CN117728064A - Optimization method of retired power battery disassembly process - Google Patents
Optimization method of retired power battery disassembly process Download PDFInfo
- Publication number
- CN117728064A CN117728064A CN202410173829.5A CN202410173829A CN117728064A CN 117728064 A CN117728064 A CN 117728064A CN 202410173829 A CN202410173829 A CN 202410173829A CN 117728064 A CN117728064 A CN 117728064A
- Authority
- CN
- China
- Prior art keywords
- wolf
- disassembly
- disassembling
- group
- wolf group
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 172
- 230000008569 process Effects 0.000 title claims abstract description 106
- 238000005457 optimization Methods 0.000 title claims abstract description 72
- 241000282461 Canis lupus Species 0.000 claims abstract description 169
- 238000010586 diagram Methods 0.000 claims abstract description 24
- 241000282421 Canidae Species 0.000 claims abstract description 16
- 230000006978 adaptation Effects 0.000 claims description 14
- 238000013468 resource allocation Methods 0.000 claims description 10
- 238000007726 management method Methods 0.000 claims description 8
- 238000009413 insulation Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 4
- 230000007423 decrease Effects 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000012804 iterative process Methods 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 3
- 238000006467 substitution reaction Methods 0.000 claims description 3
- 230000002195 synergetic effect Effects 0.000 claims description 3
- 230000001010 compromised effect Effects 0.000 claims 1
- 238000011084 recovery Methods 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 34
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000013459 approach Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 239000010926 waste battery Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000007373 indentation Methods 0.000 description 1
- 230000004941 influx Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
- Y02W30/00—Technologies for solid waste management
- Y02W30/50—Reuse, recycling or recovery technologies
- Y02W30/84—Recycling of batteries or fuel cells
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an optimization method of a retired power battery disassembly process, which comprises the following steps: decomposing and disassembling the process, collecting relevant data information of the disassembling process, and then constructing a priority sequence chart of the retired power battery disassembling process; then constructing a structured coding rule for the priority sequence diagram; then generating a process disassembly scheme by using a gray wolf optimization algorithm and a structured coding rule; calculating the relevance between the process disassembly scheme and the objective function, and updating the position of the gray wolf according to the function value of the objective function: after the position of the wolves is updated, calculating the objective function value of each wolf again, and updating the wolf clusters again; repeating until the set maximum iteration times are reached, and outputting a global optimal solution or a near optimal solution; and finally, optimizing the retired power battery disassembly process according to the output result. The optimization method can realize maximum recovery of resources, reduce disassembly cost and provide great opportunity and potential for solving the challenges in the field of retired power battery disassembly.
Description
Technical Field
The invention belongs to the field of waste battery treatment, and particularly relates to an optimization method of a retired power battery disassembly process.
Background
With the continuous maturity of new energy technology, pure electric vehicles occupy an increasingly high market share of vehicles, and the influx of a large number of electric vehicles will bring a large number of retired new energy power batteries. Because the production standard of the new energy power battery in early retirement is not perfect, the process parameter differentiation of the structure, connection and the like among the new energy power batteries of the pure electric vehicles in various models is obvious, so that the automatic production level of the new energy power battery in retirement is not high in the disassembly process, the automatic production level is mainly dependent on manual labor, the disassembly process mainly comprises manual disassembly, and high-pressure and dangerous chemical substances are involved, so that the method is time-consuming and labor-consuming, and potential safety risks exist. Further, as the market share of new energy electric vehicles increases year by year, the existing disassembly production line is difficult to meet the increasingly retired new energy power battery classification disassembly requirement, and the existing disassembly process is difficult to cope with the challenge.
In view of the limitations of the traditional dismantling method, a flexible retired power battery dismantling process is developed, and an intelligent decision method is used for improving the retired power battery dismantling process. However, in improving the disassembly process of retired power cells, we need to overcome a series of technical problems:
(1) Complex coding problem of disassembly process: retired power cell disassembly processes typically involve multiple complex steps and different types of components, how to efficiently manage and code is a critical issue;
(2) Coordination problem of manual and machine disassembly: in the process of disassembly, the manual disassembly and the machine disassembly may have differences, and how to reasonably coordinate the work of the manual disassembly and the machine disassembly to improve the overall disassembly efficiency is also a problem to be solved;
(3) Management problem of disassembling priority and parallel relation: aiming at the parallel disassembly and priority relation existing in the disassembly process, how to reasonably manage the priority and the parallel relation among the working procedures is a key for improving the flexibility of the disassembly process;
(4) Cost and time double optimization problem: how to balance the cost and time of disassembly in the disassembly process so as to maximize the utilization of resources and optimize the efficiency of the disassembly process is a core problem which needs to be solved;
(5) Application problem of intelligent decision algorithm: how to select a proper optimization algorithm to be applied to the disassembly process decision and adjust and optimize the method aiming at specific problems is also one of the keys of research and exploration.
Disclosure of Invention
The invention aims to at least overcome the technical problems, simulate analysis is carried out on disassembled data by utilizing technologies such as artificial intelligence, machine learning, an optimization algorithm and the like, an optimal disassembly scheme for intelligent decision is provided by the intelligent decision, the optimization method for the disassembly process of the retired power battery can realize maximum recovery of resources, the disassembly cost is reduced, great opportunities and potential are provided for solving the challenges in the disassembly field of the retired power battery, and further development of the battery recovery and reuse field is promoted.
In order to solve the technical problems, the invention provides an optimization method of a retired power battery disassembly process, which comprises the following steps:
(1) Decomposing and disassembling process, and collecting related data information of the disassembling process;
(2) Analyzing related data information of the dismantling process, and constructing a priority sequence chart of the dismantling process of the retired power battery; the priority sequence diagram is used for determining a priority sequence and a parallel sequence of a disassembly procedure so as to facilitate procedure decision making, and a working allocation relation between the priority sequence diagram and a manual and mechanical arm provides a visual basis for subsequent intelligent decision making and serves as constraint of an intelligent decision algorithm;
(3) Constructing a structured coding rule for the priority sequence diagram; for flexible disassembly of the priority sequence diagram, in order to consider an intelligent decision algorithm, the two-dimensional relation diagram is converted from unstructured to structured, and meanwhile, the disassembled priority sequence is displayed;
(4) Generating a process disassembly scheme by using a gray wolf optimization algorithm and a structured coding rule;
(5) Calculating the relevance of the process disassembly scheme and an objective function, wherein the function value of the objective function represents the performance evaluation of the process disassembly scheme;
(6) Updating the position of the gray wolf according to the function value of the objective function;
(7) After the position of the wolves is updated, the objective function value of each wolf is recalculated, and then the wolf group is updated again (for example, the class of the wolf group is updated);
(8) Repeating the steps (6) and (7) until the set maximum iteration times are reached, and outputting a global optimal solution or a near optimal solution; and optimizing the retired power battery disassembling process according to the output result to obtain an optimized retired power battery disassembling process.
The method and the device can better ensure that the algorithm converges to the optimal solution or approaches to the optimal solution in a limited time by setting the maximum iteration number max_iter so as to ensure the disassembly cost and the disassembly time to be minimized and ensure high efficiency and quality at the same time so as to meet the requirement of battery disassembly. The optimization method can be directly used in the actual battery disassembly process, and realizes resource recovery and cost saving.
The optimization method is preferably as follows: in the step (1), the related data information includes manual disassembly time, manual disassembly cost, mechanical disassembly time and mechanical disassembly cost of each part of the retired power battery.
The optimization method is preferably as follows: in the step (1), the decomposing and disassembling process refers to decomposing the power battery into at least one or more of the following optional operations according to the difference of the retired power battery:
(1) Unscrewing a screw on the upper cover of the battery box;
(2) Hanging an upper cover of the battery box;
(3) Taking out the heat insulation pad;
(4) Disassembling the high-voltage storage battery cover;
(5) Disassembling a plug on the contactor at the output end of the high-voltage interface;
(6) Disassembling the fixing bolts of the output end contactor and the battery shell;
(7) Disassembling the high-voltage interface output end contactor;
(8) Disassembling bolts of the baffle fixing frame;
(9) Disassembling the partition board;
(10) Disassembling a connecting sheet fixing screw;
(11) Removing the connecting sheet;
(12) Disassembling the module and the lower box body fixing bolt;
(13) Disassembling the module fixing frame;
(14) Removing the high-voltage connection harness interface module;
(15) The low-voltage wiring harness interface module is connected with the pulling-out module;
(16) Performing socket insulation treatment;
(17) Disassembling the fixing bolt of the electronic management system;
(18) Disassembling the high-voltage battery cell cover;
(19) Pulling out the battery management unit;
(20) Taking out the battery module;
(21) Unscrewing a fixing screw of an upper cover of the battery module;
(22) Taking out the upper cover of the battery module;
(23) And detecting the electric quantity of the battery cell.
The optimization method is preferably as follows: in the step (3), constructing a structured coding rule for the priority sequence diagram specifically includes the following operations:
the flexible coding mode of hierarchical substitution YAML is used for showing the relation among data, T is used for showing the total number of all nodes, D is used for showing the priority order, space is used for separating node numbers, continuous numbers are used for showing node numbers, tab keys are used for showing the retraction relation, and different retraction relations show the belonging hierarchy.
The optimization method is preferably as follows: in the step (4), the wolf optimizing algorithm comprises a step of initializing the position of the wolf group, and the selection of the initial position has an important influence on the convergence and quality of the optimization. In this step, a group of wolves is randomly generated by initialization, and each wolf is made to represent a different disassembly scheme.
The optimization method is preferably as follows: in the step (4), the initialization of the position of the wolf group at least meets the following control conditions:
(1) The position of each gray wolf comprises the sequence of the disassembly procedure, time allocation and resource allocation information, and different disassembly schemes at least reflect the difference of at least one of the disassembly sequence, the time allocation and the resource allocation;
(2) The position of each gray wolf meets the constraints of the priority sequence diagram and the structured coding rules to ensure that the generated disassembly scheme is qualified and executable;
(3) The initialization position of the wolf is used as a starting population of a wolf optimization algorithm so as to provide a starting point for subsequent optimization;
(4) The initialization process introduces population size, initial position distribution and randomness as parameters to affect the search performance and convergence speed of the algorithm.
The optimization method is preferably as follows: the objective function specifically refers to:
；
wherein:
representation ofDisassembling scheme->Is adapted to the degree of adaptation of (a);
representing a detach scheme->Step (2)>Disassembling time;
the weight of the fitness function for the disassembly time;
representing a detach scheme->Step (2)>Disassembling cost;
the weight of the fitness function is taken as the disassembly time.
The optimization method is preferably as follows: in the step (6), the updating the position of the wolf according to the function value of the objective function specifically includes: dividing the gray wolf group into the following groups according to the function value of the objective function、/>、/>And->Four classes, wherein->Wolf group and->Wolf group and->Wolves are guided during hunting>The position update in the wolf's search for hunting is as follows,
；
；
；
；
in the method, in the process of the invention,the iteration times; />Is the position vector of the gray wolves; />Is the location of the prey; />Is the distance between the population of individuals and the prey; />And->Are synergistic coefficient vectors; />And->Are respectively between +.>Random numbers of (a); />The value of (2) decreases linearly with the number of iterations, from 2 to 0;
in hunting, it relies mainly on leadership capabilitiesWolf group and->Wolf group and->The wolf group provides a guide for the wolf group,the wolf group searches towards the direction of the existence of the prey, and the position of the group is updated as follows:
；
；
；
in the method, in the process of the invention,、/>、/>respectively->Wolf group and->Wolf group and->The current position of the wolf group; />、/>、/>Distance of the other individuals>Wolf group and->Wolf group and->Distance of wolf group; />Is the current position of the wolf.
The optimization method is preferably as follows: when (when)Wolf group and->Wolf group and->The adaptation value of the wolf group is not changed, the wolf group is respectively counted and added with 1, when the count exceeds 5 times, the wolf group is added with->Wolf group and->Wolf group and->The internal information of the wolf group is partially randomly exchanged, and the local fitness is counted in the following way:
；
；
；
；
in the formula (i),representing an iterative process; />Representation->Counting when the adaptation value of the wolf group is unchanged, when +.>Wolf group is->The sub-fitness value is equal to->For times, the patient is treated with>Counting and adding 1; />Representation->Counting when the adaptation value of the wolf group is unchanged, when +.>Wolf group is->The sub-fitness value is equal to->For times, the patient is treated with>Counting and adding 1; />Representation->Counting when the adaptation value of the wolf group is unchanged, when +.>Wolf group is->The sub-fitness value is equal to->For times, the patient is treated with>Counting and adding 1; />Representation->Wolf group is->A secondary fitness value; />Representation->Wolf group is->A secondary fitness value; />Representation->Wolf group is->A secondary fitness value; />Representing->Wolf group, middle->Dimension and->Information exchange is carried out on the dimension; />Representing a random generation->An integer between 0 and D.
The traditional genetic algorithm can only be suitable for a fixed coding mode, is difficult to adapt to decision optimization of flexible intelligent disassembly process of the retired power battery under complex constraint, and aims at the process of the disassembly process of the retired power batteryThe optimization is essentially a discrete sequence optimization method, while the Hull algorithm is a heuristic algorithm simulating social level system and hunting behavior of the Hull, and is essentially a continuous real number optimization algorithm, so as to improve the information exchange capacity in the wolf group and overcome the problem of improvement at the same timeWolf group and->Wolf group and->Local convergence characteristic of wolf group, the above preferred scheme provides a local extremum exchange method for optimizing discrete gray wolf process, and provides a pair of (a)>Wolf group and->Wolf group and->The wolf group local counting method improves the global convergence of the algorithm so as to be more suitable for discrete process optimization.
The optimization method is preferably as follows: in the step (8), optimizing the retired power battery disassembly process according to the output result includes optimizing the disassembly step sequence of the disassembly process, the time allocation and the resource allocation of each disassembly step.
Compared with the prior art, the invention has the advantages that:
1. intelligent decision and optimization: the invention makes an intelligent decision by using the gray wolf optimization algorithm, and can effectively optimize the dismantling process of the retired power battery, thereby improving the dismantling efficiency and reducing the dismantling cost;
2. priority sequence diagram application: by constructing the flexible disassembly priority sequence diagram, the method can reasonably arrange the priority and parallel relation of the disassembly procedure, so that the disassembly process is more efficient and flexible;
3. flexible coding rules: the invention can convert unstructured disassembly priority sequence diagram into structured data by adopting a hierarchical replacement YAML-like coding mode, thereby realizing flexible coding and management of the disassembly process;
4. cost and time optimization: according to the invention, through the set objective function, the disassembly time and cost can be comprehensively considered, the double optimization of the disassembly process cost and time is realized, and the resource utilization efficiency is improved.
In the disassembly process of the retired power battery, the intelligent decision of the disassembly process is realized by utilizing an intelligent technical means and through data analysis and algorithm optimization, and the method can play an important role in the electric automobile industry and the waste battery treatment field.
The invention will be described in further detail with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention. In the drawings:
fig. 1 is a process flow diagram of an optimization method for a retired power battery disassembly process in an embodiment of the invention.
Fig. 2 is a diagram of a retired power cell disassembly priority sequence constructed prior to optimization in an embodiment of the invention.
FIG. 3 is a graph showing the comparison of objective function values before and after optimization of the gray wolf optimization algorithm in the embodiment of the invention.
Fig. 4 is a schematic diagram of a process scheme of disassembly after being optimized according to an optimal solution in an embodiment of the present invention.
Detailed Description
Embodiments of the invention are described in detail below with reference to the attached drawings, but the invention can be implemented in a number of different ways, which are defined and covered by the claims.
Examples:
the optimization method of the retired power battery disassembly process shown in fig. 1 comprises the following steps:
1. and decomposing the disassembling process and collecting the related data information of the disassembling process. The related data information comprises the manual disassembly time, the manual disassembly cost, the mechanical disassembly time and the mechanical disassembly cost of each part of the retired power battery. The decomposition and disassembly process refers to at least decomposition into optional ones of the following operations depending on the retired power cells:
(1) Unscrewing a screw on the upper cover of the battery box;
(2) Hanging an upper cover of the battery box;
(3) Taking out the heat insulation pad;
(4) Disassembling the high-voltage storage battery cover;
(5) Disassembling a plug on the contactor at the output end of the high-voltage interface;
(6) Disassembling the fixing bolts of the output end contactor and the battery shell;
(7) Disassembling the high-voltage interface output end contactor;
(8) Disassembling bolts of the baffle fixing frame;
(9) Disassembling the partition board;
(10) Disassembling a connecting sheet fixing screw;
(11) Removing the connecting sheet;
(12) Disassembling the module and the lower box body fixing bolt;
(13) Disassembling the module fixing frame;
(14) Removing the high-voltage connection harness interface module;
(15) The low-voltage wiring harness interface module is connected with the pulling-out module;
(16) Performing socket insulation treatment;
(17) Disassembling the fixing bolt of the electronic management system;
(18) Disassembling the high-voltage battery cell cover;
(19) Pulling out the battery management unit;
(20) Taking out the battery module;
(21) Unscrewing a fixing screw of an upper cover of the battery module;
(22) Taking out the upper cover of the battery module;
(23) And detecting the electric quantity of the battery cell.
In this embodiment, we have counted the disassembly time and cost coefficients of the manual 1, manual 2, manual 3, manipulator 1, and manipulator 2 by performing the experimental disassembly on a certain power battery, and the statistical results are shown in the following table 1:
table 1: relevant data information collected in disassembly process of certain power battery
Note that: a "-1" in the table indicates that this type of data is not operational.
2. Analyzing related data information of the dismantling process, and constructing a priority sequence chart of the dismantling process of the retired power battery; the priority sequence diagram is used for determining a priority sequence and a parallel sequence of a disassembly procedure so as to facilitate procedure decision making, and a working allocation relation between the priority sequence diagram and a manual and mechanical arm provides a visual basis for subsequent intelligent decision making and serves as constraint of an intelligent decision algorithm.
In this embodiment, by analyzing the related data collected in the disassembly process in the step 1, a retired power battery disassembly priority sequence chart is constructed, and the priority sequence chart is used for determining the priority sequence and the parallel sequence of the disassembly process, and the finally constructed priority sequence chart is shown in fig. 2.
As shown in fig. 2, the process combinations (4, 5,6, 7) in the figure represent a set of priority sequences, the disassembly process of the process 4 is defined before the process 5, and the leaf nodes (i.e., process combinations) below the process 3 node (4, 5,6, 7), (8, 9), (10, 11), (12, 13) and the like are represented as parallel sequences.
3. Constructing a structured coding rule for the priority sequence diagram; for flexible disassembly of the priority sequence diagram, in order to allow for the intelligent decision algorithm, the two-dimensional relation diagram is converted from unstructured to structured, and meanwhile, the disassembled priority sequence is displayed, and the construction of the structured coding rule for the priority sequence diagram can specifically comprise the following operations:
the flexible coding mode of hierarchical substitution YAML is used for showing the relation among data, T is used for showing the total number of all nodes, D is used for showing the priority order, space is used for separating node numbers, continuous numbers are used for showing node numbers, tab keys are used for showing the retraction relation, and different retraction relations show the belonging hierarchy.
In this example, the details are shown in table 2 below.
Table 2: structured coding example of the present embodiment
In Table 2, the first line T19 shows that the running step has 23 disassembling steps in total, the second line to the end shows the coding format of the YAML, except that no key is shown, only data is shown, the middle of the data is separated by a space, meanwhile, a space is used for representing a placeholder by using D to indicate that a leaf node exists, the attribution of the leaf node is represented by a tab key and an expression indentation relation, and one represent that a depth exists and corresponds to the position D of the upper layer.
4. And generating a process disassembly scheme by using a gray wolf optimization algorithm and a structured coding rule.
The wolf algorithm is a heuristic algorithm for simulating social level system and hunting behavior of the wolves, and is particularly suitable for being used in the optimization method of the invention.
The wolf optimization algorithm includes an initialization step for the position of the wolf clusters, the choice of initial position having a significant impact on the convergence and quality of the optimization. In this step, a group of wolves is randomly generated by initialization, and each wolf is made to represent a different disassembly scheme.
All the dismantling processes of each layer have the preferential weight of the dismantling process, and a feasible solution is generated by means of depth-first traversal recursion according to the structured coding rule.
In this embodiment, for two disassembly steps of leaf nodes (20 21 22 23) and (16) in D of the data (14D) in table 2, the disassembly weight of each leaf node is (0.2,0.7,0.3,0.1), (0.5), and the corresponding disassembly subtasks are (0, 0) and (1), so that the disassembly subtasks are ordered according to the disassembly weights, (0, 1, 0), that is, the corresponding generated feasibility solution process decision sequence is (20 21 22 16 23).
These schemes involve different orders of disassembly, time allocation and resource allocation. Since the choice of the initial position has an important impact on the convergence and quality of the optimization, we need to initialize the wolf group position first.
The initialization of the gray wolf group position at least meets the following control conditions:
(1) The position of each gray wolf comprises the sequence of the disassembly procedure, time allocation and resource allocation information, and different disassembly schemes at least reflect the difference of at least one of the disassembly sequence, the time allocation and the resource allocation;
(2) The position of each gray wolf meets the constraints of the priority sequence diagram and the structured coding rules to ensure that the generated disassembly scheme is qualified and executable;
(3) The initialization position of the wolf is used as a starting population of a wolf optimization algorithm so as to provide a starting point for subsequent optimization;
(4) The initialization process introduces population size, initial position distribution and randomness as parameters to affect the search performance and convergence speed of the algorithm.
Assume that the search space isWei (dimension)>The parameter dimension representing the problem. Assuming the position of each gray wolfRepresentation of->Index of gray wolves,>is the gray wolf at->Positions in the individual dimensions. Grey wolf group positionThe initialization of (c) may be achieved with a random distribution. One common way is to initialize the position of each wolf with a random number generator that generates random numbers that are evenly distributed across the dimensions. Assume that the search space is at->In the individual dimensions in the range of，/>Is the lower border->Is the upper bound, then each gray wolf is at +.>The initial position in the individual dimensions can be determined by the following formula:
；
wherein,is a generation interval [0, 1]]A function of the random number is uniformly distributed therein.
Through the formula, a position can be randomly generated for each wolf in each dimension, so that the initialization of the position of the wolf group is completed. This will ensure that the gray wolf clusters are evenly distributed in the search space, providing a good starting point for the subsequent iteration of the optimization algorithm.
5. Calculating the relevance of a process disassembly scheme and an objective function, wherein the function value of the objective function represents the performance evaluation of the process disassembly scheme; the subsequent steps converge to the optimal solution or near the optimal solution in a limited time by iterating constantly.
In this embodiment, the objective function specifically refers to:
；
wherein:
representing a detach scheme->Is adapted to the degree of adaptation of (a);
representing a detach scheme->Step (2)>Disassembling time;
the weight of the fitness function for the disassembly time;
representing a detach scheme->Step (2)>Disassembling cost;
the weight of the fitness function is taken as the disassembly time.
6. The position of the wolf is updated according to the function value of the objective function.
Updating the position of the gray wolf according to the function value of the objective function specifically comprises: dividing the gray wolf group into the following groups according to the function value of the objective function、/>、/>And->Four classes, wherein->Wolf group and->Wolf group and->Wolves are guided during hunting>The position update in the wolf's search for hunting is as follows,
；
；
；
；
in the method, in the process of the invention,the iteration times; />Is the position vector of the gray wolves; />Is the location of the prey; />Is the distance between the population of individuals and the prey; />And->Are synergistic coefficient vectors; />And->Are respectively between +.>Random numbers of (a); />The value of (2) decreases linearly with the number of iterations, from 2 to 0;
in hunting, it relies mainly on leadership capabilitiesWolf group and->Wolf group and->The wolf group provides a guide for the wolf group,the wolf group searches towards the direction of the existence of the prey, and the position of the group is updated as follows:
；
；
；
in the method, in the process of the invention,、/>、/>respectively->Wolf group and->Wolf group and->The current position of the wolf group; />、/>、/>Distance of the other individuals>Wolf group and->Wolf group and->Distance of wolf group; />Is the current position of the wolf.
Process optimization for retired power battery disassembly processIt is essentially a discrete sequence optimization method, while the gray wolf algorithm is essentially a continuous real number optimization algorithm, and is also overcome to improve the information exchange capability in the wolf groupWolf group and->Wolf group and->Local convergence property of wolf group, the present embodiment proposes a pair ++in step 6>Wolf group and->Wolf group and->Wolf group local counting method, when->Wolf group and->Wolf group and->Respectively counting the wolf groups by adding 1 when the adaptability value of the wolf groups is not changed any more, and adding the wolf groups when the count exceeds 5 times>Wolf group and->Wolf group and->The internal information of the wolf group is partially randomly exchanged, and the local fitness is counted in the following way:
；
；
；
；
in the formula (i),representing an iterative process; />Representation->Counting when the adaptation value of the wolf group is unchanged, when +.>Wolf group is->The sub-fitness value is equal to->For times, the patient is treated with>Counting and adding 1; />Representation->Counting when the adaptation value of the wolf group is unchanged, when +.>Wolf group is->The sub-fitness value is equal to->For times, the patient is treated with>Counting and adding 1; />Representation->Counting when the adaptation value of the wolf group is unchanged, when +.>Wolf group is->The sub-fitness value is equal to->For times, the patient is treated with>Counting and adding 1; />Representation->Wolf group is->A secondary fitness value; />Representation->Wolf group is->A secondary fitness value; />Representation->Wolf group is->A secondary fitness value; />Representing->Wolf group, middle->Dimension and->Information exchange is carried out on the dimension; />Representing a random generation->An integer between 0 and D, where m is 3./>
7. After the position of the wolves is updated, the objective function value of each wolf is recalculated, and the wolf clusters are updated again (e.g. updated、/>、/>And->Four gray wolf group categories).
8. Repeating the steps 6 and 7 until the set maximum iteration times are reached, and outputting a global optimal solution or a near optimal solution; and optimizing the retired power battery disassembling process according to the output result to obtain an optimized retired power battery disassembling process. Optimizing the retired power battery disassembly process according to the output result comprises optimizing the disassembly step sequence of the disassembly process, the time allocation of each disassembly step and the resource allocation.
The maximum iteration number max_iter is set to limit the execution of the algorithm, so that the algorithm can be better ensured to converge to the optimal solution or approach to the optimal solution in a limited time, the disassembly cost and the disassembly time are minimized, and meanwhile, the high efficiency and the quality are ensured to meet the requirement of battery disassembly. The optimization method can be directly used in the actual battery disassembly process, and realizes resource recovery and cost saving.
In this embodiment, the position data after the initialization of the wolf clusters is randomly generated within the range of [0-1], the objective function value of the basic wolf optimization algorithm (basic GWO) running optimization is 951, the result of the algorithm after the running optimization in this embodiment (self GWO) is 942, as shown in fig. 3, compared with the basic wolf optimization algorithm, the method in this embodiment has better global convergence speed and jump-out local search capability, the basic wolf optimization algorithm falls into local convergence in 18 iterations, and the algorithm after the improvement in this embodiment enters into global optimal convergence in 7 times.
In this embodiment, the solution of the disassembly process after being optimized according to the optimal solution is shown in fig. 4.
In this embodiment, the effect of the disassembly process before and after optimization of the method in terms of the disassembly cost and the disassembly time is compared with that shown in the following table 3, and it can be seen from the table 3 that the optimization method of this embodiment can realize resource recovery and cost saving, improve efficiency and reduce the disassembly cost.
Table 3: effect comparison of the disassembly process before and after optimization on the disassembly cost and the disassembly time
In the description of the present specification, reference to the terms "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, system that includes a processing module, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of embodiments of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (10)
1. An optimization method of a retired power battery disassembly process comprises the following steps:
(1) Decomposing and disassembling process, and collecting related data information of the disassembling process;
(2) Analyzing related data information of the dismantling process, and constructing a priority sequence chart of the dismantling process of the retired power battery;
(3) Constructing a structured coding rule for the priority sequence diagram;
(4) Generating a process disassembly scheme by using a gray wolf optimization algorithm and a structured coding rule;
(5) Calculating the relevance of the process disassembly scheme and an objective function, wherein the function value of the objective function represents the performance evaluation of the process disassembly scheme;
(6) Updating the position of the gray wolf according to the function value of the objective function;
(7) After the position of the wolves is updated, calculating the objective function value of each wolf again, and updating the wolf clusters again;
(8) Repeating the steps (6) and (7) until the set maximum iteration times are reached, and outputting a global optimal solution or a near optimal solution; and optimizing the retired power battery disassembling process according to the output result to obtain an optimized retired power battery disassembling process.
2. The optimization method according to claim 1, characterized in that: in the step (1), the related data information includes manual disassembly time, manual disassembly cost, mechanical disassembly time and mechanical disassembly cost of each part of the retired power battery.
3. The optimization method according to claim 1, characterized in that: in the step (1), the decomposing and disassembling process refers to decomposing the power battery into at least one or more of the following optional operations according to the difference of the retired power battery:
(1) Unscrewing a screw on the upper cover of the battery box;
(2) Hanging an upper cover of the battery box;
(3) Taking out the heat insulation pad;
(4) Disassembling the high-voltage storage battery cover;
(5) Disassembling a plug on the contactor at the output end of the high-voltage interface;
(6) Disassembling the fixing bolts of the output end contactor and the battery shell;
(7) Disassembling the high-voltage interface output end contactor;
(8) Disassembling bolts of the baffle fixing frame;
(9) Disassembling the partition board;
(10) Disassembling a connecting sheet fixing screw;
(11) Removing the connecting sheet;
(12) Disassembling the module and the lower box body fixing bolt;
(13) Disassembling the module fixing frame;
(14) Removing the high-voltage connection harness interface module;
(15) The low-voltage wiring harness interface module is connected with the pulling-out module;
(16) Performing socket insulation treatment;
(17) Disassembling the fixing bolt of the electronic management system;
(18) Disassembling the high-voltage battery cell cover;
(19) Pulling out the battery management unit;
(20) Taking out the battery module;
(21) Unscrewing a fixing screw of an upper cover of the battery module;
(22) Taking out the upper cover of the battery module;
(23) And detecting the electric quantity of the battery cell.
4. The optimization method according to claim 1, characterized in that: in the step (3), constructing a structured coding rule for the priority sequence diagram specifically includes the following operations:
the flexible coding mode of hierarchical substitution YAML is used for showing the relation among data, T is used for showing the total number of all nodes, D is used for showing the priority order, space is used for separating node numbers, continuous numbers are used for showing node numbers, tab keys are used for showing the retraction relation, and different retraction relations show the belonging hierarchy.
5. The optimization method according to claim 1, characterized in that: in step (4), the wolf optimizing algorithm includes initializing the wolf group positions, in which a group of wolves is randomly generated by initialization, and each wolf represents a different disassembly scheme.
6. The optimization method according to claim 5, wherein: in the step (4), the initialization of the position of the wolf group at least meets the following control conditions:
(1) The position of each gray wolf comprises the sequence of the disassembly procedure, time allocation and resource allocation information, and different disassembly schemes at least reflect the difference of at least one of the disassembly sequence, the time allocation and the resource allocation;
(2) The position of each gray wolf meets the constraint of the priority sequence diagram and the structural coding rule;
(3) The initialization position of the wolves is used as the initial population of the wolf optimization algorithm;
(4) The initialization process introduces population size, initial location distribution and randomness as parameters.
7. The optimization method according to any one of claims 1-6, characterized in that: the objective function specifically refers to:
；
wherein:
representing a detach scheme->Is adapted to the degree of adaptation of (a);
representing a detach scheme->Step (2)>Disassembling time;
the weight of the fitness function for the disassembly time;
representing a detach scheme->Step (2)>Disassembling cost;
the weight of the fitness function is taken as the disassembly time.
8. The optimization method according to any one of claims 1-6, characterized in that: in the step (6), the updating the position of the wolf according to the function value of the objective function specifically includes: sequentially dividing the gray wolf group into two groups according to the function value of the objective functionIs divided into、/>、And->Four classes, wherein->Wolf group and->Wolf group and->Wolves are guided during hunting>The position update in the wolf's search for hunting is as follows,
；
；
；
；
in the method, in the process of the invention,the iteration times; />Is the position vector of the gray wolves; />Is the location of the prey; />Is the distance between the population of individuals and the prey; />And->Are synergistic coefficient vectors; />And->Are respectively between +.>Random numbers of (a); />The value of (2) decreases linearly with the number of iterations, from 2 to 0;
in hunting, it relies mainly on leadership capabilitiesWolf group and->Wolf group and->Wolf group provides guidance, and is compromised>The wolf group searches towards the direction of the existence of the prey, and the position of the group is updated as follows:
；
；
；
in the method, in the process of the invention,、/>、/>respectively->Wolf group and->Wolf group and->The current position of the wolf group; />、/>、/>Distance of the other individuals>Wolf group and->Wolf group and->Distance of wolf group; />Is the current position of the wolf.
9. The optimization method according to claim 8, characterized in that: in the step (6), when theWolf group and->Wolf group and->The adaptation value of the wolf group is not changed any more, 1 is added to the count of the wolf group, and when the count exceeds 5 times, the count is added>Wolf group and->Wolf group and->The internal information of the wolf group is partially randomly exchanged, and the local fitness is counted in the following way:
；
；
；
；
in the formula (i),representing an iterative process; />Representation->Counting when the adaptation value of the wolf group is unchanged, when +.>Wolf group is->The sub-fitness value is equal to->For times, the patient is treated with>Counting and adding 1; />Representation->Counting when the adaptation value of the wolf group is unchanged, when +.>Wolf group is->The sub-fitness value is equal to->For times, the patient is treated with>Counting and adding 1; />Representation->Counting when the adaptation value of the wolf group is unchanged, when +.>Wolf group is->The sub-fitness value is equal to->For times, the patient is treated with>Counting and adding 1; />Representation->Wolf group atA secondary fitness value; />Representation->Wolf group is->A secondary fitness value; />Representation->Wolf group is->A secondary fitness value;representing->Wolf group, middle->Dimension and->Information exchange is carried out on the dimension; />Representing a random generation->An integer between 0 and D.
10. The optimization method according to any one of claims 1-6, characterized in that: in the step (8), optimizing the retired power battery disassembly process according to the output result includes optimizing the disassembly step sequence of the disassembly process, the time allocation and the resource allocation of each disassembly step.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410173829.5A CN117728064B (en) | 2024-02-07 | 2024-02-07 | Optimization method of retired power battery disassembly process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410173829.5A CN117728064B (en) | 2024-02-07 | 2024-02-07 | Optimization method of retired power battery disassembly process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117728064A true CN117728064A (en) | 2024-03-19 |
| CN117728064B CN117728064B (en) | 2024-04-30 |
Family
ID=90200148
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410173829.5A Active CN117728064B (en) | 2024-02-07 | 2024-02-07 | Optimization method of retired power battery disassembly process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117728064B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170293849A1 (en) * | 2016-04-08 | 2017-10-12 | Sentient Technologies (Barbados) Limited | Distributed rule-based probabilistic time-series classifier |
| CN110543953A (en) * | 2019-08-30 | 2019-12-06 | 西南交通大学 | Multi-target disassembly line setting method under space constraint based on wolf colony algorithm |
| CN113743566A (en) * | 2021-08-17 | 2021-12-03 | 北京梧桐车联科技有限责任公司 | Product disassembly sequence optimization method and device, computer equipment and storage medium |
| CN114327493A (en) * | 2021-12-21 | 2022-04-12 | 中国电信股份有限公司 | Data processing method and device, electronic equipment and computer readable medium |
| CN114969978A (en) * | 2022-06-08 | 2022-08-30 | 中国人民解放军海军航空大学 | Airplane offshore platform recovery scheduling method based on improved wolf optimization algorithm |
| CN115319742A (en) * | 2022-08-08 | 2022-11-11 | 同济大学 | Flexible manufacturing unit operation scheduling method with robot material handling |
| CN116070826A (en) * | 2022-09-07 | 2023-05-05 | 中车长江运输设备集团有限公司 | Scheduling method for parallel machine of spraying operation of wagon body |
| CN116985146A (en) * | 2023-09-27 | 2023-11-03 | 武汉理工大学 | Robot parallel disassembly planning method for retired electronic products |
| CN116992758A (en) * | 2023-07-17 | 2023-11-03 | 江苏科技大学 | Complex mechanical intelligent assembly method based on machine learning |
-
2024
- 2024-02-07 CN CN202410173829.5A patent/CN117728064B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170293849A1 (en) * | 2016-04-08 | 2017-10-12 | Sentient Technologies (Barbados) Limited | Distributed rule-based probabilistic time-series classifier |
| CN110543953A (en) * | 2019-08-30 | 2019-12-06 | 西南交通大学 | Multi-target disassembly line setting method under space constraint based on wolf colony algorithm |
| CN113743566A (en) * | 2021-08-17 | 2021-12-03 | 北京梧桐车联科技有限责任公司 | Product disassembly sequence optimization method and device, computer equipment and storage medium |
| CN114327493A (en) * | 2021-12-21 | 2022-04-12 | 中国电信股份有限公司 | Data processing method and device, electronic equipment and computer readable medium |
| CN114969978A (en) * | 2022-06-08 | 2022-08-30 | 中国人民解放军海军航空大学 | Airplane offshore platform recovery scheduling method based on improved wolf optimization algorithm |
| CN115319742A (en) * | 2022-08-08 | 2022-11-11 | 同济大学 | Flexible manufacturing unit operation scheduling method with robot material handling |
| CN116070826A (en) * | 2022-09-07 | 2023-05-05 | 中车长江运输设备集团有限公司 | Scheduling method for parallel machine of spraying operation of wagon body |
| CN116992758A (en) * | 2023-07-17 | 2023-11-03 | 江苏科技大学 | Complex mechanical intelligent assembly method based on machine learning |
| CN116985146A (en) * | 2023-09-27 | 2023-11-03 | 武汉理工大学 | Robot parallel disassembly planning method for retired electronic products |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117728064B (en) | 2024-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yu et al. | Surrogate-assisted hierarchical particle swarm optimization | |
| Zhang et al. | Evolutionary computation meets machine learning: A survey | |
| Li et al. | Development and investigation of efficient artificial bee colony algorithm for numerical function optimization | |
| Tenne et al. | Computational intelligence in expensive optimization problems | |
| CN112131733B (en) | Distributed power supply planning method considering influence of charging load of electric automobile | |
| Nguyen et al. | Filter based backward elimination in wrapper based PSO for feature selection in classification | |
| Liu et al. | Survey on graph neural network acceleration: An algorithmic perspective | |
| Carvalho | A cooperative coevolutionary genetic algorithm for learning bayesian network structures | |
| Cheng | Nature inspired optimization of large problems | |
| CN109241298A (en) | Semantic data stores dispatching method | |
| CN111461284A (en) | Data discretization method, device, equipment and medium | |
| Dershowitz et al. | A formalization and proof of the Extended Church-Turing Thesis | |
| CN117728064B (en) | Optimization method of retired power battery disassembly process | |
| Gero | Adaptive systems in designing: New analogies from genetics and developmental biology | |
| CN108960511A (en) | A kind of wind speed forecasting method and relevant apparatus | |
| Kuliev et al. | Problem-oriented knowledge processing on the basis of hybrid approach | |
| Arfeen et al. | A niche particle swarm optimization-Perks and perspectives | |
| CN114676042A (en) | Electric power Internet of things test data generation method and device | |
| CN115345303A (en) | Convolutional neural network weight tuning method, device, storage medium and electronic equipment | |
| CN114880929A (en) | Deep reinforcement learning-based multi-energy flow optimization intelligent simulation method and system | |
| Bacardit et al. | A mixed discrete-continuous attribute list representation for large scale classification domains | |
| Yang et al. | Optimization of classification algorithm based on gene expression programming | |
| Le Martelot et al. | A systemic computation platform for the modelling and analysis of processes with natural characteristics | |
| Sheri et al. | Learning-assisted evolutionary search for scalable function optimization: LEM (ID3) | |
| CN110288150A (en) | Wind speed forecasting method, terminal device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |