Characterization and Health Estimation Method of Energy Storage Battery against Decoupling under Multiple Mechanism Constraints

Abstract

The present invention discloses a method for anti-decoupling characterization and health estimation of energy storage batteries with multiple mechanism constraints. First, through the fusion application of anti-decoupling characterization learning and mechanism equations in a neural network, the input features are decoupled and characterized as health state-related features and domain features related to working conditions. Secondly, a mechanism parameter generator is used to generate mechanism parameters to solve the problem of different mechanism equation parameters under different working conditions. Finally, through continuous cyclic physical constraints, it is ensured that the health state decreases with the increase of the number of cycles and the problem of changes in mechanism equation parameters is solved, thereby realizing the generalization estimation of the health state under unseen working conditions. The present invention first integrates multiple mechanism constraints into the decoupling characterization learning of energy storage batteries, realizes generalization modeling under unseen working conditions without the need for target working condition data, and thus improves the accuracy of health state estimation of the model under unseen working conditions, providing necessary support for the safe operation and maintenance of energy storage batteries.

Description

Technical Field

[0001] The present invention relates to the technical field of health management of energy storage power stations, especially to the technical field of the continuous degradation problem of lithium-ion battery stacks during the operation of energy storage power stations. In particular, it relates to a method for anti-decoupling characterization and health estimation of energy storage batteries with multiple mechanism constraints. Background Art

[0002] With the rapid development of renewable energy and the popularization of electric vehicles, energy storage batteries are used more and more widely. Energy storage systems not only play a key role in the dispatching and optimization of power grids, but also play an indispensable role in the low-carbon economy. The state of health (SOH) of energy storage batteries is an important indicator for evaluating their performance and lifespan, directly affecting the reliability and economy of energy storage systems. To ensure the efficient operation of the system over a long period, accurately evaluating the health state of energy storage batteries is crucial. However, due to the diversity of the battery's usage environment and working conditions, there are significant differences even among batteries of the same model. This poses higher requirements for the further research and development of health state estimation (SOH Estimation) technology to achieve generalization ability from one type of battery to another.

[0003] Although there have been many studies on the health assessment methods for lithium batteries, each type of method has its own limitations. The direct measurement method is only suitable for use in the laboratory. Model-based methods often have difficulty ensuring the accuracy of the model or have too many parameters to be accurately identified. Therefore, more and more research tends to use data-driven methods to explore the aging mechanism and state inside the battery. However, the vast majority of data-driven assessment methods rely on the distribution of training data. Although existing research uses transfer learning to solve this problem, it still requires some information in the target domain, that is, the real application scenario. How to achieve domain generalization of the model without the operating data of energy storage batteries under real working conditions is a major problem. Representation learning is a means of domain generalization. However, general representation methods align the features between different domains. Due to the lack of mechanism constraints, only similar features that can be aligned can be found in the known source domain, and it cannot directly achieve good results. Therefore, how to accurately generalize and estimate the health state of energy storage batteries under unseen working conditions remains an urgent problem to be solved. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for anti-decoupling characterization and health estimation of energy storage batteries with multiple mechanism constraints, aiming at the deficiencies in the prior art that the health state estimation of energy storage batteries lacks mechanism constraints and requires operating data of target working conditions. The present invention can estimate the health state of energy storage batteries.

[0005] The object of the present invention is achieved by the following technical solutions: A method for anti-decoupling characterization and health estimation of energy storage batteries with multiple mechanism constraints, comprising the following steps:

[0006] (1) Obtain the complete full-life operation data of multiple energy storage batteries under different test conditions, including the current, voltage, sampling time, cycle number, and corresponding cycle capacity data of each charge-discharge cycle, so as to construct a multi-source domain dataset;

[0007] (2) Preprocess the complete full-life operation data of each charge-discharge cycle in each source domain dataset to extract health features and the health status label of each charge-discharge cycle, and merge the health features with the cycle number as input data; at the same time, initialize the parameters of the mechanism equation for each source domain and save them as mechanism parameter labels; construct a training set according to the input data and its corresponding health status label, domain label, and mechanism parameter label;

[0008] (3) Construct a neural network model, including an encoder, a health status estimator, a domain discriminator, and a mechanism parameter generator; and use the training set to train the neural network model. During the training process, minimize the total loss function of the neural network model as the optimization goal, and adjust the parameters of the neural network model to obtain a trained encoder and health status estimator;

[0009] (4) During on-line application, obtain the charge-discharge cycle data of the energy storage battery under the operating conditions, including the operating current, voltage, sampling time, and cycle number; extract health features based on the on-line operating current, voltage, and sampling time, and after normalizing them, merge them with the cycle number as input data, input them into the trained encoder, obtain encoded features, split the encoded features in half to obtain health status features and domain features, input the health status features into the trained health status estimator, obtain the health status value of the current loss, and further obtain the current health status estimation value of the energy storage battery.

[0010] Further, the step (1) specifically includes:

[0011] Obtain the current, voltage, sampling time, cycle number, and cycle capacity data during the standard charging period of each charge-discharge cycle of multiple energy storage batteries from the start of the test to the end of their life cycles under different test conditions; use the charge-discharge rate and the ambient temperature set in the test as the basis for dividing different test conditions, and divide the collected current, voltage, sampling time, cycle number, and cycle capacity data into different source domains according to different charge-discharge rates and ambient temperatures, and merge the charge-discharge rate and ambient temperature as the domain label to construct a multi-source domain dataset.

[0012] Further, the step (2) specifically includes the following sub-steps:

[0013] (2.1) For the complete full-life operation data of each charge-discharge cycle in each source domain dataset, health features are extracted based on the current, voltage, and sampling time of each charge-discharge cycle; wherein, the health features include the average value, standard deviation, kurtosis, skewness, curve slope, and curve entropy of voltage and current during cyclic charging, as well as the time and cumulative charge in two stages of constant current charging and constant voltage charging, a total of 16 health features;

[0014] (2.2) For the health features extracted in step (2.1), first, the outliers in the health features are removed using the 3-σ criterion, and then the health features are normalized using the normalization method to obtain the normalized health features, and the number of previous cycles is merged as input data;

[0015] (2.3) The health state label of each charge-discharge cycle is calculated by dividing the cycle capacity data of each charge-discharge cycle by the rated capacity of the corresponding energy storage battery;

[0016] (2.4) Use the particle swarm optimization algorithm to initialize the parameters of the mechanism equation for each source domain and save them as mechanism parameter labels;

[0017] (2.5) Construct a training set according to the input data and its corresponding health state label, domain label, and mechanism parameter label.

[0018] Further, the mechanism equation of the source domain is an equation derived from the Arrhenius formula, and its differential form is:

[0019]

[0020] In the formula, u represents the lost health state value, u = 1 - y, y represents the health state label; t represents the current cycle number; e is the natural constant; T represents the ambient temperature set in the experiment; are two parameters of the mechanism equation; is the differential symbol.

[0021] Further, in the neural network model, the encoder includes an input layer, a hidden layer, and an output layer. The input layer includes a fully connected layer and an activation function. The hidden layer is a single-layer basic network layer, and the output layer is a fully connected layer; the health state estimator, the domain discriminator, and the mechanism parameter generator all include a single-layer basic network layer and a fully connected layer; wherein, the single-layer basic network layer includes a fully connected layer, an activation function, and a dropout layer, and the activation functions are all sine functions;

[0022] The encoder is used to perform feature encoding on the input data input to the neural network model to obtain encoded features; then the encoded features are split in half to obtain two features, with the former feature used as the health state feature and the latter feature used as the domain feature; the health state estimator is used to map the health state feature to a loss of health state value; the domain discriminator is used to discriminate the working condition category of the input domain feature; the encoded features are simultaneously input to the mechanism parameter generator to generate the parameters of the mechanism equation corresponding to each sample.

[0023] Further, the neural network model is trained using the training set. During the training process, with the goal of minimizing the total loss function of the neural network model, the parameters of the neural network model are adjusted to obtain a trained encoder and health state estimator, specifically including:

[0024] The input data of the cyclic samples in the training set is input to the neural network model, and the encoded features are obtained through the encoder; after the encoded features are split in half, the health state feature and the domain feature are obtained; the health state feature passes through the health state estimator to obtain the loss of health state value output by the health state estimator; the domain feature passes through the domain discriminator to obtain the working condition category output by the domain discriminator for the domain feature; the health state feature passes through the gradient reversal layer and the domain discriminator in sequence to obtain the working condition category output by the domain discriminator for the health state feature; the encoded features pass through the mechanism parameter generator to obtain the parameters of the mechanism equation output by the mechanism parameter generator;

[0025] Based on the loss of health state value output by the health state estimator and its corresponding true loss of health state value, the health label loss is calculated, where the true loss of health state value is obtained by subtracting the corresponding health state label in the training set from 1; based on the working condition category output by the domain discriminator for the domain feature, the working condition category output by the domain discriminator for the health state feature, and the domain label corresponding to them in the training set, the domain discrimination loss is calculated; based on the parameters of the mechanism equation output by the mechanism parameter generator and the mechanism parameter label corresponding to them in the training set, the parameter generation loss is calculated; based on the loss of health state value output by the health state estimator, the parameters of the mechanism equation output by the mechanism parameter generator, and the corresponding cycle number and environmental temperature in the training set, the physical equation loss is calculated; based on the loss of health state value output by the health state estimator and the parameters of the mechanism equation output by the mechanism parameter generator, the continuous cycle physical constraint loss is calculated; based on the health label loss, the domain discrimination loss, the parameter generation loss, the physical equation loss, and the continuous cycle physical constraint loss, the total loss function of the neural network model is calculated.

[0026] With the optimization goal of minimizing the total loss function of the neural network model, iterative optimization is carried out using the gradient descent method to adjust the parameters of the encoder, health state estimator, domain discriminator, and mechanism parameter generator until the preset number of training rounds is reached to obtain the trained encoder and health state estimator.

[0027] Furthermore, the calculation formula for the total loss function of the neural network model is:

[0028]

[0029] In the formula, represents the total loss function of the neural network model, represents the health label loss, represents the domain discrimination loss, represents the parameter generation loss, represents the physical equation loss, represents the continuous cyclic physical constraint loss, and respectively represent the fixed weight parameters corresponding to the health label loss and the domain discrimination loss ; is a dynamic weight parameter, and its dynamic change formula is:

[0030]

[0031] In the formula, p is a dynamic parameter that linearly increases from 0 to 1 with the number of training rounds;

[0032] The calculation formula for the health label loss is:

[0033]

[0034] In the formula, n represents the total number of working condition categories, represents the total number of energy storage batteries under the i-th working condition category, represents the total number of cycle samples of the j-th energy storage battery, represents the health state value of the loss output by the health state estimator corresponding to the k-th cycle sample of the j-th energy storage battery under the i-th working condition category, represents the true health state value of the loss corresponding to the k-th cycle sample of the j-th energy storage battery under the i-th working condition category;

[0035] The calculation formula for the domain discrimination loss is:

[0036]

[0037] In the formula, Denote the domain feature of the k-th cycle sample of the j-th energy storage battery under the i-th operating condition category The operating condition category output by the domain discriminator Denote the health state feature of the k-th cycle sample of the j-th energy storage battery under the i-th operating condition category The operating condition category output by the domain discriminator Denote the domain label corresponding to the k-th cycle sample of the j-th energy storage battery under the i-th operating condition category in the training set

[0038] The calculation formula of the parameter generation loss is as follows:

[0039]

[0040] In the formula Denote the parameters of the mechanism equation output by the mechanism parameter generator corresponding to the k-th cycle sample of the j-th energy storage battery under the i-th operating condition category Denote the mechanism parameter label corresponding to the k-th cycle sample of the j-th energy storage battery under the i-th operating condition category in the training set

[0041] The calculation formula of the physical equation loss is as follows:

[0042]

[0043] In the formula Denote the number of cycles of the k-th cycle sample of the j-th energy storage battery under the i-th operating condition category Denote the ambient temperature of the operating condition corresponding to the k-th cycle sample of the j-th energy storage battery under the i-th operating condition category

[0044] The calculation formula of the continuous cycle physical constraint loss is as follows:

[0045]

[0046] In the formula Is the continuous cycle physical constraint loss Denote the rectified linear unit function

[0047] The beneficial effects of the present invention are as follows: The present invention first integrates multiple mechanism constraints into the decoupled characterization learning of energy storage batteries, realizes the generalization modeling of unseen operating conditions without the need for target operating condition data, and further improves the health state estimation accuracy of the model under unseen operating conditions, providing necessary support for the safe operation and maintenance of energy storage batteries Brief Description of the Drawings

[0048] Figure 1 Is the flow chart of the method for anti-decoupled characterization and health estimation of energy storage batteries with multiple mechanism constraints of the present invention

[0049] Figure 2 It is a schematic diagram of the network structure of the neural network model of the present invention;

[0050] Figure 3 It is a graph of the experimental results of the method of the present invention. Detailed implementation manners

[0051] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0052] The terms used in the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The singular forms "a", "the", and "said" used in the present invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0053] It should be understood that although the terms first, second, third, etc. may be used in the present invention to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present invention, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining".

[0054] The present invention will be described in detail below with reference to the drawings. Without conflict, the features in the following embodiments and implementation manners may be combined with each other.

[0055] See Figure 1 , the method for anti-decoupling characterization and health estimation of an energy storage battery with multiple mechanism constraints of the present invention specifically includes the following steps:

[0056] (1) Obtain the complete full-life operation data of multiple energy storage batteries under different test conditions, including the current, voltage, sampling time, number of cycles, and corresponding cycle capacity data of each charge-discharge cycle, so as to construct a multi-source domain dataset.

[0057] Specifically, the current, voltage, sampling time, number of cycles and cycle capacity data of each charge-discharge cycle of multiple energy storage batteries under different test conditions from the time of test to the end of their life cycle are obtained; the charging rate and the ambient temperature set in the test are used as the basis for dividing different test conditions, and the collected current, voltage, sampling time, number of cycles and cycle capacity data are divided into different source domains according to different charging rates and ambient temperatures, and the energy storage batteries under the same test condition are divided into the same source domain, and the charging rate and ambient temperature are combined as the domain label d to construct a multi-source domain dataset , where n represents the total number of source domain datasets.

[0058] It should be understood that the cycle number is the cycle number sequence of the charge and discharge cycles, that is, for the same energy storage battery, the cycle number of the first charge and discharge cycle is 1, the cycle number of the second charge and discharge cycle is 2, and the cycle number of the third charge and discharge cycle is 3. Similarly, the cycle number is the cycle number sequence of the charge and discharge cycles.

[0059] It should be noted that the multiple energy storage batteries described in the present invention all follow a standard charging scheme: first, they are charged to 4.2V by constant current, and then charged at a constant voltage of 4.2V until a cut-off current of 0.05C is reached. The current rate during constant current charging is the charging rate. In this embodiment, the current rate during constant current charging ranges from 0.25C to 1C, and the ambient temperature set in the experiment is 25°C to 45°C.

[0060] (2) The complete life-cycle operation data of each charge-discharge cycle in each source domain dataset is preprocessed to extract health features and the health status label of each charge-discharge cycle, and the health features are combined with the number of cycles as input data; at the same time, the parameters of the mechanism equation of each source domain are initialized and saved as mechanism parameter labels; a training set is constructed based on the input data and its corresponding health status labels, domain labels, and mechanism parameter labels.

[0061] (2.1) For the complete life-cycle operation data of each charge-discharge cycle in each source domain dataset, health features are extracted based on the current, voltage and sampling time of each charge-discharge cycle; the health features include the mean, standard deviation, kurtosis, skewness, curve slope and curve entropy of the voltage and current during the cyclic charging, as well as the time and accumulated charge of the constant current charging and constant voltage charging stages, a total of 16 health features.

[0062] (2.2) For the health features extracted in step (2.1), the 3-σ criterion is first used to eliminate outliers in the health features, and then the normalization method is used to normalize the health features to obtain the normalized health features, and the number of cycles is combined as input data, for a total of 17 input features.

[0063] It should be understood that the 3σ criterion means that in a normal distribution, most data will be concentrated within the range of the mean multiplied by the standard deviation, that is, 99.73% of the data lies within this interval. If a data point exceeds this range, it is considered an outlier or a bad value and can be considered for rejection.

[0064] Furthermore, common normalization methods include the Min-Max normalization method, the Z-Score normalization method, etc., and specific selection can be made according to actual needs.

[0065] (2.3) Divide the cycle capacity data of each charge-discharge cycle by the rated capacity of the corresponding energy storage battery to calculate the state-of-health label of each charge-discharge cycle. Then the lost state-of-health value u = 1 - y, where y represents the state-of-health label.

[0066] (2.4) Use the Particle Swarm Optimization (PSO) algorithm to initialize the parameters of the mechanism equation for each source domain. In this embodiment, there are n source domains, so there are a total of n groups of parameters, and they are saved as mechanism parameter labels.

[0067] It should be understood that PSO is a meta-heuristic optimization algorithm based on swarm intelligence, which simulates the social behavior of bird flocks or fish schools and finds the optimal solution through the cooperation of individuals and the group.

[0068] Furthermore, the mechanism equation of the source domain is an equation derived from the Arrhenius formula, and its differential form is:

[0069]

[0070] In the formula, u represents the lost state-of-health value, u = 1 - y, y represents the state-of-health label; t represents the current cycle number; e is the natural constant; T represents the environmental temperature set in the experiment; are the two parameters of the mechanism equation, and they are initialized and calculated through PSO for these two parameters; is the differential symbol.

[0071] It should be understood that the Arrhenius equation is a classical formula that describes the relationship between the reaction rate constant and temperature of a chemical reaction.

[0072] (2.5) Construct a training set according to the input data and its corresponding state-of-health label, domain label, and mechanism parameter label.

[0073] (3) Construct a neural network model, including an encoder, a health state estimator, a domain discriminator, and a mechanism parameter generator; and use the training set to train the neural network model. During the training process, minimize the total loss function of the neural network model as the optimization objective, and adjust the parameters of the neural network model to obtain a trained encoder and health state estimator.

[0074] In this embodiment, the structure of the neural network model is as Figure 2 shown. The encoder includes an input layer, a hidden layer, and an output layer. The input layer includes a fully connected layer and an activation function. The hidden layer is a single-layer basic network layer, and the output layer is a fully connected layer. The health state estimator, the domain discriminator, and the mechanism parameter generator all include a single-layer basic network layer and a fully connected layer. Among them, the single-layer basic network layer includes a fully connected layer, an activation function, and a dropout layer, and the activation function is a sine function. Specifically, the encoder is used to perform feature encoding on the input data x input to the neural network model to obtain encoded features; then split the encoded features in half to obtain two features, and use the first feature as the health state feature , and use the second feature as the domain feature ; the health state estimator is used to map the health state feature to the loss of the health state value u; the domain discriminator is used to discriminate the working condition category of the input domain feature ; the encoded features are simultaneously input to the mechanism parameter generator to generate the parameters of the mechanism equation corresponding to each sample.

[0075] Specifically, the 17 input features of the input data obtained in step (2.2) are input into the neural network model. First, they enter the encoder and pass through the input layer, hidden layer, and output layer of the encoder in sequence to obtain encoded features. Among them, the input dimension of the input layer is 17, the dimension of the hidden layer is 60, and the output dimension of the output layer is 32, that is, the dimensions of the domain feature and the health state feature are both 16. The health state estimator, the domain discriminator, and the mechanism parameter generator all include a single-layer basic network layer and a fully connected layer, and their hidden dimensions are all 32, but their specific parameters and dimensions are different. Among them, the input dimension of the health state estimator is 16, and the output dimension is 1; the input dimension of the domain discriminator is 16, and the output dimension is 2; the input dimension of the mechanism parameter generator is 32, and the output dimension is 2.

[0076] In this embodiment, a neural network model is trained using a training set. During the training process, with the goal of minimizing the total loss function of the neural network model, the parameters of the neural network model are adjusted to obtain a trained encoder and a health state estimator. Specifically, it includes: inputting the input data of the cyclic samples in the training set into the neural network model, and obtaining encoded features through the encoder; after splitting the encoded features in half, obtaining health state features and domain features; passing the health state features through the health state estimator to obtain the lossy health state value output by the health state estimator; passing the domain features through the domain discriminator to obtain the working condition category output by the domain discriminator for the domain features; passing the health state features through the gradient reversal layer and then through the domain discriminator to obtain the working condition category output by the domain discriminator for the health state features; passing the encoded features through the mechanism parameter generator to obtain the parameters of the mechanism equation output by the mechanism parameter generator. Calculate the health label loss based on the lossy health state value output by the health state estimator and its corresponding true lossy health state value, where the true lossy health state value is obtained by subtracting the corresponding health state label in the training set from 1; calculate the domain discrimination loss based on the working condition category output by the domain discriminator for the domain features, the working condition category output by the domain discriminator for the health state features, and the corresponding domain label in the training set. The adversarial training and feature alignment of the neural network model are achieved through the gradient reversal layer; calculate the parameter generation loss based on the parameters of the mechanism equation output by the mechanism parameter generator and the corresponding mechanism parameter label in the training set; calculate the physical equation loss based on the lossy health state value output by the health state estimator, the parameters of the mechanism equation output by the mechanism parameter generator, and the corresponding cycle number and environmental temperature in the training set; calculate the continuous cycle physical constraint loss based on the lossy health state value output by the health state estimator and the parameters of the mechanism equation output by the mechanism parameter generator; calculate the total loss function of the neural network model based on the health label loss, domain discrimination loss, parameter generation loss, physical equation loss, and continuous cycle physical constraint loss. With the goal of minimizing the total loss function of the neural network model, use the gradient descent method for iterative optimization to adjust the parameters of the encoder, health state estimator, domain discriminator, and mechanism parameter generator until the preset number of training rounds is reached to obtain a trained encoder and a health state estimator. The trained encoder and health state estimator can be constructed into a final health state estimation model for any working condition.

[0077] Furthermore, the calculation formula for the total loss function of the neural network model is:

[0078]

[0079] In the formula, represents the total loss function of the neural network model, represents the health label loss, represents the domain discrimination loss, Represents the parameter generation loss, Represents the physical equation loss, Represents the continuous cyclic physical constraint loss, and respectively represent the healthy label loss and the domain discrimination loss The corresponding fixed weight parameters, are dynamic weight parameters, and their dynamic change formula is:

[0080]

[0081] In the formula, p is a dynamic parameter that linearly increases from 0 to 1 with the number of training rounds.

[0082] Furthermore, the calculation formula for the healthy label loss is:

[0083]

[0084] In the formula, is the healthy label loss, n represents the total number of working condition categories, represents the total number of energy storage batteries under the i-th working condition category, represents the total number of cyclic samples of the j-th energy storage battery, represents the healthy state value of the loss corresponding to the output of the healthy state estimator for the k-th cyclic sample of the j-th energy storage battery under the i-th working condition category, represents the true healthy state value of the loss corresponding to the k-th cyclic sample of the j-th energy storage battery under the i-th working condition category, , represents the healthy state label corresponding to the k-th cyclic sample of the j-th energy storage battery under the i-th working condition category in the training set.

[0085] Furthermore, the calculation formula for the domain discrimination loss is:

[0086]

[0087] In the formula, is the domain discrimination loss, represents the domain feature of the k-th cyclic sample of the j-th energy storage battery under the i-th working condition category through the working condition category output by the domain discriminator, represents the healthy state feature of the k-th cyclic sample of the j-th energy storage battery under the i-th working condition category through the working condition category output by the domain discriminator, represents the domain label corresponding to the k-th cyclic sample of the j-th energy storage battery under the i-th working condition category in the training set.

[0088] Furthermore, the calculation formula for the parameter generation loss is as follows:

[0089]

[0090] In the formula, is the parameter generation loss, represents the parameter of the mechanism equation output by the mechanism parameter generator corresponding to the k-th cycle sample of the j-th energy storage battery under the i-th working condition category, represents the mechanism parameter label corresponding to the k-th cycle sample of the j-th energy storage battery under the i-th working condition category in the training set.

[0091] Furthermore, the calculation formula for the physical equation loss is as follows:

[0092]

[0093] In the formula, is the physical equation loss, represents the number of cycles of the k-th cycle sample of the j-th energy storage battery under the i-th working condition category, represents the ambient temperature of the working condition corresponding to the k-th cycle sample of the j-th energy storage battery under the i-th working condition category, which can be specifically obtained from the training set.

[0094] Furthermore, the calculation formula for the continuous cycle physical constraint loss is as follows:

[0095]

[0096] In the formula, is the continuous cycle physical constraint loss, represents the rectified linear unit function. RELU is used as an activation function in the neural network. Here, RELU is simply used as a part of the loss function.

[0097] In this embodiment, the Adam optimizer is used to optimize the parameters of the neural network model. The parameter settings of the Adam optimizer are as follows: the exponential decay rate of the first-moment estimate is 0.9, and the exponential decay rate of the second-moment estimate is 0.999; the learning rate is set to 1e -3 , the number of training epochs is set to 200, and the size of each batch is 512. and take the values of 100 and 1 respectively.

[0098] (4)During online application, charge-discharge cycle data of the energy storage battery under operating conditions are obtained, including the operating current, voltage, sampling time, and number of cycles; the online operating conditions are different from all the source domain conditions in training; health features are extracted based on the online operating current, voltage, and sampling time, and after normalization, they are combined with the number of cycles as input data. The input data is input into the trained encoder to obtain encoded features. The encoded features are split in half to obtain health state features and domain features. The health state features are input into the trained health state estimator to obtain the current loss of the health state value, and then the current health state estimation value of the energy storage battery is obtained. Among them, since the output of the health state estimator is u = 1 - y, subtracting the current loss of the health state value from 1 can obtain the current health state estimation value y of the energy storage battery, which represents the health state of the energy storage battery. Usually, the health state of the energy storage battery is evaluated according to different scenarios. For example, in some scenarios, when y is greater than 80% or 70%, the energy storage battery is considered healthy.

[0099] In summary, the present invention estimates the domain-generalized health state of the energy storage battery by using the adversarial decoupling representation method with multiple mechanism constraints. Among them, the multiple mechanism constraints include two constraints: physical equation loss and continuous cycle physical constraint loss; adversarial decoupling representation means splitting the encoded features into two features and achieving decoupling representation through adversarial training using a gradient reversal layer. When estimating the domain-generalized health state of the energy storage battery, first, through the fusion application of adversarial decoupling representation learning and mechanism equations in the neural network, the input features are decoupled and represented as health state-related features and domain features related to the operating conditions; second, a mechanism parameter generator is used as an auxiliary task to generate mechanism parameters to solve the problem of different mechanism equation parameters under different operating conditions; finally, through continuous cycle physical constraints, it is constrained that the health state decreases with the increase in the number of cycles and the problem of changes in mechanism equation parameters is solved, thereby realizing the generalization estimation of the health state of unseen operating conditions. Compared with the existing battery health estimation methods, the present invention first integrates multiple mechanism constraints into the decoupling representation learning of energy storage batteries, and realizes generalization modeling of unseen operating conditions without the need for target operating condition data, thereby improving the health state estimation accuracy of the model under unseen operating conditions and providing necessary support for the safe operation and maintenance of energy storage batteries.

[0100] In this embodiment, an open-source dataset is selected for experimental verification to verify the effect of the method described in the present invention. The batteries in this open-source dataset are commercially available 18650 NCA (nickel cobalt aluminum) ternary lithium batteries, with a cut-off voltage of 2.65 - 4.2V and a rated capacity of 3.5Ah. Five operating conditions are set with different environmental temperatures and charging rates, and the discharge rate is 1C for all of them. The specific data is shown in Table 1. Operating condition 4 is selected as the target domain, and the other operating conditions are source domains. The results of the experiment using the method described in the present invention are as Figure 3As shown, the abscissa is the true value of the battery's state of health, and the ordinate is the predicted value of the battery's state of health. It can be seen from this that the predicted value of the battery's state of health is not much different from the true value, which proves the effectiveness of the method described in the present invention.

[0101] Table 1: Detailed Table of Set Data for Batteries under Different Working Conditions

[0102]

[0103] To more clearly demonstrate the superiority of the method described in the present invention in estimating the state of health under unseen working conditions, the Deep Neural Networks (DNN) and the domain generalization paradigm of the Deep Adversarial Network (Domainadaptive neural network, DANN) were also used for comparison with the method described in the present invention. The experimental results are shown in Table 2. In the experiment, the evaluation criteria selected were the Root Mean Square Error (RMSE) and the Mean Absolute Percentage Error (MAPE). The encoder and the structure of the state of health estimator of the two comparison methods were the same as those of the method described in the present invention, and other training parameters were also the same.

[0104] Table 2: State of Health Estimation Errors of Different Methods

[0105]

[0106] As can be seen from Table 2, the method described in the present invention was compared with the other two methods, which proves the effectiveness of the method described in the present invention. When compared with the DNN method without domain generalization, the performance of the DANN method without the fusion of mechanism equations decreased. The method described in the present invention did not show a performance decrease and achieved the best results in both indicators.

[0107] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for anti-decoupling characterization and health estimation of an energy storage battery with multiple mechanism constraints, characterized in that It includes the following steps: (1) Obtain the complete full-life operation data of multiple energy storage batteries under different test conditions, including the current, voltage, sampling time, cycle number, and corresponding cycle capacity data for each charge-discharge cycle, so as to construct a multi-source domain dataset; (2) Preprocess the complete full-life operation data of each charge-discharge cycle in each source domain dataset to extract health features and the health status label of each charge-discharge cycle, and merge the health features with the cycle number as input data; at the same time, initialize the parameters of the mechanism equation for each source domain and save them as mechanism parameter labels; construct a training set according to the input data and its corresponding health status label, domain label, and mechanism parameter label; (3) Construct a neural network model, including an encoder, a health status estimator, a domain discriminator, and a mechanism parameter generator; and use the training set to train the neural network model. During the training process, with minimizing the total loss function of the neural network model as the optimization goal, adjust the parameters of the neural network model to obtain a trained encoder and health status estimator; the calculation formula of the total loss function of the neural network model is: In the formula, represents the total loss function of the neural network model, represents the healthy label loss, represents the domain discrimination loss, represents the parameter generation loss, represents the physical equation loss, represents the continuous cyclic physical constraint loss, and α and β respectively represent the healthy label loss and the domain discrimination loss corresponding fixed weight parameters, and γ is the dynamic weight parameter; (4) During on-line application, obtain the charge-discharge cycle data of the energy storage battery under the operating condition, including the operating current, voltage, sampling time, and cycle number; Extract health features based on the on-line operating current, voltage, and sampling time, perform normalization processing on them, and then merge them with the cycle number as input data, input them into the trained encoder, obtain encoded features, split the encoded features in half to obtain health status features and domain features, input the health status features into the trained health status estimator, obtain the health status value of the current loss, and further obtain the current health status estimation value of the energy storage battery.

2. The method for anti-decoupling characterization and health estimation of an energy storage battery with multiple mechanism constraints according to claim 1, characterized in that, The specific content of step (1) includes: Obtain the current, voltage, sampling time, cycle number, and cycle capacity data during the standard charging period of each charge-discharge cycle of multiple energy storage batteries from the start of the test to the end of their life cycles under different test conditions; use the charging rate and the ambient temperature set in the test as the basis for dividing different test conditions, and divide the collected current, voltage, sampling time, cycle number, and cycle capacity data into different source domains according to different charging rates and ambient temperatures, and merge the charging rate and ambient temperature as the domain label to construct a multi-source domain dataset.

3. The method for anti-decoupling characterization and health estimation of an energy storage battery with multiple mechanism constraints according to claim 1, wherein The specific content of step (2) includes the following sub-steps: (2.1) For the complete full-life operation data of each charge-discharge cycle in each source domain dataset, extract health features based on the current, voltage, and sampling time of each charge-discharge cycle; among them, the health features include the average value, standard deviation, kurtosis, skewness, curve slope, and curve entropy of the voltage and current during the cyclic charging period, as well as the time and cumulative charge of the constant current charging and constant voltage charging stages, a total of 16 health features; (2.2) For the health features extracted in step (2.1), first use the 3-σ criterion to eliminate outliers in the health features, then use the normalization method to normalize the health features, obtain the normalized health features, and combine the number of cycles as input data; (2.3) Dividing the cycle capacity data of each charge and discharge cycle by the rated capacity of the corresponding energy storage battery to calculate the health status label of each charge and discharge cycle; (2.4) Use the particle swarm optimization algorithm to initialize the parameters of the mechanism equation of each source domain and save them as mechanism parameter labels; (2.5) Construct a training set based on the input data and its corresponding health status labels, domain labels, and mechanism parameter labels.

4. The method for anti-decoupling characterization and health estimation of a multi-mechanism constrained energy storage battery according to claim 1 or 3, characterized in that, The mechanism equation of the source domain is derived from the Arrhenius formula, and its differential form is: Wherein, u represents the value of the lost health state, u = 1 - y, y represents the health state label; t represents the current number of cycles; e is the natural constant; T represents the ambient temperature set in the experiment; Λ, λ are two parameters of the mechanism equation; is the differential symbol.

5. The method for anti-decoupling characterization and health estimation of an energy storage battery with multiple mechanism constraints according to claim 1, characterized in that, In the neural network model, the encoder includes an input layer, a hidden layer and an output layer, the input layer includes a fully connected layer and an activation function, the hidden layer is a single-layer basic network layer, and the output layer is a fully connected layer; the health state estimator, the domain discriminator and the mechanism parameter generator all include a single-layer basic network layer and a fully connected layer; wherein the single-layer basic network layer includes a fully connected layer, an activation function and a random loss layer, and the activation functions are all sine functions; The encoder is used to perform feature encoding on the input data input to the neural network model to obtain the encoded features; the encoded features are then split in half to obtain two features, the former feature is used as the health state feature, and the latter feature is used as the domain feature; the health state estimator is used to map the health state feature to the health state value of the loss; the domain discriminator is used to discriminate the working condition category of the input domain feature; the encoded features are simultaneously input to the mechanism parameter generator to generate the parameters of the mechanism equation corresponding to each sample.

6. The method for anti-decoupling characterization and health estimation of a multi-mechanism constrained energy storage battery according to claim 1, wherein The neural network model is trained using the training set. During the training process, the parameters of the neural network model are adjusted with minimizing the total loss function of the neural network model as the optimization goal to obtain the trained encoder and health state estimator, which specifically includes: Input the input data of the cycle samples in the training set into the neural network model, and obtain the encoding features through the encoder; the encoding features are split in half to obtain the health state features and domain features; the health state features pass through the health state estimator to obtain the lost health state value output by the health state estimator; the domain features pass through the domain discriminator to obtain the working condition category output by the domain discriminator; the health state features pass through the gradient reversal layer and the domain discriminator in turn to obtain the working condition category output by the domain discriminator; the encoding features pass through the mechanism parameter generator to obtain the parameters of the mechanism equation output by the mechanism parameter generator; Calculate the health label loss based on the health state value of the loss output by the health state estimator and its corresponding true health state value of the loss, where the true health state value of the loss is obtained by subtracting the corresponding health state label in the training set from 1; calculate the domain discrimination loss based on the operating condition category output by the domain discriminator for the domain features, the operating condition category output by the domain discriminator for the health state features, and the domain label corresponding to them in the training set; calculate the parameter generation loss based on the parameters of the mechanism equation output by the mechanism parameter generator and the corresponding mechanism parameter label in the training set; calculate the physical equation loss based on the health state value of the loss output by the health state estimator, the parameters of the mechanism equation output by the mechanism parameter generator, and the corresponding number of cycles and ambient temperature in the training set; calculate the continuous cycle physical constraint loss based on the health state value of the loss output by the health state estimator and the parameters of the mechanism equation output by the mechanism parameter generator; calculate the total loss function of the neural network model based on the health label loss, domain discrimination loss, parameter generation loss, physical equation loss, and continuous cycle physical constraint loss; With the goal of minimizing the total loss function of the neural network model, use the gradient descent method for iterative optimization to adjust the parameters of the encoder, health state estimator, domain discriminator, and mechanism parameter generator until the preset number of training rounds is reached to obtain the trained encoder and health state estimator.

7. The method for anti-decoupling characterization and health estimation of a multi-mechanism constrained energy storage battery according to claim 6, wherein The dynamic weight parameter has the following dynamic change formula: In the formula, p is a dynamic parameter that linearly increases from 0 to 1 with the number of training rounds; The calculation formula for the health label loss is: where n represents the total number of operating condition categories, B i represents the total number of energy storage batteries under the i-th operating condition category, N j represents the total number of cycle samples of the j-th energy storage battery, represents the health state value of the loss output by the health state estimator corresponding to the k-th cycle sample of the j-th energy storage battery under the i-th operating condition category, u i,j,k represents the true health state value of the loss corresponding to the k-th cycle sample of the j-th energy storage battery under the i-th operating condition category; The calculation formula for the domain discrimination loss is: In the formula, represents the domain feature z of the k-th cycle sample of the j-th energy storage battery under the i-th working condition category d is the working condition category output by the domain discriminator, represents the health state feature z of the k-th cycle sample of the j-th energy storage battery under the i-th working condition category u is the working condition category output by the domain discriminator, d i,j,k represents the domain label corresponding to the k-th cycle sample of the j-th energy storage battery under the i-th working condition category in the training set; The calculation formula for the parameter generation loss is: In the formula, represents the parameter of the mechanism equation output by the mechanism parameter generator corresponding to the k-th cycle sample of the j-th energy storage battery under the i-th working condition category, λ i,j,k , Λ i,j,k represents the mechanism parameter label corresponding to the k-th cycle sample of the j-th energy storage battery under the i-th working condition category in the training set; The calculation formula for the physical equation loss is: where t i,j,k represents the number of cycles of the k-th cycle sample of the j-th energy storage battery under the i-th working condition category, and T i,j,k represents the ambient temperature of the working condition corresponding to the k-th cycle sample of the j-th energy storage battery under the i-th working condition category; the calculation formula for the continuous cycle physical constraint loss is as follows: In the formula, is the continuous cyclic physical constraint loss, and RELU() represents the rectified linear unit function.

Images