Capacity estimation method, device and equipment of lithium ion battery, storage medium and program product

Abstract

The invention relates to a lithium ion battery capacity estimation method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring electrochemical impedance data of the lithium ion battery, and constructing a feature vector of the lithium ion battery according to the electrochemical impedance data; determining a target feature value of the lithium ion battery based on the feature vector of the lithium ion battery and a pre-trained feature extraction model; and inputting the target characteristic value into a pre-trained lithium ion battery capacity prediction model to obtain a battery capacity prediction value of the lithium ion battery output by the lithium ion battery capacity prediction model. By adopting the method, the accuracy of estimating the battery capacity can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of lithium-ion batteries, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for capacity estimation of lithium-ion batteries. Background Art

[0002] With the rapid development of renewable energy and energy storage technologies, lithium-ion batteries have attracted widespread attention as efficient energy conversion and storage devices. Since battery capacity is a key parameter for measuring battery performance and lifespan, accurately estimating battery capacity is crucial for optimizing battery management systems.

[0003] In traditional technologies, battery capacity is mostly estimated based on characteristic parameters such as voltage, current and temperature.

[0004] However, this method of estimating battery capacity based on characteristic parameters such as voltage, current, and temperature is unable to capture the complex electrochemical processes inside the battery, resulting in poor accuracy in battery estimation. Summary of the Invention

[0005] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for estimating the capacity of a lithium-ion battery with high accuracy to address the above technical problems.

[0006] In a first aspect, the present application provides a method for estimating the capacity of a lithium-ion battery, comprising:

[0007] Acquiring electrochemical impedance data of a lithium-ion battery and constructing a characteristic vector of the lithium-ion battery based on the electrochemical impedance data;

[0008] Determining a target feature value of the lithium-ion battery based on a feature vector of the lithium-ion battery and a pre-trained feature extraction model;

[0009] The target characteristic value is input into a pre-trained lithium-ion battery capacity estimation model to obtain a battery capacity prediction value of the lithium-ion battery output by the lithium-ion battery capacity estimation model.

[0010] In one embodiment, determining a target feature value of the lithium-ion battery based on a feature vector of the lithium-ion battery and a pre-trained feature extraction model includes: normalizing the feature vector of the lithium-ion battery based on a feature normalization algorithm to obtain a normalized feature vector; and inputting the normalized feature vector into the pre-trained feature extraction model to obtain the target feature value of the lithium-ion battery output by the feature extraction model.

[0011] In one embodiment, the feature extraction model includes a convolutional neural network model and a double-layer long short-term memory network model, and the standardized feature vector is input into a pre-trained feature extraction model to obtain the target feature value of the lithium-ion battery output by the feature extraction model, including: inputting the standardized feature vector into the convolutional neural network model to obtain the initial feature value output by the convolutional neural network model; and inputting the initial feature value into the double-layer long short-term memory network model to obtain the target feature value output by the double-layer long short-term memory network model.

[0012] In one embodiment, the standardized feature vector is input into the convolutional neural network model to obtain the initial feature value output by the convolutional neural network model, including: inputting the standardized feature vector into the convolutional neural network model so that the convolutional neural network model performs convolution and normalization operations on the standardized feature vector to obtain a convolution output; and determining the initial feature value based on the convolutional neural network model and the convolution output.

[0013] In one embodiment, the target feature value is input into a pre-trained lithium-ion battery capacity estimation model to obtain a battery capacity prediction value of the lithium-ion battery output by the lithium-ion battery capacity estimation model, including: inputting the target feature value into the pre-trained lithium-ion battery capacity estimation model so that the lithium-ion battery capacity estimation model determines a query vector value, a key vector value, and a value vector value based on the target feature value, and determining the battery capacity prediction value of the lithium-ion battery based on the query vector value, the key vector value, and the value vector value.

[0014] In one embodiment, determining a predicted value of the battery capacity of the lithium-ion battery based on the query vector value, the key vector value, and the value vector value includes: determining a self-attention weight matrix based on the query vector and the key vector; and determining a predicted value of the battery capacity of the lithium-ion battery based on the self-attention weight matrix and the value vector.

[0015] In a second aspect, the present application further provides a device for estimating the capacity of a lithium-ion battery, comprising:

[0016] An acquisition module is used to acquire electrochemical impedance data of a lithium-ion battery and construct a characteristic vector of the lithium-ion battery based on the electrochemical impedance data;

[0017] A first execution module is configured to determine a target feature value of the lithium-ion battery based on a feature vector of the lithium-ion battery and a pre-trained feature extraction model;

[0018] The second execution module is used to input the target feature value into a pre-trained lithium-ion battery capacity estimation model to obtain a battery capacity prediction value of the lithium-ion battery output by the lithium-ion battery capacity estimation model.

[0019] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method described in any embodiment of the first aspect are implemented.

[0020] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any embodiment of the first aspect above.

[0021] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method described in any embodiment of the first aspect above.

[0022] The above-mentioned lithium-ion battery capacity estimation method, device, computer equipment, computer-readable storage medium and computer program product first obtain the electrochemical impedance data of the lithium-ion battery and construct the characteristic vector of the lithium-ion battery based on the electrochemical impedance data. Then, based on the characteristic vector of the lithium-ion battery and a pre-trained feature extraction model, the target characteristic value of the lithium-ion battery is determined. Then, the target characteristic value is input into the pre-trained lithium-ion battery capacity estimation model to obtain the battery capacity prediction value of the lithium-ion battery output by the lithium-ion battery capacity estimation model. The capacity estimation method of the lithium-ion battery provided in the present application is based on the electrochemical impedance data as the target characteristic value input into the pre-trained lithium-ion battery capacity estimation model. Since the electrochemical impedance data can better reflect the electrochemical characteristics inside the battery, the model can obtain information related to battery aging from the electrochemical impedance data, thereby improving the accuracy of the battery capacity estimation. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0024] Figure 1 1 is a flow chart of a method for estimating the capacity of a lithium-ion battery in one embodiment;

[0025] Figure 21 is a flow chart of a method for determining a target characteristic value of a lithium-ion battery in one embodiment;

[0026] Figure 3 A schematic flow chart of a method for obtaining a target characteristic value of a lithium-ion battery output by a feature extraction model in one embodiment;

[0027] Figure 4 A flowchart of a method for obtaining initial eigenvalues ​​output by the convolutional neural network model in one embodiment;

[0028] Figure 5 A schematic flow chart of a method for determining a predicted value of battery capacity of a lithium-ion battery based on a query vector value, a key vector value, and a value vector value in one embodiment;

[0029] Figure 6 is a schematic flow chart of a method for estimating the capacity of a lithium-ion battery in another embodiment;

[0030] Figure 7 is a structural block diagram of a capacity estimation device for a lithium-ion battery in one embodiment;

[0031] Figure 8 is a diagram of the internal structure of a computer device in one embodiment;

[0032] Figure 9 FIG. 4 is a diagram showing the internal structure of a computer device in another embodiment. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0034] It should be noted that the terms "include", "have" and any variations thereof used in this application are intended to cover non-exclusive inclusions.

[0035] With the rapid development of renewable energy and energy storage technologies, lithium-ion batteries have attracted widespread attention as efficient energy conversion and storage devices. Since battery capacity is a key parameter for measuring battery performance and lifespan, accurately estimating battery capacity is crucial for optimizing battery management systems.

[0036] In traditional technologies, battery capacity is mostly estimated based on characteristic parameters such as voltage, current and temperature.

[0037] However, this method of estimating battery capacity based on characteristic parameters such as voltage, current, and temperature is unable to capture the complex electrochemical processes inside the battery, resulting in poor accuracy in battery estimation.

[0038] In view of this, the present application provides a capacity estimation method for lithium-ion batteries, based on inputting electrochemical impedance data as the target feature value into a pre-trained lithium-ion battery capacity estimation model. Since electrochemical impedance data can better reflect the electrochemical characteristics inside the battery, the model can obtain information related to battery aging from the electrochemical impedance data, thereby improving the accuracy of battery capacity estimation.

[0039] The method for estimating the capacity of a lithium-ion battery provided in the present application may be executed by a computer device, which may be a terminal or a server.

[0040] In an exemplary embodiment, Figure 1 As shown, a method for estimating the capacity of a lithium-ion battery is provided, the method comprising the following steps:

[0041] Step 101: Obtain electrochemical impedance data of a lithium-ion battery, and construct a characteristic vector of the lithium-ion battery according to the electrochemical impedance data.

[0042] Lithium-ion battery refers to a secondary battery that stores and releases energy through the migration of lithium ions between positive and negative electrodes.

[0043] Electrochemical impedance spectral data is obtained by applying a small sinusoidal AC voltage or current signal to a lithium-ion battery and measuring the amplitude and phase changes of the response signal. For example, electrochemical impedance spectral data can be used to reflect electrochemical processes within the battery, such as charge transfer, ion diffusion, and interfacial reactions.

[0044] In some exemplary embodiments, the computer device may first obtain electrochemical impedance data of the lithium-ion battery.

[0045] Specifically, the computer device can obtain electrochemical impedance data of the lithium-ion battery based on an electrochemical impedance spectroscopy algorithm.

[0046] Furthermore, after acquiring the electrochemical impedance data of the lithium-ion battery, the computer device may construct a characteristic vector of the lithium-ion battery according to the electrochemical impedance data.

[0047] Specifically, the characteristic vector of the lithium-ion battery can be expressed as Z=[ , ],in, is the real part of the impedance vector determined from the electrochemical impedance data, is the imaginary impedance vector determined from the electrochemical impedance data.

[0048] Step 102: Determine a target feature value of the lithium-ion battery based on the feature vector of the lithium-ion battery and a pre-trained feature extraction model.

[0049] In some exemplary embodiments, after obtaining the feature vector of the lithium-ion battery, the computer device may determine a target feature value of the lithium-ion battery based on the feature vector of the lithium-ion battery and a pre-trained feature extraction model.

[0050] Specifically, the computer device may input the feature vector of the lithium-ion battery into a pre-trained feature extraction model to obtain the target feature value of the lithium-ion battery output by the feature extraction model.

[0051] Step 103: input the target characteristic value into a pre-trained lithium-ion battery capacity estimation model to obtain a battery capacity prediction value of the lithium-ion battery output by the lithium-ion battery capacity estimation model.

[0052] The lithium-ion battery capacity estimation model can be a model based on the self-attention mechanism.

[0053] In some exemplary embodiments, after determining the target characteristic value of the lithium-ion battery based on the characteristic vector of the lithium-ion battery and a pre-trained feature extraction model, the computer device can determine the battery capacity prediction value of the lithium-ion battery based on the target characteristic value and a pre-trained lithium-ion battery capacity estimation model.

[0054] Specifically, the computer device may input the target feature value into a pre-trained lithium-ion battery capacity estimation model to obtain a battery capacity prediction value of the lithium-ion battery output by the lithium-ion battery capacity estimation model.

[0055] In an optional embodiment of the present application, the feature extraction model and the lithium-ion battery capacity estimation model are two sub-models in a hybrid model. After obtaining the electrochemical impedance data of the lithium-ion battery, the computer device can directly input the electrochemical impedance data of the lithium-ion battery into the hybrid model to obtain the battery capacity prediction value of the lithium-ion battery output by the hybrid model.

[0056] The above-mentioned lithium-ion battery capacity estimation method first obtains the electrochemical impedance data of the lithium-ion battery and constructs a feature vector of the lithium-ion battery based on the electrochemical impedance data. Then, based on the feature vector of the lithium-ion battery and a pre-trained feature extraction model, the target feature value of the lithium-ion battery is determined. Then, the target feature value is input into the pre-trained lithium-ion battery capacity estimation model to obtain the battery capacity prediction value of the lithium-ion battery output by the lithium-ion battery capacity estimation model. The capacity estimation method of the lithium-ion battery provided in the present application is based on inputting the electrochemical impedance data as the target feature value into the pre-trained lithium-ion battery capacity estimation model. Since the electrochemical impedance data can better reflect the electrochemical characteristics inside the battery, the model can obtain information related to battery aging from the electrochemical impedance data, thereby improving the accuracy of the battery capacity estimation.

[0057] In an exemplary embodiment, Figure 2 As shown, based on the feature vector of the lithium-ion battery and a pre-trained feature extraction model, determining the target feature value of the lithium-ion battery includes the following steps:

[0058] Step 201: normalize the feature vector of the lithium-ion battery based on a feature normalization algorithm to obtain a normalized feature vector.

[0059] A feature normalization algorithm is an algorithm that uses mathematical transformations to scale features of different dimensions and numerical ranges to a uniform scale. Exemplary feature normalization algorithms include Z-score normalization, maximum-minimum normalization, and logarithmic transformation algorithms.

[0060] In some exemplary embodiments, after obtaining the feature vector of the lithium-ion battery, the computer device may perform normalization processing on the feature vector of the lithium-ion battery based on a feature normalization algorithm to obtain a normalized feature vector.

[0061] Specifically, the computer device can first determine the mean value and standard deviation of the feature vector, and then standardize the feature vector based on the mean value and standard deviation of the feature vector. The standardized feature vector can be expressed as , , , where Z is the eigenvector, is the mean of the eigenvector, is the standard deviation of the eigenvector.

[0062] Step 202: Input the normalized feature vector into a pre-trained feature extraction model to obtain a target feature value of the lithium-ion battery output by the feature extraction model.

[0063] In some exemplary embodiments, after obtaining the normalized feature vector, the computer device may determine the target feature value of the lithium-ion battery based on the normalized feature vector and a pre-trained feature extraction model.

[0064] Specifically, the computer device can input the normalized feature vector into a pre-trained feature extraction model to obtain the target feature value of the lithium-ion battery output by the feature extraction model.

[0065] In an exemplary embodiment, Figure 3 As shown, the feature extraction model includes a convolutional neural network model and a double-layer long short-term memory network model. The standardized feature vector is input into a pre-trained feature extraction model to obtain the target feature value of the lithium-ion battery output by the feature extraction model, including the following steps:

[0066] Step 301: Input the normalized feature vector into the convolutional neural network model to obtain the initial feature value output by the convolutional neural network model.

[0067] Optionally, the convolutional neural network model can be a double-layer one-dimensional convolutional neural network Conv1d, which refers to a CNN model with two one-dimensional convolutional layers.

[0068] In some exemplary embodiments, after obtaining the standardized feature vector, the computer device may input the standardized feature vector into the convolutional neural network model to obtain the initial feature value output by the convolutional neural network model.

[0069] Step 302: Input the initial eigenvalue into the double-layer long short-term memory network model to obtain the target eigenvalue output by the double-layer long short-term memory network model.

[0070] In some exemplary embodiments, after obtaining the initial eigenvalue, the computer device may input the initial eigenvalue into the double-layer long short-term memory network model to obtain the target eigenvalue output by the double-layer long short-term memory network model.

[0071] Specifically, the forget gate in the two-layer long short-term memory network model can be expressed as ,in, is the hidden state of the previous time step, is the input feature of the current time step, that is, the initial eigenvalue, is the weight matrix of the forget gate, is the bias vector of the forget gate, Sigmoid activation function is used to map values ​​to [0, 1].

[0072] The input gate in the two-layer long short-term memory network model can be expressed as ,in, is the output of the input gate, which is used to decide what new information needs to be written into the current cell state. and are the weight matrix and bias term of the input gate respectively.

[0073] The candidate memory states in the two-layer long short-term memory network model can be expressed as ,in, is a candidate memory that can be used to update the cell state. is the weight matrix of candidate memory, For paranoid items, is the hyperbolic tangent function, which is used to map the output value to the range [-1, 1].

[0074] The output gate in the two-layer long short-term memory network model can be expressed as ,in, is the output of the output gate, which can be used to control the influence of the current cell state on the hidden state. and is the weight matrix and bias of the output gate.

[0075] The cell state update in the two-layer long short-term memory network model can be expressed as ,in, is the cell state at the current time step, , are the outputs of the forget gate and input gate respectively, is the cell state at the previous time step, Represents the candidate memory cell state.

[0076] The cell state update in the two-layer long short-term memory network model can be expressed as ,in, As a time step The hidden state vector of is the output of the output gate.

[0077] The final output of the two-layer long short-term memory network model can be expressed as , is the integration of the hidden states of all time steps, and H is the target eigenvalue.

[0078] In an exemplary embodiment, Figure 4 As shown, the normalized feature vector is input into the convolutional neural network model to obtain the initial feature value output by the convolutional neural network model, including the following steps:

[0079] Step 401: Input the standardized feature vector into the convolutional neural network model, so that the convolutional neural network model performs convolution and normalization operations on the standardized feature vector to obtain a convolution output.

[0080] In some exemplary embodiments, after obtaining the standardized feature vector, the computer device may input the standardized feature vector into the convolutional neural network model so that the convolutional neural network model performs convolution and normalization operations on the standardized feature vector to obtain a convolution output.

[0081] Specifically, the convolution operation can be expressed as ,in, For output channels At time step The value of , are the normalized input impedance real part vector and impedance imaginary part vector, and is the weight of the convolution kernel, which is used for the normalized real impedance vector and imaginary impedance vector, is the bias term of the output channel, is the size of the convolution kernel.

[0082] This normalization operation can be expressed as ,in, For the channels at time step The convolution output of , are the mean and variance, , For scaling and offsetting, Parameter used for numerical stability to avoid zero denominator problems during calculations.

[0083] Step 402: Determine the initial eigenvalue based on the convolutional neural network model and the convolution output.

[0084] In some exemplary embodiments, after the computer device inputs the standardized feature vector into the convolutional neural network model so that the convolutional neural network model performs convolution and normalization operations on the standardized feature vector to obtain a convolution output, the computer device can determine the initial eigenvalue based on the convolutional neural network model and the convolution output.

[0085] Specifically, the computer device can process the convolution output using the activation function based on the convolutional neural network model, which can be expressed as ,in, is the convolution output, is the output value after activation, is the slope of the function.

[0086] Furthermore, the computer device may determine an initial eigenvalue based on the maximum pooling layer in the convolutional neural network model, and the initial eigenvalue may be expressed as .

[0087] In an exemplary embodiment, the target feature value is input into a pre-trained lithium-ion battery capacity estimation model to obtain a battery capacity prediction value of the lithium-ion battery output by the lithium-ion battery capacity estimation model, including: inputting the target feature value into the pre-trained lithium-ion battery capacity estimation model so that the lithium-ion battery capacity estimation model determines a query vector value, a key vector value, and a value vector value based on the target feature value, and determines the battery capacity prediction value of the lithium-ion battery based on the query vector value, the key vector value, and the value vector value.

[0088] The query vector can be used to indicate the importance of the current time step when querying features at other time steps. The key vector can be used to describe the features of each time step so that other time steps can be queried based on them. The value vector can be used to retain feature information and be referenced during weighted summation.

[0089] In some exemplary embodiments, after obtaining the target feature value, the computer device can input the target feature value into a pre-trained lithium-ion battery capacity estimation model, so that the lithium-ion battery capacity estimation model determines the query vector value, the key vector value and the value vector value based on the target feature value, and determines the battery capacity prediction value of the lithium-ion battery based on the query vector value, the key vector value and the value vector value.

[0090] Specifically, the query vector value can be expressed as , where H is the target eigenvalue, is a learnable weight matrix;

[0091] The key vector value can be expressed as ,in, is a learnable weight matrix;

[0092] The value vector can be expressed as ,in, is the learnable weight matrix.

[0093] In an exemplary embodiment, Figure 5 As shown, determining the predicted value of the battery capacity of the lithium-ion battery based on the query vector value, the key vector value, and the value vector value includes the following steps:

[0094] Step 501: Determine a self-attention weight matrix based on the query vector and the key vector.

[0095] Optionally, a self-attention weight matrix can be used to represent the relevance of each time step to other time steps.

[0096] In some exemplary embodiments, after obtaining the query vector, the key vector, and the value vector, the computer device may determine a self-attention weight matrix based on the query vector and the key vector.

[0097] Specifically, the self-attention weight matrix can be expressed as ,in, is the scaling factor.

[0098] Step 502: Determine a predicted value of the battery capacity of the lithium-ion battery based on the self-attention weight matrix and the value vector.

[0099] In some exemplary embodiments, after determining the self-attention weight matrix based on the query vector and the key vector, the computer device can determine the predicted value of the battery capacity of the lithium-ion battery based on the self-attention weight matrix and the value vector.

[0100] Specifically, the computer device performs weighted summation processing based on the self-attention weight matrix and the value vector to determine the battery capacity prediction value of the lithium-ion battery. The battery capacity prediction value of the lithium-ion battery can be expressed as .

[0101] In an optional embodiment of the present application, as described above, the feature extraction model and the lithium-ion battery capacity estimation model are two sub-models in a hybrid model. The hybrid model can be trained based on training data, and the training data can include electrochemical impedance data and battery capacity data of lithium-ion batteries under different cycles.

[0102] Furthermore, HuberLoss can be used as a loss function to evaluate the training of the hybrid model during training. Root mean square error, mean absolute error, and mean absolute percentage error are used as evaluation indicators to assess the generalization ability and robustness of the hybrid model.

[0103] Specifically, the loss function can be expressed as , the root mean square error can be expressed as , the mean absolute error can be expressed as , the mean absolute percentage error can be expressed as ,in, is the true value of the battery capacity of the i-th lithium-ion battery, is the predicted value of the battery capacity of the i-th lithium-ion battery, and n is the total number of samples.

[0104] Furthermore, in order to verify the effectiveness of the hybrid model, the hybrid model can be compared with the single model to output the predicted value of the battery capacity. The specific error can be shown in Table 1. It can be seen that the hybrid model used in this application has a higher accuracy.

[0105] Table 1

[0106]

[0107] In an exemplary embodiment, Figure 6 As shown, another method for estimating the capacity of a lithium-ion battery is provided, the method comprising the following steps:

[0108] Step 601: Obtain electrochemical impedance data of a lithium-ion battery, and construct a feature vector of the lithium-ion battery based on the electrochemical impedance data; perform normalization processing on the feature vector of the lithium-ion battery based on a feature normalization algorithm to obtain a normalized feature vector;

[0109] Step 602: Input the feature vector into the convolutional neural network model, so that the convolutional neural network model performs a convolution operation and a normalization operation on the feature vector to obtain a convolution output; and determine the initial feature value based on the convolutional neural network model and the convolution output.

[0110] Step 603: input the initial eigenvalue into the double-layer long short-term memory network model to obtain the target eigenvalue output by the double-layer long short-term memory network model;

[0111] Step 604: input the target eigenvalue into a pre-trained lithium-ion battery capacity estimation model so that the lithium-ion battery capacity estimation model determines the query vector value, the key vector value, and the value vector value based on the target eigenvalue, and determines the self-attention weight matrix according to the query vector and the key vector; and determines the battery capacity prediction value of the lithium-ion battery according to the self-attention weight matrix and the value vector.

[0112] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily performed in sequence in the order indicated by the arrows. Unless clearly stated herein, the execution of these steps is not strictly limited in order, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of the steps or stages in other steps or other steps. It is understandable that the various steps in different embodiments can be freely combined as needed, and the various non-contradictory schemes formed by the combination all fall within the scope of protection of this application.

[0113] Based on the same inventive concept, embodiments of the present application also provide a lithium-ion battery capacity estimation device for implementing the aforementioned lithium-ion battery capacity estimation method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more of the following embodiments of the lithium-ion battery capacity estimation device can be found in the limitations of the lithium-ion battery capacity estimation method described above and will not be further elaborated here.

[0114] In an exemplary embodiment, Figure 7 As shown, a lithium-ion battery capacity estimation device 700 is provided, comprising: an acquisition module 701, a first execution module 702 and a second execution module 703, wherein:

[0115] An acquisition module 701 is configured to acquire electrochemical impedance data of a lithium-ion battery and construct a characteristic vector of the lithium-ion battery based on the electrochemical impedance data.

[0116] A first execution module 702 is configured to determine a target feature value of the lithium-ion battery based on a feature vector of the lithium-ion battery and a pre-trained feature extraction model;

[0117] The second execution module 703 is configured to input the target feature value into a pre-trained lithium-ion battery capacity estimation model to obtain a battery capacity prediction value of the lithium-ion battery output by the lithium-ion battery capacity estimation model.

[0118] In one embodiment, the first execution module 702 is specifically used to normalize the feature vector of the lithium-ion battery based on a feature normalization algorithm to obtain a standardized feature vector; and input the standardized feature vector into a pre-trained feature extraction model to obtain a target feature value of the lithium-ion battery output by the feature extraction model.

[0119] In one embodiment, the feature extraction model includes a convolutional neural network model and a double-layer long short-term memory network model. The first execution module 702 is specifically used to input the standardized feature vector into the convolutional neural network model to obtain the initial feature value output by the convolutional neural network model; and input the initial feature value into the double-layer long short-term memory network model to obtain the target feature value output by the double-layer long short-term memory network model.

[0120] In one embodiment, the first execution module 702 is specifically used to input the standardized feature vector into the convolutional neural network model, so that the convolutional neural network model performs convolution and normalization operations on the standardized feature vector to obtain a convolution output; and determine the initial eigenvalue based on the convolutional neural network model and the convolution output.

[0121] In one embodiment, the second execution module 703 is specifically used to input the target feature value into a pre-trained lithium-ion battery capacity estimation model, so that the lithium-ion battery capacity estimation model determines the query vector value, the key vector value and the value vector value based on the target feature value, and determines the battery capacity prediction value of the lithium-ion battery based on the query vector value, the key vector value and the value vector value.

[0122] In one embodiment, the second execution module 703 is specifically used to determine a self-attention weight matrix based on the query vector and the key vector; and determine a predicted value of the battery capacity of the lithium-ion battery based on the self-attention weight matrix and the value vector.

[0123] Each module in the aforementioned lithium-ion battery capacity estimation device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0124] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 8As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for estimating the capacity of a lithium-ion battery is implemented.

[0125] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 9 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a method for estimating the capacity of a lithium-ion battery is implemented.

[0126] Those skilled in the art will understand that Figure 8 and Figure 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0127] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0128] Acquiring electrochemical impedance data of a lithium-ion battery and constructing a characteristic vector of the lithium-ion battery based on the electrochemical impedance data;

[0129] Determining a target feature value of the lithium-ion battery based on a feature vector of the lithium-ion battery and a pre-trained feature extraction model;

[0130] The target characteristic value is input into a pre-trained lithium-ion battery capacity estimation model to obtain a battery capacity prediction value of the lithium-ion battery output by the lithium-ion battery capacity estimation model.

[0131] In one embodiment, when the processor executes the computer program, it further implements the following steps: normalizing the feature vector of the lithium-ion battery based on a feature normalization algorithm to obtain a standardized feature vector; and inputting the standardized feature vector into a pre-trained feature extraction model to obtain a target feature value of the lithium-ion battery output by the feature extraction model.

[0132] In one embodiment, when the processor executes the computer program, it also implements the following steps: inputting the standardized feature vector into the convolutional neural network model to obtain the initial feature value output by the convolutional neural network model; inputting the initial feature value into the double-layer long short-term memory network model to obtain the target feature value output by the double-layer long short-term memory network model.

[0133] In one embodiment, when the processor executes the computer program, it also implements the following steps: inputting the standardized feature vector into the convolutional neural network model so that the convolutional neural network model performs convolution and normalization operations on the standardized feature vector to obtain a convolution output; and determining the initial eigenvalue based on the convolutional neural network model and the convolution output.

[0134] In one embodiment, when the processor executes the computer program, the following steps are further implemented: the target feature value is input into a pre-trained lithium-ion battery capacity estimation model, so that the lithium-ion battery capacity estimation model determines a query vector value, a key vector value, and a value vector value based on the target feature value, and determines a predicted battery capacity value of the lithium-ion battery based on the query vector value, the key vector value, and the value vector value.

[0135] In one embodiment, when the processor executes the computer program, it further implements the following steps: determining a self-attention weight matrix based on the query vector and the key vector; and determining a predicted value of the battery capacity of the lithium-ion battery based on the self-attention weight matrix and the value vector.

[0136] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0137] Acquiring electrochemical impedance data of a lithium-ion battery and constructing a characteristic vector of the lithium-ion battery based on the electrochemical impedance data;

[0138] Determining a target feature value of the lithium-ion battery based on a feature vector of the lithium-ion battery and a pre-trained feature extraction model;

[0139] The target characteristic value is input into a pre-trained lithium-ion battery capacity estimation model to obtain a battery capacity prediction value of the lithium-ion battery output by the lithium-ion battery capacity estimation model.

[0140] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: normalizing the feature vector of the lithium-ion battery based on a feature normalization algorithm to obtain a normalized feature vector; and inputting the normalized feature vector into a pre-trained feature extraction model to obtain a target feature value of the lithium-ion battery output by the feature extraction model.

[0141] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the standardized feature vector is input into the convolutional neural network model to obtain the initial feature value output by the convolutional neural network model; the initial feature value is input into the double-layer long short-term memory network model to obtain the target feature value output by the double-layer long short-term memory network model.

[0142] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: inputting the standardized feature vector into the convolutional neural network model so that the convolutional neural network model performs convolution and normalization operations on the standardized feature vector to obtain a convolution output; and determining the initial eigenvalue based on the convolutional neural network model and the convolution output.

[0143] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: the target feature value is input into a pre-trained lithium-ion battery capacity estimation model, so that the lithium-ion battery capacity estimation model determines a query vector value, a key vector value, and a value vector value based on the target feature value, and determines a predicted battery capacity value of the lithium-ion battery based on the query vector value, the key vector value, and the value vector value.

[0144] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determining a self-attention weight matrix based on the query vector and the key vector; and determining a predicted value of the battery capacity of the lithium-ion battery based on the self-attention weight matrix and the value vector.

[0145] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0146] Acquiring electrochemical impedance data of a lithium-ion battery and constructing a characteristic vector of the lithium-ion battery based on the electrochemical impedance data;

[0147] Determining a target feature value of the lithium-ion battery based on a feature vector of the lithium-ion battery and a pre-trained feature extraction model;

[0148] The target characteristic value is input into a pre-trained lithium-ion battery capacity estimation model to obtain a battery capacity prediction value of the lithium-ion battery output by the lithium-ion battery capacity estimation model.

[0149] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: normalizing the feature vector of the lithium-ion battery based on a feature normalization algorithm to obtain a normalized feature vector; and inputting the normalized feature vector into a pre-trained feature extraction model to obtain a target feature value of the lithium-ion battery output by the feature extraction model.

[0150] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the standardized feature vector is input into the convolutional neural network model to obtain the initial feature value output by the convolutional neural network model; the initial feature value is input into the double-layer long short-term memory network model to obtain the target feature value output by the double-layer long short-term memory network model.

[0151] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: inputting the standardized feature vector into the convolutional neural network model so that the convolutional neural network model performs convolution and normalization operations on the standardized feature vector to obtain a convolution output; and determining the initial eigenvalue based on the convolutional neural network model and the convolution output.

[0152] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: the target feature value is input into a pre-trained lithium-ion battery capacity estimation model, so that the lithium-ion battery capacity estimation model determines a query vector value, a key vector value, and a value vector value based on the target feature value, and determines a predicted battery capacity value of the lithium-ion battery based on the query vector value, the key vector value, and the value vector value.

[0153] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determining a self-attention weight matrix based on the query vector and the key vector; and determining a predicted value of the battery capacity of the lithium-ion battery based on the self-attention weight matrix and the value vector.

[0154] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0155] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0156] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for estimating the capacity of a lithium-ion battery, characterized in that: The method comprises: Acquiring electrochemical impedance data of a lithium-ion battery, and constructing a characteristic vector of the lithium-ion battery based on the electrochemical impedance data; Determining a target feature value of the lithium-ion battery based on a feature vector of the lithium-ion battery and a pre-trained feature extraction model; The target characteristic value is input into a pre-trained lithium-ion battery capacity estimation model to obtain a battery capacity prediction value of the lithium-ion battery output by the lithium-ion battery capacity estimation model.

2. The method according to claim 1, characterized in that The target characteristic value of the lithium-ion battery is determined based on the characteristic vector of the lithium-ion battery and a pre-trained feature extraction model. include: Performing standardization on the feature vector of the lithium-ion battery based on a feature standardization algorithm to obtain a standardized feature vector; The standardized feature vector is input into a pre-trained feature extraction model to obtain the target feature value of the lithium-ion battery output by the feature extraction model.

3. The method according to claim 2, characterized in that The feature extraction model includes a convolutional neural network model and a double-layer long short-term memory network model. The standardized feature vector is input into a pre-trained feature extraction model to obtain the target feature value of the lithium-ion battery output by the feature extraction model, including: Inputting the normalized feature vector into the convolutional neural network model to obtain an initial feature value output by the convolutional neural network model; The initial eigenvalue is input into the double-layer long short-term memory network model to obtain the target eigenvalue output by the double-layer long short-term memory network model.

4. The method according to claim 3, characterized in that Inputting the normalized feature vector into the convolutional neural network model to obtain an initial feature value output by the convolutional neural network model includes: Inputting the standardized feature vector into the convolutional neural network model, so that the convolutional neural network model performs a convolution operation and a normalization operation on the standardized feature vector to obtain a convolution output; The initial eigenvalue is determined based on the convolutional neural network model and the convolution output.

5. The method according to claim 1, wherein Inputting the target characteristic value into a pre-trained lithium-ion battery capacity estimation model to obtain a battery capacity prediction value of the lithium-ion battery output by the lithium-ion battery capacity estimation model includes: The target feature value is input into a pre-trained lithium-ion battery capacity estimation model, so that the lithium-ion battery capacity estimation model determines a query vector value, a key vector value, and a value vector value based on the target feature value, and determines a battery capacity prediction value of the lithium-ion battery based on the query vector value, the key vector value, and the value vector value.

6. The method according to claim 5, characterized in that The determining the predicted value of the battery capacity of the lithium-ion battery based on the query vector value, the key vector value, and the value vector value includes: Determine a self-attention weight matrix based on the query vector and the key vector; A predicted value of the battery capacity of the lithium-ion battery is determined based on the self-attention weight matrix and the value vector.

7. A capacity estimation device for a lithium-ion battery, characterized in that: The device comprises: an acquisition module, configured to acquire electrochemical impedance data of a lithium-ion battery and construct a characteristic vector of the lithium-ion battery based on the electrochemical impedance data; A first execution module is configured to determine a target feature value of the lithium-ion battery based on a feature vector of the lithium-ion battery and a pre-trained feature extraction model; The second execution module is used to input the target feature value into a pre-trained lithium-ion battery capacity estimation model to obtain a battery capacity prediction value of the lithium-ion battery output by the lithium-ion battery capacity estimation model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images