A method and device for predicting the state of health of a retired power battery and an electronic device

Abstract

The present application relates to a kind of decommissioned power battery health state prediction method, device and electronic equipment, belong to battery health state evaluation technical field, wherein, the method includes: the battery parameter obtained is classified, obtains multiple different grades of battery parameters;With battery number and battery parameter grade value as node, with the name of battery parameter as edge, construct the graph network structure with time stamp;And according to graph network structure, construct the battery state feature matrix based on time;The battery state feature matrix based on time is input into the battery health state estimation model trained perfectly, obtains the health state of decommissioned power battery reorganization utilization.The present application solves the technical problem that the change rule of capacity, voltage, internal resistance and other parameters of decommissioned power battery affected by battery inconsistency in the prior art is difficult to capture, leading to the difficulty of accurate estimation of health state.

Description

Technical Field

[0001] The present invention relates to the technical field of battery health status assessment, and in particular to a method, device and electronic equipment for predicting the health status of retired power batteries. Background Art

[0002] There are two ways to reuse retired power batteries: direct utilization and reorganization. Reorganization means that retired power batteries are disassembled and reassembled according to different consistency and capacity levels to form reorganized batteries for reuse. However, since the consistency of retired power batteries is far worse than that of new batteries, the problem of poor consistency is magnified again during the battery reorganization process. The battery's own battery management system and the new battery management system have large deviations and poor accuracy in estimating the parameters related to the health status of the reorganized battery, resulting in overcharge and over-discharge problems in some reorganized batteries, which may lead to battery thermal runaway and other safety hazards. Therefore, it is of great significance to estimate the health status of retired power batteries for reorganization, provide data support for the battery management system of the reorganized battery to achieve balanced management, and improve the efficiency of the reuse of retired power batteries.

[0003] Estimating the state of health (SOH) of retired power batteries requires a redesigned SOH estimation method based on the characteristics of the reconstituted batteries. This method must address the current inconsistency issues faced by reconstituted batteries and be quickly and easily deployed in real-world applications. Currently, the main approaches used are experimental estimation and model-based approaches. Experimental estimation requires extensive experimentation to obtain SOH-related data to analyze battery aging patterns. This approach suffers from high experimental costs, the difficulty in replicating experimental conditions in real-world applications, which affects estimation accuracy, and the inability to perform dynamic estimation. Model-based approaches use data from the physical and chemical processes of battery aging to establish a mathematical relationship between changes in parameters such as current and voltage and SOH decay. However, this approach suffers from strong dependency on model parameters, making accurate parameter acquisition difficult in real-world applications. Furthermore, accurate estimation often requires lengthy calculations and complex algorithms, resulting in a lag in the estimated results and preventing real-time estimation. The variations in capacity, voltage, internal resistance, and other parameters of retired power batteries caused by cell inconsistencies are difficult to capture, making accurate SOH estimation difficult. Summary of the Invention

[0004] In view of this, it is necessary to provide a method, device and electronic equipment for predicting the health status of retired power batteries to solve the technical problem in the existing technology that the changing patterns of parameters such as capacity, voltage, internal resistance, etc. of retired power batteries caused by battery inconsistency are difficult to capture, resulting in difficulty in accurately estimating the health status.

[0005] In order to solve the above problems, the present invention provides a method for predicting the health status of retired power batteries, comprising:

[0006] The obtained battery parameters are divided into different levels to obtain battery parameters of multiple different levels;

[0007] A graph network structure with timestamps is constructed using battery numbers and battery parameter level values ​​as nodes and battery parameter names as edges.

[0008] And according to the graph network structure, a time-based battery state feature matrix is ​​constructed;

[0009] The time-based battery state feature matrix is ​​input into the well-trained battery health state estimation model to obtain the health state of the retired power battery for re-utilization.

[0010] In a possible implementation, the graph network structure with timestamps is constructed by using battery numbers and battery parameter level values ​​as nodes and battery parameter names as edges, including:

[0011] Construct the initial graph network structure and define the head entity node and tail entity node;

[0012] Constructing a static graph network structure at a certain moment with the battery number as the head entity node, the battery parameter level value as the tail entity node, and the battery parameter name as the edge;

[0013] Based on the static graph network structure, the association between the battery status and the battery parameter level value and the battery parameters is determined.

[0014] In one possible implementation, determining the association between the battery status, the battery parameter level value, and the battery parameter based on the static graph network structure includes:

[0015] Based on the static graph network structure, a four-tuple model of battery status, battery status value, battery number and time is constructed;

[0016] Based on the four-tuple model, a time sequence relationship between the battery state value and the battery parameter level value is determined according to the battery number.

[0017] In one possible implementation, constructing a time-based battery state feature matrix according to the graph network structure includes:

[0018] Using a distance-based translation model TransE, determining a feature coding value of each entity node in the graph network structure, and constructing an initial vector based on the feature coding value;

[0019] According to the initial vector of each entity node, a battery state feature matrix is ​​constructed.

[0020] In one possible implementation, the distance-based translation model TransE is used to determine the feature coding value of each entity node in the graph network structure, and the initial vector is constructed according to the feature coding value, including:

[0021] Dividing the graph network structure into a head entity node set, a tail entity node set and an attribute edge set;

[0022] Based on the equivalence relationship between the sum of the head entity initial vector and the attribute edge initial vector and the tail entity initial vector, the initial distance between the head entity initial vector and the tail entity initial vector is determined according to a preset Euclidean distance scoring function;

[0023] The initial distance is optimized according to the minimum objective function to determine the initial distance of each entity.

[0024] In a possible implementation, the preset Euclidean distance scoring function is expressed by the following formula:

[0025]

[0026] in, represents the initial distance, Indicates the head entity node, represents the attribute edge, t represents the tail entity node, and Represent the first distance and the second distance respectively.

[0027] In one possible implementation, the fully trained battery health state estimation model includes at least one of a long short-term memory recurrent network model, a deep learning model, and a support vector machine.

[0028] In a second aspect, the present invention further provides a device for predicting the health status of retired power batteries, comprising:

[0029] A classification module is used to classify the acquired battery parameters to obtain multiple battery parameters of different levels;

[0030] A graph network structure construction module is used to construct a graph network structure with timestamps using battery numbers and battery parameter level values ​​as nodes and battery parameter names as edges;

[0031] A feature matrix construction module is used to construct a time-based battery state feature matrix based on the graph network structure;

[0032] The health state determination module is used to input the time-based battery state feature matrix into the trained battery health state estimation model to obtain the health state of retired power batteries for re-utilization.

[0033] In a third aspect, the present invention further provides an electronic device, comprising: a processor and a memory;

[0034] The memory stores a computer-readable program executable by the processor;

[0035] When the processor executes the computer-readable program, the steps in the above-mentioned method for predicting the health status of retired power batteries are implemented.

[0036] In a fourth aspect, the present invention also provides a computer-readable storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in the retired power battery health status prediction method as described above.

[0037] The beneficial effects of the present invention are: by dividing the acquired battery parameters into levels, multiple battery parameters of different levels are obtained, and a graph network structure is constructed according to the levels of the battery parameters, battery numbers and battery parameter names, so as to capture the hidden relationship between different battery parameters and their levels on the health status of retired power batteries based on the graph network structure, and construct a battery status feature matrix based on the influence of battery parameters on consistency represented by the graph network structure, and finally use a well-trained battery health status assessment model to evaluate the health status of retired power batteries based on the battery status feature matrix, and combine inconsistency and timing information to improve the estimation accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A flowchart of an embodiment of a method for predicting the health status of retired power batteries provided by the present invention;

[0039] Figure 2 for Figure 1 A method flow chart of an embodiment of step S102;

[0040] Figure 3 This is a structural diagram of an embodiment of a network structure in the health status prediction method for retired power batteries provided by the present invention;

[0041] Figure 4 A schematic diagram of another embodiment of the network structure in the health status prediction method for retired power batteries provided by the present invention;

[0042] Figure 5 2 is a schematic diagram of an embodiment of a device for predicting the health status of retired power batteries provided by the present invention;

[0043] Figure 6 It is a schematic diagram of the operating environment of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, and are not used to limit the scope of the present invention.

[0045] A specific embodiment of the present invention discloses a method for predicting the health status of retired power batteries. Figure 1 ,include:

[0046] S101, classifying the acquired battery parameters into different levels to obtain battery parameters of multiple different levels;

[0047] S102, constructing a graph network structure with timestamps using battery numbers and battery parameter level values ​​as nodes and battery parameter names as edges;

[0048] S103, constructing a time-based battery state feature matrix according to the graph network structure;

[0049] S104: Input the time-based battery state feature matrix into a well-trained battery health state estimation model to obtain the health state of the retired power battery for reutilization.

[0050] In this embodiment, the obtained battery parameters are divided into levels to obtain multiple battery parameters of different levels, and a graph network structure is constructed according to the battery parameter levels, battery numbers and battery parameter names, so as to capture the hidden relationship between different battery parameters and their levels on the health status of retired power batteries for reutilization based on the graph network structure, and construct a battery status feature matrix based on the influence of battery parameters on consistency represented by the graph network structure. Finally, a well-trained battery health status assessment model is used to evaluate the health status of retired power batteries for reutilization based on the battery status feature matrix, and the estimation accuracy is improved by combining inconsistency and timing information.

[0051] Specifically, the amount of battery data is huge, and the attenuation of battery health status is a long time series problem. In order to strengthen the connection between time series information and battery health status attenuation, the data in the battery dataset needs to be divided according to certain time intervals, thereby strengthening the expression of time series information.

[0052] In step S101, the preprocessing of the collected historical data includes two parts: data cleaning and data processing. Data cleaning mainly includes the processing of abnormal values ​​and missing values ​​of battery data in the battery management system to obtain a complete battery data set; data processing is to reprocess the battery data set so that its inconsistency impact can be captured by the graph network structure and improve the accuracy of neural network estimation. Its steps include: interval processing of time series information to ensure the diversity of time series information; taking the attribute value of the battery parameter as the tail entity node of the graph network structure, and classifying the value of the tail entity node.

[0053] The essence of a graph is a network structure. Using batteries with different numbers as the head nodes of the graph network structure and the attribute values ​​of the battery parameters as the tail nodes results in an excessive number of tail nodes in the graph network structure, which in turn reduces the inconsistency between the different parameter attributes of different batteries and the degradation law of the battery health state. Therefore, a reasonable hierarchical classification of the parameter attribute values ​​that serve as tail nodes helps reduce the number of tail nodes, enhances the capture of the potential laws between inconsistency and battery health state degradation, and constructs a more reasonable graph network structure. It should be noted that battery parameters include at least voltage, capacity, internal resistance, temperature, and self-discharge rate. Grading the acquired battery parameters includes classifying them into different levels based on their parameter values, and constructing a graph network structure based on the divided levels. This allows the graph network structure to characterize the degree of influence of consistency on the battery health state and determine the battery health state to improve recycling efficiency.

[0054] In some embodiments, the battery number and battery parameter level value are used as nodes, and the battery parameter name is used as an edge to construct a graph network structure with a timestamp. Figure 2 ,include:

[0055] S201, constructing an initial graph network structure and defining a head entity node and a tail entity node;

[0056] S202: Construct a static graph network structure at a certain moment using the battery number as a head entity node, the battery parameter level value as a tail entity node, and the battery parameter name as an edge;

[0057] S203: Determine the association between the battery status, the battery parameter level value, and the battery parameter based on the static graph network structure.

[0058] In step S201, the head entity node is typically defined as a battery number (e.g., battery ID), representing a specific battery instance. The tail entity node is defined as the level value of a battery parameter, such as voltage level (A, B, C) or capacity level. The edge is defined as the name of a battery parameter, such as "voltage," "capacity," or "internal resistance," connecting the head entity node and the tail entity node.

[0059] For example:

[0060] Battery number: 001

[0061] Voltage level: A

[0062] Side: Voltage

[0063] In this example, see Figure 3 and Figure 4 A graph network structure is constructed based on the battery parameter levels. The nodes and edges in the graph network structure can intuitively reflect the relationship between battery status and battery parameter levels. Specifically, the level of the tail entity node can be used to determine the overall health of the battery. For example, if most parameters are rated A, the battery is in good condition; if many parameters are rated C, the battery is in poor condition.

[0064] Association between battery status and parameter names: Edge types (such as "voltage," "capacity," and "internal resistance") can be used to identify which parameters have a significant impact on battery status. For example, a low value for a parameter (such as capacity) may indicate a decrease in battery life.

[0065] It should be noted that the finer the parameter value level division, the more value levels there are, and the more nodes the corresponding graph network structure has. Therefore, graph network structures with different numbers of nodes are constructed according to different parameter value level divisions.

[0066] In some embodiments, determining the association between the battery status, the battery parameter level value, and the battery parameter based on the static graph network structure includes:

[0067] Based on the static graph network structure, a four-tuple model of battery status, battery status value, battery number and time is constructed;

[0068] Based on the four-tuple model, a time sequence relationship between the battery state value and the battery parameter level value is determined according to the battery number.

[0069] In this embodiment, the network structure of the health state diagram of retired power batteries can be expressed as follows: ,in , represents the static graph network structure at time i, E represents the entity set in the graph network structure, and R represents the relationship set in the graph network structure. Represents the set of knowledge facts that occurred at time i, that is, the knowledge facts that occurred in the real world are described by the relationship R between different entities E at time i. Combined with the historical data in the power battery management system over a certain period of time, the retired power battery reorganization utilizes the health status graph network structure, and the battery number in the battery pack at a certain time The state of health (SOH) is expressed as a four-tuple , through this example, we can see that at different times , different battery numbers and different battery parameter information can be represented by four tuples.

[0070] In some embodiments, constructing a time-based battery state characteristic matrix according to the graph network structure includes:

[0071] Using a distance-based translation model TransE, determining a feature coding value of each entity node in the graph network structure, and constructing an initial vector based on the feature coding value;

[0072] According to the initial vector of each entity node, a battery state feature matrix is ​​constructed.

[0073] In this embodiment, based on the above-mentioned constructed graph network structure, the distance-based translation model TransE is used to implement the embedding of entity nodes and attribute edges in the graph network structure, and determine the low-dimensional vector representation of each entity node, including: using the distance-based translation model TransE to implement the low-dimensional vector representation of entity nodes and attribute edges in the graph network structure; splicing the low-dimensional vector representation of each entity node to obtain a feature matrix. The translation model TransE is inspired by word steering and regards the relationship (attribute) in the triple as a translation operation. Its judgment basis is that the sum of the head entity vector and the attribute vector should be as equal as possible to the tail entity, that is, h+r≈t; therefore, a scoring function based on Euclidean distance is used. To measure the distance between the head entity and the tail entity, and optimize the low-dimensional vector representation of the triples according to the minimum objective function, and then determine the low-dimensional vector representation of each entity.

[0074] The TransE algorithm defines a scoring function based on Euclidean distance:

[0075]

[0076] In order to better learn the representation of entities and attributes in low-dimensional vector space, the minimized objective function is:

[0077]

[0078]

[0079] in >0 is a marginal constant, S is the correct set of triples, is a set of wrong triples, E is a set of entities, and the wrong triples are obtained by randomly replacing one of the head entity or the tail entity of the correct triple.

[0080] Specifically, the graph network structure is divided into entity node set, attribute edge set and Figure 3 Tuple set, first initialize the entity nodes and attribute edges in the entity node set and attribute edge set with low-dimensional vectors and Figure 3 The tuple set is divided into training, validation, and test sets. The model training process first extracts triplets from the training set as positive samples and randomly replaces the head or tail entity node of the triplet as negative samples. A scoring function is used to calculate the scores of the positive and negative samples, respectively. According to the algorithm's expectations, the positive sample scores should be close to 0, while the negative sample scores should be far from 0. Then, by minimizing the objective function and using the optimizer, the low-dimensional vector representations of the entity nodes and attribute edges are updated during backpropagation to meet the algorithm's requirements. Finally, the MRR and HITS@n metrics are used to measure the embedding level of the entity nodes and attribute edges in the graph network structure. The low-dimensional vector representations of each entity node are then combined to form a feature matrix that serves as the input to the LSTM estimation model, preserving the data information of the graph network structure to the greatest extent possible.

[0081] The calculation formulas for MRR and HITS@n indicators are as follows:

[0082]

[0083]

[0084] Where S represents a triple set, Indicates the number of triplets, represents the ranking of the i-th triple in link prediction, Represents the indicator function. The larger the MRR and HITS@n index values, the better.

[0085] The fully trained battery health state estimation model includes at least one of a long short-term memory recurrent network model, a deep learning model, and a support vector machine. Specifically, the battery health state estimation model is an LSTM estimation model, which includes an input layer (which is a time window data), two LSTM layers, a fully connected layer, and an output layer. The problem of power battery health state decay is a long-term series problem. In addition to being affected by changes in battery parameters, the external environment, and inconsistencies, its decay process also exhibits a clear trend. The long short-term memory network (LSTM) selectively stores and deletes information through different gating units, which can effectively handle long-term dependencies in data.

[0086] The LSTM network formula is as follows:

[0087]

[0088] In the formula is the hidden state at time step t, is the cell state at time step t, is the input at time step t, W and b are the weight matrix and bias vector, , , , They are input gate, forget gate, cell state and output gate, is the sigmoid activation function, is the hyperbolic tangent activation function, is the Hadamard product.

[0089] Specifically, based on the feature matrix obtained by the aforementioned embedding, the battery data is re-divided into a training set, a validation set, and a test set, and a time window sample for multivariate rolling estimation is constructed as the input of the model. The window size (how many previous sample data are used to estimate the target data) needs to be set according to the actual situation; the training set is used to train the model to obtain a graph-embedded retired power battery health status prediction model; the validation set is used for model parameter adjustment, and the trained estimation model is estimated on the validation set and the parameters are adjusted in time to obtain the optimal estimation model parameters; the test set is used for model evaluation, and the estimation model that meets the accuracy is estimated on the test set. The obtained estimated value is compared with the true value to verify the effectiveness of the model;

[0090] Furthermore, three evaluation indicators are used to verify the effectiveness of the model: root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination ( ), the calculation formulas of the three evaluation indicators are:

[0091]

[0092]

[0093]

[0094] In the formula, m is the number of samples, is the true value, is the true mean value, is the estimated value. The smaller the RMSE and MAE values ​​are, the higher the estimation accuracy is. The larger the value, the better the model fit.

[0095] Based on this, the key points of the embodiments of the present invention mainly lie in the following aspects:

[0096] 1. Capture the potential factor of battery inconsistency that affects the health degradation of power batteries by modeling a graph network structure with time series characteristics.

[0097] 2. Setting different parameter value levels to adjust the number of nodes in the graph network structure so that it can capture battery inconsistencies to the greatest extent while providing sufficient graph structure information and time series information for subsequent graph embedding tasks and time series estimation tasks.

[0098] 3. Use graph embedding technology to complete the connection between upstream graph network structure and downstream time series estimation.

[0099] Based on the above-mentioned retired power battery health status prediction method, the embodiment of the present invention also provides a retired power battery health status prediction device, please refer to Figure 5 ,include:

[0100] A classification module 510 is used to classify the acquired battery parameters to obtain multiple battery parameters of different levels;

[0101] A graph network structure construction module 520 is used to construct a graph network structure with timestamps using battery numbers and battery parameter level values ​​as nodes and battery parameter names as edges;

[0102] A feature matrix construction module 530 is configured to construct a time-based battery state feature matrix based on the graph network structure;

[0103] The health state determination module 540 is used to input the time-based battery state feature matrix into a well-trained battery health state estimation model to obtain the health state of the retired power battery for re-utilization.

[0104] like Figure 6As shown, based on the above-mentioned retired power battery health state prediction method, the application further provides an electronic device, which can be a mobile terminal, a desktop computer, a notebook, a palm computer, a server, and the like. The electronic device includes a processor 610, a memory 620, and a display 630. Figure 6 Only some components of the electronic device are shown, but it should be understood that all the shown components are not required, and more or less components can be implemented instead.

[0105] The memory 620 can be an internal storage unit of the electronic device, such as a hard disk or a memory of the electronic device, in some embodiments. The memory 620 can also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, and the like, in other embodiments. Further, the memory 620 can include both an internal storage unit and an external storage device of the electronic device. The memory 620 is used to store application software and various data installed in the electronic device, such as program codes installed in the electronic device. The memory 620 can also be used to temporarily store data that has been output or will be output. In an embodiment, the memory 620 stores a retired power battery health state prediction program 640, which can be executed by the processor 610 to implement the retired power battery health state prediction method of the embodiments of the application.

[0106] The processor 610 can be a central processing unit (CPU), a microprocessor, or other data processing chip, which is used to run program codes or process data stored in the memory 620, such as to execute the retired power battery health state prediction method, in some embodiments.

[0107] The display 630 can be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, and the like, in some embodiments. The display 630 is used to display information of the retired power battery health state prediction electronic device and to display a visualized user interface. The components 610-630 of the electronic device communicate with each other through a system bus.

[0108] Those skilled in the art can understand that all or part of the processes of the above-mentioned embodiment methods can be completed by instructing the relevant hardware by a computer program, and the program can be stored in a computer readable storage medium. The computer readable storage medium is a disk, an optical disk, a read-only memory, a random access memory, etc.

[0109] The above description is merely preferred specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application.

Claims

1. A method for predicting the health status of retired power batteries, characterized in that: include: The obtained battery parameters are divided into different levels to obtain battery parameters of multiple different levels; Construct the initial graph network structure and define the head entity node and tail entity node; With the battery number as the head entity node, the battery parameter level value as the tail entity node, and the battery parameter name as the edge, a static graph network structure at a certain moment is constructed; Based on the static graph network structure, a four-tuple model of battery status, battery status value, battery number and time is constructed; Based on the four-tuple model, determining a time sequence relationship between a battery status value and a battery parameter level value according to the battery number; Constructing a time-based battery state feature matrix based on a graph network structure, including: using a distance-based translation model TransE to determine feature coding values ​​for each entity node in the graph network structure, and constructing an initial vector based on the feature coding values; constructing a battery state feature matrix based on the initial vector of each entity node; The time-based battery state feature matrix is ​​input into the well-trained battery health state estimation model to obtain the health state of the retired power battery for re-utilization.

2. The method for predicting the health status of retired power batteries according to claim 1, characterized in that: The distance-based translation model TransE is used to determine the feature coding value of each entity node in the graph network structure, and an initial vector is constructed according to the feature coding value, including: Dividing the graph network structure into a head entity node set, a tail entity node set and an attribute edge set; Based on the equivalence relationship between the sum of the head entity initial vector and the attribute edge initial vector and the tail entity initial vector, the initial distance between the head entity initial vector and the tail entity initial vector is determined according to a preset Euclidean distance scoring function; The initial distance is optimized according to the minimum objective function to determine the initial distance of each entity.

3. The method for predicting the health status of retired power batteries according to claim 2, characterized in that: The preset Euclidean distance scoring function is expressed by the following formula: in, represents the initial distance, Indicates the head entity node, represents the attribute edge, t represents the tail entity node, and Represent the first distance and the second distance respectively.

4. The method for predicting the health status of retired power batteries according to claim 1, characterized in that: The fully trained battery health status estimation model includes at least one of a long short-term memory recurrent network model, a deep learning model and a support vector machine.

5. A device for predicting the health status of retired power batteries, characterized in that: include: A classification module is used to classify the acquired battery parameters to obtain multiple battery parameters of different levels; The graph network structure construction module is used to build the initial graph network structure and define the head entity node and the tail entity node; With the battery number as the head entity node, the battery parameter level value as the tail entity node, and the battery parameter name as the edge, a static graph network structure at a certain moment is constructed; Based on the static graph network structure, a four-tuple model of battery status, battery status value, battery number and time is constructed; Based on the four-tuple model, determining a time sequence relationship between a battery status value and a battery parameter level value according to the battery number; A feature matrix construction module is used to construct a time-based battery state feature matrix based on a graph network structure, including: using a distance-based translation model TransE to determine feature coding values ​​for each entity node in the graph network structure, and constructing an initial vector based on the feature coding values; and constructing a battery state feature matrix based on the initial vector of each entity node; The health state determination module is used to input the time-based battery state feature matrix into the trained battery health state estimation model to obtain the health state of retired power batteries for re-utilization.

6. An electronic device, characterized in that: include: processor and memory; The memory stores a computer-readable program executable by the processor; When the processor executes the computer-readable program, the steps of the method for predicting the health status of retired power batteries according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in the retired power battery health status prediction method according to any one of claims 1 to 4.

Images