A new energy vehicle waste battery recycling box site selection planning method, system and terminal equipment

Abstract

The application provides a new energy automobile waste battery recycling box site selection planning method, system and terminal equipment, comprising: dividing a planning area and obtaining relevant information of each area; predicting the number of new energy automobile waste battery recycling in each area through a smoothed grey model; determining a network simulation model, mapping each area parameter information to bee colony parameter information in an improved artificial bee colony algorithm; performing simulation analysis through the improved artificial bee colony algorithm, solving the simulation model, and obtaining recycling box site selection layout site information; and determining the number of new energy automobile waste battery recycling boxes configured at each site according to the site service area and the predicted recycling amount of waste batteries in the area. The application can standardize the site selection planning process of new energy automobile waste battery recycling boxes, reduce the early-stage fund investment before the installation of waste battery recycling boxes, and promote the efficient recycling of retired waste batteries.

Description

Technical Field

[0001] This invention relates to the field of reverse logistics technology, specifically to a method, system, and terminal equipment for site selection and planning of recycling bins for waste batteries from new energy vehicles. Background Technology

[0002] Reverse logistics primarily studies how to achieve efficient recycling and reuse of products. Its effective implementation can bring significant social, economic, and environmental benefits. In recent years, my country's new energy vehicle industry has flourished, and the number of power batteries installed in new energy vehicles has also increased dramatically. During use, the performance of these batteries continuously declines, and when they reach a certain level of degradation, they face retirement from new energy vehicles. Retired batteries often still have significant reuse value. By rationally implementing reverse logistics to recycle and reuse these batteries, more of their residual value can be tapped, reducing environmental pollution and resource waste caused by discarding old batteries.

[0003] Although the government strongly advocates for the recycling and reuse of used batteries, and scholars and departments have made great efforts to ensure their effective recycling, the results have been less than satisfactory. There are many reasons for this, such as: poor public environmental awareness, complex recycling procedures, low recycling prices, a lack of formal recycling channels, and an inadequate recycling management system. By rationally distributing used battery recycling bins in various cities and implementing standardized management and formalized operation, the amount of used batteries recycled can be significantly increased. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method, system, and terminal equipment for site selection and planning of waste battery recycling bins for new energy vehicles. By rationally distributing the recycling bins, the service area of ​​recycling bin sites is optimized, greatly facilitating the recycling of retired batteries by new energy vehicle users. Secondly, this invention provides a site selection and planning system and terminal equipment for waste battery recycling bins, standardizing the site selection and planning process, reducing upfront investment in bin installation, and promoting efficient recycling of retired batteries. This invention solves the problems of a lack of formal recycling channels for new energy vehicle batteries, unreasonable recycling bin layout planning, and excessive upfront investment in planning.

[0005] The present invention achieves the above-mentioned technical objectives through the following technical means.

[0006] A method for site selection and planning of recycling bins for used batteries from new energy vehicles includes the following steps:

[0007] The planning area is divided into grids, and the number of new energy vehicles D in each year within the i-th region is obtained. i and scrap volume S iThis allows us to determine the proportion P of new energy vehicle scrapping volume within each grid relative to the total number of new energy vehicles scrapped in the planned area. N =(P1,P2,…P) i ,…,P n ), where i represents the community corresponding to the i-th region, and n is the total number of regions.

[0008] The amount of waste batteries from new energy vehicles in each region is predicted using a smoothed grey prediction model.

[0009] The network simulation model is determined, and the parameter information of each region is mapped to the bee colony parameter information in the improved artificial bee colony algorithm;

[0010] The improved artificial bee colony algorithm was used for simulation analysis to solve the simulation model and obtain the location information of the recycling bins.

[0011] The number and configuration of new energy vehicle waste battery recycling bins at each station are determined based on the service area of ​​the station and the predicted recycling volume of waste batteries in the area.

[0012] Furthermore, the gray prediction model with smoothing process is used to predict the recycling volume of waste batteries from new energy vehicles in various regions, including the following steps:

[0013] The number of new energy vehicles D in each year within the i-th region. i The proportion (P) of the number of new energy vehicles scrapped in each grid to the total number of new energy vehicles scrapped in the planned area. N The proportion of new energy vehicles scrapped in region i to the total number of vehicles in the region P i Sort them separately to generate the original data series X (0) =(x (0) (1),x (0) (2),…,x (0) (k),…,x (0) (n)) in the form of, where x (0) (k)≥0,k=0,1,2,…,n;

[0014] The original data series is preprocessed using a three-point smoothing method, as follows:

[0015] Intermediate data is processed separately as follows:

[0016] Where k = 2, 3, ..., n-1;

[0017] The data at both ends are processed separately as follows:

[0018]

[0019]

[0020] The grey model is used to predict the preprocessed data for a series of... A new sequence is formed through a single accumulation. in,

[0021] series Establish differential equations In the formula, α is the development coefficient, used to characterize... and The development trend; u is the endogenous control gray number;

[0022] The parameters α and u are determined using the least squares method, [α, u] T = (B T B) -1 B T Y, where B is a data matrix and Y is a data vector, are represented as follows:

[0023]

[0024] Solving the differential equation yields Where k = 1, 2, ..., n;

[0025] right Perform cumulative subtraction to obtain the predicted values ​​for the data series:

[0026]

[0027] Where k = 1, 2, ..., n.

[0028] Furthermore, the network simulation model is determined as follows:

[0029] The convenience level for customers is represented by labor costs, calculated by multiplying the convenience factor coefficient by the distance between the demand point and the location of the waste battery recycling bin. The objective function of the network simulation model is:

[0030] Where U represents the total network cost; F a The fixed costs and operating costs of placing waste battery recycling bins at demand point a; decision variable h. a ∈{0,1}, a value of 1 indicates that the demand point i is selected as a layout point for the waste battery recycling bin, and a value of 0 indicates that it is not selected; f ab =ξ·X ab For the client's labor costs, X ab Let ξ be the distance between demand point a and the location b of the waste battery recycling bin; x is the convenience factor coefficient. abThis represents the predicted amount of used battery recycling demand generated at demand point a and collected at the used battery recycling bin location point b.

[0031] Furthermore, the bee colony parameter information in the improved artificial bee colony algorithm includes nectar sources.

[0032] The nectar source represents a feasible solution to the problem. The nectar source is generated through a natural number encoding method. Each value in the nectar source encoding is generated by scout bees and follower bees. The nectar source encoding represents the community number corresponding to each grid in the planning area. The quality of the nectar source is represented by the fitness of the problem. The fitness value is obtained through a network simulation model. The optimization of the nectar source is completed through the search behavior of bees, where the search behavior is the process of the bee colony algorithm.

[0033] The honey source is generated using a natural number encoding method as follows: For a problem involving selecting M locations from N demand points for the placement of waste battery recycling bins, each honey source corresponds to a two-dimensional matrix with two rows and H columns, where H = max{M,N}; the first row of each honey source is X... a This indicates whether the desired location has been selected for the placement of waste battery recycling bins; 0 indicates it has not been selected, and a natural number z indicates that the location has been selected as the z-th waste battery recycling bin placement point; the second row of each honey source X b This indicates which layout point serves the demand point. It generates |MN| virtual points and assigns them the value 0 to complete the two-dimensional matrix.

[0034] Furthermore, simulation analysis was conducted using an improved artificial bee colony algorithm to solve the simulation model and obtain the location information for the recycling bins. The specific steps include the following:

[0035] S041: Initialize the bee colony; scout bees perform a global search based on the formula x. s,t =lb t +rand(0,1)·(ub t -lb t Assign an initial value to each location in the nectar source. Generate an initial feasible solution using natural numbers based on the number of demand points and the number of simulated planned layout points. Normalize the initial feasible solution to integers. The initial feasible solution is the initial nectar source, used to assign hired bees and follower bees to the selected initial layout points after normalization. Set the maximum number of iterations L and the number of iterations without improvement l of the bee colony algorithm. Set the control variables L′ (recording the global iteration count), L″ (recording the local iteration count), l′ (recording the number of iterations without improvement in local optimization), and l″ (recording the number of iterations without improvement in neighborhood search) to 0. The initial fitness value is denoted as f = f1 = f2 = f3 = ∞.

[0036] Where s represents the s-th solution set s = 1, 2, ..., N, x is a D-dimensional vector, t represents its dimension, t ∈ {1, 2, ..., D}, rand(0, 1) represents a random decimal number from 0 to 1, and lb t It is the minimum value of x in the t-th dimension, ub t It is the maximum value of x in the t-th dimension;

[0037] S042: Calculate the fitness value f1 of the current feasible solution according to the objective function of the network simulation model. If the fitness value f1 of the current feasible solution is less than f, then set the current fitness value f1 to f; otherwise, keep it unchanged and increment l′ by 1.

[0038] S043: If the fitness f2 is better than the fitness f1 of the original solution, then replace it; otherwise, follow the bee to use the neighborhood generation strategy to generate a new feasible solution. If the fitness f3 of the new solution is better than f2, then replace f2; otherwise, keep f2 unchanged and increment l″ by 1.

[0039] S044: If the fitness value f2 remains unchanged after l iterations (i.e., l″≥l), record the current fitness value f2, activate the scout bee, and check X. b The global search formula described in step S041 is used for updating and integer normalization, and l″ is set to 0, and the iteration count L″ is incremented by 1.

[0040] S045: Determine whether L″ has reached the maximum number of iterations. If L″ > L, proceed to the next step; otherwise, return to step S043.

[0041] S046: If the fitness value f1 remains unchanged after l iterations (i.e., l′≥l), record the current fitness value f1, activate the scout bee, and check X. a The global search formula described in step S041 is used to update and perform integer normalization, and l′ is set to 0, while the iteration count L′ is incremented by 1.

[0042] S047: Determine whether L′ has reached the maximum number of iterations. If L′>L, output the current solution as the optimal solution; otherwise, return to step S042.

[0043] Furthermore, the neighborhood generation strategy employs a two-point crossover transformation method, randomly selecting the second row X of the honey source. b The two positions swapped the data.

[0044] Furthermore, the number and configuration of new energy vehicle waste battery recycling bins at each station are determined based on the service area of ​​the station and the predicted recycling volume of waste batteries within the area, specifically as follows:

[0045] The solution results are decoded according to the encoding method. Based on the number of grids in the service area of ​​the layout points and the predicted recycling quantity of waste batteries from new energy vehicles in each grid, according to N...m =λ1·X m +λ2·Y m The number of new energy vehicle waste battery recycling bins to be deployed within the M proposed site selection locations was calculated.

[0046] Where m∈{1,2,…,M} represents the number of the planned site selected for the layout of recycling bins for waste batteries from new energy vehicles;

[0047] N m This represents the number of recycling bins expected to be placed at the m-th planned site;

[0048] X m This represents the number of demand points served by the m-th planned site;

[0049] Y m This represents the total predicted recycling volume of waste batteries from new energy vehicles within the demand area served by the m-th planned site.

[0050] λ1 and λ2 are both preset weighting factors.

[0051] A system for site selection and planning of waste battery recycling bins for new energy vehicles includes:

[0052] Planning Area Information Acquisition Unit: Used to divide the area to be planned into grids and number them, and to collect, store and manage relevant data information of the area to be planned;

[0053] Waste battery quantity prediction unit: used to predict the data required for site selection planning;

[0054] Site selection planning unit: used to construct a mathematical model for the site selection planning problem of the planned area in the future, and to map the data obtained by the planning area information acquisition unit and the waste battery quantity prediction unit to the corresponding parameters of the bee colony algorithm, introduce the initial parameters of the algorithm, and solve the model through the improved bee colony algorithm;

[0055] Site planning scheme determination unit: It is used to decode the solution results transmitted by the site planning unit according to the rules, determine the site selection of recycling bins for waste batteries of new energy vehicles, and then determine the number of recycling bins at each site based on the number of grids in the service area of ​​the layout point and the predicted recycling quantity of waste batteries of new energy vehicles in each grid.

[0056] Furthermore, the planning area information acquisition unit is interconnected with the waste battery quantity prediction unit and the site selection planning unit to transmit the original data of the planning area and each grid; the waste battery quantity prediction unit is interconnected with the site selection planning unit and the site planning scheme determination unit to transmit relevant prediction data; the site selection planning unit is interconnected with the site planning scheme determination unit to transmit the algorithm solution results.

[0057] A terminal device for site selection and planning of waste battery recycling bins for new energy vehicles, comprising:

[0058] Input terminal: Used to collect data and information required for the site selection and planning of waste battery recycling bins for new energy vehicles;

[0059] Main body: Used for site selection planning of recycling bins for used batteries from new energy vehicles;

[0060] Memory: Used to receive and store data information transmitted from the input terminal, main body and processor; to store and manage the calculation programs and data required by the terminal device for a long time, and to temporarily store data information that has been output or will be output.

[0061] Processor: Used to receive data information and calculation programs from the memory, and to call relevant data information and calculation programs to perform data prediction, function solving and data decoding according to different instructions from the main body;

[0062] Output end: Used to convert the site selection planning results of waste battery recycling bins for new energy vehicles into image or sound signals for output;

[0063] The main body is equipped with the system of the new energy vehicle waste battery recycling bin site selection and planning method. The main body is connected to the input terminal, memory, processor and output terminal. The input terminal is associated with the main body and memory, the memory is associated with the main body and processor, and the processor is associated with the main body and output terminal. Corresponding data is transmitted between the interconnected modules.

[0064] The beneficial effects of this invention are as follows:

[0065] 1. The new energy vehicle waste battery recycling bin site selection planning method, system, and terminal equipment described in this invention first smooths the data obtained from the planning area information acquisition unit for prediction, reducing the interference of accidental factors on the prediction results; it adopts an improved artificial bee colony algorithm for new energy vehicle waste battery recycling bin site selection planning, realizing the rationalization of the service range of the recycling bins, making it more convenient for new energy vehicle users to recycle retired waste batteries; the waste battery recycling bin site selection planning system and terminal equipment standardize the site selection planning process of new energy vehicle waste battery recycling bins, reduce the initial investment in waste battery recycling bin installation, and promote the efficient recycling of retired waste batteries. Attached Figure Description

[0066] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. The drawings described below are some embodiments of the present invention. For those skilled in the art, it is obvious that other drawings can be obtained from these drawings without creative effort.

[0067] Figure 1 This is a schematic diagram of the site selection and planning method for waste battery recycling bins for new energy vehicles as described in this invention.

[0068] Figure 2 This is a flowchart of the algorithm for solving the problem of waste battery recycling bin layout and location using the improved artificial bee colony algorithm described in this invention.

[0069] Figure 3 This is a schematic diagram of the site selection and planning system for waste battery recycling bins for new energy vehicles as described in this invention.

[0070] Figure 4 This is a schematic diagram of the terminal equipment for site selection and planning of waste battery recycling bins for new energy vehicles as described in this invention. Detailed Implementation

[0071] The present invention will be further described below with reference to the accompanying drawings and specific embodiments, but the scope of protection of the present invention is not limited thereto.

[0072] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0073] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "axial," "radial," "vertical," "horizontal," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0074] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0075] like Figure 1 As shown, the site selection and planning method for waste battery recycling bins for new energy vehicles according to the present invention includes the following steps:

[0076] S01: Divide the planning area and obtain relevant information for each area, specifically:

[0077] The planning area is divided into grids, and the number of new energy vehicles D in each year within the i-th region is obtained. i and scrap volume S i This allows us to determine the proportion P of new energy vehicle scrapping volume within each grid relative to the total number of new energy vehicles scrapped in the planned area. N =(P1,P2,…P) i ,…,P n ), where i represents the community corresponding to the i-th region, and n is the total number of regions.

[0078] S02: The amount of recycled waste batteries from new energy vehicles in each region is predicted using a smoothed grey prediction model. Using a smoothed grey prediction model effectively avoids the significant impact of data randomness on the prediction results. The specific steps are as follows:

[0079] S021: The number of new energy vehicles D in each year within the i-th region. i The proportion (P) of the number of new energy vehicles scrapped in each grid to the total number of new energy vehicles scrapped in the planned area. N The proportion of new energy vehicles scrapped in region i to the total number of vehicles in the region P i Sort them separately to generate the original data series X( 0 )=(x (0) (1),x (0) (2),…,x (0) (k),…,x (0) (n)) in the form of, where x (0 (k)≥0, k=0,1,2,…,n;

[0080] S022: The original data series is preprocessed using the three-point smoothing method, as follows:

[0081] Intermediate data is processed separately as follows:

[0082] Where k = 2, 3, ..., n-1;

[0083] The data at both ends are processed separately as follows:

[0084]

[0085]

[0086] S023: Use a grey model to predict the preprocessed data for a series of... A new sequence is formed through a single accumulation. in, k = 1, 2, ..., n;

[0087] series Establish differential equations In the formula, α is the development coefficient, used to characterize... and The development trend; u is the endogenous control gray number;

[0088] The parameters α and u are determined using the least squares method, [α, u] T = (B T B) -1 B T Y, where B is a data matrix and Y is a data vector, are represented as follows:

[0089]

[0090] Solving the differential equation yields Where k = 1, 2, ..., n;

[0091] right Perform cumulative subtraction to obtain the predicted values ​​for the data series:

[0092]

[0093] Where k = 1, 2, ..., n.

[0094] Based on the above prediction method, the planned annual number of new energy vehicles D within the planning area is obtained. i The proportion of scrapped items to the total number of vehicles in stock (p) i The proportion of new energy vehicles scrapped within each grid to the total number of vehicles in the planned area, P. N The predicted value. According to the formula S i =D i ·p iThe number of new energy vehicles scrapped within the planned area in the planned year is calculated according to the formula s. N =S i ·P N The number of new energy vehicles scrapped in each grid of the planning area in the planning year is calculated, according to the formula R. N =β·s N The amount of used batteries from new energy vehicles recycled in each grid within the planning area for the planning year was calculated.

[0095] Where N∈{1,2,…,n} represents the grid number within the planning area.

[0096] s N This indicates the number of new energy vehicles scrapped within each grid of the planned area in the planning year.

[0097] β represents the pre-set proportion of recycled batteries from new energy vehicles to the total number of scrapped vehicles.

[0098] R N This indicates the amount of waste batteries from new energy vehicles recycled within each grid of the planned area in the planning year.

[0099] S03: Determine the network simulation model and map the parameter information of each region to the bee colony parameter information in the improved artificial bee colony algorithm;

[0100] The network simulation model is determined as follows:

[0101] By considering the convenience of residents disposing of used batteries, and representing customer convenience in terms of labor costs, the total network cost is minimized. This cost is obtained by multiplying the convenience factor coefficient by the distance between the demand point and the location of the used battery recycling bins. The objective function of the network simulation model is:

[0102] Where U represents the total network cost; F a The fixed costs and operating costs of placing waste battery recycling bins at demand point a; decision variable h. a ∈{0,1}, a value of 1 indicates that the demand point i is selected as a layout point for the waste battery recycling bin, and a value of 0 indicates that it is not selected; f ab =ξ·X ab For the client's labor costs, X ab Let ξ be the distance between demand point a and the location b of the waste battery recycling bin; x is the convenience factor coefficient. ab This represents the predicted amount of used battery recycling demand generated at demand point a and collected at the used battery recycling bin location point b.

[0103] The improved artificial bee colony algorithm includes bee colony parameter information such as nectar sources, hired bees, and non-hired bees (including follower bees and scout bees). A nectar source represents a feasible solution to the problem. The nectar source is generated using a natural number encoding method, with each value in the nectar source encoding generated by scout bees and follower bees. The nectar source encoding represents the community number corresponding to each grid in the planning area. The quality of the nectar source is represented by the fitness of the problem, which is obtained through a network simulation model. The optimization of the nectar source is accomplished through the bees' search behavior, where the search behavior is the process of the bee colony algorithm.

[0104] A honey source coding method is constructed, using natural numbers. For a problem involving selecting M locations from N demand points for the placement of waste battery recycling bins, each honey source corresponds to a two-dimensional matrix of 2 rows and H columns, where H = max{M, N}. The constructed waste battery recycling bin location problem needs to address two aspects: first, whether each demand point is selected for bin placement; and second, which placement point serves each demand point. The first row X of the feasible solution (honey source) is... a This indicates whether the required point has been selected for the placement of waste battery recycling bins; 0 indicates that it has not been selected, and the natural number z indicates that this point is the z-th waste battery recycling bin placement point; the second line of the feasible solution X b This indicates which layout point serves the current requirement. |MN| virtual points are generated to complete the two-dimensional matrix and set to 0. For example, if there are 5 requirement points and 3 points are selected for layout, the encoding method for a certain honey source would be:

[0105] At this point, positions 1, 3, and 5 are selected as layout points, and sorted as 2, 1, and 3 respectively; and the layout point sorted as 1 serves the 1st and 2nd demand points, the layout point sorted as 2 serves the 4th demand point, and the layout point sorted as 3 serves the 3rd and 5th demand points.

[0106] S04: Simulation analysis is performed using an improved artificial bee colony algorithm to solve the simulation model and obtain the location information for the recycling bin layout;

[0107] The improved artificial bee colony algorithm offers fast optimization speed and good portability. Furthermore, the improved encoding method and neighborhood search rules effectively prevent the algorithm from getting trapped in local optima, which is significant for solving multi-site location problems. The specific steps are as follows: Figure 2 As shown:

[0108] S041: Initialize the bee colony; scout bees perform a global search based on the formula x. s,t =lb t +rand(0,1)·(ub t -lb tAssign an initial value to each location in the nectar source. Generate an initial feasible solution using natural numbers based on the number of demand points and the number of simulated planned layout points. Normalize the initial feasible solution to integers. The initial feasible solution is the initial nectar source, used to assign hired bees and follower bees to the selected initial layout points after normalization. Set the maximum number of iterations L and the number of iterations without improvement l of the bee colony algorithm. Set the control variables L′ (recording the global iteration count), L″ (recording the local iteration count), l′ (recording the number of iterations without improvement in local optimization), and l″ (recording the number of iterations without improvement in neighborhood search) to 0. The initial fitness value is denoted as f = f1 = f2 = f3 = ∞.

[0109] Where s represents the s-th solution set s = 1, 2, ..., N, x is a D-dimensional vector, t represents its dimension, t ∈ {1, 2, ..., D}, rand(0, 1) represents a random decimal number from 0 to 1, and lb t It is the minimum value of x in the t-th dimension, ub t It is the maximum value of x in the t-th dimension;

[0110] For a problem involving selecting M locations from N demand points to arrange waste battery recycling bins, consider the first row X of the MiYuan X... a Take the first M digits based on their numerical value and assign them the values ​​M, M-1, ..., 1 respectively. Create |MN| virtual points at the remaining positions and assign them the value 0. For the second row X of the honey source... b Round up. If the value exceeds the range [1, M], then take the boundary value. For example, if there are 5 requirement points and 3 points are selected for layout, the encoding method for a feasible solution is as follows: The encoding method after integer normalization becomes

[0111] S042: Calculate the fitness value f1 of the current feasible solution according to the objective function of the network simulation model. If the fitness value f1 of the current feasible solution is less than f, then set the current fitness value f1 to f; otherwise, keep it unchanged and increment l′ by 1.

[0112] S043: If the fitness f2 is better than the fitness f1 of the original solution, then replace it; otherwise, follow the bee and use the neighborhood generation strategy to generate a new feasible solution. If the fitness f3 of the new solution is better than f2, then replace f2; otherwise, keep f2 unchanged and increment l″ by 1. The neighborhood generation strategy uses a two-point crossover transformation method, randomly selecting the second row X of the honey source. b Swap the data in two positions

[0113] S044: If the fitness value f2 remains unchanged after l iterations (i.e., l″≥l), record the current fitness value f2, activate the scout bee, and check X. bThe global search formula described in step S041 is used for updating and integer normalization, and l″ is set to 0, and the iteration count L″ is incremented by 1.

[0114] S045: Determine whether L″ has reached the maximum number of iterations. If L″ > L, proceed to the next step; otherwise, return to step S043.

[0115] S046: If the fitness value f1 remains unchanged after l iterations (i.e., l′≥l), record the current fitness value f1, activate the scout bee, and check X. a The global search formula described in step S041 is used to update and perform integer normalization, and l′ is set to 0, while the iteration count L′ is incremented by 1.

[0116] S047: Determine whether Lv has reached the maximum number of iterations. If L′>L, output the current solution as the optimal solution; otherwise, return to step S042.

[0117] S05: The number and configuration of new energy vehicle waste battery recycling bins at each station are determined based on the service area of ​​the station site and the predicted recycling volume of waste batteries within the area, specifically:

[0118] The solution results are decoded according to the encoding method. Based on the number of grids in the service area of ​​the layout points and the predicted recycling quantity of waste batteries from new energy vehicles in each grid, according to N... m =λ1·X m +λ2·Y m The number of new energy vehicle waste battery recycling bins to be deployed within the M proposed site selection locations was calculated.

[0119] Where m∈{1,2,…,M} represents the number of the planned site selected for the layout of recycling bins for waste batteries from new energy vehicles;

[0120] N m This represents the number of recycling bins expected to be placed at the m-th planned site;

[0121] X m This represents the number of demand points served by the m-th planned site;

[0122] Y m This represents the total predicted recycling volume of waste batteries from new energy vehicles within the demand area served by the m-th planned site.

[0123] λ1 and λ2 are both preset weighting factors.

[0124] like Figure 3 As shown, the new energy vehicle waste battery recycling bin site selection and planning system of the present invention includes a planning area information acquisition unit, a waste battery quantity prediction unit, a site selection planning unit, and a site planning scheme determination unit;

[0125] The planning area information acquisition unit is used to divide the planning area into grids and number them, collect, store, and manage relevant information such as the number of new energy vehicles in the planning area, the number of scrapped vehicles, and the distance between the centers of each grid. Based on the collected data, it calculates the proportion of new energy vehicle scrapping in the planning area to the total number of vehicles in the planning area for each year, and the proportion of new energy vehicle scrapping in each grid to the total number of new energy vehicles scrapped in the planning area. The obtained data is then transmitted to the waste battery quantity prediction unit and the site selection planning unit.

[0126] The waste battery quantity prediction unit is used to predict the number of new energy vehicles in the planning area in the future, the proportion of new energy vehicles scrapped in the planning area to the total number of vehicles in the planning area, and the proportion of new energy vehicles scrapped in each grid to the total number of new energy vehicles scrapped in the planning area. Based on the predicted data, it calculates the number of new energy vehicles scrapped in each grid in the planning year and the amount of waste batteries recycled from new energy vehicles. Then, it transmits the predicted data to the site selection planning unit and the site planning scheme determination unit.

[0127] The site selection planning unit is used to construct a mathematical model for the site selection planning problem of the planned area in the future, and to map the data obtained by the planning area information acquisition unit and the waste battery quantity prediction unit to the corresponding parameters of the bee colony algorithm. Some initial parameters of the algorithm are introduced, and the model is solved by the improved bee colony algorithm. The solution is transmitted to the site planning scheme determination unit.

[0128] The site planning scheme determination unit decodes the solution results transmitted by the site selection planning unit according to the rules, determines the site selection sites for the recycling bins of new energy vehicle waste batteries, and then determines the number configuration of recycling bins at each site based on the number of grids in the service area of ​​the layout point and the predicted recycling quantity of new energy vehicle waste batteries in each grid.

[0129] like Figure 4 As shown, the new energy vehicle waste battery recycling bin site selection and planning terminal equipment of the present invention includes an input terminal, a main body, a memory, a processor, and an output terminal;

[0130] The input terminal receives instructions from the planning area information acquisition unit of the main body, collects the data information required for the site selection planning of waste battery recycling bins for new energy vehicles, and transmits the acquired data information to the main body and the memory. The input terminal can be a microphone, touchpad, speaker, sensor, or other input device.

[0131] The main body is used for site selection planning of waste battery recycling bins for new energy vehicles. It is equipped with the new energy vehicle waste battery recycling bin site selection planning system and is connected to the input terminal, memory, processor and output terminal. During the site selection planning process, it issues relevant instructions to call each unit and module to work. It is the core module of the new energy vehicle waste battery recycling bin site selection terminal equipment.

[0132] The memory is used to receive and store data information transmitted from the input terminal, various units of the main body, and the processor; to transmit data information required for site selection planning to the waste battery quantity prediction unit and site selection planning unit of the main body of the terminal device; to transmit the required data information and calculation program to the processor; and to transmit the solution results to the output terminal. It also performs long-term storage and management of the calculation program and data required by the terminal device, and temporarily stores data information that has been output or will be output. The memory can be a storage medium such as a USB flash drive, terminal hard drive, disk, or data cloud drive.

[0133] The processor receives data and calculation programs from the memory, and, based on instructions from each unit of the main body, invokes relevant data and calculation programs to perform data prediction, algorithm solving, and result decoding, outputting the results to the memory, the processor, and an output terminal. The processor can be a central processing unit or other general-purpose processors.

[0134] The output terminal receives instructions from the site planning scheme determination unit of the main body and converts the site selection planning results of the new energy vehicle waste battery recycling bins into image or sound signals for output. The output terminal can be a display screen, speaker, etc.

[0135] It should be understood that although this specification is described according to various embodiments, not every embodiment contains only one independent technical solution. This way of describing the specification is only for clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other implementation methods that can be understood by those skilled in the art.

[0136] The detailed descriptions listed above are merely specific illustrations of feasible embodiments of the present invention and are not intended to limit the scope of protection of the present invention. All equivalent embodiments or modifications made without departing from the spirit of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for site selection and planning of recycling bins for used batteries from new energy vehicles, characterized in that, Includes the following steps: The planning area is divided into grids to obtain the first... The number of new energy vehicles in the region each year and scrap volume This allows us to determine the proportion of new energy vehicles scrapped within each grid to the total number of new energy vehicles scrapped in the planned area. Where i represents the community corresponding to the i-th region, and n is the total number of regions. ; The amount of waste batteries from new energy vehicles in each region is predicted using a smoothed grey prediction model. The network simulation model is determined by mapping the parameter information of each region to the bee colony parameter information in the improved artificial bee colony algorithm. Specifically, the network simulation model is determined as follows: The convenience level for customers is represented by labor costs, calculated by multiplying the convenience factor coefficient by the distance between the demand point and the location of the waste battery recycling bin. The objective function of the network simulation model is: , in, This represents the total cost of the network; To meet the demand point Fixed and operating costs of deploying waste battery recycling bins; decision variables Taking 1 to represent the demand point Selected as a layout point for waste battery recycling bins; a value of 0 indicates that it has not been selected. For the client's labor costs, For demand points Location of waste battery recycling bins The distance between them For convenience factor coefficient; Indicate demand points The demand for used battery recycling is generated, and the locations of used battery recycling bins are being established. The predicted amount to be recovered; The improved artificial bee colony algorithm was used for simulation analysis to solve the simulation model and obtain the location information of the recycling bins. The number and configuration of new energy vehicle waste battery recycling bins at each station are determined based on the service area of ​​the station and the predicted recycling volume of waste batteries in the area.

2. The site selection and planning method for waste battery recycling bins for new energy vehicles according to claim 1, characterized in that, The gray prediction model, which uses smoothing, predicts the recycling volume of waste batteries from new energy vehicles in various regions, including the following steps: The first The number of new energy vehicles in the region each year The proportion of new energy vehicle scrapping in each grid to the total number of new energy vehicle scrapping in the planned area. The proportion of new energy vehicles scrapped in region i to the total number of vehicles in the region. Sort them separately to generate the original data series In the form of, ; The original data series is preprocessed using a three-point smoothing method, as follows: Intermediate data is processed separately as follows: ,in, ; The data at both ends are processed separately as follows: ， ； The grey model is used to predict the preprocessed data for a series of... A new sequence is formed through a single accumulation. , ,in, , ; series Establish differential equations In the formula, The development coefficient is used to characterize... and The development trend; To control the gray number endogenously; parameter and Determined by the least squares method ,in, For data matrix, The data vectors are represented as follows: ， ， Solving the differential equation yields ,in ; right Perform cumulative subtraction to obtain the predicted values ​​for the data series: ； ,in, .

3. The site selection and planning method for waste battery recycling bins for new energy vehicles according to claim 1, characterized in that, The improved artificial bee colony algorithm includes bee colony parameter information such as nectar source. The nectar source represents a feasible solution to the problem. The nectar source is generated through a natural number encoding method. Each value in the nectar source encoding is generated by scout bees and follower bees. The nectar source encoding represents the community number corresponding to each grid in the planning area. The quality of the nectar source is represented by the fitness of the problem. The fitness value is obtained through a network simulation model. The optimization of the nectar source is completed through the search behavior of bees, where the search behavior is the process of the bee colony algorithm. The honey source is generated using a natural number encoding method as follows: For a problem involving selecting M locations from N demand points for the layout of waste battery recycling bins, each honey source corresponds to a two-dimensional matrix with two rows and H columns. The first line of each honey source This indicates whether the request point has been selected for the placement of waste battery recycling bins; 0 indicates that it has not been selected. (Number) This indicates that the point has been selected as the first... The layout of waste battery recycling bins; the second row of each honey source. This indicates which layout point serves the demand point, and how it is generated. Add virtual points and assign them the value 0 to complete the two-dimensional matrix.

4. The site selection and planning method for waste battery recycling bins for new energy vehicles according to claim 3, characterized in that, The improved artificial bee colony algorithm is used for simulation analysis to solve the simulation model and obtain the location information of the recycling bins. The specific steps include the following: S041: Initialize the bee colony; scout bees perform a global search based on the formula. Each location in the nectar source is assigned an initial value. Based on the number of demand points and the number of simulated planned layout points, an initial feasible solution is generated using a nectar source encoding method with natural numbers. The initial feasible solution is then normalized to an integer. The initial feasible solution serves as the initial nectar source, used to assign hired bees and follower bees to the normalized initial layout points. The maximum number of iterations of the bee colony algorithm is set. and no improvement in iteration count The control variable that records the number of global iterations Control variables that record the number of local iterations Control variables that record the number of iterations without improvement in local optimization. And recording the domain search without improving the number of iterations Set to 0, and record the initial fitness value as . ; in, Representing the Solution , It is dimensional vector, This represents its dimension. , Represents a random decimal number between 0 and 1. It is the first Weizhong The minimum value, It is the first Weizhong The maximum value; S042: Calculate the fitness value of the current feasible solution based on the objective function of the network simulation model. If the fitness value of the current feasible solution Then the current fitness value will be set. Order Otherwise, it will remain unchanged and will Add 1; S043: If fitness Fitness better than the original solution If a replacement is made, then the bee follows up by using a neighborhood generation strategy to generate a new feasible solution. If the fitness of the new solution is... Superior Then replace Otherwise keep Unchanged and will Add 1; S044: If fitness value go through No change after the second iteration Record the current fitness value Activate the reconnaissance bee to... The global search formula described in step S041 is used for updating and integer normalization, and the integers are then... Set to 0, number of iterations Add 1; S045: Judgment Has the maximum number of iterations been reached? Proceed to the next step; otherwise, return to step S043. S046: If fitness value go through No change after the second iteration Record the current fitness value Activate the reconnaissance bee to... The global search formula described in step S041 is used for updating and integer normalization, and then... Set to 0, number of iterations Add 1; S047: Judgment Has the maximum number of iterations been reached? If the current solution is the optimal solution, then output the current solution; otherwise, return to step S042.

5. The site selection and planning method for waste battery recycling bins for new energy vehicles according to claim 4, characterized in that, The neighborhood generation strategy employs a two-point crossover transformation method, randomly selecting the second row of the honey source. The two positions swapped the data.

6. The method for site selection and planning of waste battery recycling bins for new energy vehicles according to claim 4, characterized in that, The number and configuration of new energy vehicle waste battery recycling bins at each station are determined based on the service area of ​​the station and the predicted recycling volume of waste batteries within the area, as follows: The solution results are decoded according to the encoding method, based on the number of grids in the service area of ​​the layout points and the predicted recycling quantity of waste batteries from new energy vehicles in each grid. Calculated at The number of new energy vehicle waste battery recycling bins to be installed within the proposed site selection area. in, This indicates the number of the planned site selected for the layout of recycling bins for used batteries from new energy vehicles; Indicates the first The number of recycling bins expected to be placed within each planned site; This represents the number of demand points served by the m-th planned site; This represents the total predicted recycling volume of waste batteries from new energy vehicles within the demand area served by the m-th planned site. All of these are preset weighting factors.

7. A system for site selection and planning of waste battery recycling bins for new energy vehicles according to any one of claims 1-6, characterized in that, include: Planning Area Information Acquisition Unit: Used to divide the area to be planned into grids and number them, and to collect, store and manage relevant data information of the area to be planned; Waste battery quantity prediction unit: used to predict the data required for site selection planning; Site selection planning unit: used to construct a mathematical model for the site selection planning problem of the planned area in the future, and to map the data obtained by the planning area information acquisition unit and the waste battery quantity prediction unit to the corresponding parameters of the bee colony algorithm, introduce the initial parameters of the algorithm, and solve the model through the improved bee colony algorithm; Site planning scheme determination unit: It is used to decode the solution results transmitted by the site planning unit according to the rules, determine the site selection of recycling bins for waste batteries of new energy vehicles, and then determine the number of recycling bins at each site based on the number of grids in the service area of ​​the layout point and the predicted recycling quantity of waste batteries of new energy vehicles in each grid.

8. The site selection and planning system for waste battery recycling bins for new energy vehicles according to claim 7, characterized in that, The planning area information acquisition unit is interconnected with the waste battery quantity prediction unit and the site selection planning unit to transmit the original data of the planning area and each grid; the waste battery quantity prediction unit is interconnected with the site selection planning unit and the site planning scheme determination unit to transmit relevant prediction data; the site selection planning unit is interconnected with the site planning scheme determination unit to transmit the algorithm solution results.

9. A terminal device for site selection and planning of waste battery recycling bins for new energy vehicles, characterized in that, include: Input terminal: Used to collect data and information required for the site selection and planning of waste battery recycling bins for new energy vehicles; Main body: Used for site selection planning of recycling bins for used batteries from new energy vehicles; Memory: Used to receive and store data information transmitted from the input terminal, the main body, and the processor; It performs long-term storage and management of the computing programs and data required by the terminal device, and temporarily stores the data information that has been output or will be output. Processor: Used to receive data information and calculation programs from the memory, and to call relevant data information and calculation programs to perform data prediction, function solving and data decoding according to different instructions from the main body; Output end: Used to convert the site selection planning results of waste battery recycling bins for new energy vehicles into image or sound signals for output; The main body is equipped with the system of the new energy vehicle waste battery recycling bin site selection and planning method according to claim 7. The main body is connected to the input terminal, memory, processor and output terminal. The input terminal is associated with the main body and memory, the memory is associated with the main body and processor, and the processor is associated with the main body and output terminal. Corresponding data is transmitted between the interconnected modules.

Images