a plurality of target power batteries to be stored, wherein each of the target information includes a plurality of target index parameters, and the target index parameters are used to characterize a characteristic parameter of the corresponding target power battery, and the characteristic parameter includes an internal characteristic parameter and an external characteristic parameter;

After preprocessing the multiple target indicator parameters corresponding to each of the target power batteries to generate the corresponding multiple standard feature parameters, the multiple standard feature parameters corresponding to each of the target power batteries are processed using the trained evaluation classification model to obtain classification label data corresponding to each of the target power batteries, wherein the classification label data includes a target recombination heat classification and a target recombination heat score value corresponding to the target power battery, the target recombination heat classification is used to characterize the priority of the target power battery to be used during recombination, and the evaluation classification model is a machine learning model trained based on the extreme gradient boosting decision tree algorithm XGBoost, and is trained to generate classification label data corresponding to the corresponding battery according to the input recombination battery feature parameters;

Based on the layout parameter information corresponding to the preset storage area and the plurality of target power batteries, a multi-objective genetic NSGA-II algorithm is used to perform storage allocation planning to generate corresponding initial storage allocation information, wherein the initial storage allocation information includes an alternative storage area allocated to each target power battery;

Determine the first storage fitness corresponding to all the alternative storage areas in the initial storage allocation information, and according to the difference between the target storage fitness corresponding to the target recombination heat classification and the target recombination heat score value and the first storage fitness, perform non-dominated sorting iteration and genetic evolution operation iteration based on the NSGA-II algorithm on the initial storage allocation information until the difference is no more than a preset threshold, and generate the corresponding target storage allocation information, wherein the target storage allocation information includes the target storage area assigned to each target power battery.

2. The method according to claim 1, characterized in that the multiple target index parameters corresponding to each of the target power batteries are preprocessed to generate corresponding multiple standard characteristic parameters, including:

Extracting a plurality of target indicator parameters corresponding to each target power battery from the target information of each target power battery, wherein the target indicator parameter includes one of the following: power battery type, power battery brand, power battery type, and power battery electrical parameter;

Filtering, reducing noise and cleaning the target index parameters corresponding to all the target power batteries to generate standard index parameters;

The standard index parameters corresponding to all the target power batteries are normalized to generate the standard characteristic parameters.

3. The method according to claim 2, characterized in that, before obtaining target information of a plurality of target power batteries to be stored, the method further comprises:

Using a preset data collector, obtain corresponding hypertext markup language HTML page data from the target network platform;

Extracting transaction data corresponding to the power storage battery from the HTML page data, and parsing the first indicator parameter corresponding to the external characteristic parameter from the transaction data;

The second indicator parameter corresponding to the collected internal characteristic parameter and the first indicator parameter are used as the target indicator parameter.

4. The method according to claim 1 is characterized in that, based on the layout parameter information corresponding to the preset storage area and the plurality of target power batteries, a multi-objective genetic NSGA-II algorithm is used to perform storage allocation planning to generate corresponding initial storage allocation information, including:

Obtaining the coding information corresponding to the plurality of target power batteries and the layout parameter information of each storage area, wherein the layout parameter information includes a reorganization picking efficiency parameter, a storage safety parameter and a storage state parameter corresponding to each storage area, the reorganization picking efficiency parameter is determined according to the location information of the storage area, and the storage safety parameter is determined according to the storage environment corresponding to the storage area and the location information;

After determining the currently idle storage area according to the storage state parameter, randomly assigning codes to the currently idle storage area and each of the coding information to obtain multiple coding bodies corresponding to multiple target power batteries, and taking the storage area corresponding to each coding body as the corresponding candidate storage area;

Determine the first storage fitness corresponding to each of the alternative storage areas, and generate the initial storage allocation information based on the alternative storage areas and the first storage fitness corresponding to all the target power batteries, wherein the first storage fitness is generated by weighting the reorganization picking efficiency parameters and the storage safety parameters corresponding to the corresponding storage areas.

5. The method according to claim 4 is characterized in that, according to the difference between the target storage fitness corresponding to the target recombination heat classification and the target recombination heat score value and the first storage fitness, the initial storage allocation information is subjected to non-dominated sorting iteration and genetic evolution operation iteration based on the NSGA-II algorithm, comprising:

Determine the fitness interval corresponding to the target reorganization heat classification corresponding to each of the target power batteries, and determine whether the first storage fitness corresponding to each of the candidate storage areas is within the corresponding fitness interval;

When it is determined that the first storage fitness corresponding to at least one of the candidate storage areas is not within the fitness interval, the initial storage allocation information is subjected to multiple non-dominated sorting iterations and genetic evolution operation iterations based on the NSGA-II algorithm until the first storage fitness corresponding to the current storage area allocated to each target power battery in the generated current storage allocation information is within the corresponding fitness interval, wherein the genetic evolution operation includes a coding body selection operation, a coding body crossover operation, and a coding body mutation operation;

Determine whether the difference between the first storage fitness corresponding to the current storage area and the target storage fitness corresponding to the target reorganization heat score is greater than a preset threshold. When it is determined that the difference between the first storage fitness corresponding to the current storage area and the target storage fitness is not greater than the preset threshold, use the current storage area as the target storage area corresponding to the target power battery, and generate the target storage allocation information.

6. The method according to claim 5 is characterized in that, before the first storage fitness corresponding to at least one of the current storage areas is not in the corresponding fitness interval, the method further comprises: repeatedly performing non-dominated sorting iterations and genetic evolution operation iterations based on the NSGA-II algorithm on the storage allocation information generated at the time;

When it is determined that the difference between the first storage fitness corresponding to the current storage area and the target storage fitness corresponding to the target recombination heat score value is greater than a preset threshold, the method further includes: performing non-dominated sorting iteration and genetic evolution operation iteration based on the NSGA-II algorithm on the current storage allocation information.

7. The method according to claim 1, characterized in that the training of the evaluation classification model comprises:

Acquire a preset data set, wherein the data set includes the target indicator parameters corresponding to a plurality of power batteries;

After preprocessing the target indicator parameter corresponding to each power storage battery in the data set to generate a feature parameter set, all the standard feature parameters corresponding to each power storage battery in the feature parameter set are divided into a recombinant battery feature group, and the recombinant battery feature group corresponding to each power storage battery is annotated with the corresponding classification label data to generate a recombinant battery feature parameter set;

The recombinant battery characteristic parameter set is divided into a recombinant battery characteristic parameter training set and a recombinant battery characteristic parameter test set according to a preset ratio, and the recombinant battery characteristic parameter training set is used to train the initially constructed XGBoost machine learning model until regression fitting is achieved to obtain a trained XGBoost machine learning model;

The trained XGBoost machine learning model is tested and evaluated using the recombinant battery characteristic parameter test set to train and generate the evaluation classification model.

8. An intelligent storage device for retired power batteries, comprising:

An acquisition module, used for obtaining target information of a plurality of target power batteries to be stored, wherein each of the target information includes a plurality of target index parameters, and the target index parameters are used for characterizing a characteristic parameter of the corresponding target power battery, and the characteristic parameters include an internal characteristic parameter and an external characteristic parameter;

A prediction module, used for, after preprocessing the multiple target indicator parameters corresponding to each of the target power batteries to generate the corresponding multiple standard feature parameters, using the trained evaluation classification model to process the multiple standard feature parameters corresponding to each of the target power batteries to obtain classification label data corresponding to each of the target power batteries, wherein the classification label data includes a target recombination heat classification and a target recombination heat score value corresponding to the target power battery, the target recombination heat classification is used to characterize the priority of the target power battery to be used during recombination, and the evaluation classification model is a machine learning model trained based on the extreme gradient boosting decision tree algorithm XGBoost, and is trained to generate classification label data corresponding to the corresponding battery according to the input recombination battery feature parameters;

A planning module, for performing storage allocation planning using a multi-objective genetic algorithm NSGA-II based on the layout parameter information corresponding to the preset storage area and the plurality of target power batteries, and generating corresponding initial storage allocation information, wherein the initial storage allocation information includes an alternative storage area allocated to each of the target power batteries;

A processing module is used to determine the first storage fitness corresponding to all the alternative storage areas in the initial storage allocation information, and according to the difference between the target storage fitness determined by the target recombination heat classification and the target recombination heat score value and the first storage fitness, perform non-dominated sorting iteration and genetic evolution iteration based on the NSGA-II on the initial storage allocation information until the difference is no more than a preset threshold, and generate corresponding target storage allocation information, wherein the target storage allocation information includes a target storage area allocated to each target power battery.

9. An intelligent warehousing system, comprising a memory and a processor, characterized in that a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps of the intelligent warehousing method for retired power batteries according to any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the method for intelligent storage of retired power batteries according to any one of claims 1 to 7 is implemented.