Method and device for predicting service life of energy storage battery
By constructing a topological relationship diagram and integrating multi-dimensional features, combining temperature reference and neural network model, the problem of low prediction accuracy of energy storage battery life is solved, achieving higher prediction accuracy and adaptability.
Patent Information
- Application Number
- CN202410306565.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-18
- Publication Date
- 2025-07-25
AI Technical Summary
The existing energy storage battery residual life prediction methods have low accuracy and are difficult to meet actual usage needs, especially the prediction accuracy of lithium-ion batteries is insufficient.
Build a topological relationship diagram, fuse multi-dimensional features and introduce temperature references, and train a local capacity prediction model, combine the Transformer encoder and the node contribution rate convolution network, extract and enhance the weights of the nodes of interest, and perform adaptive fusion to predict the service life of energy storage batteries.
It improves the accuracy of the service life prediction of the energy storage system, can update and correct predictions according to actual working conditions, and enhances the accuracy and adaptability of predictions.
Smart Images
Figure CN120370187A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of batteries, and in particular, to a method and device for predicting the service life of energy storage batteries. Background Art
[0002] Electrochemical energy storage technology represented by lithium-ion batteries has become the energy storage technology with the fastest growing installed capacity in the current energy storage field due to its flexible and fast advantages. Especially in recent years, the scale effect of lithium batteries has emerged, the cost has been rapidly reduced, and its role in the renewable energy consumption and transportation electrification industrial chains has become increasingly important.
[0003] The remaining life of a battery refers to the number of cycle periods of the cycle life required for the maximum available capacity of the battery to decay and degrade to a certain specified failure threshold under certain charge and discharge conditions. The prediction of the remaining life of a battery is a process of predicting and calculating its remaining life by using certain mathematical means based on the historical data of the battery.
[0004] Currently, the methods for predicting the remaining life of a battery are mainly divided into: 1. Empirical prediction methods (including single exponential model, double exponential model, linear model, polynomial model, Verhulst model, etc.); 2. Filtering prediction methods (including: Kalman filter, extended Kalman filter, unscented Kalman filter, particle filter, unscented particle filter, etc.). Among them, for empirical prediction methods, although they have good online computing capabilities, their predictability is too poor to meet the actual usage requirements of the battery; while for filtering prediction methods, although they can improve the accuracy and convergence of empirical prediction methods, they increase the dependence of the algorithm on the model and complex data calculations. Summary of the Invention
[0005] The embodiments of this application provide a method and device for predicting the service life of energy storage batteries, which are used to fuse multi-dimensional features, introduce temperature as a reference, and mainly consider the main factors affecting the remaining capacity of the energy storage system, so as to solve the technical problem of low accuracy in predicting the remaining life of existing energy storage batteries.
[0006] The embodiments of this application propose a method for predicting the service life of energy storage batteries, which is applied to an energy storage system including multiple energy storage subsystems, and any energy storage subsystem includes multiple energy storage batteries. The method for predicting the service life of the energy storage batteries includes the following steps:
[0007] For any energy storage subsystem, obtain the layout information of each energy storage battery in any energy storage subsystem, as well as historical charge and discharge data, temperature information, and corresponding historical energy storage parameters;
[0008] Based on the acquired layout information, construct a topological relationship graph for each energy storage battery of any energy storage subsystem, where in the topological relationship graph, the distance between nodes is used to describe the proximity relationship of the energy storage batteries, and the series and parallel relationships of the energy storage batteries are described by connecting lines;
[0009] Screen the historical charge and discharge data and historical energy storage parameters of each energy storage battery of the any energy storage subsystem obtained, and assign the charge and discharge data and energy storage parameters of each energy storage battery in the same time period to the corresponding nodes of the topological relationship graph; and, endow the topological relationship graph with a temperature background based on the acquired temperature information;
[0010] Based on the formed topological relationship graphs, construct a training data set, and train a local capacity prediction model based on the training data set;
[0011] Process the newly collected charge and discharge data, temperature information and energy storage parameters of each energy storage battery of the energy storage subsystem, and input them into the trained local capacity prediction model;
[0012] Based on the obtained local capacity, fit the change trend of the local capacity to predict the service life of the energy storage battery.
[0013] Optionally, screening the historical charge and discharge data of each energy storage battery of the any energy storage subsystem obtained includes:
[0014] At each time period, trim or perform forward and backward time queries on the historical charge and discharge data of each energy storage battery, so that the charge and discharge data within any time period cover the charge data and discharge data with the same power ratio for charging and discharging any energy storage battery;
[0015] Judge the number of energy storage batteries in the charging or discharging state at the start moment of the any time period, and take the mode of the number as the alignment basis;
[0016] On the time axis of any time period, based on the determined alignment basis, align the start moments of each data segment of the charge data and discharge data, and arrange the charge data and discharge data at intervals;
[0017] Assigning the energy storage parameters in the same time period to the corresponding nodes of the topological relationship graph includes:
[0018] Determine the energy storage parameters at the end moment of the any time period, and assign the energy storage parameters at the end moment of the any time period to the corresponding nodes in the topological relationship graph.
[0019] Optionally, training the local capacity prediction model based on the training data set includes:
[0020] Extract the charge and discharge characteristics of the charge and discharge data after alignment; and,
[0021] According to the temperature background, nodes with temperature deviation greater than the preset temperature deviation threshold are regarded as nodes of interest, and based on the formed topological relationship graph, topological features are extracted;
[0022] Node strengthening is performed on the extracted features to enhance the weights of the nodes of interest;
[0023] The extracted charge-discharge features, topological features, and features after weight enhancement are adaptively fused through an adaptive weighted fusion function;
[0024] The features after weight enhancement are again subjected to feature extraction, and the extracted features are added to the adaptively fused features;
[0025] The added features are input into a fully connected layer, and the output of the fully connected layer is used as the prediction result of the local capacity prediction model.
[0026] Optionally, the extraction of charge-discharge features from the aligned charge-discharge data is implemented through a Transformer encoder;
[0027] Based on the formed topological relationship graph, the extraction of topological features is to first divide the topological relationship graph into multiple sub-topological graphs, and for any sub-topological graph, a node contribution rate convolutional network is used to extract them, where the node contribution rate convolutional network processes the input sub-topological graph in the following way:
[0028] D1 = ISRU{CNN(D, D node ).norm}
[0029] δ = top n (D T )
[0030]
[0031] Among them, ISRU represents the ISRU activation function, D and D node respectively represent the nodes and the features of the nodes in the sub-topological graph, as the input of the CNN convolutional neural network, norm is a mathematical norm, CNN represents the convolutional neural network, D1 represents the features after convolutional operation, top n represents n nodes of interest in the sub-topological graph that retain the temperature deviation greater than the preset temperature deviation threshold D T , δ represents the weight factor, represents feature multiplication, and D2 represents the output features of the node contribution rate convolutional network.
[0032] Optionally, the node strengthening of the extracted features to enhance the weights of the nodes of interest includes:
[0033] Neighbor nodes with temperature correlation for each node of interest will be determined;
[0034] Based on the determined neighbor nodes, enhance the weight of the node of interest, satisfying:
[0035] a(d m ,d k )=c T ReLU(H·[d m ,d k )
[0036]
[0037] where tanh represents the tanh activation function, ReLU represents the ReLU activation function, H represents the weight matrix, m represents the serial number of the node of interest, k represents the serial number of the neighbor node with temperature correlation, k′ represents the variable for performing summation, K represents the number of neighbor nodes with temperature correlation, d m ,d k represents the unenhanced feature, d′ m represents the feature of the enhanced node of interest m, a(d m ,d k ) represents the attention metric of the node of interest, c is a learnable hyperparameter, and T represents transpose.
[0038] Optionally, adaptively fuse the extracted charge-discharge features, topological features, and features after weight enhancement through an adaptive weighted fusion function, satisfying:
[0039] X out =[Sigmoid(r)X1+(1 - Sigmoid(r))X2]
[0040] where X out represents the feature after adaptive fusion, Sigmoid(*) represents the Sigmoid function, r represents the randomly initialized weight factor, X1 represents the extracted charge-discharge features and topological features, and X2 represents the features after weight enhancement.
[0041] Optionally, based on the obtained local capacity, fit the change trend of the local capacity to predict the service life of the energy storage battery, including:
[0042] For the local capacity obtained at any prediction time, fit it with a smooth curve to obtain a fitted curve;
[0043] Determine the intersection point between the current fitted curve and the given remaining capacity limit to determine the service life of the energy storage battery.
[0044] An embodiment of the present application also provides a prediction device for the service life of an energy storage battery, including a processor and a memory. A computer program is stored on the memory, and when the computer program is executed by the processor, the steps of the prediction method for the service life of the energy storage battery as described above are implemented.
[0045] The prediction method for the service life of the energy storage battery in the embodiment of the present application uses multi-dimensional features for fusion, introduces temperature as a reference, and focuses on the main factors affecting the remaining capacity (capacity attenuation) of the energy storage system. At each prediction node, prediction update and correction can be performed according to the actual working conditions, which can effectively improve the prediction accuracy of the service life of the energy storage system.
[0046] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically illustrates the specific embodiments of the present invention. Description of the Drawings
[0047] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:
[0048] Figure 1 It is a schematic diagram of the basic process of the prediction method for the service life of the energy storage battery in this embodiment. Detailed Embodiments
[0049] Hereinafter, exemplary embodiments of the present disclosure will be described in more detail with reference to the drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.
[0050] An embodiment of the present application provides a prediction method for the service life of an energy storage battery, which is applied to an energy storage system including a plurality of energy storage subsystems, and any energy storage subsystem includes a plurality of energy storage batteries. For example, the energy storage system includes a plurality of energy storage subsystems managed by partitions, and any energy storage subsystem can include a plurality of energy storage batteries. For example, the energy storage battery can be a lithium battery. The prediction method for the service life of the energy storage battery in the embodiment of the present application includes the following steps:
[0051] In step S101, for any energy storage subsystem, obtain the layout information of each energy storage battery in any energy storage subsystem, as well as historical charge and discharge data, temperature information, and corresponding historical energy storage parameters. In subsequent specific implementations, the embodiments of the present application comprehensively consider the possible impacts of the layout of energy storage batteries, temperature data, and historical charge and discharge data on battery performance, and thus collect relevant data. The historical energy storage parameters referred to in the embodiments of the present application can be, for example, one or more parameters such as the rated capacity, internal resistance, and open-circuit voltage of the energy storage battery.
[0052] In step S102, based on the obtained layout information, construct a topological relationship graph for each energy storage battery in any energy storage subsystem, where in the topological relationship graph, the distance between nodes is used to describe the proximity position relationship of energy storage batteries, and the series and parallel relationships of energy storage batteries are described by connecting lines. That is, by establishing the positional relationship of the layout in the form of a topological graph, an energy storage battery is used as a node, and the nodes with electrical connections are represented by connecting lines.
[0053] In step S103, screen the historical charge and discharge data and historical energy storage parameters of each energy storage battery in any energy storage subsystem obtained, and assign the charge and discharge data and energy storage parameters of each energy storage battery in the same time period to the corresponding nodes in the topological relationship graph; and, assign a temperature background to the topological relationship graph based on the obtained temperature information. Specifically, the historical charge and discharge data and historical energy storage parameters of each energy storage battery in any energy storage subsystem obtained can be screened and processed, and the historical energy storage parameters can be assigned to the corresponding nodes after screening. Specific energy storage parameters, charge and discharge data, and the remaining capacity in the corresponding state (corresponding to capacity attenuation) can be obtained for different specifications of energy storage batteries, such as lithium batteries, in a test environment. Then, add a temperature background to the nodes in the topology. For example, a temperature field distribution can be established in the topological relationship graph based on the temperature data measured by each energy storage battery, so as to add a temperature background to the topological relationship graph. In subsequent examples, features can be extracted based on the topological relationship graph.
[0054] In step S104, based on the formed topological relationship graphs, construct a training data set, and train a local capacity prediction model based on the training data set. Specifically, the training data set can be constructed in chronological order, and the local capacity prediction model can be trained. In subsequent examples of the present application, segmentation is performed based on the topological relationship graph, and then the segmented images of the topological relationship graph are trained.
[0055] In step S105, the charge-discharge data, temperature information, and energy storage parameters of each energy storage battery in the newly collected energy storage subsystem are processed and input into the trained local capacity prediction model. In the embodiments of the present application, considering the charge-discharge data, temperature information, and battery parameters of the energy storage battery, feature fusion is performed through the local capacity prediction model, so as to use the local capacity prediction model to predict the remaining battery capacity of, for example, some interested energy storage batteries. By introducing the charge-discharge data and temperature information for processing and fusing them into features, the main factors affecting the remaining capacity of the energy storage system are mainly considered, and the accuracy of predicting the service life of the energy storage system is improved.
[0056] In step S106, based on the obtained local capacity, the change trend of the local capacity is fitted to predict the service life of the energy storage battery. In some embodiments, fitting the change trend of the local capacity based on the obtained local capacity to predict the service life of the energy storage battery includes:
[0057] For the local capacity obtained at any prediction moment, it is fitted through a smooth curve to obtain a fitted curve;
[0058] Determine the intersection point between the current fitted curve and the given remaining capacity limit value to determine the service life of the energy storage battery.
[0059] In some examples, the number of interested nodes can be graded, that is, the proportion of the interested nodes in all energy storage batteries in the energy storage subsystem. For example, if there are only a small number of interested nodes, such as less than 5%, then based on the predicted values of the non-interested nodes, a capacity decay curve that conforms to the actual working conditions of the energy storage battery is fitted, and with the given remaining capacity limit value as the boundary, the service life of the energy storage battery is determined.
[0060] For another example, if the proportion of the interested nodes exceeds 30%, then a decay curve can be fitted based on the capacity prediction values of the interested nodes, and with the given remaining capacity limit value as the boundary, the service life of the energy storage battery is determined. The above percentage values are only examples and are not specific limitations.
[0061] In the embodiments of the present application, the interested nodes can be, for example, nodes with a relatively large deviation in working temperature compared to the normal working temperature range. The energy storage batteries corresponding to such nodes correspond to the environmental influencing factors of the energy storage system working. For example, the energy storage battery is in a low-temperature environment, or some work in a high-temperature environment. In the embodiments of the present application, taking the capacity of the energy storage battery of the interested nodes as the calculation basis for the capacity decay and life prediction of the energy storage system further improves the authenticity and accuracy of the service life prediction.
[0062] In some embodiments, screening the historical charge-discharge data of each energy storage battery of any of the obtained energy storage subsystems includes:
[0063] During each time period, the historical charge and discharge data of each energy storage battery are clipped or queried forward and backward in time, so that the charge and discharge data within any time period cover the charge data and discharge data with the same proportion of the same amount of charge and discharge for any energy storage battery.
[0064] Judge the number of energy storage batteries in the charging or discharging state at the start time of any time period, and take the mode of the number as the alignment basis.
[0065] On the time axis of any time period, based on the determined alignment basis, align the start times of each data segment of the charge data and the discharge data, and arrange the charge data and the discharge data at intervals. In some specific examples, the charge and discharge data can be corresponding charge and discharge curves. By alignment and interval arrangement, features such as the curve slope and duration of the charge and discharge with the same proportion of the same amount of charge can be highlighted in subsequent feature extraction, improving the representative value of the extracted features.
[0066] In some embodiments, assigning the energy storage parameters in the same time period to the corresponding nodes of the topological relationship graph includes:
[0067] Determine the energy storage parameters at the end time of any time period, and assign the energy storage parameters at the end time of any time period to the corresponding nodes in the topological relationship graph. Specifically, in the embodiments of the present application, the energy storage parameters at the end time of the same time period are considered to characterize the energy storage situation at the end time of each time period.
[0068] In some embodiments, training the local capacity prediction model based on the training data set includes:
[0069] Extract the charge and discharge features of the charge and discharge data after alignment; and,
[0070] According to the temperature background, take the nodes with a temperature deviation greater than the preset temperature deviation threshold as the nodes of interest, and based on the formed topological relationship graph, extract the topological features. Specifically, the formed topological relationship graph can be divided into multiple sub-topological graphs according to a specified specification. In the case of assigning the temperature background, referring to the normal operating temperature range of charge and discharge, take the nodes corresponding to the energy storage batteries outside this temperature range as the nodes of interest, and extract the topological features (topological image features) of the sub-topological graphs.
[0071] Perform node strengthening on the extracted features to enhance the weights of the nodes of interest.
[0072] Adaptive fusion is performed on the extracted charge and discharge features, topological features, and the features with enhanced weights through an adaptive weighted fusion function.
[0073] The features after weight enhancement are subjected to feature extraction again, and the extracted features are added to the adaptively fused features. Specifically, the feature extraction performed again on the features after weight enhancement can use the same network structure as that for the first extraction of charge-discharge features and the extraction of topological features.
[0074] The added features are input into a fully connected layer, and the output of the fully connected layer is used as the prediction result of the local capacity prediction model.
[0075] In some embodiments, the extraction of charge-discharge features from the aligned charge-discharge data is implemented by a Transformer encoder.
[0076] Based on the formed topological relationship graph, the extraction of topological features is to first divide the topological relationship graph into multiple sub-topological graphs, and for any sub-topological graph, a node contribution rate convolutional network is used to extract the features, where the node contribution rate convolutional network processes the input sub-topological graph in the following way:
[0077] D1 = ISRU{CNN(D, D node ).norm}
[0078] δ = top n (D T )
[0079]
[0080] where ISRU represents the ISRU activation function, D and D node respectively represent the nodes and the features of the nodes in the sub-topological graph, which are used as the input of the CNN convolutional neural network, norm is a mathematical norm, CNN represents the convolutional neural network, D1 represents the features after convolutional operation, top n represents n interesting nodes in the sub-topological relationship graph whose remaining temperature deviation is greater than the preset temperature deviation threshold D T , δ represents the weight factor, represents feature multiplication, and D2 represents the output features of the node contribution rate convolutional network.
[0081] In some embodiments, node strengthening is performed on the extracted features to enhance the weights of interesting nodes, including:
[0082] Determine the neighbor nodes that have temperature correlation with each interesting node. In some examples, for example, after a certain node changes to an interesting node, if based on the temperature background, the neighbor node also changes to an interesting node, it is determined to have temperature correlation. A temperature correlation coefficient can be added to the neighbor nodes of the interesting node to represent the strength of the correlation between the nodes.
[0083] Enhance the weight of the node of interest based on the determined neighbor nodes, satisfying:
[0084] a(d m , d k ) = c T ReLU(H·[d m , d k )
[0085]
[0086] where tanh represents the tanh activation function, ReLU represents the ReLU activation function, H represents the weight matrix, m represents the serial number of the node of interest, k represents the serial number of the neighbor nodes with temperature correlation, k′ represents the variable for performing summation, K represents the number of neighbor nodes with temperature correlation, d m , d k represents the unenhanced feature, d′ m represents the feature of the enhanced node of interest m, a(d m , d k ) represents the attention measure of the node of interest, c is a learnable hyperparameter, and T represents transpose.
[0087] In some embodiments, the extracted charge-discharge features, topological features, and the features after weight enhancement are adaptively fused through an adaptive weighted fusion function, satisfying:
[0088] X out = [Sigmoid(r)X1 + (1 - Sigmoid(r))X2]
[0089] where X out represents the feature after adaptive fusion, Sigmoid(*) represents the Sigmoid function, r represents the randomly initialized weight factor, X1 represents the extracted charge-discharge features and topological features, and X2 represents the features after weight enhancement.
[0090] The life prediction method of this application realizes feature extraction at different levels by designing a Transformer encoder + a convolutional network for node contribution rate based on CNN, and then enhances the neighbor nodes with temperature correlation of each node of interest, enabling the processed features to contain both deep feature information and important information at the shallow level that is beneficial to improving the recognition effect.
[0091] In the fusion branch, the extracted charge-discharge features, topological features, and features after weight enhancement are fused through a designed adaptive weighted fusion function. Thus, through self-adaptive fusion, the recognition effect of unknown working conditions that may exist under operating conditions can be further improved, the compatibility of the algorithm with unknown working conditions can be improved, and the forgetting problem of the model can be alleviated. Through the service life prediction method of the present application, the predicted service life of the energy storage battery can be made to fit the usage conditions, and the accuracy of life prediction can be improved.
[0092] The embodiment of the present application also proposes a device for predicting the service life of an energy storage battery, including a processor and a memory. A computer program is stored on the memory, and when the computer program is executed by the processor, the steps of the method for predicting the service life of the energy storage battery as described above are implemented.
[0093] In addition, although exemplary embodiments have been described herein, the scope includes any and all embodiments based on the present disclosure having equivalent elements, modifications, omissions, combinations (e.g., solutions that cross various embodiments), adaptations, or changes. It is not limited to the examples described in this specification or during the implementation of this application, and the examples will be construed as non-exclusive.
[0094] The above description is intended to be illustrative and not restrictive. For example, the above examples (or one or more of them) can be used in combination with each other. For example, those of ordinary skill in the art can use other embodiments when reading the above description.
[0095] The above embodiments are only exemplary embodiments of the present disclosure. Those skilled in the art can make various modifications or equivalent replacements to the present invention within the essence and protection scope of the present disclosure, and such modifications or equivalent replacements should also be regarded as falling within the protection scope of the present invention.
Claims
1. A method for predicting the service life of an energy storage battery, characterized in that, Applied to an energy storage system including multiple energy storage subsystems, and any one of the energy storage subsystems includes multiple energy storage batteries. The prediction method for the service life of the energy storage batteries includes the following steps: For any one of the energy storage subsystems, obtain the layout information of each energy storage battery in the energy storage subsystem, as well as historical charge and discharge data, temperature information, and corresponding historical energy storage parameters; Based on the obtained layout information, construct a topological relationship graph for each energy storage battery in any one of the energy storage subsystems. In the topological relationship graph, the distance between nodes is used to describe the proximity position relationship of the energy storage batteries, and the series and parallel relationships of the energy storage batteries are described by connecting lines; Screen the historical charge and discharge data and historical energy storage parameters of each energy storage battery in any one of the obtained energy storage subsystems, and assign the charge and discharge data and energy storage parameters of each energy storage battery in the same time period to the corresponding nodes of the topological relationship graph; and, assign a temperature background to the topological relationship graph based on the obtained temperature information; Based on the formed topological relationship graphs, construct a training data set, and train a local capacity prediction model based on the training data set; Process the newly collected charge and discharge data, temperature information, and energy storage parameters of each energy storage battery in the energy storage subsystem, and input them into the trained local capacity prediction model; Based on the obtained local capacity, fit the change trend of the local capacity to predict the service life of the energy storage battery.
2. The prediction method for the service life of the energy storage battery according to claim 1, characterized in that, The screening of the historical charge and discharge data of each energy storage battery in any one of the obtained energy storage subsystems includes: In each time period, perform clipping or forward-backward time query on the historical charge and discharge data of each energy storage battery, so that the charge and discharge data within any time period cover the charging data and discharging data with the same power ratio for charging and discharging any one of the energy storage batteries; Judge the number of energy storage batteries in the charging or discharging state at the start time of any time period, and take the mode of the number as the alignment basis; On the time axis of any time period, based on the determined alignment basis, align the start times of each data segment of the charging data and discharging data, and arrange the charging data and discharging data at intervals; Assigning the energy storage parameters in the same time period to the corresponding nodes of the topological relationship graph includes: Determine the energy storage parameters at the end time of any time period, and assign the energy storage parameters at the end time of any time period to the corresponding nodes in the topological relationship graph.
3. The method for predicting the service life of an energy storage battery according to claim 2, wherein Training the local capacity prediction model based on the training data set includes: Extract the charge and discharge characteristics of the charge and discharge data after alignment; and, According to the temperature background, use the nodes with temperature deviation greater than the preset temperature deviation threshold as the nodes of interest, and based on the formed topological relationship graph, extract topological characteristics;; Perform node enhancement on the extracted features to enhance the weights of the nodes of interest; Perform adaptive fusion on the extracted charge and discharge characteristics, topological characteristics, and features with enhanced weights through an adaptive weighted fusion function; Perform feature extraction on the features with enhanced weights again, and add the extracted features to the adaptively fused features; Input the added features into a fully connected layer, and use the output of the fully connected layer as the prediction result of the local capacity prediction model.
4. The method for predicting the service life of the energy storage battery according to claim 3, wherein, The charging and discharging characteristics of the charging and discharging data after extraction and alignment are realized by a Transformer encoder; Based on the formed topological relationship graph, to extract topological features, the topological relationship graph is first divided into multiple sub-topological graphs, and any sub-topological graph is extracted by using a node contribution rate convolutional network, where the node contribution rate convolutional network processes the input sub-topological graph in the following manner: D1 = ISRU{CNN(D, D node ).norm} δ = top n (D T ) Among them, ISRU represents the ISRU activation function, D, D node respectively represent the nodes and their features in the sub-topological graph, which are used as the input of the CNN (Convolutional Neural Network). Norm is a mathematical norm, CNN represents the Convolutional Neural Network, D1 represents the features after convolutional operation, top n represents n interesting nodes in the sub-topological graph where the retained temperature deviation is greater than the preset temperature deviation threshold D T δ represents the weight factor, represents feature multiplication, and D2 represents the output features of the node contribution rate convolutional network.
5. The method for predicting the service life of an energy storage battery according to claim 4, wherein Node enhancement is performed on the extracted features to enhance the weights of the nodes of interest, including: Determine the neighbor nodes that have temperature correlation with each node of interest; Based on the determined neighbor nodes, enhance the weights of the nodes of interest, satisfying: a(d m ,d k ) = c T ReLU(H·[d m ,d k ) Among them, tanh represents the tanh activation function, ReLU represents the ReLU activation function, H represents the weight matrix, m represents the serial number of the node of interest, k represents the serial number of the neighbor node with temperature correlation, k' represents the variable for performing summation, K represents the number of neighbor nodes with temperature correlation, d m , d k represents the unenhanced feature, d' m represents the feature of the enhanced node of interest m, a(d m , d k ) represents the attention metric of the node of interest, c is a learnable hyperparameter, and T represents the transpose.
6. The method for predicting the service life of an energy storage battery according to claim 5, wherein The extracted charging and discharging characteristics, topological features, and the features with enhanced weights are adaptively fused through an adaptive weighted fusion function, satisfying: X out = {Sigmoid(r)X1+(1 - Sigmoid(r))X2} Among them, X out represents the feature after adaptive fusion, Sigmoid(*) represents the Sigmoid function, r represents the randomly initialized weight factor, X1 represents the extracted charge-discharge feature and topological feature, and X2 represents the feature after weight enhancement.
7. The method for predicting the service life of an energy storage battery according to claim 1, wherein Based on the obtained local capacity, fitting the change trend of the local capacity to predict the service life of the energy storage battery includes: For the local capacity obtained at any prediction moment, fitting is performed through a smooth curve to obtain a fitting curve; Determine the intersection point between the current fitting curve and the given remaining capacity limit to determine the service life of the energy storage battery.
8. A prediction device for the service life of an energy storage battery, characterized in that, It includes a processor and a memory, and a computer program is stored on the memory. When the computer program is executed by the processor, the steps of the method for predicting the service life of the energy storage battery according to any one of claims 1 to 7 are implemented.