A dynamic disassembly path decision method for retired batteries based on deep search

Abstract

The present invention relates to the technical field of power battery disassembly and recycling, and discloses a method for dynamically determining the disassembly path of retired batteries based on depth search. A disassembly path is constructed based on the battery disassembly process steps, and a graph matrix encoding is constructed according to the disassembly path; the machine state is obtained, and the machine state and the graph matrix encoding are input into the pre-constructed reinforcement learning model to obtain the disassembly weight; the first optimized disassembly path is obtained by combining the disassembly weight with depth search, and disassembly is carried out according to the first optimized disassembly path, and battery information is obtained. According to the battery pack information, the second optimized disassembly path is obtained by combining the reinforcement learning model and depth search again, and the machine is allocated according to the second optimized disassembly path to complete the disassembly of the retired battery, solving the problem that the existing disassembly path cannot be adjusted in real time.

Description

Technical Field

[0001] The present invention relates to the technical field of power battery disassembly and recycling, and particularly to a method for dynamically determining the disassembly path of retired batteries based on depth search. Background Art

[0002] With the rapid development of the global electric vehicle industry, the production and usage of power batteries have increased sharply, and the problem of disassembly and recycling of retired batteries has become increasingly prominent. How to efficiently and safely disassemble retired batteries and maximize the recovery of valuable materials has become a technical problem that urgently needs to be solved in the battery recycling industry.

[0003] Currently, the disassembly process of power batteries mainly relies on traditional path planning and scheduling methods. Although these methods perform well in some fixed scenarios, they have obvious deficiencies in dealing with the complexity and diversity of retired power batteries.

[0004] Existing technical methods include static path planning methods, disassembly path selection methods based on optimization algorithms, frequent pattern mining methods, and power battery disassembly decision-making methods based on scenario matching. Although the foregoing technologies have solved some problems in the disassembly of retired batteries, they still have obvious limitations, such as limited graph matrix expression ability, insufficient complex path selection ability, insufficient ability to handle battery structure diversity, weak real-time adjustment ability, etc. In dealing with complex paths, dynamic adjustment, and real-time optimization, they limit the efficiency and resource utilization rate of power battery disassembly. And the market's demand for efficient and intelligent disassembly technologies is increasing day by day, and traditional static scheduling methods and simple path planning can no longer meet the requirements for real-time adjustment and complex path selection in the disassembly process. In order to improve the disassembly efficiency, reduce the disassembly cost, and maximize the resource recovery rate, the market needs a disassembly method that can flexibly adjust and intelligently select paths in a complex environment. Summary of the Invention

[0005] The present invention provides a method for dynamically determining the disassembly path of retired batteries based on depth search to solve the problem that the existing disassembly path cannot be adjusted in real time.

[0006] To achieve the above object, the present invention is realized through the following technical solutions:

[0007] The present invention provides a method for dynamically determining the disassembly path of retired batteries based on depth search, including the following steps:

[0008] Step 1: Construct a disassembly path based on the battery disassembly process steps, and construct a graph matrix encoding according to the disassembly path;

[0009] Step 2: Obtain the machine state, and input the machine state and the graph matrix encoding into the pre-constructed reinforcement learning model to obtain the disassembly weight;

[0010] Step 3: Obtain the first optimized disassembly path by combining the disassembly weights with depth search, and perform disassembly according to the first optimized disassembly path;

[0011] Step 4: After obtaining the battery pack information of the retired battery and inputting it into the reinforcement learning model again to obtain the disassembly weights, then combine depth search to obtain the second optimized disassembly path, and allocate machines to complete the disassembly of the retired battery according to the second optimized disassembly path;

[0012] Both the first optimized disassembly path and the second optimized disassembly path are determined in the following manner: Traverse the disassembly path under predetermined constraints according to the disassembly weights combined with depth search to calculate the statistical value, and determine the first optimized disassembly path based on the statistical value combined with the battery pack detection information.

[0013] Further, constructing the disassembly path based on the battery disassembly process steps includes: constructing the disassembly path according to the battery disassembly process steps combined with the first predetermined rule;

[0014] The first predetermined rule includes: numbering the main processes and key nodes of the battery disassembly process steps, setting the nodes that need to meet the multi-process condition paths as AND nodes, and setting the path nodes for whether to perform disassembly after battery performance detection as OR nodes.

[0015] Further, constructing the graph matrix encoding according to the disassembly path includes: using the numbers of the nodes of the disassembly path as the rows and columns of the matrix encoding, and filling the rows and columns of the matrix encoding based on the node relationships of the disassembly path combined with the second predetermined rule;

[0016] The second predetermined rule includes: defining 1 for the node relationships that are AND nodes or connection relationships, and defining 2 for the node relationships that are OR nodes.

[0017] Further, constructing the graph matrix encoding according to the disassembly path: constructing an encoding file according to the disassembly path, and constructing the graph matrix encoding based on the encoding file;

[0018] The encoding file includes: an identifier and several arrays representing the edge information of the disassembly path;

[0019] The identifier is set based on the node relationship, and the array is set based on the node number.

[0020] Further, the reinforcement learning model constructs an incentive function based on the average completion time, process waiting time, delay penalty, assembly and disassembly time, and station processing capacity;

[0021] The incentive function is represented by the following formula:

[0022] ;

[0023] Among them, represents the activation function, represents the average completion time, represents the process waiting time, represents the delay penalty, represents the assembly and disassembly time, represents the station processing capacity, are the weight coefficients based on the above-mentioned parameters respectively;

[0024] The average completion time is expressed by the following formula:

[0025] ;

[0026] Among them, represents the time required to complete the disassembly of the th battery pack, represents the maximum allowed completion time;

[0027] The process waiting time is expressed by the following formula:

[0028] ;

[0029] Among them, represents the process waiting time for the disassembly of the th battery pack, represents the maximum allowed waiting time;

[0030] The delay penalty is expressed by the following formula:

[0031] ;

[0032] Among them, represents the total delay time for disassembling the battery pack;

[0033] The assembly and disassembly time is expressed by the following formula:

[0034] ;

[0035] Among them, represents the time required to disassemble the battery pack from the machine, represents the time required to assemble the battery pack onto the machine;

[0036] The station processing capacity is expressed by the following formula:

[0037] ;

[0038] Among them, Represents the maximum processing capacity of the work station, i.e., the time required to process one battery pack. Represents the th battery pack at the th process by the time required for the machine to process.

[0039] Furthermore, the predetermined constraints are set based on the status of the machine and the battery, the process sequence, single process, assembly and disassembly time, and the inspection work station nodes.

[0040] The status constraints of the machine and the battery are represented by the following formula:

[0041] ;

[0042] Where represents that all machines and batteries can be used at time and are not bound to any machine;

[0043] The process sequence constraints are represented by the following formula:

[0044] ;

[0045] Where represents the time required for the th battery pack at the th process;

[0046] represents the time required for the th battery pack at the th process;

[0047] represents the time required for the th battery pack at the th process by the machine to process;

[0048] represents the time required to disassemble the battery pack from the machine, represents the time required to assemble the battery pack onto the machine;

[0049] The single process constraints are represented by the following formula:

[0050] ;

[0051] Where represents the total number of processes for the th battery pack, represents the number of machines in the workshop;

[0052] Indicates that at moment, the th battery pack's th process is processed by machine, then , otherwise it is 0;

[0053] ;

[0054] The assembly and disassembly time constraint is expressed by the following formula:

[0055] ;

[0056] Among them, At moment, the th battery pack's th process is processed by machine, then , otherwise it is 0;

[0057] The inspection station node constraint is expressed by the following formula:

[0058] ;

[0059] Among them, Represents the processing capacity of the inspection station, that is, the number of batteries that can be inspected per unit time.

[0060] Furthermore, the statistical value is calculated by the following formula:

[0061] ;

[0062] Among them, Indicates that when traversing to node, the statistical value of the th branch and the th node, Represents the total sum of all possible out-degrees triggered from this node, Represents the in-degree of the th branch and the th node, Represents the out-degree of the th branch and the th node, Represents the in-degree of the th branch and the th node.

[0063] Furthermore, during the process of calculating the statistical value, if the statistical value of this node is 0, then this node is defined as a JOIN node.

[0064] Further, the reinforcement learning model is a multi-graph convolutional network, which is constructed according to MGCN units that extract the connectivity and topological structure between different parts of retired batteries;

[0065] The MGCN unit is constructed based on Conv2d k1 blocks and Conv2d k3 blocks.

[0066] Further, the MGCN unit is a multi-source information fusion feature extraction unit with three inputs and one output, and the MGCN unit includes an input layer, a fusion extraction layer, a weighting layer, and an output layer;

[0067] The input layer includes three Conv2d k1 blocks that respectively extract local features of three inputs;

[0068] The fusion extraction layer includes a fusion block and a Conv2d k3 block that extracts spatial relationships;

[0069] The weighting layer includes an SE block;

[0070] The output layer includes a Conv2d k1 block and an output block that perform linear transformation and dimensionality compression.

[0071] Further, the construction of the multi-graph convolutional network according to MGCN units that extract the connectivity and topological structure between different parts of retired batteries includes: constructing an action module and a value module according to the MGCN unit, and constructing a multi-graph convolutional network based on the action module and the value module;

[0072] The action module extracts multi-scale features based on the machine state and the graph matrix encoding to obtain disassembly weights;

[0073] The value module obtains the multi-scale features extracted by the action module and optimizes the disassembly weights in combination with an activation function.

[0074] Further, the action module sequentially includes an MGCN unit for extracting machine state and graph matrix encoding features, a detail extraction Conv2d k3 block for further extracting surface and internal detail features of the machine state and the graph matrix encoding, an MGCN unit for strengthening the machine state and graph matrix encoding features, a detail strengthening Conv2d k3 block for further strengthening surface and internal detail features of the machine state and the graph matrix encoding, and a Conv2d k1 block for compressing and integrating all the strengthened features.

[0075] Further, the value module is respectively connected to the detail extraction Conv2d k3 block and the detail strengthening Conv2d k3 block of the action module, and integrates and evaluates the obtained multi-scale features;

[0076] The value module includes an acquisition unit for acquiring multi-scale features, an integration unit for integrating the multi-scale features, and an evaluation unit for evaluating the integrated multi-scale features;

[0077] The acquisition unit includes a first channel, a second channel, and a Conv2d k1 block. Both the first channel and the second channel are composed of two Conv2d k3 blocks and are connected to the action module and the integration module. The Conv2d k1 block is arranged between the first Conv2d k3 block in the connection direction of the first channel, the second channel and the action module;

[0078] The integration unit includes 1 Conv2d k1 block;

[0079] The evaluation unit includes 1 fully connected block and an MGCN unit.

[0080] Beneficial effects:

[0081] A method for making a dynamic disassembly path decision for retired batteries based on depth search provided by the present invention realizes dynamic search by introducing depth search and a reinforcement learning model. Compared with traditional static scheduling methods, it has better real-time performance and self-adaptability. In this process, secondary path planning is carried out according to the battery pack information of the retired batteries obtained, and the disassembly path is planned better based on the battery types, realizing dynamic response to complex data and more efficient realization of the circuit disassembly path planning.

[0082] Furthermore, the incentive function set based on the industrial environment takes into account the detection result processing, resource utilization optimization, real-time response, self-adaptability, and bottleneck effect. This design not only learns and optimizes in a better direction but also can quickly adjust the strategy in a complex environment, reflecting the high efficiency and flexibility that existing scheduling methods do not have.

[0083] Furthermore, by introducing an MGCN unit, the multi-graph convolutional network enhances the ability to capture the complex relationships and interactions between different parts of the power battery. Traditional methods may not be able to effectively integrate multi-scale information, while the present invention optimizes the multi-scale feature extraction path through the MGCN unit and can accurately capture different levels of details of the battery components during the disassembly process. Description of the drawings

[0084] Figure 1 It is a disassembly path flow chart constructed based on the disassembly processes of three different batteries in the method for making a dynamic disassembly path decision for retired batteries according to the embodiment of the present invention;

[0085] Figure 2 It is a schematic diagram of the graph matrix encoding constructed according to the embodiment of the present invention;

[0086] Figure 3Schematic diagram of constructing an encoding file based on the disassembly path according to an embodiment of the present invention;

[0087] Figure 4 Flow chart of the disassembly process steps of three different batteries according to an embodiment of the present invention; optimized flow chart of the disassembly process steps

[0088] Figure 5 Schematic diagram of the network structure of the multi-graph convolutional network according to an embodiment of the present invention, where A represents the first optimized disassembly path or the second optimized disassembly path;

[0089] Figure 6 Schematic diagram of the network structure of the MGCN unit in the multi-graph convolutional network according to an embodiment of the present invention. Detailed implementation manners

[0090] The technical solutions of the present invention will be described clearly and completely below. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0091] Unless otherwise defined, the technical terms or scientific terms used in the present invention shall have the ordinary meanings understood by those of ordinary skill in the art in the field to which the present invention belongs. The "first", "second" and similar terms used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, terms such as "a" or "one" do not indicate a quantity limitation, but indicate that there is at least one. "Connection" or "connected" and similar terms are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Upper", "lower", "left", "right", etc. are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship also changes accordingly.

[0092] An embodiment of the present invention provides a method for dynamically determining the disassembly path of retired batteries based on depth search, including the following steps:

[0093] Step 1: Construct a disassembly path based on the battery disassembly process steps, and construct a graph matrix encoding according to the disassembly path;

[0094] Please refer to Figure 1 , in this embodiment, according to the disassembly process steps of three different batteries, combined with the first predetermined rule, disassembly paths are constructed to obtain the 3 disassembly path flow charts shown in Figure 1 .

[0095] As shown in Figure 2 , in this embodiment, directly from Figure 1Construct a coding matrix for the disassembly path of the middle battery 1. Based on the numbers of the nodes in the disassembly path as the rows and columns of the matrix coding, and fill the rows and columns of the matrix coding in combination with the second predetermined rule based on the node relationships in the disassembly path. The construction of the matrix coding more effectively expresses the OR nodes, improving the decision-making of node selection and the efficiency of the disassembly path.

[0096] As Figure 3 shown, in other embodiments, a coding file can also be constructed based on the disassembly path of the above-mentioned battery 1, and then a graph matrix coding is further constructed based on the coding file. During the process of constructing the coding file, identifiers are set based on the node relationships, and arrays are set based on the node numbers. For example, use "#OR" as the identifier in the first line of the file, and then connect the node numbers "3 7", indicating that the connection relationship between node 3 and node 7 is an OR node. Each group of arrays recorded in the coding file is the edge information of the disassembly path. After constructing the coding file, the matrix coding is constructed according to the identifiers and data in the coding file.

[0097] Among them, the first predetermined rule includes: numbering the main processes and key nodes of the battery disassembly process steps, setting the nodes that need to meet the multi-process condition paths as AND nodes, and setting the path nodes of whether to disassemble after battery performance detection as OR nodes.

[0098] The second predetermined rule includes that if the node relationship is an AND node or a connection relationship, it is defined as 1, and if the node relationship is an OR node, it is defined as 2;

[0099] Step 2: Obtain the machine state, and input the machine state and the graph matrix coding into the constructed reinforcement learning model to obtain the disassembly weight;

[0100] Among them, the reinforcement learning model is a multi-graph convolutional network. The multi-graph convolutional network constructs an incentive function based on the average completion time, process waiting time, delay penalty, assembly and disassembly time, and station processing capacity. The machine state represents the number of machines and the time required for the machines to execute their corresponding processes;

[0101] Specifically, the incentive function is expressed by the following formula:

[0102] ;

[0103] Among them, represents the incentive function, represents the average completion time, represents the process waiting time, represents the delay penalty, represents the assembly and disassembly time, represents the station processing capacity, respectively represent the weight coefficients based on the foregoing parameters. In this embodiment, the weight coefficients of all parameters are 0.2;

[0104] The average completion time is expressed by the following formula:

[0105] ;

[0106] where represents the time required to complete the disassembly of the th battery pack, represents the maximum allowed completion time;

[0107] The process waiting time is expressed by the following formula:

[0108] ;

[0109] where represents the process waiting time for the th battery pack to be disassembled, represents the maximum allowed waiting time;

[0110] The delay penalty is expressed by the following formula:

[0111] ;

[0112] where represents the total delay time of disassembling the battery;

[0113] The assembly and disassembly time is expressed by the following formula:

[0114] ;

[0115] where represents the time required to disassemble the battery pack from the machine, represents the time required to assemble the battery pack onto the machine;

[0116] The station processing capacity is expressed by the following formula:

[0117] ;

[0118] where represents the maximum station processing capacity, represents the th battery pack at the th process by the machine processing time required, represents the total number of battery packs to be disassembled.

[0119] Step 3: Obtain the first optimized disassembly path according to the disassembly weight in combination with depth search, and perform disassembly according to the first optimized disassembly path;

[0120] Specifically, search and traverse the disassembly path under a predetermined constraint according to the disassembly weight in combination with the depth, calculate the statistical value, and determine the first optimized disassembly path based on the statistical value;

[0121] The predetermined constraint is set based on the states of the machine and the battery, the process sequence, the single process, the assembly and disassembly time, and the inspection station nodes;

[0122] The state constraint of the machine and the battery is expressed by the following formula:

[0123] ;

[0124] Among them, means that all machines and batteries can be used at time and are not bound to any machine;

[0125] The process sequence constraint is expressed by the following formula:

[0126] ;

[0127] Among them, represents the time required for the th battery pack in the th process;

[0128] represents the time required for the th battery pack in the th process;

[0129] represents the time required for the th battery pack to be processed by the machine in the th process;

[0130] represents the time required for the battery pack to be disassembled from the machine, represents the time required for the battery pack to be assembled onto the machine, and this formula means that the processes of the battery are executed in sequence;

[0131] The single process constraint is expressed by the following formula:

[0132] ;

[0133] Among them, represents the total number of processes of the th battery pack, Represents the number of machines in the workshop;

[0134] Represents at time , the th battery pack's th process is processed by machine, then , otherwise it is 0;

[0135] This formula indicates that a battery can only undergo one process at any given time;

[0136] ;

[0137] This formula indicates that each machine can only process one process at any given time;

[0138] The assembly and disassembly time constraint is expressed by the following formula:

[0139] ;

[0140] Among them, At time, if the th battery pack's th process is processed by machine, then , otherwise it is 0;

[0141] This formula indicates that time constraints must be considered for each battery during assembly and disassembly;

[0142] The inspection station node constraint is expressed by the following formula:

[0143] ;

[0144] Among them, Represents the total number of retired batteries, Represents the processing capacity of the inspection station, that is, the number of batteries that can be inspected per unit time; this formula indicates that the modules and cells of each battery are the bottleneck in the inspection station process, and its processing capacity needs to be considered first.

[0145] Step 4: After obtaining the disassembly weights by inputting the battery pack information of the retired batteries into the reinforcement learning model again, combine it with depth search to obtain the second optimized disassembly path, and allocate machines according to the second optimized disassembly path to complete the disassembly of the retired batteries.

[0146] Please refer to Figure 4, after determining the first optimized disassembly path based on the above constraints, obtain the optimized disassembly weights according to the module information and cell information in combination with the reinforcement learning model. Based on the optimized disassembly weights, traverse the first optimized disassembly path under the predetermined constraints in combination with depth search to calculate the statistical value, and determine the second optimized disassembly path based on the statistical value in combination with the battery pack detection information.

[0147] Among them, the battery information includes module information and cell information, and the battery pack detection information includes the quality of the module and the cell, that is, the disassembly path is determined based on the statistical value in combination with the module and cell disassembled from the battery pack.

[0148] The statistical value is calculated by the following formula:

[0149] ;

[0150] Among them, represents the statistical value of the th node in the th branch when traversing to the th node, represents the total sum of all possible out-degrees triggered from this node, represents the in-degree of the th node in the th branch, represents the out-degree of the th node in the th branch, represents the in-degree of the th node in the th branch.

[0151] Please refer to Figure 1 , for the 6th node of Battery 1, the out-degree of the 6th node is -3. When there are a total of nodes in the th branch, when , the branch statistics are the 9th and 10th nodes. Among them, the sum of the in-degree and out-degree of the 9th node is equal to 0, while the in-degree of the 10th node is 1. At this time, the statistical value is -2. When

[0152] In the process of calculating the statistical value, if the statistical value of this node is 0, then define this node as a JOIN node. The JOIN node more intuitively represents the convergence point of the nodes, which is convenient for operators to understand and operate.

[0153] In this embodiment, please refer to Figures 5 - 6, the multi-graph convolutional network is further improved as follows. The multi-graph convolutional network is constructed based on the MGCN units that extract the connectivity and topological structure between different parts of the retired battery. Specifically, an action module and a value module are constructed according to the MGCN units, and the multi-graph convolutional network is constructed based on the action module and the value module.

[0154] Among them, the action module sequentially includes MGCN units for extracting machine state and graph matrix encoding features, a detail extraction Conv2d k3 block for further extracting the surface and internal detail features of the machine state and graph matrix encoding, MGCN units for strengthening the machine state and graph matrix encoding features, a detail strengthening Conv2d k3 block for further strengthening the surface and internal detail features of the machine state and graph matrix encoding, and a Conv2d k1 block for compressing and integrating all the strengthened features.

[0155] The value module is connected to the detail extraction Conv2d k3 block and the detail strengthening Conv2d k3 block of the action module respectively, and integrates and evaluates the obtained multi-scale features;

[0156] The value module includes an acquisition unit for acquiring multi-scale features, an integration unit for integrating the multi-scale features, and an evaluation unit for evaluating the integrated multi-scale features;

[0157] The acquisition unit includes a first channel, a second channel, and a Conv2d k1 block. Both the first channel and the second channel are composed of two Conv2d k3 blocks and are connected to the action module and the integration module. The Conv2d k1 block is set between the first Conv2d k3 block in the connection direction of the first channel, the second channel and the action module;

[0158] The integration unit includes 1 Conv2d k1 block;

[0159] The evaluation unit includes 1 fully connected block and an MGCN unit.

[0160] The MGCN unit is constructed based on the Conv2d k1 block and the Conv2d k3 block.

[0161] Among them, the MGCN unit is a multi-source information fusion feature extraction unit with three inputs and one output. The MGCN unit includes an input layer, a fusion extraction layer, a weighting layer, and an output layer;

[0162] The input layer includes three Conv2d k1 blocks that respectively extract the local features of three inputs;

[0163] The fusion extraction layer includes a fusion block and a Conv2d k3 block for extracting spatial relationships;

[0164] The weighting layer includes an SE block;

[0165] The output layer includes a Conv2d k1 block for linear transformation and dimension compression and an output block.

[0166] Finally, in this embodiment, a multi-graph convolutional network in the reinforcement learning model is combined with a method for dynamically disassembling path decision of retired batteries based on depth search in the present invention to make decisions on the disassembly path with manual scheduling, genetic algorithm, and particle swarm optimization algorithm. For the specific decision results, please refer to Table 1;

[0167] Table 1: Average Completion Time, Process Waiting Time, Delay Penalty, and Total Objective

[0168]

[0169] As can be seen from Table 1, the multi-graph convolutional network is superior to the traditional manual scheduling, genetic algorithm, and particle swarm optimization algorithm in the dynamic scheduling of retired battery disassembly. In terms of indicators such as average completion time, process waiting time, and delay penalty, the multi-graph convolutional network using the method for dynamically disassembling path decision of retired batteries based on depth search in the present invention shows the most prominent performance. In particular, the average completion time is reduced to 3287 seconds, the process waiting time is reduced to 482 seconds, the delay penalty is reduced to 65 seconds, and the comprehensive total objective value reaches 3834 seconds. Each value is the lowest among all methods, clearly demonstrating that the method of the present invention has excellent real-time scheduling optimization ability.

[0170] Compared with the genetic algorithm and particle swarm optimization algorithm for static optimization, the multi-graph convolutional network using the method for dynamically disassembling path decision of retired batteries based on depth search in the present invention can adjust the priority at each moment during the disassembly process by dynamically monitoring the states of battery modules and cells, and flexibly respond to changing working conditions. This dynamic and adaptive scheduling method significantly improves the resource utilization rate and on-time completion rate, making the disassembly process more efficient and smooth, and demonstrating its superiority in complex and changing environments.

[0171] The preferred specific embodiments of the present invention have been described in detail above. It should be understood that those of ordinary skill in the art can make many modifications and variations based on the concept of the present invention without creative work. Therefore, all technical solutions that can be obtained by those skilled in the art in the technical field of the present invention based on the concept of the present invention through logical analysis, reasoning, or limited experiments on the basis of the prior art should be within the protection scope determined by the claims.

Claims

1. A dynamic disassembly path decision method for retired batteries based on deep search, characterized in that: The steps include: Step 1: Construct a disassembly path based on the battery disassembly process steps, and construct a graph matrix encoding according to the disassembly path; The constructing a disassembly path based on the battery disassembly process steps includes: constructing a disassembly path according to the battery disassembly process steps in combination with a first predetermined rule; The first predetermined rule includes: numbering the main processes and key nodes of the battery disassembly process steps, setting the nodes of the paths that need to meet multiple process conditions at the same time as AND nodes, and setting the path nodes of whether to disassemble the battery after performance testing as OR nodes; Step 2: Obtain the machine state, and input the machine state and graph matrix encoding into the built reinforcement learning model to obtain the disassembly weight; Step 3: Obtain a first optimized disassembly path according to the disassembly weight and in-depth search, and perform disassembly according to the first optimized disassembly path; Step 4: After inputting the obtained battery pack information of the retired battery into the reinforcement learning model again to obtain the disassembly weight, a second optimized disassembly path is obtained in combination with the deep search, and machines are allocated according to the second optimized disassembly path to complete the disassembly of the retired battery; The first optimized disassembly path and the second optimized disassembly path are both determined by: calculating statistical values ​​by traversing the disassembly path under predetermined constraints according to the disassembly weight in combination with the depth search, and determining the first optimized disassembly path and the second optimized disassembly path based on the statistical values ​​in combination with the battery pack detection information; The statistical value is calculated by the following formula: ； in, Indicates traversal to At node time, The first branch The statistics of nodes, Indicates that from The sum of all possible out-degrees triggered by the node, Indicates The first branch The in-degree of a node, Indicates The first branch The out-degree of a node, Indicates The first branch The in-degree of a node.

2. The method for dynamic disassembly path decision of retired batteries based on deep search according to claim 1 is characterized in that: The constructing the graph matrix code according to the disassembly path includes: using the numbers of the nodes of the disassembly path as the rows and columns of the matrix code, and filling the rows and columns of the matrix code based on the node relationship of the disassembly path in combination with a second predetermined rule; The second predetermined rule includes: if the node relationship is an AND node or a connection relationship, it is defined as 1; if the node relationship is an OR node, it is defined as 2.

3. The method for dynamic disassembly path decision of retired batteries based on deep search according to claim 1 is characterized in that: The constructing of the graph matrix code according to the disassembly path: constructing a code file according to the disassembly path, and constructing the graph matrix code based on the code file; The encoding file includes: an identifier and an array of several groups of side information representing the disassembly path; The identifier is set based on the node relationship, and the array is set based on the node number.

4. The method for dynamic disassembly path decision of retired batteries based on deep search according to any one of claims 1 to 3, characterized in that: The reinforcement learning model constructs an incentive function based on average completion time, process waiting time, delay penalty, assembly and disassembly time, and station processing capacity; The activation function is expressed by the following formula: ； in, represents the activation function, represents the average completion time, Indicates the process waiting time, represents the delay penalty, Indicates assembly and disassembly time, Indicates the processing capacity of the workstation. are the weight coefficients corresponding to each parameter; The average completion time is expressed by the following formula: ； in, Indicates The time required to complete the disassembly of a battery pack, Indicates the maximum allowed completion time; The process waiting time is expressed by the following formula: ； in, Indicates The waiting time for the disassembly process of each battery pack, Indicates the maximum allowed waiting time; The delay penalty is expressed by the following formula: ； in, Indicates the total delay time for disassembling the battery pack; The assembly and disassembly time is expressed by the following formula: ； in, Indicates the battery pack from The time required for disassembly on the machine, Indicates that the battery pack is delivered to The time required by the machine; The processing capacity of the workstation is expressed by the following formula: ； in, Indicates the maximum processing capacity of the station, that is, the time required to process a battery pack. Indicates The battery pack is in The process is The time required for machine processing, Indicates the total number of battery packs to be disassembled.

5. The method for dynamic disassembly path decision of retired batteries based on deep search according to claim 4 is characterized in that: The predetermined constraints are based on the status of the machine and the battery, the process sequence, the single process, the assembly and disassembly time, and the detection station node setting; The state constraints of the machine and the battery are expressed by the following formula: ； in, Indicates that all devices and battery packs are at the time It can be used at any time and is not bound to any machine; The process sequence constraint is expressed by the following formula: ； in, Indicates The battery pack is in The time required for each process; Indicates The battery pack is in The time required for each process; Indicates The battery pack is in The process is The time required for machine processing; Indicates the battery pack from The time required to disassemble the machine, Indicates that the battery pack is delivered to The time required on the machine; The single process constraint is expressed by the following formula: ； in, Indicates The total number of processes for a battery pack, Indicates the number of machines in the workshop; Indicated in Moment, Battery Pack The process is Machine processing, , otherwise 0; ； The assembly and disassembly time constraint is expressed by the following formula: ； in, exist Moment, Battery Pack The process is Machine processing, , otherwise 0; The detection station node constraint is expressed by the following formula: ； in, Indicates the processing capacity of the inspection station, that is, the number of batteries that can be inspected per unit time.

6. The method for dynamic disassembly path decision of retired batteries based on deep search according to claim 1, characterized in that: During the process of calculating the statistical value, if the statistical value of the node is 0, the node is defined as a JOIN node.

7. The method for dynamic disassembly path decision of retired batteries based on deep search according to any one of claims 1 to 3, characterized in that: The reinforcement learning model is a multi-graph convolutional network, which is constructed based on MGCN units that extract connectivity and topological structures between different parts of retired batteries; The MGCN unit is constructed based on Conv2d k1 blocks and Conv2d k3 blocks.

8. The method for dynamic disassembly path decision of retired batteries based on deep search according to claim 7 is characterized in that: The MGCN unit is a multi-source information fusion feature extraction unit with three inputs and one output, and the MGCN unit includes an input layer, a fusion extraction layer, a weighted layer and an output layer; The input layer includes three Conv2d k1 blocks for extracting local features of three types of inputs respectively; The fusion extraction layer includes a fusion block and a Conv2d k3 block for extracting spatial relations; The weighted layer comprises a SE block; The output layer includes a Conv2d k1 block and an output block for performing linear transformation and dimensionality compression.

9. The method for dynamic disassembly path decision of retired batteries based on deep search according to claim 7, characterized in that: The multi-graph convolutional network is constructed according to the MGCN unit for extracting connectivity and topological structures between different parts of the retired battery, including: constructing an action module and a value module according to the MGCN unit, and constructing a multi-graph convolutional network based on the action module and the value module; The action module extracts multi-scale features based on machine state and graph matrix encoding to obtain disassembly weights; The value module obtains the multi-scale features extracted by the action module and optimizes the disassembly weights in combination with the incentive function.

10. The method for dynamic disassembly path decision of retired batteries based on deep search according to claim 9, characterized in that: The action module sequentially includes an MGCN unit for extracting machine state and graph matrix encoding features, a detail extraction Conv2d k3 block for further extracting machine state and graph matrix encoding surface and internal detail features, an MGCN unit for strengthening machine state and graph matrix encoding features, a detail strengthening Conv2d k3 block for further strengthening machine state and graph matrix encoding surface and internal detail features, and a Conv2d k1 block for compressing and integrating all strengthened features.

11. The method for dynamic disassembly path decision of retired batteries based on deep search according to claim 10, characterized in that: The value module is connected to the detail extraction Conv2d k3 block and the detail enhancement Conv2d k3 block of the action module respectively, and integrates and evaluates the acquired multi-scale features; The value module includes an acquisition unit for acquiring multi-scale features, an integration unit for integrating the multi-scale features, and an evaluation unit for evaluating the integrated multi-scale features; The acquisition unit includes a first channel, a second channel and a Conv2d k1 block, the first channel and the second channel are each composed of two Conv2d k3 blocks, and are both connected to the action module and the integration module, and the Conv2d k1 block is arranged between the first Conv2d k3 block in the direction where the first channel, the second channel and the action module are connected; The integration unit includes 1 Conv2d k1 block; The evaluation unit includes 1 fully connected block and one MGCN unit.

Images