Battery health assessment method, device, equipment and storage medium

Abstract

The present application discloses a battery health assessment method, device, equipment and storage medium, which relates to the field of new energy technology. The disclosed battery health assessment method includes: obtaining the current charging parameters of the target battery, performing filling and dimensionality reduction processing on the current charging parameters to obtain the features to be evaluated; performing feature mapping on the features to be evaluated based on the current estimation model to obtain the reference charging current; obtaining the charging stage according to the charging power curve of the reference charging current; obtaining the current fluctuation amplitude according to the current value in the charging stage, and obtaining the health status of the target battery according to the current fluctuation amplitude; the method predicts the actual charging current of the battery and divides the charging stage through the features after the current charging parameters are processed, and judges the battery health status based on the current fluctuation amplitude in different stages, so as to realize real-time and continuous detection of the battery health status without destroying the battery structure, thereby ensuring the safety of battery use and extending the battery service life.

Description

Technical Field

[0001] The present application relates to the field of new energy technology, and in particular to a battery health assessment method, device, equipment and storage medium. Background Art

[0002] Lithium-ion batteries (lithium batteries) have been widely used in the field of new energy vehicles due to their high energy density, long life, strong stability and low environmental impact. In practical applications, lithium ion deposition, SEI film thickening and active material loss in the battery lead to battery aging and capacity decay, which reduces the vehicle's driving range. Usually, the battery state of health (SOH) is used to describe the battery's decay (aging) state. SOH research is of great value to the use, maintenance and evaluation of batteries. Because the actual battery operation data includes many types of batteries, it is difficult to obtain unified parameters to characterize the health status of lithium batteries.

[0003] During the use of the battery system, accurate estimation of the battery health status plays an important role in extending the life of the battery system and improving the safety and overall performance of the battery system. The existing health status estimation method is obtained by combining a large amount of laboratory measurement data with algorithm estimation. It is impossible to detect the battery health status in real time, and the experimental process is complicated and labor-intensive.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a battery health assessment method, device, equipment and storage medium, aiming to solve the technical problem that the existing technology cannot continuously and accurately assess the battery health status.

[0006] To achieve the above objectives, the present application proposes a battery health assessment method, which includes:

[0007] Acquire current charging parameters of the target battery, and perform filling and dimensionality reduction processing on the current charging parameters to obtain features to be evaluated;

[0008] Performing feature mapping on the feature to be evaluated based on a current estimation model to obtain a reference charging current;

[0009] Obtaining a charging stage according to a charging power curve of the reference charging current;

[0010] The current fluctuation amplitude is obtained according to the current value in the charging stage, and the health state of the target battery is obtained according to the current fluctuation amplitude.

[0011] In one embodiment, the step of obtaining the current charging parameters of the target battery and performing filling and dimensionality reduction processing on the current charging parameters to obtain the features to be evaluated includes:

[0012] Acquire current charging parameters of the target battery, and identify parameter inflection points of the current charging parameters;

[0013] Dividing the current charging parameter according to the parameter inflection point to obtain a plurality of bands, sampling the bands to obtain a sampled charging feature;

[0014] Zero-filling the sampled charging features to obtain features to be processed;

[0015] The features to be processed are subjected to feature perception according to the number of sampling points, the size of the sliding window, and the number of features to be processed to obtain features to be evaluated.

[0016] In one embodiment, the step of performing feature mapping on the feature to be evaluated based on the current estimation model to obtain a reference charging current includes:

[0017] Extracting the battery health features of the features to be evaluated according to the dynamic involution kernel through the current estimation model;

[0018] Dividing the battery health characteristics into stage health characteristics, dynamically weighting the stage health characteristics, and obtaining a global health dependency characteristic;

[0019] The global health-dependent feature and the stage health feature are transformed nonlinearly to obtain a reference feature, and the reference feature is mapped to a reduced dimension feature to obtain a reference charging current.

[0020] In one embodiment, obtaining the charging stage according to the charging power curve of the reference charging current includes:

[0021] Compare the magnitudes of multiple reference charging currents to obtain a target charging current;

[0022] Obtaining a phase node based on the target charging current;

[0023] The reference charging current is divided into a plurality of charging stages based on the stage nodes.

[0024] In one embodiment, comparing the magnitudes of a plurality of reference charging currents to obtain a target charging current includes:

[0025] using adjacent reference charging currents in the reference charging currents as a first reference charging current and a second reference charging current;

[0026] Obtaining a current difference according to the first reference charging current and the second reference charging current, and obtaining an adjacent current ratio according to the current difference and the first reference charging current;

[0027] When the adjacent current ratio is greater than a preset ratio amplitude threshold, a first reference charging current corresponding to the adjacent reference current is used as a target charging current.

[0028] In one embodiment, obtaining a current fluctuation amplitude according to the current value in the charging stage, and obtaining a health state of the target battery according to the current fluctuation amplitude includes:

[0029] Extracting the maximum current value in the charging stage, and obtaining a plurality of current fluctuation amplitudes from each current value in the charging stage and the maximum current value;

[0030] Obtaining a current fluctuation amplitude in the charging stage according to the multiple current fluctuation amplitudes;

[0031] The health status of the target battery is obtained according to the current fluctuation amplitude in each charging stage.

[0032] In one embodiment, the health status includes a normal state and an abnormal state;

[0033] The method of obtaining the health status of the target battery according to the current fluctuation amplitude of each charging stage includes:

[0034] The charging current fluctuation amplitude of the target battery is obtained according to the stage current fluctuation amplitude of each charging stage;

[0035] When the charging current fluctuation amplitude is less than or equal to a preset current fluctuation amplitude, taking the normal state as the health state of the target battery and generating a battery health assessment report based on the normal state;

[0036] When the charging current fluctuation amplitude is greater than a preset current fluctuation amplitude, the abnormal state is used as the health state of the target battery and a battery health abnormality warning is generated based on the abnormal state.

[0037] In addition, to achieve the above objectives, the present application also proposes a battery health assessment device, the battery health assessment device comprising:

[0038] An acquisition module, used to acquire current charging parameters of a target battery, and perform filling and dimensionality reduction processing on the current charging parameters to obtain features to be evaluated;

[0039] A current estimation module, used for performing feature mapping on the feature to be evaluated based on a current estimation model to obtain a reference charging current;

[0040] A charging stage division module, used for obtaining a charging stage according to a charging power curve of the reference charging current;

[0041] The battery health assessment module is used to obtain the current fluctuation amplitude according to the current value in the charging stage, and obtain the health status of the target battery according to the current fluctuation amplitude.

[0042] In addition, to achieve the above-mentioned objectives, the present application also proposes a battery health assessment device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the battery health assessment method described above.

[0043] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the battery health assessment method described above are implemented.

[0044] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the battery health assessment method described above are implemented.

[0045] One or more technical solutions proposed in this application have at least the following technical effects:

[0046] The actual charging current of the current battery is predicted by processing the characteristics of the current charging parameters that affect the battery current, and the charging stages are divided according to the charging current. The battery health state is judged based on the current fluctuation amplitude in different stages. The battery health state can be continuously detected in real time without destroying the battery structure, and the battery can be maintained and replaced in time according to the battery health state, ensuring the safety of battery use while extending the battery life. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings herein are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the description, are used to explain the principles of the present application.

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0049] Figure 1 A flowchart of the first embodiment of the battery health assessment method of the present application is provided;

[0050] Figure 2 A schematic diagram of the inner roll block structure provided for the first embodiment of the battery health assessment method of the present application;

[0051] Figure 3 A schematic diagram of a structure of a current estimation model provided in Example 1 of the battery health assessment method of the present application;

[0052] Figure 4 A schematic diagram of a flow chart of calculating the current fluctuation amplitude in a battery health assessment in a battery health assessment method according to a first embodiment of the present application;

[0053] Figure 5 A flowchart of the second embodiment of the battery health assessment method of the present application is provided;

[0054] Figure 6 This is a schematic diagram of the module structure of the battery health assessment device according to an embodiment of the present application;

[0055] Figure 7 Schematic diagram of the device structure of the hardware operating environment involved in the battery health assessment method in the embodiment of the present application. DETAILED DESCRIPTION

[0056] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0057] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0058] The main solution of the embodiment of the present application is: obtain the current charging parameters of the target battery, fill in and reduce the dimension of the current charging parameters to obtain the features to be evaluated; perform feature mapping on the features to be evaluated based on the current estimation model to obtain a reference charging current; obtain the charging stage according to the charging power curve of the reference charging current; obtain the current fluctuation amplitude according to the current value of the charging stage, and obtain the health status of the target battery according to the current fluctuation amplitude.

[0059] In this embodiment, for ease of description, the following description is made by taking identification of a battery health assessment device as the execution subject.

[0060] Due to the advantages of high energy density, long life, strong stability and low environmental impact, existing lithium-ion batteries (lithium batteries) have been widely used in the field of new energy vehicles. In practical applications, with the deposition of lithium ions in the battery, the thickening of the SEI film and the loss of active substances, the battery ages and the capacity decays, which reduces the driving range of the vehicle. Usually, the battery state of health (State of Health, SOH) is used to describe the decay (aging) state of the battery. SOH research is of great value to the use, maintenance and evaluation of the battery. Because the actual operation data of the battery includes many types of batteries, it is difficult to obtain unified characterization parameters for the health status of lithium batteries.

[0061] During the use of the battery system, accurate estimation of the battery health status plays an important role in extending the life of the battery system and improving the safety and overall performance of the battery system. The existing health status estimation method is obtained by combining a large amount of laboratory measurement data with algorithm estimation. It is impossible to detect the battery health status in real time, and the experimental process is complicated and labor-intensive.

[0062] The present application provides a solution, which predicts the actual charging current of the battery and divides the charging stages through the characteristics of the current charging parameters processed, and judges the battery health status based on the current fluctuation amplitude in different stages, so as to realize real-time and continuous detection of the battery health status without destroying the battery structure, thereby ensuring the safety of battery use and extending the battery life.

[0063] It can be seen from the above embodiments that the present application discloses a battery health assessment method, device, equipment and storage medium, which relates to the field of new energy technology. The disclosed battery health assessment method includes: obtaining the current charging parameters of the target battery, filling and reducing the current charging parameters to obtain the features to be evaluated; performing feature mapping on the features to be evaluated based on the current estimation model to obtain a reference charging current; obtaining the charging stage according to the charging power curve of the reference charging current; obtaining the current fluctuation amplitude according to the current value in the charging stage, and obtaining the health status of the target battery according to the current fluctuation amplitude; the method predicts the actual charging current of the battery and divides the charging stage through the features after the current charging parameters are processed, and judges the battery health status based on the current fluctuation amplitude in different stages, so as to realize real-time and continuous detection of the battery health status without destroying the battery structure, thereby ensuring the safety of battery use and extending the battery life.

[0064] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a battery health assessment device, etc. The following takes the battery health assessment device as an example to illustrate this embodiment and the following embodiments.

[0065] Based on this, the present application embodiment provides a battery health assessment method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the battery health assessment method of the present application.

[0066] In this embodiment, the battery health assessment method includes steps S10 to S40:

[0067] Step S10, obtaining the current charging parameters of the target battery, and performing filling and dimensionality reduction processing on the current charging parameters to obtain features to be evaluated.

[0068] It should be noted that the current charging parameters may include charging current, ambient temperature, and battery usage time (or battery usage cycle).

[0069] It is understandable that the charging current of the target battery can be measured by a current sensor (such as a Hall effect sensor) installed in the battery or the charging circuit. There may be a certain difference between the charging current measured by the current sensor (such as a Hall effect sensor) installed in the battery or the charging circuit and the actual charging current, which may be affected by ambient temperature, battery aging and other issues.

[0070] It is understandable that the ambient temperature can be obtained by placing a temperature sensor (such as a thermistor, a thermocouple, etc.) near the battery or directly contacting the battery surface to obtain the actual temperature of the environment where the battery is located.

[0071] It is understandable that the battery usage time can be calculated by recording the time when the battery starts to be used or the time when the battery starts to work. The recording of the usage time can automatically track the accumulated working time through the built-in timer function of the smart device.

[0072] It should be noted that performing filling and dimensionality reduction processing on the current charging parameters to obtain the features to be evaluated may be performing data preprocessing on the current charging parameters and then performing feature extraction on the current charging parameters to obtain features that are more capable of representing the current charging health status.

[0073] In a feasible implementation, step S10 may include steps A11 to A14:

[0074] Step A11, obtaining current charging parameters of the target battery, and identifying parameter inflection points of the current charging parameters.

[0075] It is understandable that the parameter inflection point may be a time point at which a significant change occurs in the charging current.

[0076] It should be noted that the places where the current changes significantly often correspond to important chemical changes in the battery charging and discharging process, and can better reflect the health status of the battery and its changing trends. Therefore, by detecting the local maximum and minimum values, they serve as parameter inflection points in the current charging parameter curve.

[0077] Step A12, dividing the current charging parameter into a plurality of bands according to the parameter inflection point, sampling the bands to obtain sampled charging characteristics.

[0078] It is understandable that the current charging parameters are divided into multiple bands through the inflection points, sampling can be performed evenly in each band, and the number of sampling points can be determined according to actual conditions.

[0079] It should be understood that the sampled charging parameters are taken as sampled charging characteristics.

[0080] Step A13, performing zero filling on the sampled charging feature to obtain a feature to be processed.

[0081] It is understandable that zero-filling the sampled charging features may be to replace part of the sampled charging features with data "0" after linear interpolation of the sampled charging features, and use a series of sampled charging features replaced with 0 as features to be processed.

[0082] It should be noted that zero-filling after segmented sampling can not only effectively maintain data integrity but also significantly reduce the number of input data points, reduce computational complexity, and use data "0" to replace part of the original data to increase data diversity and robustness, reduce dependence on complete data, and thus effectively perform battery health assessment even when data is incomplete.

[0083] Step A14, performing feature perception on the features to be processed according to the number of sampling points, the size of the sliding window and the number of features to be processed to obtain features to be evaluated.

[0084] It should be noted that feature perception of the data to be processed means that outliers may appear during data collection or feature sampling, which will have an adverse impact on the reliability and effectiveness of the model. Eliminating outliers through perception can effectively improve the accuracy of the model.

[0085] In the specific implementation, the specific processing method of feature perception can refer to the following formula:

[0086]

[0087] Among them, F represents the feature to be evaluated, S represents the number of sampling points, T represents the battery usage time / battery charge and discharge cycle, γ represents the feature to be processed, P represents the sampling point feature, and N represents the number of features.

[0088] In this embodiment, by dividing the charging process into multiple bands with similar characteristics and sampling these bands to extract representative charging features, the amount of data can be reduced while retaining the most important information in the charging process, which can effectively improve the accuracy and efficiency of battery charging status monitoring, thereby more accurately evaluating the battery health status.

[0089] The above are only feasible implementations of step S10 provided in this embodiment, and this embodiment does not specifically limit the specific implementation of step S10.

[0090] Step S20: performing feature mapping on the feature to be evaluated based on the current estimation model to obtain a reference charging current.

[0091] It is understandable that the current estimation model can be a pre-trained and qualified battery real charging current prediction model. Based on this model, the influence of ambient temperature and battery aging on the battery charging current can be better analyzed, and the real charging current, i.e., the reference charging current, can be estimated based on the detected charging current and influencing factors (ambient temperature and battery usage time).

[0092] It should be noted that this embodiment continuously estimates the battery current, records the battery current for a period of time, and evaluates the battery health status based on the battery current over a period of time.

[0093] It should be understood that the reference charging current may be an estimated current value that is closer to the actual charging current of the battery after being estimated by a model.

[0094] In a feasible implementation, step S20 may include steps A21 to A23:

[0095] Step A21, extracting the battery health features of the features to be evaluated according to the dynamic involution kernel through the current estimation model.

[0096] It should be noted that the inner convolution kernel can be obtained by the inner convolution function of the inner convolution layer in the current estimation model. The structure of the inner convolution layer can refer to Figure 2 ,The current estimation model in the figure includes a convolution block consisting of two inner convolution layers.

[0097] It should be further explained that the battery health feature to be evaluated can be extracted according to the dynamic involution kernel by referring to the following formula:

[0098]

[0099] Where m represents the mth charging cycle, or the mth cycle divided by the highest / lowest current, n represents the nth current characteristic of the mth stage, and k m,n represents the charging current set of each divided cycle; θ(·) represents the inner convolution function, and x represents the current feature vector.

[0100] It should be further explained that the features to be evaluated can be processed in advance, the identified abnormal data can be repaired, and then the data can be normalized so that the data is between [0,1].

[0101] It is understandable that the method of identifying abnormal data is not limited in this embodiment and can be selected according to actual conditions. The data obtained by time series processing after preprocessing can be sliding window analysis combined with historical data or time series decomposition to obtain reference data.

[0102] It should be understood that the convolution layer extracts the battery health characteristics through the dynamic involution kernel, retaining the time variation pattern of the charging current to the maximum extent.

[0103] It should be noted that, to extract the time characteristics of the battery health characteristics through the convolution layer of the current estimation model, a convolution layer can be defined first, with a convolution kernel size of 3, a step size of 1, and a padding of 1 (so that the output feature map has the same length as the input). The convolution kernel slides on the time series, sliding one time point each time, calculating the weighted sum within each time window, and stacking multiple convolution layers, each of which is responsible for extracting time features at different levels.

[0104] Step A22: divide the battery health characteristics into stage health characteristics, dynamically weight the stage health characteristics, and obtain global health dependency characteristics.

[0105] It should be noted that dividing the battery health characteristics into stage health characteristics may be converting the battery health characteristics into a data matrix, and then dividing the data matrix into a plurality of database blocks, each data block being used as a stage health characteristic.

[0106] It should be noted that the health characteristics of the stages are dynamically weighted to obtain the global health-dependent characteristics. The self-attention mechanism is used to adaptively weight the health characteristics of each stage dynamically, so as to obtain the correlation between the health characteristics of each cycle.

[0107] It should be further explained that the battery health characteristics can be divided into stage health characteristics by referring to the following formula:

[0108]

[0109] Among them, ρ represents the stage health characteristics, P represents the amount of data for battery health characteristics, and P v Represents each stage, N represents the sampling point information, N v Indicates the number of sampling points in each stage.

[0110] Step A23, performing nonlinear transformation on the global health dependency feature and the stage health feature to obtain a reference feature, and performing dimension reduction feature mapping on the reference feature to obtain a reference charging current.

[0111] It should be noted that the global health-dependent features and the stage health features are flattened into a one-dimensional vector through the involution kernel, and the product operation is performed on the channel with the feature points at the corresponding position of the involution kernel flattened, and the sum operation is performed in space, and finally a feature map corresponding to the input dimension is output, and the output feature map is the reference charging current.

[0112] In a specific implementation, the global health dependency feature and the stage health feature are subjected to nonlinear transformation to obtain a reference feature, which can refer to the following formula:

[0113]

[0114] Among them, ω1 and ω2 represent two nonlinear transformations, K represents the number of charging stages, c is the number of convolution channels, G is the number of shared channels, and σ(·) represents ReLU (BN(·)).

[0115] For example, if the output of the last convolutional layer is a tensor of shape (batch_size, num_channels, length), then after flattening it will get a vector of (batch_size, num_channels*length).

[0116] It should be noted that the reference charging current can be obtained by performing dimension reduction feature mapping on the reference feature, which is the final output of the TransformerEncoder using a two-layer MLP. The functions of the MLP are mainly in two aspects: one is to perform dimensional transformation to ensure that the input and output dimensions of the TransformerEncoder are consistent; the other is to introduce a nonlinear activation function to provide nonlinear features and learn degraded complex relationships.

[0117] Furthermore, the flattened feature vector is input into one or more fully connected layers. Each neuron in the fully connected layer is connected to all neurons in the previous layer, so it can integrate information from different convolution channels; the fully connected layer reduces the dimension of the input features by learning a set of weights to obtain the reference charging current. It should be noted that the reference charging current is a predicted continuous value, usually a single neuron, and there is no activation function, and the predicted value is directly output.

[0118] In the specific implementation, the internal structure of the current estimation model can refer to Figure 3 In the figure, the input layer preprocesses the input features to be evaluated to obtain a sequence with time characteristics, and then convolves the features of the input layer through the convolution layer. It mainly extracts the features to be evaluated through the inner convolution layer including the dynamic inner convolution kernel to obtain the battery health features, and then divides the battery health features through the network layer, and dynamically weights the stage health features through the self-attention network structure to obtain the global health dependency features, and then performs nonlinear transformation and dimensionality reduction feature mapping processing through the fully connected layer to obtain the reference charging current.

[0119] In this implementation, the reference charging current is estimated by detecting the charging current, ambient temperature, and battery usage time. Based on the reference charging current that is closer to the actual current, the charging power curve of the target battery can be obtained more accurately, and the actual charging current changes of the battery can be more accurately portrayed, thereby more accurately calculating the rate of change of the charging current of the target battery at different stages, and further more accurately judging the health status of the battery.

[0120] The above are only feasible implementations of step S20 provided in this embodiment, and this embodiment does not specifically limit the specific implementation of step S20.

[0121] It should be noted that, before the feature mapping of the feature to be evaluated based on the current estimation model to obtain the reference charging current, it also includes: obtaining the sample charging current, sample ambient temperature, sample battery usage time and actual charging current of the target battery; preprocessing the sample charging current, the sample ambient temperature, the sample battery usage time and the actual charging current to obtain training data and sample data; training the initial current estimation model according to preset model parameters, number of iterations and training data to obtain a reference current estimation model; evaluating the reference current estimation model according to the sample data to obtain an evaluation result; when the evaluation result meets the preset model requirements, using the reference current estimation model as the current estimation model.

[0122] It can be understood that the sample charging current, the sample ambient temperature, the sample battery usage time and the actual charging current are preprocessed to obtain the training data and the preprocessed sample data, and the identified abnormal data is repaired, and then the data is normalized so that the data is between [0,1].

[0123] It should be understood that the training data and sample data can be obtained by dividing the sample charging current, sample ambient temperature, sample battery usage time and actual charging current according to a preset ratio, and 70% of the preprocessed data group can be used as training data and 30% as sample data.

[0124] It should be noted that the initial current estimation model is trained according to the preset model parameters, number of iterations and training data, and the number of iterations in the reference current estimation model can be selected as 100 times, and the model parameters can be obtained by using an optimization algorithm (such as Adam, SGD, etc.) through an optimizer to minimize the loss function, thereby adjusting the network parameters to improve the prediction accuracy.

[0125] Among them, it should be noted that the loss function can be mean square error (MSE), mean absolute error (MAE), root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE), which are used to measure the difference between the predicted value and the actual value. In the specific implementation, the model performance is quantified by calculating relevant indicators, and the research model is compared with other benchmark models with the help of evaluation indicators to reflect its generalization ability. For details, please refer to the following formula:

[0126]

[0127]

[0128]

[0129] Among them, Q j represents the reference battery current, represents the actual battery current, and S represents the number of samples.

[0130] Step S30, obtaining a charging stage according to the charging power curve of the reference charging current.

[0131] It is understandable that the charging power curve can be obtained based on the reference charging current and the voltage and time corresponding to the current.

[0132] It should be understood that the charging power curve can be a graph used to describe the change in the rate of electrical energy input to the battery during the charging process, and can usually be used to analyze and optimize the charging process to ensure the safety and efficiency of the battery and extend its service life.

[0133] It is understandable that the charging power curve may be drawn with time as the horizontal axis and the charging current as the vertical axis.

[0134] It is understandable that the charging stage may include a constant current charging stage, a constant voltage charging stage and a floating charging stage.

[0135] It should be understood that during the constant current charging stage, the charger supplies power to the battery at a fixed current value until the battery voltage reaches a preset threshold (usually around 4.2V for a single-cell lithium battery). The main purpose of this stage is to quickly replenish the battery with energy. During this stage, the current remains unchanged, but as the chemical reaction inside the battery proceeds, the battery voltage will gradually rise.

[0136] Furthermore, the constant voltage charging stage is when the battery voltage reaches the preset upper limit, and the charging mode changes from constant current to constant voltage. At this time, the charger maintains a fixed maximum voltage, and the charging current gradually decreases. In this stage, although the voltage remains unchanged, as the battery approaches a fully charged state, the ability to accept current decreases, so the charging current will gradually decrease. When the charging current drops to a certain threshold (such as 0.01C or lower), or after a predetermined period of time, the battery is considered to be fully charged.

[0137] Furthermore, the floating charge stage can be after the battery is considered to be fully charged. In order to compensate for the battery self-discharge loss, the charger will continue to provide power at a very low current (usually less than 0.01C) to keep the battery in a state close to full charge. The current in the floating charge stage is very small and will hardly cause damage to the battery, but it can ensure that the battery is in a high power state for a long time.

[0138] In a feasible implementation, step S30 may include steps A31 to A33:

[0139] Step A31, comparing the magnitudes of multiple reference charging currents to obtain a target charging current.

[0140] It is understandable that the charging current of the target battery is continuously acquired through the current sensor, so that the reference charging current can be continuously obtained, and the charging power curve is plotted according to the time sequence of the reference charging current.

[0141] It should be noted that the target charging current may be a signature current used to distinguish charging stages.

[0142] It should be noted that the comparison of the sizes of multiple reference charging currents to obtain the target charging current includes: taking adjacent reference charging currents in the reference charging current as the first reference charging current and the second reference charging current; obtaining a current difference based on the first reference charging current and the second reference charging current, and obtaining an adjacent current ratio based on the current difference and the first reference charging current; when the adjacent current ratio is greater than a preset ratio amplitude threshold, taking the first reference charging current corresponding to the adjacent reference current as the target charging current.

[0143] It is understandable that the reference charging current at the first time point and the reference charging current at the second time point can be used as adjacent charging currents; the reference charging current at the second time point and the reference charging current at the third time point can also be used as adjacent charging currents.

[0144] It should be noted that the current difference is obtained according to the first reference charging current and the second reference charging current, and the adjacent current ratio is obtained according to the current difference and the first reference charging current, which can be obtained by subtracting the first reference charging current from the second reference charging current to obtain the current difference, and the current difference can be a positive number or a negative number; the absolute value of the ratio of the current difference to the first reference charging current is used as the adjacent current ratio, and the specific formula can be referred to as follows:

[0145]

[0146] Among them, I n I represents the nth reference charging current, that is, the second reference charging current; n-1 represents the n-1th reference charging current, that is, the first reference charging current; M represents the adjacent current ratio.

[0147] It should be noted that when the adjacent current ratio is greater than the preset ratio amplitude threshold, the first reference charging current corresponding to the adjacent reference current is used as the preset ratio amplitude threshold in the target charging current, which can be 0.2 or other values, and can be adjusted according to actual conditions. This embodiment does not limit this.

[0148] Step A32, obtaining a phase node based on the target charging current.

[0149] It is understandable that the stage node can be a mark used to divide the constant current charging stage, the constant voltage charging stage and the floating charging stage. There can be multiple stage nodes. From the first time as the starting time of the first stage, each stage node can be understood as the starting time point of the subsequent charging node.

[0150] It should be understood that taking the time point corresponding to the target charging current as the stage node can be understood as the next charging stage after the time point corresponding to the stage node.

[0151] Step A33: dividing the reference charging current into multiple charging stages based on the stage nodes.

[0152] It is understandable that the time period corresponding to the reference charging current can be divided into three charging stages with the stage nodes as stages; it should be emphasized that if there are other stages that can be further divided in more detail, this embodiment does not limit this.

[0153] In this embodiment, by sequentially calculating the current difference ratio between two adjacent reference charging currents, the battery charging time period is accurately divided into a plurality of different stages, and the battery health status can be judged based on the current fluctuation amplitudes in different stages.

[0154] The above are only feasible implementations of step S30 provided in this embodiment, and this embodiment does not specifically limit the specific implementation of step S30.

[0155] Step S40, obtaining a current fluctuation amplitude according to the current value in the charging stage, and obtaining a health state of the target battery according to the current fluctuation amplitude.

[0156] It is understandable that the current value of the charging stage may be the current value of the reference charging current corresponding to each time point in each charging stage.

[0157] It should be understood that the current fluctuation amplitude may be the fluctuation amplitude of the reference charging current in each charging stage.

[0158] It should be noted that the health state of the target battery can be obtained based on the current fluctuation amplitude. The larger the fluctuation, the worse the battery health state is, and the smaller the fluctuation, the worse the battery health state is.

[0159] In the specific implementation, the current fluctuation amplitude calculation process in battery health assessment can refer to Figure 4 , the algorithm research prototype in the figure is to judge the health of the electric bicycle battery through the current curve, which mainly depends on the analysis of the current and voltage change curves during the charging and discharging process. First of all, the charging process of a regular electric bicycle usually consists of three stages: constant current charging stage, constant voltage charging stage and floating charging stage. The charging curves of these three stages are an important basis for judging the health of the charger and the vehicle. If the charging process does not meet the requirements of these three stages, it may mean that the charger is an unqualified product or there is a situation of cutting corners, which may cause the battery to overheat or even catch fire and explode. During the charging process, by observing the discharge current and voltage change curves, the health status of the battery can be comprehensively diagnosed. For example, the performance of the battery can be evaluated by parameters such as the maximum charging current, the average charging current, and the cut-off voltage. In addition, by the discharge voltage difference change curve, it can be judged whether there is an abnormality inside the battery pack. For example, a large voltage difference may indicate that there is an imbalance or damage inside the battery. For lead-acid batteries, the charging process includes a constant current section, a constant voltage section, and a floating charge section. In the constant current section, the battery is charged with the maximum charging current. When the voltage reaches a certain value, it enters the constant voltage section. At this time, the current gradually decreases, and finally enters the floating charge section, charging with a small current. If there is a problem in this process, it will also affect the health of the battery.

[0160] This embodiment provides a battery health assessment method, which predicts the actual charging current of the battery and divides the charging stage through the characteristics of the current charging parameters processed, and judges the battery health status based on the current fluctuation amplitude in different stages, so as to realize real-time and continuous detection of the battery health status without destroying the battery structure, thereby ensuring the safety of battery use and extending the battery service life.

[0161] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 5 , step S40 also includes steps S41 to S43:

[0162] Step S41, extracting the maximum current value in the charging stage, and obtaining a plurality of current fluctuation amplitudes from each current value in the charging stage and the maximum current value.

[0163] It should be noted that the current fluctuation amplitude is calculated for each charging stage respectively, and then the current fluctuation amplitude of the battery in the entire charging process is calculated based on the current fluctuation amplitude of each charging stage.

[0164] It is understandable that the maximum current value extracted during the charging phase may be a maximum current value obtained by comparing the reference charging currents at various time points during the charging phase.

[0165] It should be noted that the maximum current value is compared with the current values ​​corresponding to each time point in the charging stage to obtain the current fluctuation amplitude at each time point.

[0166] Step S42, obtaining the current fluctuation amplitude of the charging stage according to the multiple current fluctuation amplitudes.

[0167] It is understandable that the average value of the current fluctuation amplitudes is obtained according to the multiple current fluctuation amplitudes as the current fluctuation amplitude in the charging stage.

[0168] In the specific implementation, each group of currents is compared with the maximum value of the stage, and the ratio of the difference is calculated. This ratio is used as the fluctuation amplitude, and then the average value of the fluctuation amplitude of a group is calculated. The specific calculation formula is:

[0169]

[0170] Among them, AVG (L1) represents the current fluctuation amplitude of the L1 charging stage, and L1 (01) represents the current fluctuation amplitude corresponding to the charging current value at time point 01 of the L1 charging stage.

[0171] Step S43, obtaining the health status of the target battery according to the current fluctuation amplitude of each charging stage.

[0172] It should be noted that the current fluctuation amplitude during the charging process is calculated based on the stage current fluctuation amplitude of each charging stage, and then the health status of the target battery is obtained based on the current fluctuation amplitude.

[0173] It should be further explained that the health status of the target battery includes a normal state and an abnormal state.

[0174] In a feasible implementation, step S43 may include steps A431 to A433:

[0175] Step A431, obtaining the charging current fluctuation amplitude of the target battery according to the stage current fluctuation amplitude of each charging stage.

[0176] It should be noted that the current fluctuation amplitudes of each charging stage are averaged and the average value is used as the fluctuation amplitude of the target battery. The specific calculation formula is as follows:

[0177]

[0178] Wherein, AVG represents the charging current fluctuation amplitude of the target battery.

[0179] Step A432, when the charging current fluctuation amplitude is less than or equal to the preset current fluctuation amplitude, taking the normal state as the health state of the target battery and generating a battery health assessment report based on the normal state.

[0180] It is understandable that the preset current fluctuation amplitude can be 0.2-0.5, and can also be adjusted according to actual conditions.

[0181] It should be understood that when the charging current fluctuation amplitude is less than or equal to the preset current fluctuation amplitude, it is considered that the battery is in a normal state and there is no problem.

[0182] It should be noted that generating a battery health assessment report based on a normal state can be based on a preset report template, in which each test result, or the test result over a period of time, the reference battery current of each test, and the charging power curve drawn by the reference battery current are plotted into a battery health assessment report.

[0183] Step A433, when the charging current fluctuation amplitude is greater than the preset current fluctuation amplitude, the abnormal state is used as the health state of the target battery and a battery health abnormality warning is generated based on the abnormal state.

[0184] It is understandable that when the battery is in a healthy state, an abnormal battery state alarm is issued in real time, and information can be fed back to the user terminal. An alarm can also be issued after multiple abnormal states have occurred cumulatively, or a voice alarm can be issued.

[0185] It should be noted that when the battery health status is in an abnormal state, a battery health assessment report can be generated while issuing an early warning, and the detection time of the abnormal state can be marked in the battery health assessment report.

[0186] In this embodiment, the preset current fluctuation amplitude is used to determine whether the charging current fluctuation amplitude of the target battery is too large. If the charging current fluctuation amplitude is too large, it is determined that the battery health status is abnormal, a warning is issued, and an abnormal status assessment report is generated. If the battery health status is normal, detection is continued and a normal battery health assessment report is generated.

[0187] The above are only feasible implementations of step S43 provided in this embodiment, and this embodiment does not specifically limit the specific implementation of step S43.

[0188] The present embodiment provides a battery health assessment method, which obtains the current fluctuation amplitude of each stage through the reference charging current of each charging stage, and more accurately calculates the current fluctuation amplitude of the target battery based on the current fluctuation amplitude of each stage, and accurately judges the health status of the target battery based on the current fluctuation amplitude of the target battery.

[0189] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the battery health assessment method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0190] This application also provides a battery health assessment device, please refer to Figure 6 , the battery health assessment device comprises:

[0191] An acquisition module 10 is used to acquire the charging current, ambient temperature and battery usage time of the target battery;

[0192] A current estimation module 20, configured to obtain a reference charging current according to the charging current of the target battery, the ambient temperature and the battery usage time based on a current estimation model;

[0193] A charging stage division module 30, configured to obtain a charging stage according to a charging power curve of the reference charging current;

[0194] The battery health assessment module 40 is used to obtain a current fluctuation amplitude according to the current value in the charging stage, and obtain a health state of the target battery according to the current fluctuation amplitude.

[0195] The battery health assessment device provided by the present application adopts the battery health assessment method in the above embodiment, which can solve the technical problem that the prior art cannot continuously and accurately assess the battery health status. Compared with the prior art, the beneficial effects of the battery health assessment device provided by the present application are the same as the beneficial effects of the battery health assessment method provided by the above embodiment, and the other technical features in the battery health assessment device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0196] In one embodiment, the current estimation module 20 is further used to pre-process the charging current, the ambient temperature and the battery usage time through an input layer of a current estimation model to obtain reference data;

[0197] Extracting the time characteristics of the reference data through the convolution layer of the current estimation model;

[0198] Extracting the before and after information of the time feature through the network layer of the current estimation model to obtain a time period feature;

[0199] The time feature and the time period feature are fused through the connection layer of the current estimation model to obtain a reference charging current.

[0200] In one embodiment, the current estimation module 20 is further used to obtain a sample charging current, a sample ambient temperature, a sample battery usage time, and a real charging current of the target battery;

[0201] Preprocessing the sample charging current, the sample ambient temperature, the sample battery usage time, and the real charging current to obtain training data and sample data;

[0202] The initial current estimation model is trained according to preset model parameters, number of iterations and training data to obtain a reference current estimation model;

[0203] Evaluate the reference current estimation model according to the sample data to obtain an evaluation result;

[0204] When the evaluation result meets the preset model requirement, the reference current estimation model is used as the current estimation model.

[0205] In one embodiment, the charging stage division module 30 is further used to compare the magnitudes of a plurality of reference charging currents to obtain a target charging current;

[0206] Obtaining a phase node based on the target charging current;

[0207] The reference charging current is divided into a plurality of charging stages based on the stage nodes.

[0208] In one embodiment, the charging stage division module 30 is further configured to use adjacent reference charging currents in the reference charging current as the first reference charging current and the second reference charging current;

[0209] Obtaining a current difference according to the first reference charging current and the second reference charging current, and obtaining an adjacent current ratio according to the current difference and the first reference charging current;

[0210] When the adjacent current ratio is greater than a preset ratio amplitude threshold, a first reference charging current corresponding to the adjacent reference current is used as a target charging current.

[0211] In one embodiment, the battery health assessment module 40 is further used to extract the maximum current value of the charging stage, and obtain multiple current fluctuation amplitudes from each current value of the charging stage and the maximum current value;

[0212] Obtaining a current fluctuation amplitude in the charging stage according to the multiple current fluctuation amplitudes;

[0213] The health status of the target battery is obtained according to the current fluctuation amplitude in each charging stage.

[0214] In one embodiment, the battery health assessment module 40 is further used to obtain the charging current fluctuation amplitude of the target battery according to the stage current fluctuation amplitude of each charging stage;

[0215] When the charging current fluctuation amplitude is less than or equal to a preset current fluctuation amplitude, taking the normal state as the health state of the target battery and generating a battery health assessment report based on the normal state;

[0216] When the charging current fluctuation amplitude is greater than a preset current fluctuation amplitude, the abnormal state is used as the health state of the target battery and a battery health abnormality warning is generated based on the abnormal state.

[0217] The present application provides a battery health assessment device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the battery health assessment method in the above-mentioned embodiment one.

[0218] Reference below Figure 7 , which shows a schematic diagram of the structure of a battery health assessment device suitable for implementing an embodiment of the present application. The battery health assessment device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7The battery health assessment device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0219] like Figure 7 As shown, the battery health assessment device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the battery health assessment device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the battery health assessment device to communicate with other devices wirelessly or wired to exchange data. Although the figure shows a battery health assessment device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have instead.

[0220] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0221] The battery health assessment device provided by this application adopts the battery health assessment method in the above embodiment, which can solve the technical problem that the prior art cannot continuously and accurately assess the battery health status. Compared with the prior art, the beneficial effects of the battery health assessment device provided by this application are the same as the beneficial effects of the battery health assessment method provided by the above embodiment, and the other technical features in the battery health assessment device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0222] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0223] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0224] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the battery health assessment method in the above-mentioned embodiment.

[0225] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0226] The computer-readable storage medium may be included in the battery health assessment device; or may exist independently without being assembled into the battery health assessment device.

[0227] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the battery health assessment device, the battery health assessment device: obtains the charging current, ambient temperature and battery usage time of the target battery; obtains a reference charging current based on the current estimation model according to the charging current, ambient temperature and battery usage time of the target battery; obtains the charging stage according to the charging power curve of the reference charging current; obtains the current fluctuation amplitude according to the current value in the charging stage, and obtains the health status of the target battery according to the current fluctuation amplitude.

[0228] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0229] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0230] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0231] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned battery health assessment method, and can solve the technical problem that the prior art cannot continuously and accurately assess the battery health status. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the battery health assessment method provided in the above-mentioned embodiment, and will not be repeated here.

[0232] The present application also provides a computer program product, including a computer program, which implements the steps of the battery health assessment method as described above when executed by a processor.

[0233] The computer program product provided by this application can solve the technical problem that the prior art cannot continuously and accurately evaluate the battery health status. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the battery health evaluation method provided by the above embodiment, which will not be repeated here.

[0234] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A battery health assessment method, characterized in that: The battery health assessment method comprises: Obtaining the current charging parameters of the target battery at the current moment, and performing filling and dimensionality reduction processing on the current charging parameters to obtain features to be evaluated; Performing feature mapping on the feature to be evaluated based on the current estimation model to obtain a reference charging current at the current moment; Obtaining a charging power curve according to reference charging currents at multiple consecutive time points, and dividing the charging power curve into multiple charging stages; Extract the maximum current value of each charging stage, and obtain multiple current fluctuation amplitudes by combining the current values ​​of each charging stage and the maximum current value; obtain the stage current fluctuation amplitude of the charging stage according to the multiple current fluctuation amplitudes; and obtain the health status of the target battery according to the stage current fluctuation amplitude of each charging stage.

2. The battery health assessment method according to claim 1, characterized in that: The step of obtaining the current charging parameters of the target battery at the current moment and performing filling and dimensionality reduction processing on the current charging parameters to obtain features to be evaluated includes: Obtaining current charging parameters of the target battery at the current moment, and identifying parameter inflection points of the current charging parameters; Dividing the current charging parameter according to the parameter inflection point to obtain a plurality of bands, sampling the bands to obtain a sampled charging feature; Zero-filling the sampled charging features to obtain features to be processed; The features to be processed are subjected to feature perception according to the number of sampling points, the size of the sliding window, and the number of features to be processed to obtain features to be evaluated.

3. The battery health assessment method according to claim 1, characterized in that: The performing feature mapping on the feature to be evaluated based on the current estimation model to obtain a reference charging current at the current moment includes: Extracting the battery health features of the features to be evaluated according to the dynamic involution kernel through the current estimation model; Dividing the battery health characteristics into stage health characteristics, dynamically weighting the stage health characteristics, and obtaining a global health dependency characteristic; The global health dependency feature and the stage health feature are transformed nonlinearly to obtain a reference feature, and the reference feature is mapped to a dimension reduction feature to obtain a reference charging current at the current moment.

4. The battery health assessment method according to claim 1, characterized in that: The step of obtaining a charging power curve according to the reference charging current at multiple consecutive time points, and dividing the charging power curve into multiple charging stages by charging stages, includes: Obtaining a charging power curve according to a reference charging current at a plurality of consecutive time points; Compare the magnitudes of multiple reference charging currents to obtain a target charging current; Obtaining a phase node based on the target charging current; The charging power curve is divided into a plurality of charging stages based on the stage nodes.

5. The battery health assessment method according to claim 4, characterized in that: The comparing the magnitudes of the plurality of reference charging currents to obtain the target charging current includes: using adjacent reference charging currents among a plurality of reference charging currents as a first reference charging current and a second reference charging current; Obtaining a current difference according to the first reference charging current and the second reference charging current, and obtaining an adjacent current ratio according to the current difference and the first reference charging current; When the adjacent current ratio is greater than a preset ratio amplitude threshold, a first reference charging current corresponding to the adjacent reference charging current is used as a target charging current.

6. The battery health assessment method according to claim 1, characterized in that: The health status includes a normal state and an abnormal state; The method of obtaining the health status of the target battery according to the current fluctuation amplitude of each charging stage includes: The charging current fluctuation amplitude of the target battery is obtained according to the stage current fluctuation amplitude of each charging stage; When the charging current fluctuation amplitude is less than or equal to a preset current fluctuation amplitude, taking the normal state as the health state of the target battery and generating a battery health assessment report based on the normal state; When the charging current fluctuation amplitude is greater than a preset current fluctuation amplitude, the abnormal state is used as the health state of the target battery and a battery health abnormality warning is generated based on the abnormal state.

7. A battery health assessment device, characterized in that: The battery health assessment device comprises: An acquisition module is used to acquire the current charging parameters of the target battery at the current moment, and perform filling and dimensionality reduction processing on the current charging parameters to obtain features to be evaluated; A current estimation module, used for performing feature mapping on the feature to be evaluated based on a current estimation model to obtain a reference charging current at a current moment; A charging stage division module, used to obtain a charging power curve according to a reference charging current at a plurality of consecutive time points, and to divide the charging power curve into charging stages to obtain a plurality of charging stages; A battery health assessment module is used to extract the maximum current value of each charging stage, obtain multiple current fluctuation amplitudes from each current value of each charging stage and the maximum current value; obtain the stage current fluctuation amplitude of the charging stage according to the multiple current fluctuation amplitudes; and obtain the health status of the target battery according to the stage current fluctuation amplitude of each charging stage.

8. A battery health assessment device, characterized in that: The device comprises: a memory, a processor, and a battery health assessment program stored in the memory and executable on the processor, wherein the battery health assessment program is configured to implement the battery health assessment method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a battery health assessment program, and when the battery health assessment program is executed by the processor, the battery health assessment method according to any one of claims 1 to 6 is implemented.

Images