Battery charge state estimation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a battery charge state estimation method and device, electronic equipment and a storage medium. Comprising the following steps: in response to a state-of-charge estimation request of a target battery, determining a first state-of-charge of the target battery at the current moment calculated based on an ampere-hour integration method; determining a plurality of candidate identification parameter data of a fractional order equivalent circuit model corresponding to the target battery, and taking the candidate identification parameter data, meeting relevant conditions with the state of charge, in the plurality of candidate identification parameter data as target identification parameter data; inputting the target identification parameter data into a pre-trained battery charge state prediction model to obtain a second charge state of the target battery at the current moment; and determining a real-time state of charge of the target battery at the current moment based on the first state of charge and the second state of charge. According to the technical scheme of the embodiment of the invention, high-precision estimation of the state of charge of the battery is realized, and the influence of accumulative errors on an estimation result is reduced.

Description

Technical Field

[0001] Embodiments of the present invention relate to the technical field of batteries, and in particular, to a method, device, electronic device, and storage medium for estimating the state of charge of a battery. Background Art

[0002] In related technologies, the ampere-hour integration method is usually used to estimate the state of charge (SOC) of a battery. Specifically, according to the current and time of battery charging and discharging, the amount of charge charged or discharged by the battery is calculated by integration, so as to estimate the state of charge of the battery. However, using this method has the problem of long-term cumulative error, which leads to inaccurate estimation of the state of charge of the battery. Summary of the Invention

[0003] In view of the above problems, the present invention provides a method, device, electronic device, and storage medium for estimating the state of charge of a battery, so as to solve the technical problem that the estimation accuracy is low due to the cumulative error when using the ampere-hour integration method to estimate the state of charge of a battery in related technologies.

[0004] According to one aspect of the present invention, there is provided a method for estimating the state of charge of a battery, the method including:

[0005] In response to a request for estimating the state of charge of a target battery, determining a first state of charge of the target battery at the current moment calculated based on the ampere-hour integration method;

[0006] Determining a plurality of candidate identification parameter data of a fractional-order equivalent circuit model corresponding to the target battery, and using the candidate identification parameter data that meets the relevant conditions with the state of charge among the plurality of candidate identification parameter data as the target identification parameter data;

[0007] Inputting the target identification parameter data into a pre-trained battery state-of-charge prediction model to obtain a second state of charge of the target battery at the current moment;

[0008] Based on the first state of charge and the second state of charge, determining the real-time state of charge of the target battery at the current moment.

[0009] According to another aspect of the present invention, there is provided a device for estimating the state of charge of a battery. The device includes:

[0010] A first state-of-charge determination module, configured to, in response to a request for estimating the state of charge of a target battery, determine a first state of charge of the target battery at the current moment calculated based on the ampere-hour integration method;

[0011] An identification parameter data determination module, configured to determine a plurality of candidate identification parameter data of a fractional-order equivalent circuit model corresponding to the target battery, and use the candidate identification parameter data that meets the relevant conditions with the state of charge as the target identification parameter data;

[0012] A second state of charge determination module, configured to input the target identification parameter data into a pre-trained battery state of charge prediction model to obtain a second state of charge of the target battery at the current moment;

[0013] A real-time state of charge determination module, configured to determine a real-time state of charge of the target battery at the current moment based on the first state of charge and the second state of charge.

[0014] According to another aspect of the present invention, there is provided an electronic device, the electronic device includes:

[0015] One or more processors;

[0016] A storage device, configured to store one or more programs,

[0017] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for estimating the state of charge of a battery as described in any one of the embodiments of the present disclosure.

[0018] According to another aspect of the present invention, there is provided a computer-readable storage medium, the computer-readable storage medium stores computer instructions, and the computer instructions are used to implement the method for estimating the state of charge of a battery as described in any one of the present inventions when executed by a processor.

[0019] In the technical solution of the embodiment of the present invention, in response to a request for estimating the state of charge of a target battery, a first state of charge of the target battery at the current moment calculated based on the ampere-hour integration method is determined. A plurality of candidate identification parameter data of a fractional-order equivalent circuit model corresponding to the target battery are determined, and the candidate identification parameter data that meet the relevant conditions with the state of charge among the plurality of candidate identification parameter data are used as the target identification parameter data, so as to dynamically obtain the parameter values of the identification parameters of the fractional-order equivalent circuit model. Furthermore, the target identification parameter data is input into a pre-trained battery state-of-charge prediction model to obtain a second state of charge of the target battery at the current moment, and the state of charge of the battery can be predicted more conveniently and accurately through the prediction model. Based on the first state of charge and the second state of charge, the real-time state of charge of the target battery at the current moment is determined, so as to correct the first state of charge through the second state of charge, thereby improving the accuracy of the battery state of charge. The technical solution of the embodiment of the present invention solves the technical problem that the estimation accuracy is low due to the cumulative error when the ampere-hour integration method is used to estimate the state of charge of the battery in the related art, realizes the high-precision estimation of the state of charge of the battery, and reduces the influence of the cumulative error on the estimation result.

[0020] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0022] Figure 1 It is a schematic flowchart of a method for estimating the state of charge of a battery provided by an embodiment of the present invention;

[0023] Figure 2 It is a schematic flowchart of a method for estimating the state of charge of a battery provided by an embodiment of the present invention;

[0024] Figure 3 It is a schematic structural diagram of a fractional-order equivalent circuit model applicable to a method for estimating the state of charge of a battery provided in an embodiment of the present invention;

[0025] Figure 4 It is a schematic structural diagram of a device for estimating the state of charge of a battery provided by an embodiment of the present invention;

[0026] Figure 5 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. Specific implementation manners

[0027] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order different from those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0029] It can be understood that the data involved in the technical solution of the present invention (including but not limited to the data itself, the acquisition or use of the data) should comply with the requirements of relevant laws, regulations and related regulations.

[0030] Figure 1 A schematic flowchart of a method for estimating the state of charge of a battery provided by an embodiment of the present invention. This embodiment is applicable to the situation of estimating the state of charge of a battery. This method can be executed by a device for estimating the state of charge of a battery. The device for estimating the state of charge of a battery can be implemented in the form of hardware and / or software. The device for estimating the state of charge of a battery can be configured in an electronic device such as a computer or a server. As Figure 1 shown, the method of this embodiment includes:

[0031] S110. In response to a request for estimating the state of charge of a target battery, determine a first state of charge of the target battery at the current moment calculated based on the ampere-hour integration method.

[0032] Among them, the target battery can be the battery for which the state of charge is to be estimated. The state of charge (SOC) of a battery is a representative indicator of the remaining battery charge, which describes the ratio of the remaining capacity of the battery after being used for a period of time or left unused for a long time to the capacity in its fully charged state. Optionally, the target battery can be a vehicle battery. The technical solution in the embodiment of the present invention can be applied to estimate the state of charge of the vehicle battery of the target vehicle when the vehicle is in a running state or a stationary state. In practical applications, SOC can be a value between 0 and 1 (usually expressed as a percentage). It can be understood that SOC = 0% can indicate that the battery is completely discharged, that is, the battery can no longer provide power. SOC = 100% can indicate that the battery is fully charged, that is, the battery is in a fully charged state. In the embodiment of the present invention, the target battery can be a vehicle battery. The state of charge estimation request can be understood as a request for estimating the state of charge of the target battery at the current moment. In the embodiment of the present invention, after receiving the state of charge estimation request of the target battery, the ampere-hour integration method can be used to estimate the state of charge of the target battery at the current moment, so as to obtain the state of charge of the target battery at the current moment, that is, the first state of charge.

[0033] S120. Determine a plurality of candidate identification parameter data of the fractional-order equivalent circuit model corresponding to the target battery, and use the candidate identification parameter data that meets the relevant conditions with the state of charge among the plurality of candidate identification parameter data as the target identification parameter data.

[0034] In the embodiment of the present invention, the fractional-order equivalent circuit model can be used to accurately simulate the electrochemical process of the target battery, so as to more accurately predict the state of charge of the target battery. The candidate identification parameter data can be understood as the identification parameter data related to the electrochemical characteristics of the target battery in the fractional-order equivalent circuit model. In the embodiment of the present invention, the candidate identification parameter data of the fractional-order equivalent circuit model can be pre-set model parameter data. The target identification parameter data can be understood as the candidate identification parameter data related to the electrochemical characteristics of the target battery in the fractional-order equivalent circuit model at the current moment. It can be understood that the target identification parameter data of the target battery at different moments can be the same or different. In the embodiment of the present invention, the target identification parameter data can also reflect the state of health (SOH) of the battery and can be used to correct the battery capacity of the target battery. Based on this, the estimation accuracy of the state of charge of the target battery can be improved by adding the aging factor.

[0035] Specifically, after receiving the request for estimating the state of charge of the target battery, a plurality of candidate identification parameter data of the fractional-order equivalent circuit model corresponding to the target battery can be determined. Furthermore, the candidate identification parameter data related to the electrochemical characteristics of the target battery at the current moment can be determined from the plurality of candidate identification parameter data, and the determined identification parameter data is used as the target identification parameter data of the fractional-order equivalent circuit model.

[0036] In the embodiment of the present invention, the online identification parameters of the fractional-order equivalent circuit model can be obtained by updating the ARSR (adaptive recursive square root) algorithm parameters, gain matrix, model parameter matrix, forgetting factor, and algorithm parameters, that is, the parameter values of the identification parameters of the fractional-order equivalent circuit model at the current moment.

[0037] Optionally, the ARSR algorithm parameters can be updated by the following formula:

[0038] f k =S K-1 T H k T

[0039] g k =(f k T f k +λ k-1 ) -1

[0040]

[0041] Wherein, f k represents the frequency vector. S K-1 represents the state vector at the previous moment. H k represents the observation matrix. T represents the state transition matrix. g k represents the gain factor. λ k-1 represents the forgetting factor at the previous moment. a k represents the adaptive factor.

[0042] Optionally, the gain matrix can be updated by the following formula:

[0043] K k =S k-1 f k g k

[0044] Wherein, K k represents the Kalman gain.

[0045] Optionally, the model parameter matrix can be updated by the following formula:

[0046]

[0047] Among them, e k represents the observation error. U t,k represents the battery terminal voltage (observed value). represents the product of the observation matrix and the state estimate at the previous moment. represents the state estimate at the current moment. represents the state estimate at the previous moment. K k ·e k represents the product of the Kalman gain and the observation error.

[0048] Optionally, the forgetting factor can be updated by the following formula:

[0049] λ k = 1 - [1 - H k K k e k 2 / Σ0

[0050] Among them, λ k represents the forgetting factor at the current moment.

[0051] Optionally, the algorithm parameters can be updated by the following formula:

[0052]

[0053] Among them, S k represents the state vector at the current moment. λ k represents the forgetting factor at the current moment.

[0054] S130. Input the target identification parameter data into the pre-trained state of charge prediction model of the battery to obtain the second state of charge of the target battery at the current moment.

[0055] Among them, the state of charge prediction model of the battery can be understood as a pre-trained prediction model for predicting the state of charge of the target battery based on the target identification parameter data. In the embodiment of the present invention, the state of charge prediction model of the battery can be trained based on the support vector machine regression model. The second state of charge can be understood as the state of charge of the target battery predicted by the state of charge prediction model of the battery based on the target identification parameter data at the current moment.

[0056] In an embodiment of the present invention, the method for obtaining the battery state of charge prediction model may include: constructing a to-be-trained state of charge prediction model; obtaining a plurality of training sample data and corresponding expected result data for each of the training sample data, wherein the training sample data includes sample identification parameter data of the battery at historical moments, and the expected result data is the historical state of charge of the battery at the historical moments; inputting the training sample data into the to-be-trained state of charge prediction model to obtain an actual output result, and adjusting the model parameters of the to-be-trained state of charge prediction model based on the actual output result and the expected result data to obtain a trained battery state of charge prediction model.

[0057] In an embodiment of the present invention, the to-be-trained state of charge prediction model can be set according to actual needs, and specific limitations are not made herein. Optionally, the to-be-trained state of charge prediction model can be constructed based on a support vector machine regression model (Support Vector Machine, SVM) using a Gaussian kernel function. In an embodiment of the present invention, using a support vector machine regression model with a Gaussian kernel function to construct a prediction model for predicting the battery state of charge can efficiently handle the non-linear relationship in battery state of charge prediction, capture complex dynamic characteristics by mapping to a high-dimensional space, thereby improving the prediction accuracy and stability of the battery state of charge.

[0058] In an embodiment of the present invention, the training sample data may include sample identification parameter data of the battery at historical moments. The expected result data may be the historical state of charge of the battery at the historical moments. The historical state of charge can be understood as the state of charge of the battery at historical moments. The actual output result may be the state of charge output by the to-be-trained state of charge prediction model after inputting the sample identification parameter data of the battery at historical moments into the to-be-trained state of charge prediction model.

[0059] In an embodiment of the present invention, after obtaining the training sample data, the kernel function of the to-be-trained battery state of charge prediction model can be used to map the sample from the original space to a higher-dimensional feature space, thereby obtaining processed training sample data.

[0060] Optionally, the kernel function of the to-be-trained battery state of charge prediction model can be

[0061] K(x i -x j )=exp(-γ||x i -x j || 2 )

[0062] wherein, x i and x jare the support vector and the input feature vector respectively, γ is a parameter for controlling the model complexity, ||x i -x j || 2 is the squared Euclidean distance between the two.

[0063] In an embodiment of the present invention, based on the actual output result and the expected result data, the model parameters of the to-be-trained state of charge prediction model are adjusted to obtain a trained state of charge prediction model for the battery, which may include: determining the function value of a preset loss function based on the actual output result and the expected result data, and adjusting the to-be-corrected model parameters in the to-be-trained state of charge prediction model according to the function value; taking the convergence of the preset loss function as the training objective, and training the to-be-trained state of charge prediction model to obtain a trained state of charge prediction model for the battery. In an embodiment of the present invention, the to-be-corrected model parameters may be at least part of the model parameters in the model.

[0064] In an embodiment of the present invention, a to-be-battery state of charge prediction model is constructed based on a support vector machine regression model. The optimization problem of the to-be-trained battery state of charge prediction model can be represented by the following formula:

[0065]

[0066] Among them, the constraint conditions of the above optimization problem are:

[0067]

[0068] Among them, w represents the weight vector, b represents the bias, ξ represents the slack variable, and C represents the penalty parameter, which is used to control the trade-off between the training error and the model complexity.

[0069] Based on this, by introducing Lagrange multipliers, the above optimization problem can be transformed into a Lagrangian dual problem. Furthermore, the Lagrangian dual problem is solved, that is, the result and solution method for constructing the state of charge prediction model for the battery are obtained.

[0070] In an embodiment of the present invention, a grid search can be used to systematically traverse the predefined hyperparameter combinations in the to-be-battery state of charge prediction model. Thus, the optimal parameter configuration in the to-be-battery state of charge prediction model can be determined to train the support vector machine regression model, that is, to train the to-be-battery state of charge prediction model.

[0071] In an embodiment of the present invention, the training error of the loss function can be used as a condition for detecting whether the loss function has reached convergence, such as whether the training error is less than a preset error, or whether the error change trend tends to be stable, or whether the current number of iterations is equal to a preset number. If it is detected that the convergence condition is met, such as the training error of the loss function reaching less than the preset error or the error change tending to be stable, it indicates that the training of the initial state of charge prediction model for the battery is completed, and at this time, the iterative training can be stopped. If it is detected that the current convergence condition is not met, the training sample data in the training sample data can be further obtained to train the state of charge prediction model for the battery to be trained until the training error of the loss function is within the preset range. When the training error of the loss function reaches convergence, the state of charge prediction model for the battery to be trained can be used as the state of charge prediction model for the battery. The state of charge of the target battery at the current moment can be determined based on the trained state of charge prediction model for the battery.

[0072] Furthermore, in order to ensure the accuracy of the trained state of charge prediction model for the battery, after obtaining the trained state of charge prediction model for the battery, the trained state of charge prediction model for the battery can also be tested. Specifically, the test sample data can be input into the trained state of charge prediction model for the battery to obtain the test output data corresponding to the training sample data; furthermore, the accuracy of the trained state of charge prediction model for the battery can be determined based on the expected result data corresponding to the test sample data and the test output data. When the accuracy is lower than the preset accuracy threshold, the hyperparameters, training samples, or network structure of the training are optimized, and based on the optimized hyperparameters, training samples, or network structure of the training, the state of charge prediction model for the battery to be trained is retrained until the accuracy of the output result of the state of charge prediction model for the battery to be trained is higher than the preset accuracy threshold.

[0073] Based on the above embodiments, after obtaining the sample data, the sample data can be divided into training sample data and test sample data. Optionally, the sample data can be divided into training sample data and test sample data at a preset ratio. Among them, the preset ratio can be set according to actual needs, and no specific limitation is made here. For example, 7:3 or 6:4.

[0074] In an embodiment of the present invention, K-fold cross-validation can be used to optimize the hyperparameters, which can improve the model performance to ensure the stability and generalization ability of the model. In addition, in an embodiment of the present invention, the state of charge prediction model for the battery can also be evaluated. For example, at least one evaluation index among the evaluation indexes mean square error (MSE), mean absolute error (MAE), and coefficient of determination (R 2 ) can be selected for model evaluation.

[0075] It should be noted that, compared with training based on an equivalent circuit model to establish a more complex SOC prediction model, the battery state of charge prediction model in the embodiments of the present invention does not need to run all the time, and only needs to run during the battery impedance test stage, which can reduce the computing power requirement. In addition, in the embodiments of the present invention, the combination of the equivalent circuit model and machine learning makes the determination of the battery state of charge more physically interpretable, with less computational complexity and better generalization ability.

[0076] S140. Determine the real-time state of charge of the target battery at the current moment based on the first state of charge and the second state of charge.

[0077] Among them, the implemented state of charge can be understood as the state of charge of the target battery at the current moment. Specifically, the first state of charge and the second state of charge can be weighted and summed to obtain a weighted sum result, that is, the real-time state of charge of the target battery at the current moment is obtained. It should be noted that in the embodiments of the present invention, the weights corresponding to the first state of charge and the second state of charge can be set according to actual needs, and no specific limitation is made here. It should be noted that the sum of the weight corresponding to the first state of charge and the weight corresponding to the second state of charge is 1. In the embodiments of the present invention, the state of charge obtained by the battery state of charge prediction model obtained through a machine learning algorithm is used to correct the state of charge calculated by ampere-hour integration. That is, by combining with ampere-hour integration, when efficiently calculating the state of charge of the battery, not only can the accuracy be improved, but also the disadvantages of cumulative error and initial error can be solved.

[0078] In the embodiments of the present invention, the determining the real-time state of charge of the target battery at the current moment based on the first state of charge and the second state of charge may include: using the Kalman filter algorithm to determine the real-time state of charge of the target battery at the current moment based on the first state of charge and the second state of charge. In the embodiments of the present invention, the Kalman filter algorithm effectively fuses the measurement value and the model prediction through recursive estimation, thereby improving the estimation accuracy of the state of charge of the target battery. It should be noted that the technical solution of the embodiments of the present invention can more accurately reflect the actual state of charge of the battery in the battery management system, providing a reliable basis for the safe use, charge and discharge control, and life prediction of the battery; in application fields such as electric vehicles and energy storage systems, it improves the energy utilization efficiency and system performance, and reduces the energy waste and safety hazards caused by inaccurate battery state estimation.

[0079] In the technical solution of the embodiment of the present invention, in response to a request for estimating the state of charge of a target battery, a first state of charge of the target battery at the current moment calculated based on the ampere-hour integration method is determined. A plurality of candidate identification parameter data of a fractional-order equivalent circuit model corresponding to the target battery are determined, and the candidate identification parameter data that meets the relevant conditions for the state of charge among the plurality of candidate identification parameter data is used as the target identification parameter data. The target identification parameter data is input into a pre-trained battery state of charge prediction model to obtain a second state of charge of the target battery at the current moment. Based on the first state of charge and the second state of charge, the real-time state of charge of the target battery at the current moment is determined. The technical solution of the embodiment of the present invention solves the technical problem that the estimation accuracy is low due to the cumulative error when the ampere-hour integration method is used to estimate the state of charge of the battery in the related art, realizes the high-precision estimation of the state of charge of the battery, and reduces the influence of the cumulative error on the estimation result.

[0080] Figure 2 FIG. is a schematic flow chart of a method for estimating the state of charge of a battery provided by an embodiment of the present invention. On the basis of the foregoing embodiment, optionally, the determining a plurality of candidate identification parameter data of a fractional-order equivalent circuit model corresponding to the target battery includes: performing impedance tests on the target battery under different preset states of charge through a battery test device to obtain Nyquist curves of the target battery under different preset states of charge; establishing a fractional-order equivalent circuit model of the target battery according to the Nyquist curves, where the fractional-order equivalent circuit model includes a plurality of initial identification parameter data; and determining a plurality of candidate identification parameter data of the fractional-order equivalent circuit model corresponding to the target battery based on the plurality of initial identification parameter data. The technical features that are the same as or similar to those in the above embodiment will not be described in detail herein.

[0081] As Figure 2 shown, the method of this embodiment specifically includes:

[0082] S210. In response to a request for estimating the state of charge of a target battery, determine a first state of charge of the target battery at the current moment calculated based on the ampere-hour integration method.

[0083] S220. Perform impedance tests on the target battery under different preset states of charge through a battery test device to obtain Nyquist curves of the target battery under different preset states of charge.

[0084] Among them, the battery testing device may include an electrochemical workstation and an incubator; or, an impedance analyzer and an incubator. Among them, the incubator can be used to control the test environment temperature to ensure temperature stability. Before using the battery testing device to perform impedance testing on the target battery, the target battery can also be subjected to charge and discharge pretreatment to eliminate historical effects and homogenize the state of charge of the battery. In the embodiments of the present invention, the working electrode, reference electrode, and auxiliary electrode (if any) of the electrochemical workstation can be correctly connected to the positive and negative electrodes of the target battery. When the electrochemical workstation and the battery are electrically connected, based on the preset scanning frequency range and the input signal amplitude, the system will measure the impedance of the battery at different frequencies, that is, perform impedance testing on the battery under different preset states of charge. Among them, the preset scanning frequency range is that the electrochemical workstation applies a series of alternating current signals with different frequencies (such as 10 mHz to 100 kHz).

[0085] In the embodiments of the present invention, different preset states of charge can be set according to actual needs. For example, 100%, 75%, 50%, 25%, 0%. In the embodiments of the present invention, performing impedance testing on the target battery under different preset states of charge includes: performing impedance testing on the target battery under different preset states of charge at different numbers of cycles; among them, different numbers of cycles can be set according to actual needs. For example, 0, 1, 40, 100, 140, 200, 240, 280, 300 cycles.

[0086] In the embodiments of the present invention, the impedance testing of the target battery is performed through the battery testing device, and the impedance test results are visually represented. Specifically, by plotting the trajectories of the real part and the imaginary part of the impedance as a function of frequency, the Nyquist curve of the target battery under different preset states of charge is obtained, so as to intuitively reflect the electrochemical process inside the target battery.

[0087] S230. Establish a fractional-order equivalent circuit model of the target battery according to the Nyquist curve, where the fractional-order equivalent circuit model includes a plurality of initial identification parameter data.

[0088] Such as Figure 3As shown, in the embodiment of the present invention, the fractional-order equivalent circuit model of the target battery includes an ohmic resistance R0, a solid electrolyte interface film capacitance C1 and a resistance R1, a charge transfer resistance R2, and a double-layer capacitance C2. Due to the diffusion resistance in the transfer of particles inside the battery, a diffusion impedance is added to the fractional-order equivalent circuit model of the target battery. In the embodiment of the present invention, according to the battery impedance test results, a fractional-order equivalent circuit model is built. Without increasing the complexity of the RC network, the accuracy of the equivalent circuit algorithm can be improved, and it is more suitable for the target battery being tested. Among them, the RC network is composed of resistance (R) and capacitance (C) elements, and can form series, parallel or more complex series-parallel structures.

[0089] Optionally, the transfer function of the fractional-order equivalent circuit model of the target battery is represented by the following formula:

[0090]

[0091] Wherein, U d (s) represents the Laplace transform of the output voltage. U ocv (s) represents the Laplace transform of the open-circuit voltage. I(s) represents the Laplace transform of the current. W represents the impedance of the diffusion process. s represents the complex variable of the Laplace transform. v represents the order of the fractional derivative. r represents the model parameter of the fractional-order equivalent circuit model, which can be related to the diffusion impedance. k represents the coefficient of the diffusion impedance.

[0092] Based on this, the frequency-domain system can be transformed into a time-domain system and discretized, and the following can be obtained:

[0093]

[0094] Wherein, WD r y(t) represents the fractional derivative term corresponding to the diffusion impedance. R1C1D v u(t) represents the fractional derivative term of the R1-C1 network with respect to Ouyang. y(t) represents the voltage difference, y(t)=U d (t)-Uocv(t). U d (t) represents the output voltage (terminal voltage). Uocv(t) represents the open-circuit voltage. u(t) represents the current, u(t)=I(t). I(t) represents the current. T represents the sampling period. N represents the number of sampling points. i represents the discrete-time index. v represents the order of the fractional derivative. r represents the model parameter of the fractional-order equivalent circuit model, which can be related to the diffusion impedance. k represents the coefficient of the diffusion impedance.

[0095] In an embodiment of the present invention, after discretizing the frequency-domain system, multiple identification parameters of the fractional-order equivalent circuit model are θ = [R0, R1, R2, C1, C2, W, v, k, r]. It can be understood that the initial identification parameter data are the initial values corresponding to each identification parameter of the fractional-order equivalent circuit model.

[0096] S240. Determine multiple candidate identification parameter data of the fractional-order equivalent circuit model corresponding to the target battery based on the multiple initial identification parameter data.

[0097] In an embodiment of the present invention, the multiple candidate identification parameter data of the fractional-order equivalent circuit model may be the multiple initial identification parameter data of the fractional-order equivalent circuit model; or, they may be parameter data obtained after adjusting at least part of the initial identification parameter data.

[0098] In an embodiment of the present invention, the determining multiple candidate identification parameter data of the fractional-order equivalent circuit model corresponding to the target battery based on the multiple initial identification parameter data includes: determining first electrochemical characteristic data of the target battery obtained based on the multiple initial identification parameter data in the fractional-order equivalent circuit model, where the initial identification parameter data are parameter values obtained after initializing the identification parameters of the fractional-order equivalent circuit model; obtaining second electrochemical characteristic data obtained by testing the target battery with an electrochemical characteristic testing device; and determining multiple candidate identification parameter data of the fractional-order equivalent circuit model corresponding to the target battery based on the first electrochemical characteristic data and the second electrochemical characteristic data.

[0099] Among them, the first electrochemical characteristic data can be understood as electrochemical characteristic data obtained through the multiple initial identification parameter data in the fractional-order equivalent circuit model. The second electrochemical characteristic data can be understood as electrochemical characteristic data obtained by testing the target battery with an electrochemical characteristic testing device. Optionally, the first electrochemical characteristic data may be the voltage difference obtained through the multiple initial identification parameter data in the fractional-order equivalent circuit model. The second electrochemical characteristic data may be the voltage difference obtained after voltage testing of the target battery with an electrochemical characteristic testing device (such as a voltage tester, etc.).

[0100] Specifically, determine the first electrochemical characteristic data of the target battery obtained based on a plurality of the initial identification parameter data in the fractional-order equivalent circuit model. Obtain the second electrochemical characteristic data obtained by testing the target battery with an electrochemical characteristic testing device. After obtaining the first electrochemical characteristic data and the second electrochemical characteristic data, the first electrochemical characteristic data and the second electrochemical characteristic data can be compared. Thus, according to the comparison result, determine a plurality of candidate identification parameter data of the fractional-order equivalent circuit model corresponding to the target battery.

[0101] In an embodiment of the present invention, determining a plurality of candidate identification parameter data of the fractional-order equivalent circuit model corresponding to the target battery based on the first electrochemical characteristic data and the second electrochemical characteristic data includes: A target function can be preset. Adjust the parameter values of the identification parameters of the fractional-order equivalent circuit model corresponding to the target battery by sequentially performing multiple iteration operations, where the current iteration operation includes: determining the function value of the target function based on the first electrochemical characteristic data and the second electrochemical characteristic data; and then, the current parameter values of the identification parameters of the fractional-order equivalent circuit model corresponding to the target battery can be adjusted according to the function value; when it is determined that the current parameter values of the identification parameters satisfy a preset convergence condition or the total number of iteration operations reaches a predetermined set value, the iteration operation can be stopped, so as to determine the current parameter values of the identification parameters as a plurality of candidate identification parameter data of the fractional-order equivalent circuit model corresponding to the target battery.

[0102] Among them, the target function can be used to calculate the error value between the first electrochemical characteristic data and the second electrochemical characteristic data. That is, the function value of the target function can characterize the error between the first electrochemical characteristic data and the second electrochemical characteristic data. The preset convergence condition can be that the error value between the first electrochemical characteristic data and the second electrochemical characteristic data is less than or equal to a preset error threshold. The total number of iteration operations reaches a predetermined set value, that is to say, the total number of iteration operations reaches the set maximum number of iterations. Among them, the total number of iteration operations can be understood as the number of iteration operations that have occurred currently.

[0103] In an embodiment of the present invention, determining the function value of the target function based on the first electrochemical characteristic data and the second electrochemical characteristic data includes: calculating the function value between the first electrochemical characteristic data and the second electrochemical characteristic data through the target function, that is, the error value between the first electrochemical characteristic data and the second electrochemical characteristic data.

[0104] Optionally, the error value between the first electrochemical characteristic data and the second electrochemical characteristic data is calculated based on the objective function by the following formula:

[0105]

[0106] where y(t) represents the second electrochemical characteristic data of the target battery obtained based on impedance testing of the target battery. Represents the first electrochemical characteristic data of the target battery obtained based on multiple initial identification parameter data in the fractional-order equivalent circuit model.

[0107] In an embodiment of the present invention, the Levenberg-Marquardt algorithm can be used to minimize the objective function and adjust the initial identification parameters of the fractional-order equivalent circuit model.

[0108] Optionally, the initial identification parameters of the fractional-order equivalent circuit model are adjusted by the following formula:

[0109]

[0110] where θ old can represent the identification parameters before adjustment. θ new can represent the identification parameters after adjustment.

[0111] S250. Use the candidate identification parameter data that meets the relevant conditions with the state of charge among the multiple candidate identification parameter data as the target identification parameter data.

[0112] In an embodiment of the present invention, the step of using the candidate identification parameter data that meets the relevant conditions with the state of charge among the multiple candidate identification parameter data as the target identification parameter data may include: for each preset state of charge, calculate the Pearson coefficient between each candidate identification parameter data and the preset state of charge, and calculate the Spearman rank correlation coefficient between each candidate identification parameter data and the preset state of charge; use the candidate identification parameter data corresponding to the Pearson coefficient exceeding the second preset threshold and the Spearman rank correlation coefficient exceeding the third preset threshold as the target identification parameter data.

[0113] Optionally, the Spearman rank correlation coefficient between the candidate identification parameter data and the preset state of charge can be calculated by the following formula:

[0114]

[0115] where ρ X,YIt can be expressed as the Spearman rank correlation coefficient between the candidate identification parameter data and the preset state of charge. X can be expressed as the candidate identification parameter data. Y can be expressed as the preset state of charge. In the embodiments of the present invention, ρ X,Y ranges from [-1, 1]. 1 indicates a positive correlation, -1 indicates a negative correlation, and 0 indicates linear independence.

[0116] Optionally, the Spearman rank correlation coefficient between the candidate identification parameter data and the preset state of charge can be calculated by the following formula:

[0117]

[0118] where ρ s can be expressed as the Spearman rank correlation coefficient between the candidate identification parameter data and the preset state of charge. N represents the number of samples. d i represents the rank difference of the i-th data pair. i represents an index, indicating the i-th data pair. Among them, the data pair includes the candidate identification parameter data and the preset state of charge.

[0119] S260. Input the target identification parameter data into the pre-trained battery state of charge prediction model to obtain the second state of charge of the target battery at the current moment.

[0120] S270. Based on the first state of charge and the second state of charge, determine the real-time state of charge of the target battery at the current moment.

[0121] The technical solution of the embodiments of the present invention is to perform impedance tests on the target battery under different preset states of charge through a battery test device to obtain the Nyquist curve diagram of the target battery under different preset states of charge; establish a fractional-order equivalent circuit model of the target battery according to the Nyquist curve diagram, where the fractional-order equivalent circuit model includes a plurality of initial identification parameter data; based on the plurality of initial identification parameter data, determine a plurality of candidate identification parameter data of the fractional-order equivalent circuit model corresponding to the target battery, so as to obtain more accurate identification parameter data of the fractional-order equivalent circuit model.

[0122] Figure 4 is a schematic structural diagram of a device for estimating the state of charge of a battery provided by an embodiment of the present invention. As Figure 4As shown in the figure, the device includes: a first state of charge determination module 310, an identification parameter data determination module 320, a second state of charge determination module 330, and a real-time state of charge determination module 340. Among them, the first state of charge determination module 310 is configured to, in response to a state of charge estimation request of a target battery, determine a first state of charge of the target battery at the current moment calculated based on the ampere-hour integration method; the identification parameter data determination module 320 is configured to determine a plurality of candidate identification parameter data of a fractional-order equivalent circuit model corresponding to the target battery, and use the candidate identification parameter data that meets the relevant conditions for the state of charge among the plurality of candidate identification parameter data as the target identification parameter data; the second state of charge determination module 330 is configured to input the target identification parameter data into a pre-trained battery state of charge prediction model to obtain a second state of charge of the target battery at the current moment; the real-time state of charge determination module 340 is configured to determine the real-time state of charge of the target battery at the current moment based on the first state of charge and the second state of charge.

[0123] In the technical solution of the embodiment of the present invention, the first state of charge determination module 310 responds to the state of charge estimation request of the target battery to determine the first state of charge of the target battery at the current moment calculated based on the ampere-hour integration method; the identification parameter data determination module 320 determines a plurality of candidate identification parameter data of the fractional-order equivalent circuit model corresponding to the target battery, and uses the candidate identification parameter data that meets the relevant conditions for the state of charge among the plurality of candidate identification parameter data as the target identification parameter data; the second state of charge determination module 330 inputs the target identification parameter data into a pre-trained battery state of charge prediction model to obtain the second state of charge of the target battery at the current moment; the real-time state of charge determination module determines the real-time state of charge of the target battery at the current moment based on the first state of charge and the second state of charge. The technical solution of the embodiment of the present invention solves the technical problem that the estimation accuracy is relatively low due to the cumulative error when the ampere-hour integration method is used to estimate the state of charge of the battery in the related art, realizes the high-precision estimation of the state of charge of the battery, and reduces the influence of the cumulative error on the estimation result.

[0124] Optionally, the identification parameter data determination module 320 is configured to perform impedance tests on the target battery under different preset states of charge through a battery test device to obtain Nyquist curves of the target battery under different preset states of charge; establish a fractional-order equivalent circuit model of the target battery according to the Nyquist curves, where the fractional-order equivalent circuit model includes a plurality of initial identification parameter data; based on the plurality of initial identification parameter data, determine a plurality of candidate identification parameter data of the fractional-order equivalent circuit model corresponding to the target battery.

[0125] Optionally, an identification parameter data determination module 320 is configured to determine first electrochemical characteristic data of the target battery obtained based on a plurality of pieces of the initial identification parameter data in the fractional-order equivalent circuit model, where the initial identification parameter data is a parameter value obtained after initializing the identification parameters of the fractional-order equivalent circuit model; obtain second electrochemical characteristic data obtained by testing the target battery with an electrochemical characteristic testing device; and determine a plurality of candidate identification parameter data of the fractional-order equivalent circuit model corresponding to the target battery based on the first electrochemical characteristic data and the second electrochemical characteristic data.

[0126] Optionally, the identification parameter data determination module 320 is configured to adjust the parameter values of the identification parameters of the fractional-order equivalent circuit model corresponding to the target battery by sequentially performing multiple iteration operations, where the current iteration operation includes: determining a function value of an objective function based on the first electrochemical characteristic data and the second electrochemical characteristic data, and adjusting the current parameter values of the identification parameters of the fractional-order equivalent circuit model corresponding to the target battery according to the function value; where the function value of the objective function represents the error between the first electrochemical characteristic data and the second electrochemical characteristic data; when it is determined that the current parameter values of the identification parameters meet a preset convergence condition or the total number of iteration operations reaches a predetermined set value, stop performing the iteration operation, and determine the current parameter values of the identification parameters as a plurality of candidate identification parameter data of the fractional-order equivalent circuit model corresponding to the target battery.

[0127] Optionally, the identification parameter data determination module 320 is configured to calculate a Pearson coefficient between each piece of the candidate identification parameter data and the preset state of charge, and calculate a Spearman rank correlation coefficient between each piece of the candidate identification parameter data and the preset state of charge for each preset state of charge; and use the candidate identification parameter data corresponding to a Pearson coefficient exceeding a second preset threshold and a Spearman rank correlation coefficient exceeding a third preset threshold as the target identification parameter data.

[0128] Optionally, the device further includes a model training module; where the model training module is configured to construct a to-be-trained state-of-charge prediction model; obtain a plurality of training sample data and expected result data corresponding to each piece of the training sample data, where the training sample data includes sample identification parameter data of the battery at a historical moment, and the expected result data is the historical state of charge of the battery at the historical moment; input the training sample data into the to-be-trained state-of-charge prediction model to obtain an actual output result, and adjust the model parameters of the to-be-trained state-of-charge prediction model based on the actual output result and the expected result data to obtain a trained battery state-of-charge prediction model.

[0129] Optionally, the to-be-trained state of charge prediction model is constructed based on a support vector machine regression model using a Gaussian kernel function.

[0130] The state of charge estimation device for a battery provided by an embodiment of the present invention can execute the state of charge estimation method for a battery provided by any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution of the method.

[0131] It should be noted that the various units and modules included in the above-mentioned state of charge estimation device for a battery are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the embodiments of the present invention.

[0132] Figure 5 FIG. shows a schematic structural diagram of an electronic device 10 that can be used to implement an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present invention described herein and / or claimed.

[0133] As Figure 5 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0134] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0135] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for estimating the state of charge of the battery.

[0136] In some embodiments, the method for estimating the state of charge of the battery can be implemented as a computer program, which is tangibly included in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for estimating the state of charge of the battery described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the method for estimating the state of charge of the battery by any other suitable means (e.g., by means of firmware).

[0137] The various embodiments of the systems and technologies described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special or general programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0138] A computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, a special purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine, or entirely on a remote machine or server.

[0139] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0140] In order to provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0141] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend, middleware, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0142] A computing system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0143] It should be understood that various forms of the processes shown above can be used, steps can be reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0144] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for estimating a battery state of charge, characterized in that: include: In response to a state of charge estimation request of a target battery, determining a first state of charge of the target battery at a current moment calculated based on an ampere-hour integration method; Determine a plurality of candidate identification parameter data of a fractional-order equivalent circuit model corresponding to the target battery, and use candidate identification parameter data that meets relevant conditions with the state of charge among the plurality of candidate identification parameter data as target identification parameter data; Inputting the target identification parameter data into a pre-trained battery state of charge prediction model to obtain a second state of charge of the target battery at the current moment; Based on the first state of charge and the second state of charge, a real-time state of charge of the target battery at a current moment is determined.

2. The method according to claim 1, characterized in that: The determining of a plurality of candidate identification parameter data of a fractional-order equivalent circuit model corresponding to the target battery includes: Performing impedance tests on the target battery at different preset states of charge by a battery testing device to obtain Nyquist curves of the target battery at different preset states of charge; Establishing a fractional-order equivalent circuit model of the target battery according to the Nyquist curve diagram, wherein the fractional-order equivalent circuit model includes a plurality of initial identification parameter data; Based on the plurality of initial identification parameter data, a plurality of candidate identification parameter data of a fractional-order equivalent circuit model corresponding to the target battery are determined.

3. The method according to claim 2, characterized in that The determining, based on the plurality of initial identification parameter data, a plurality of candidate identification parameter data of a fractional-order equivalent circuit model corresponding to the target battery comprises: Determining first electrochemical characteristic data of the target battery obtained based on a plurality of the initial identification parameter data in the fractional-order equivalent circuit model, wherein the initial identification parameter data is a parameter value obtained after initializing the identification parameters of the fractional-order equivalent circuit model; Acquiring second electrochemical characteristic data obtained by testing the target battery using an electrochemical characteristic testing device; Based on the first electrochemical characteristic data and the second electrochemical characteristic data, a plurality of candidate identification parameter data of a fractional-order equivalent circuit model corresponding to the target battery are determined.

4. The method according to claim 3, characterized in that The determining, based on the first electrochemical characteristic data and the second electrochemical characteristic data, a plurality of candidate identification parameter data of a fractional-order equivalent circuit model corresponding to the target battery comprises: The parameter values ​​of the identification parameters of the fractional-order equivalent circuit model corresponding to the target battery are adjusted by sequentially performing multiple iteration operations, wherein the current iteration operation includes: Based on the first electrochemical characteristic data and the second electrochemical characteristic data, determining a function value of an objective function, and adjusting a current parameter value of an identification parameter of a fractional-order equivalent circuit model corresponding to the target battery according to the function value; wherein the function value of the objective function represents an error between the first electrochemical characteristic data and the second electrochemical characteristic data; When it is determined that the current parameter value of the identification parameter satisfies the preset convergence condition or the total number of iterations of the iterative operation reaches a predetermined set value, the iterative operation is stopped and the current parameter value of the identification parameter is determined to be a plurality of candidate identification parameter data of the fractional-order equivalent circuit model corresponding to the target battery.

5. The method according to claim 2, characterized in that: The step of taking, among the plurality of candidate identification parameter data, candidate identification parameter data that meets relevant conditions with respect to the state of charge as target identification parameter data comprises: For each preset state of charge, calculating a Pearson coefficient between each candidate identification parameter data and the preset state of charge, and calculating a Spearman rank correlation coefficient between each candidate identification parameter data and the preset state of charge; The candidate identification parameter data corresponding to the Pearson coefficient exceeding the second preset threshold and the Spearman rank correlation coefficient exceeding the third preset threshold are used as the target identification parameter data.

6. The method according to claim 1, characterized in that The method further comprises: Construct a state of charge prediction model to be trained; Acquire a plurality of training sample data and expected result data corresponding to each of the training sample data, wherein the training sample data includes sample identification parameter data of the battery at a historical moment, and the expected result data is a historical state of charge of the battery at the historical moment; The training sample data is input into the state of charge prediction model to be trained to obtain an actual output result, and the model parameters of the state of charge prediction model to be trained are adjusted based on the actual output result and the expected result data to obtain a trained battery state of charge prediction model.

7. The method according to claim 6, characterized in that The state of charge prediction model to be trained is constructed based on a support vector machine regression model using a Gaussian kernel function.

8. A battery state of charge estimation device, characterized in that: include: A first state of charge determination module, configured to determine, in response to a state of charge estimation request of a target battery, a first state of charge of the target battery at a current moment calculated based on an ampere-hour integration method; an identification parameter data determination module, used to determine a plurality of candidate identification parameter data of a fractional-order equivalent circuit model corresponding to the target battery, and to use the candidate identification parameter data that meets the relevant conditions with the state of charge among the plurality of candidate identification parameter data as the target identification parameter data; A second state of charge determination module, used for inputting the target identification parameter data into a pre-trained battery state of charge prediction model to obtain a second state of charge of the target battery at the current moment; A real-time state of charge determination module is used to determine the real-time state of charge of the target battery at a current moment based on the first state of charge and the second state of charge.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method for estimating the state of charge of a battery as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for estimating the state of charge of a battery according to any one of claims 1 to 7 when executed.

Images