Battery health state prediction method and device, equipment and medium

Abstract

The invention discloses a battery health state prediction method, device and equipment and a medium, and relates to the technical field of new energy, and the method comprises the steps: obtaining the charge-discharge cycle data of a to-be-detected lithium battery; inputting the charge-discharge cycle data into a trained battery health state prediction model to obtain a battery life result output by the battery health state prediction model; the battery health state prediction model is obtained by training by adopting a supervised deep learning mode based on sample fusion features of a sample lithium battery and the battery health state of each sample charge-discharge cycle, and the sample fusion features are input data used for training; the battery health state of each sample charge-discharge cycle is a label used for training. According to the method, the prediction precision of the model is effectively improved, and the task of predicting the health state of the battery is more accurately completed while the problem of unbalanced data distribution is effectively solved.

Description

Technical Field

[0001] The present invention relates to the field of new energy technologies, and in particular to a battery health status prediction method, device, equipment and medium. Background Art

[0002] After repeated charge and discharge cycles, the internal resistance of lithium batteries will gradually increase. The increase in internal resistance will cause the battery to generate significant heat during the charge and discharge process, which will cause irreversible aging and performance degradation of the lithium battery. The state of health (SOH) of the battery can be used to indicate the remaining life of the lithium battery. As the number of charge and discharge cycles of the lithium battery increases, the SOH will decrease, that is, the remaining life of the battery will decrease and the available capacity will gradually decrease. When the SOH drops to a certain threshold, such as below 80%, it is necessary to stop using the lithium battery or limit its use. Therefore, accurately predicting the SOH of the lithium battery is extremely important for its use. At present, machine learning-based methods such as neural network models are widely used to predict the SOH of lithium batteries.

[0003] During the lithium battery charge and discharge cycle, there is a specific time node in the discharge process. Before and after this specific time node, there is a significant difference in the rate of voltage drop. This specific time node is called the inflection point of the discharge voltage-time characteristic curve. The inflection point voltage will gradually decrease with the aging and performance degradation of the lithium battery. It is precisely because of the existence of this inflection point that the data collected during the lithium battery charge and discharge cycle are unevenly distributed. This imbalance may cause the neural network model to over-focus on the data features of dense areas during training, while ignoring important information in sparse areas, resulting in the neural network model failing to fully learn the data features of sparse areas based on these data, and thus limiting the generalization performance of new data.

[0004] Therefore, how to improve the accuracy of neural network models in predicting lithium battery SOH is an important issue that needs to be urgently addressed in the industry. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a battery health status prediction method, device, equipment and medium to solve the problem.

[0006] According to a first aspect, an embodiment of the present invention provides a method for predicting a battery health state, the method comprising: Obtain the charge and discharge cycle data of the lithium battery to be tested; Inputting the charge and discharge cycle data into a trained battery health state prediction model to obtain a battery life result output by the battery health state prediction model; The battery health status prediction model is based on the sample fusion features of the sample lithium battery and the battery health status of each sample charge and discharge cycle, and is trained using a supervised deep learning method. The sample fusion features are the input data used for training, and the battery health status of each sample charge and discharge cycle is the label used for training; The sample fusion feature is extracted from the sample charge and discharge cycle data of the sample lithium battery based on the time-voltage decay relationship to identify the inflection point in the charge and discharge cycle process and to mine the differential features implicit in the data. The battery health status of each sample charge and discharge cycle is determined based on the ratio of the battery capacity of the sample charge and discharge cycle to the battery capacity of the initial sample charge and discharge cycle.

[0007] In combination with the first aspect, in a first implementation manner of the first aspect, the battery health state prediction model is trained by the following steps: Obtaining sample charge and discharge cycle data of a sample lithium battery, preprocessing the sample charge and discharge cycle data, and filtering out sample features of each sample charge cycle from the sample charge and discharge cycle data; the sample features include: temperature, current, voltage, power, time, and battery capacity; Determine the battery health status of each sample charge and discharge cycle according to the ratio of the battery capacity of each sample charge and discharge cycle to the battery capacity of the initial sample charge and discharge cycle; According to the sample characteristics of each sample charge and discharge cycle, a voltage-time decay characteristic curve of each sample charge and discharge cycle is constructed; Merge sample features of the same voltage value in the voltage-time decay characteristic curve of each sample charge-discharge cycle to obtain voltage grouping features, obtain derived features of the voltage grouping features, perform feature fusion of the voltage grouping features and the derived features, and obtain sample fusion features; The sample fusion features are used as input data for training, and the battery health status of each sample charge and discharge cycle is used as a label. Supervised deep learning is used for training to obtain a battery health status prediction model for predicting the battery life results of lithium batteries.

[0008] In combination with the first embodiment of the first aspect, in the second embodiment of the first aspect, the sample features of the same voltage value in the voltage-time decay characteristic curve of each sample charge and discharge cycle are merged to obtain a voltage grouping feature, and a derivative feature of the voltage grouping feature is obtained, and feature fusion of the voltage grouping feature and the derivative feature is performed to obtain a sample fusion feature, specifically including: Fitting each voltage-time decay characteristic curve respectively through a preset experience curve, identifying the turning point on the preset experience curve, and obtaining the inflection point and the inflection starting point of each voltage-time decay characteristic curve; Merge the sample features with the same voltage value in the voltage-time decay characteristic curve of each sample charge-discharge cycle to obtain the voltage grouping feature; Determine the difference between each voltage value in the voltage grouping feature and the initial voltage of the voltage-time decay characteristic curve to obtain a voltage difference, and determine the time offset of each voltage value in the voltage grouping feature relative to the inflection point and the starting point of the inflection point of the voltage-time decay characteristic curve to obtain a first time difference and a second time difference; the derived feature includes the voltage difference, the first time difference and the second time difference; The voltage grouping feature and the derived feature are fused to obtain the sample fusion feature.

[0009] In combination with the first aspect, in a third implementation of the first aspect, the battery health state prediction model is a composite neural network model combining a convolutional neural network and a long short-term memory network; The battery health status prediction model includes a convolutional neural network layer and a long short-term memory network layer. The convolutional neural network layer is used to extract local features of the charge and discharge cycle data, and the long short-term memory network layer is used to capture the dependency of the local features on the time series.

[0010] In combination with the third implementation of the first aspect, in the fourth implementation of the first aspect, the convolutional neural network layer includes a sequentially connected convolutional layer, a maximum pooling layer, a data flattening layer, and a first fully connected layer; The long short-term memory network layer includes a first relationship capture layer, a second relationship capture layer and a third relationship capture layer which are connected in sequence.

[0011] In combination with the fourth implementation manner of the first aspect, in the fifth implementation manner of the first aspect, the battery health state prediction model further includes an identity mapping layer, a feature fusion layer, and a corrected linear layer of a residual network structure; The charge and discharge cycle data are processed by the identity mapping layer, the convolutional neural network layer and the long short-term memory network layer in sequence, and then processed by the feature fusion layer and the corrected linear layer in sequence to obtain the battery life result.

[0012] In combination with the fifth implementation manner of the first aspect, in the sixth implementation manner of the first aspect, inputting the charge and discharge cycle data into a trained battery health state prediction model to obtain a battery life result output by the battery health state prediction model specifically includes: Inputting the charge-discharge cycle data into the identity mapping layer to obtain an identity mapping feature outputted by the identity mapping layer after identity processing; Inputting the charge-discharge cycle data into the convolutional neural network layer to obtain a first output feature output by the convolutional neural network layer; Inputting the first output feature into a long short-term memory network layer to obtain a third abstract feature output by the long short-term memory network layer; The identity mapping feature and the third abstract feature are input into the feature fusion layer for feature fusion, and the battery life result is obtained after being processed by the corrected linear layer.

[0013] According to a third aspect, an embodiment of the present invention further provides a battery health status prediction device, the device comprising: A data acquisition module, used to acquire the charge and discharge cycle data of the lithium battery to be tested; A battery prediction module, used to input the charge and discharge cycle data into a trained battery health state prediction model to obtain a battery life result output by the battery health state prediction model; The battery health status prediction model is based on the sample fusion features of the sample lithium battery and the battery health status of each sample charge and discharge cycle, and is trained using a supervised deep learning method. The sample fusion features are the input data used for training, and the battery health status of each sample charge and discharge cycle is the label used for training; The sample fusion feature is extracted from the sample charge and discharge cycle data of the sample lithium battery based on the time-voltage decay relationship to identify the inflection point in the charge and discharge cycle process and to mine the differential features implicit in the data. The battery health status of each sample charge and discharge cycle is determined based on the ratio of the battery capacity of the sample charge and discharge cycle to the battery capacity of the initial sample charge and discharge cycle.

[0014] According to the third aspect, an embodiment of the present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above-mentioned battery health status prediction methods are implemented.

[0015] According to a fourth aspect, an embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above-described battery health status prediction methods are implemented.

[0016] According to a fifth aspect, an embodiment of the present invention further provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps of the battery health status prediction method as described in any one of the above items are implemented.

[0017] The battery health status prediction method, device, equipment and medium of the present invention predict the battery life result of the lithium battery to be tested through a trained battery health status prediction model, wherein the battery health status prediction model locates the inflection point by accurately fitting and calculating the voltage-time decay characteristic relationship, which not only provides key time information for the data, but also can amplify the difference between repeated information before the voltage occurs, which is helpful to complete the subsequent feature derivation and feature fusion process, and secondly, divides the data according to the inflection point information to alleviate the uneven distribution of data, and simultaneously performs feature derivation and feature fusion, amplifies the difference of window data, and mines important information in sparse areas, so that the model can fully learn the data features of sparse areas, effectively improving the prediction accuracy of the model, while effectively solving the uneven distribution of data, and more accurately completing the task of battery health status prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The features and advantages of the present invention will be more clearly understood by referring to the accompanying drawings, which are schematic and should not be construed as limiting the present invention in any way. In the accompanying drawings: Figure 1 A schematic diagram showing a flow chart of a battery health status prediction method provided by the present invention is shown; Figure 2 A schematic diagram showing a voltage-time decay characteristic curve in a battery health status prediction method provided by the present invention; Figure 3 A schematic diagram showing the structure of a battery health state prediction model in a battery health state prediction method provided by the present invention; Figure 4 A schematic diagram showing the structure of a battery health status prediction device provided by the present invention is shown; Figure 5 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0020] Lithium batteries are important energy storage devices that are widely used in new energy fields such as mobile devices, electric vehicles, and energy storage systems due to their high energy density, environmental protection, and long life.

[0021] However, after repeated charge and discharge cycles, the internal resistance of lithium batteries will gradually increase. The increase in internal resistance will cause the battery to generate significant heat during the charge and discharge process, which will cause irreversible aging and performance degradation of lithium batteries. SOH can be used to indicate the remaining life of lithium batteries. As the number of charge and discharge cycles of lithium batteries increases, SOH will decrease, that is, the remaining life of the battery will decrease and the available capacity will gradually decrease. When SOH drops to a certain threshold, such as below 80%, it is necessary to stop using the lithium battery or limit its use. Therefore, accurately predicting the SOH of lithium batteries is extremely important for their use. It can help users understand the remaining life and capacity decay of lithium batteries. At the same time, SOH is also important for accurately predicting other related battery health indicators, such as the state of charge (SOC) of lithium batteries. Currently, machine learning-based methods such as neural network models are widely used to predict the SOH of lithium batteries.

[0022] The common neural network model predicts the process of lithium battery SOH as follows: Feature selection: Select reasonable features to describe the state of the lithium battery, and select features that have a key impact on the prediction of lithium battery SOH. The above features include lithium battery voltage, current, temperature, number of charge and discharge cycles, battery capacity, etc.; Data collection: Collect and record characteristic data of lithium batteries under different working conditions; Data preprocessing: preprocess the collected data, including data cleaning, denoising, missing value processing and feature extraction; Model selection and training: Select a suitable neural network model for training, and use evaluation indicators such as root mean square error (RSME) and mean absolute error (MAE) to evaluate the performance of the neural network model and adjust the parameters of the model; SOH prediction: Use the trained neural network model to predict the lithium battery to be evaluated and obtain the SOH prediction result of the lithium battery.

[0023] During the charge and discharge cycle of lithium batteries, there is a specific time node in the discharge process. Before and after this specific time node, there is a significant difference in the rate of voltage drop. This specific time node is called the inflection point of the discharge voltage-time characteristic curve. The inflection point voltage will gradually decrease as the lithium battery ages and its performance declines.

[0024] It is precisely because of the existence of this inflection point that the data distribution of the collected lithium battery charge and discharge cycle process is uneven, which is specifically manifested as follows: the voltage at the time nodes before the inflection point drops slowly and the data distribution is relatively dense, while the voltage at the time nodes after the inflection point drops rapidly and the data distribution is relatively sparse. The above-mentioned voltage change characteristics are not conducive to the application of neural network models in the field of battery health status prediction. This imbalance may cause the neural network model to pay too much attention to the data features of dense areas during training, while ignoring the important information of sparse areas, resulting in the neural network model failing to fully learn the data features of sparse areas based on these data, and thus limiting the generalization performance of new data.

[0025] Therefore, how to improve the accuracy of neural network models in predicting lithium battery SOH is an important issue that needs to be urgently addressed in the industry.

[0026] In order to solve the above problems, a battery health state prediction method is provided in this specification, which aims to solve the above-mentioned data imbalance problem and effectively complete the task of battery health state prediction based on battery data. The battery health state prediction method provided in this specification can be applied to electronic devices capable of predicting the SOH of lithium batteries. The electronic devices may include notebooks, desktop computers, smart phones, smart wearable devices (virtual reality glasses, smart watches, etc.), tablet computers, etc. Of course, the battery health state prediction method provided in this specification can also be applied to applications running in the above-mentioned electronic devices. For example, the battery health state prediction method can be applied to a browser capable of predicting the SOH of lithium batteries, and can also be applied to software capable of predicting the SOH of lithium batteries. Figure 1 FIG. 1 is a flow chart of a method for predicting a battery health state according to an embodiment of the present invention. Figure 1 As shown, the method may include the following steps: S10, obtaining charge and discharge cycle data of the lithium battery to be tested.

[0027] In this embodiment, the charge and discharge cycle data of the lithium battery to be tested may be stored in advance in the electronic device, or may be acquired by the electronic device from the outside. For example, the electronic device acquires the charge and discharge cycle data from an external acquisition device, and the specific acquisition form of the charge and discharge cycle data is not limited, and it is only necessary to ensure that the electronic device can acquire the charge and discharge cycle data.

[0028] S20, inputting the charge and discharge cycle data into the trained battery health state prediction model to obtain the battery life result output by the battery health state prediction model.

[0029] Among them, the battery health status prediction model is based on the sample fusion features of the sample lithium battery and the battery health status of each sample charge and discharge cycle, and is trained using a supervised deep learning method. The sample fusion features are the input data used for training, and the battery health status of each sample charge and discharge cycle is the label used for training. The sample fusion features are extracted from the sample charge and discharge cycle data of the sample lithium battery based on the time-voltage decay relationship to identify the inflection point in the charge and discharge cycle process and mine the implicit differential features in the data. The battery health status of each sample charge and discharge cycle is determined based on the ratio of the battery capacity of the sample charge and discharge cycle to the battery capacity of the initial sample charge and discharge cycle.

[0030] The battery health status prediction model uses the battery health status represented by the lithium battery cycle data as a label. This indicator is correlated with the capacity of the battery in the current cycle. By learning from sample data, the battery health status prediction model can predict the battery health status of the current charge and discharge cycle of the lithium battery.

[0031] In this embodiment, the battery health status prediction model is trained by the following steps: A10. Obtain sample charge and discharge cycle data of the sample lithium battery, pre-process the sample charge and discharge cycle data, and filter out sample features of each sample charge cycle from the sample charge and discharge cycle data.

[0032] In this embodiment, sample features are first screened out from the sample charge and discharge cycle data during preprocessing. The sample features include: temperature, current, voltage, power, time, battery capacity, etc.

[0033] Similarly, in this embodiment, the sample charge and discharge cycle data of the sample lithium battery may be stored in advance in the electronic device, or may be obtained by the electronic device from the outside. For example, the electronic device obtains the sample charge and discharge cycle data from an external acquisition device, and there is no restriction on the specific acquisition form of the sample charge and discharge cycle data. It is only necessary to ensure that the electronic device can obtain the sample charge and discharge cycle data. By collecting all the sample charge and discharge cycle data of the offline sample lithium battery as sample data, a large amount of data support is provided for subsequent training.

[0034] A20. Determine the battery health status of each sample charge and discharge cycle based on the ratio of the battery capacity of each sample charge and discharge cycle to the battery capacity of the initial sample charge and discharge cycle. Specifically:

[0035] in, Indicates Battery health status for each sample charge and discharge cycle; Indicates the battery capacity of the initial sample charge and discharge cycle, that is, the first sample charge and discharge cycle; Indicates the battery capacity of the current charge and discharge cycle.

[0036] The battery health status prediction model will be based on the Battery health status of sample charge and discharge cycles as labels for the sample data, and It is obtained based on the initial discharge capacity of the selected sample lithium battery sample charge and discharge cycle data. This key indicator directly reflects the health status of lithium batteries. By obtaining the ratio between the discharge capacity in each charge and discharge cycle and the discharge capacity in the initial cycle, label information is provided for the battery health status prediction model, thereby establishing a supervised learning model.

[0037] A30. According to the sample characteristics of each sample charge and discharge cycle, a voltage-time decay characteristic curve of each sample charge and discharge cycle is constructed.

[0038] After data preprocessing, the sample charge and discharge cycle data only contains sample features, which meets the data analysis requirements. Subsequently, the voltage-time decay characteristic curve within each sample charge and discharge cycle is calculated and determined, and time information is provided for the lithium battery data within a single sample charge and discharge cycle.

[0039] A40. Combine sample features of the same voltage value in the voltage-time decay characteristic curve of each sample charge and discharge cycle to obtain voltage grouping features, obtain derived features of the voltage grouping features, perform feature fusion of the voltage grouping features and the derived features, and obtain sample fusion features.

[0040] Since the sample characteristics in each sample charge and discharge cycle include temperature, current, voltage, power, time and battery capacity, the time corresponding to the inflection point starting point and the time corresponding to the inflection point can be calculated based on the voltage-time decay characteristic curve corresponding to each sample charge and discharge cycle.

[0041] See also Figure 2 , using the preset experience curve obtained by expert experience as a benchmark. Next, the partial least squares regression method is used to fit the actually measured voltage-time decay characteristic curve with the initialized preset experience curve to identify the turning points on the preset experience curve. These turning points on the preset experience curve often correspond to the inflection points or inflection starting points of the voltage-time decay characteristic curve.

[0042]

[0043] in, Represents the preset experience curve for initialization; Represents the voltage-time decay characteristic curve within a complete sample charge and discharge cycle; represents a random variable that is normally distributed and centered around zero representing the residual; Indicates the inflection point of the voltage-time decay characteristic curve; Indicates the inflection point starting point of the voltage-time decay characteristic curve; express The intercept at ; represents the first slope of the adjusted intersection line, represents the second slope of the adjusted intersection line, represents the third slope of the adjustment intersection line; represents a constant that controls the abruptness of the transition and is initialized to a low value; represents the hyperbolic tangent function. The two turning points of the curve model obtained by fitting are considered to be the inflection starting point and inflection point of the voltage-time decay characteristic curve.

[0044] For the voltage data before the inflection point, the data distribution is relatively dense, and multiple data points are recorded repeatedly at the same voltage value. In this embodiment, part of the voltage-time decay characteristic curve shows that the voltage drops very slowly before the starting point of the inflection point, approaching a straight line, and there are too many identical values, which causes duplicate data in a small data window. In order to improve data processing efficiency and solve data density, the sample features under the same voltage value are merged into a group, and the average values ​​of temperature, current, voltage, power and other features under the voltage value are calculated to obtain the voltage grouping feature, and the voltage grouping feature is used as the representative data at the voltage level.

[0045] At the same time, in order to fully explore the implicit differential features in the data, we deeply analyze each voltage data point, calculate the difference between each voltage value and the initial voltage, that is, the voltage change, and the time offset of these voltage data points relative to the inflection point starting point and inflection point. These derived features amplify the differences between the data and make the data set more compact. Further feature fusion is performed with the original voltage grouping features. The fusion process can integrate information from multiple dimensions to form a rich and comprehensive fusion feature data set, which is used as input data to provide a data basis for subsequent battery life prediction.

[0046] The voltage grouping feature is fused with the derived features of the potential differences such as the time difference of the inflection point starting point, the time difference of the inflection point, and the voltage difference of the starting voltage to obtain input data for training.

[0047] A50. The sample fusion features are used as input data for training, and the battery health status of each sample charge and discharge cycle is used as a label. Supervised deep learning is used for training to obtain a battery health status prediction model for predicting the battery life results of lithium batteries.

[0048] In this embodiment, the battery health status prediction model is a composite neural network model that combines a convolutional neural network (CNN) and a long short-term memory network (LSTM). The input data passes through the CNN and LSTM structures in sequence, and finally returns the predicted battery life result through the fully connected layer. That is, the battery health status prediction model includes a convolutional neural network layer and a long short-term memory network layer. The convolutional neural network layer is used to extract high-level local features of the charge and discharge cycle data, and the long short-term memory network layer is used to capture the long-term dependency of local features on the time series. The composite neural network model of CNN and LSTM can not only capture spatial local features, but also mine the time information in the sequence features, while effectively preventing the model from overfitting. The model has good battery health status prediction capabilities.

[0049] See also Figure 3 The battery health status prediction model is a residual network structure. In addition to the above-mentioned convolutional neural network layer and long short-term memory network layer, it also includes an identity mapping layer for skip connections in the residual network, a feature fusion layer, a second fully connected layer for learning nonlinear combinations between features, and a rectified linear layer (ReLU activation function layer) for enhancing the nonlinear ability of features.

[0050] Specifically, the convolutional neural network layer (CNN layer) includes sequentially connected convolution layers, maximum pooling layers, data flattening layers, and the first fully connected layer. The convolution layer is used to perform convolution processing on the input sample fusion features. The convolution layer is a one-dimensional network structure, including three convolution kernels, and the size of each convolution kernel is 3 and the step size is 1; the maximum pooling layer is used to pool the maximum value in each region of the convolution features input to the convolution layer. The maximum pooling layer window size is 3 and the step size is 1. A smaller step size can maximize the retention of sequence information. The maximum pooling layer reduces the spatial dimension of the data by selecting the maximum value in the window, helping the model focus on important features and reducing the amount of calculation; the data flattening layer is used to flatten the pooled features output by the maximum pooling layer, converting multi-dimensional features into one-dimensional features for transition to the first fully connected layer; the first fully connected layer is used to integrate the flattened features input to the data flattening layer to obtain the first output features. The CNN layer aims to capture local features, such as trends and patterns, from the sample fusion features.

[0051] The long short-term memory network layer (LSTM layer) includes three sequentially connected relationship capture layers, namely the first, second and third relationship capture layers. The input of the first relationship capture layer of the long short-term memory network layer comes from the output of the convolutional neural network layer, and the input of the subsequent two layers comes from the output of the previous layer. The number of neurons in the hidden layer of the LSTM layer is 200. The output of the LSTM layer learns the nonlinear combination of features through two fully connected layers, and finally outputs the prediction result. In this way, the LSTM layer learns and memorizes the information in the neurons through the gating mechanism (including the forgetting gate, input gate and output gate, etc.), and can effectively learn the complex features and long-term dependencies in the sequence data by stacking multiple layers of LSTM networks.

[0052] Specifically, the first relationship capture layer is used to perform the first feature extraction and abstract processing on the first output feature of the second connection layer input to obtain the first abstract feature; the second relationship capture layer is used to perform the second feature extraction and abstract processing on the first abstract feature of the first relationship capture layer input to obtain the second abstract feature; the third relationship capture layer is used to perform the third feature extraction and abstract processing on the second abstract feature of the second relationship capture layer input to obtain the third abstract feature. Both the second and third relationship capture layers use the output of the previous layer to further extract and abstract features, and finally generate a fixed-length vector containing the entire sequence information.

[0053] For the entire battery health status prediction model, the processing process is: The battery health state prediction model has two branches: the first branch is the charge and discharge cycle data as input data input into the identity mapping layer of the battery health state prediction model, the identity mapping layer performs identity mapping processing, and outputs the identity mapping feature. The second branch is the charge and discharge cycle data as input data input into the CNN layer of the battery health state prediction model, the CNN layer performs local feature extraction, outputs the first output feature, and then inputs the first output feature into the LSTM layer, the LSTM layer performs dependency capture, and outputs the third abstract feature. It should be noted that in the second branch, a second fully connected layer is also set after the LSTM layer, and the second fully connected layer is also intended to perform integration processing. Afterwards, the identity mapping feature output by the first branch and the third abstract feature after integration processing output by the second branch are feature fused at the feature fusion layer, and then processed by the corrected linear layer that enhances the nonlinear ability of the feature, and finally output to obtain the battery life result of the lithium battery to be tested.

[0054] In order to evaluate the performance of the battery health state prediction model and optimize it, in this embodiment, the battery health state prediction model uses mean square error (MSE) as the loss function to intuitively reflect the degree of difference between the predicted value and the actual value. Specifically:

[0055] in, The total number of sample data representing the true value and predicted value; Indicates the real battery health status reflected by the lithium battery charge and discharge cycle data, that is, the sample data, and serves as a label for the lithium battery cycle data to measure the actual status of the battery performance; It represents the predicted battery health status after the fusion feature processing and input into the fully trained battery health status prediction model with a CNN-LSTM composite network structure.

[0056] In this embodiment, during the training of the battery health status prediction model, the adaptive motion estimation algorithm (Adaptive Moment Estimation, Adam) in the gradient descent method with an adaptive learning rate is used for model training, which can effectively handle the optimization problem of large-scale data. In order to fully train the model and achieve a good convergence effect, the training cycle (epoch) is set to 15 to obtain better model performance.

[0057] By using data mining feature fusion strategy and combining innovative CNN and LSTM-based battery health status prediction models, detailed charge and discharge cycle data verification has been carried out in a laboratory environment for the selected A and B batteries. In this embodiment, battery cycle data is selected from the discharge cycle of 750 complete charge and discharge cycles of each battery of the above A and B models as the research data set to ensure the comprehensiveness and representativeness of the data.

[0058] More specifically, when training the model, 80% of the historical discharge cycle data collected from the selected lithium battery is allocated as a training set to train and optimize the battery health status prediction model, while the remaining 20% ​​of the data is used as an independent test set to evaluate the prediction and generalization performance of the battery health status prediction model, thereby verifying the effectiveness of the model in complex battery charge and discharge cycles.

[0059] During verification, mean square error (MSE), root mean square error (RMSE) and mean absolute error (MAE) were selected as evaluation indicators of the model. At the same time, the constructed CNN-LSTM battery health status prediction model was compared and evaluated with the standard LSMT model, where:

[0060]

[0061]

[0062] The battery health status prediction method of the present invention predicts the battery life result of the lithium battery to be tested through a trained battery health status prediction model, wherein the battery health status prediction model locates the inflection point by accurately fitting and calculating the voltage-time decay characteristic relationship, which not only provides key time information for the data, but also can amplify the difference between repeated information before the voltage occurs, which is helpful to complete the subsequent feature derivation and feature fusion process, and secondly, divides the data according to the inflection point information to alleviate the uneven distribution of data, and simultaneously performs feature derivation and feature fusion, amplifies the difference of window data, and mines important information in sparse areas, so that the model can fully learn the data features of sparse areas, effectively improves the prediction accuracy of the model, and more accurately completes the task of battery health status prediction while effectively solving the uneven distribution of data.

[0063] The battery health state prediction device provided by an embodiment of the present invention is described below. The battery health state prediction device described below and the battery health state prediction method described above can be referenced to each other.

[0064] In order to solve the above problems, a battery health status prediction device is provided in this specification, aiming to. Figure 4 is a schematic diagram of the structure of a battery health status prediction device according to an embodiment of the present invention. Figure 4 As shown, the device may include: The data acquisition module 10 is used to acquire the charge and discharge cycle data of the lithium battery to be tested.

[0065] In this embodiment, the charge and discharge cycle data of the lithium battery to be tested may be stored in advance in the electronic device, or may be acquired by the electronic device from the outside. For example, the electronic device acquires the charge and discharge cycle data from an external acquisition device, and the specific acquisition form of the charge and discharge cycle data is not limited, and it is only necessary to ensure that the electronic device can acquire the charge and discharge cycle data.

[0066] The battery prediction module 20 is used to input the charge and discharge cycle data into the trained battery health state prediction model to obtain the battery life result output by the battery health state prediction model.

[0067] Among them, the battery health status prediction model is based on the sample fusion features of the sample lithium battery and the battery health status of each sample charge and discharge cycle, and is trained using a supervised deep learning method. The sample fusion features are the input data used for training, and the battery health status of each sample charge and discharge cycle is the label used for training. The sample fusion features are extracted from the sample charge and discharge cycle data of the sample lithium battery based on the time-voltage decay relationship to identify the inflection point in the charge and discharge cycle process and mine the implicit differential features in the data. The battery health status of each sample charge and discharge cycle is determined based on the ratio of the battery capacity of the sample charge and discharge cycle to the battery capacity of the initial sample charge and discharge cycle.

[0068] The battery health status prediction model uses the battery health status represented by the lithium battery cycle data as a label. This indicator is correlated with the capacity of the battery in the current cycle. By learning from sample data, the battery health status prediction model can predict the battery health status of the current charge and discharge cycle of the lithium battery.

[0069] The battery health status prediction device of the present invention predicts the battery life result of the lithium battery to be tested through a trained battery health status prediction model, wherein the battery health status prediction model locates the inflection point by accurately fitting and calculating the voltage-time decay characteristic relationship, which not only provides key time information for the data, but also can amplify the difference between repeated information before the voltage occurs, which is helpful to complete the subsequent feature derivation and feature fusion process, and secondly, divides the data according to the inflection point information to alleviate the uneven data distribution, and simultaneously performs feature derivation and feature fusion to amplify the difference of window data and mine important information in sparse areas, so that the model can fully learn the data features of sparse areas, effectively improving the prediction accuracy of the model, while effectively solving the uneven data distribution, and more accurately completing the task of battery health status prediction.

[0070] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5 As shown, the electronic device may include: a processor 510 (processor), a communication interface 520 (Communications Interface), a memory 530 (memory) and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic command in the memory 530 to execute the battery health state prediction method, which includes: Obtain the charge and discharge cycle data of the lithium battery to be tested; Inputting the charge and discharge cycle data into a trained battery health state prediction model to obtain a battery life result output by the battery health state prediction model; The battery health status prediction model is based on the sample fusion features of the sample lithium battery and the battery health status of each sample charge and discharge cycle, and is trained using a supervised deep learning method. The sample fusion features are the input data used for training, and the battery health status of each sample charge and discharge cycle is the label used for training; The sample fusion feature is extracted from the sample charge and discharge cycle data of the sample lithium battery based on the time-voltage decay relationship to identify the inflection point in the charge and discharge cycle process and to mine the differential features implicit in the data. The battery health status of each sample charge and discharge cycle is determined based on the ratio of the battery capacity of the sample charge and discharge cycle to the battery capacity of the initial sample charge and discharge cycle.

[0071] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memor), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0072] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, when the program instructions are executed by a computer, the computer can execute the battery health state prediction method provided by the above methods, the method comprising: Obtain the charge and discharge cycle data of the lithium battery to be tested; Inputting the charge and discharge cycle data into a trained battery health state prediction model to obtain a battery life result output by the battery health state prediction model; The battery health status prediction model is based on the sample fusion features of the sample lithium battery and the battery health status of each sample charge and discharge cycle, and is trained using a supervised deep learning method. The sample fusion features are the input data used for training, and the battery health status of each sample charge and discharge cycle is the label used for training; The sample fusion feature is extracted from the sample charge and discharge cycle data of the sample lithium battery based on the time-voltage decay relationship to identify the inflection point in the charge and discharge cycle process and to mine the differential features implicit in the data. The battery health status of each sample charge and discharge cycle is determined based on the ratio of the battery capacity of the sample charge and discharge cycle to the battery capacity of the initial sample charge and discharge cycle.

[0073] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the computer program is implemented to execute the above-mentioned battery health state prediction method, the method comprising: Obtain the charge and discharge cycle data of the lithium battery to be tested; Inputting the charge and discharge cycle data into a trained battery health state prediction model to obtain a battery life result output by the battery health state prediction model; The battery health status prediction model is based on the sample fusion features of the sample lithium battery and the battery health status of each sample charge and discharge cycle, and is trained using a supervised deep learning method. The sample fusion features are the input data used for training, and the battery health status of each sample charge and discharge cycle is the label used for training; The sample fusion feature is extracted from the sample charge and discharge cycle data of the sample lithium battery based on the time-voltage decay relationship to identify the inflection point in the charge and discharge cycle process and to mine the differential features implicit in the data. The battery health status of each sample charge and discharge cycle is determined based on the ratio of the battery capacity of the sample charge and discharge cycle to the battery capacity of the initial sample charge and discharge cycle.

[0074] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0075] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting battery health status, characterized in that: The method comprises: Obtain the charge and discharge cycle data of the lithium battery to be tested; Inputting the charge and discharge cycle data into a trained battery health state prediction model to obtain a battery life result output by the battery health state prediction model; The battery health status prediction model is based on the sample fusion features of the sample lithium battery and the battery health status of each sample charge and discharge cycle, and is trained using a supervised deep learning method. The sample fusion features are the input data used for training, and the battery health status of each sample charge and discharge cycle is the label used for training; The sample fusion feature is extracted from the sample charge and discharge cycle data of the sample lithium battery based on the time-voltage decay relationship to identify the inflection point in the charge and discharge cycle process and to mine the differential features implicit in the data. The battery health status of each sample charge and discharge cycle is determined based on the ratio of the battery capacity of the sample charge and discharge cycle to the battery capacity of the initial sample charge and discharge cycle.

2. The battery health status prediction method according to claim 1, characterized in that: The battery health status prediction model is trained by the following steps: Obtaining sample charge and discharge cycle data of a sample lithium battery, preprocessing the sample charge and discharge cycle data, and filtering out sample features of each sample charge cycle from the sample charge and discharge cycle data; the sample features include: temperature, current, voltage, power, time, and battery capacity; Determine the battery health status of each sample charge and discharge cycle according to the ratio of the battery capacity of each sample charge and discharge cycle to the battery capacity of the initial sample charge and discharge cycle; According to the sample characteristics of each sample charge and discharge cycle, a voltage-time decay characteristic curve of each sample charge and discharge cycle is constructed; Merge sample features of the same voltage value in the voltage-time decay characteristic curve of each sample charge-discharge cycle to obtain voltage grouping features, obtain derived features of the voltage grouping features, perform feature fusion of the voltage grouping features and the derived features, and obtain sample fusion features; The sample fusion features are used as input data for training, and the battery health status of each sample charge and discharge cycle is used as a label. Supervised deep learning is used for training to obtain a battery health status prediction model for predicting the battery life results of lithium batteries.

3. The battery health status prediction method according to claim 2, characterized in that: The method of combining sample features of the same voltage value in the voltage-time decay characteristic curve of each sample charge and discharge cycle to obtain voltage grouping features, obtaining derived features of the voltage grouping features, and performing feature fusion of the voltage grouping features and the derived features to obtain sample fusion features specifically includes: Fitting each voltage-time decay characteristic curve respectively through a preset experience curve, identifying the turning point on the preset experience curve, and obtaining the inflection point and the inflection starting point of each voltage-time decay characteristic curve; Merge the sample features with the same voltage value in the voltage-time decay characteristic curve of each sample charge-discharge cycle to obtain the voltage grouping feature; Determine the difference between each voltage value in the voltage grouping feature and the initial voltage of the voltage-time decay characteristic curve to obtain a voltage difference, and determine the time offset of each voltage value in the voltage grouping feature relative to the inflection point and the starting point of the inflection point of the voltage-time decay characteristic curve to obtain a first time difference and a second time difference; the derived feature includes the voltage difference, the first time difference and the second time difference; The voltage grouping feature and the derived feature are fused to obtain the sample fusion feature.

4. The battery health status prediction method according to claim 1, characterized in that: The battery health status prediction model is a composite neural network model that combines a convolutional neural network and a long short-term memory network; The battery health status prediction model includes a convolutional neural network layer and a long short-term memory network layer. The convolutional neural network layer is used to extract local features of the charge and discharge cycle data, and the long short-term memory network layer is used to capture the dependency of the local features on the time series.

5. The battery health status prediction method according to claim 4, characterized in that: The convolutional neural network layer includes a sequentially connected convolutional layer, a maximum pooling layer, a data flattening layer and a first fully connected layer; The long short-term memory network layer includes a first relationship capture layer, a second relationship capture layer and a third relationship capture layer which are connected in sequence.

6. The battery health status prediction method according to claim 5, characterized in that: The battery health status prediction model also includes an identity mapping layer, a feature fusion layer and a corrected linear layer of a residual network structure; The charge and discharge cycle data are processed by the identity mapping layer, the convolutional neural network layer and the long short-term memory network layer in sequence, and then processed by the feature fusion layer and the corrected linear layer in sequence to obtain the battery life result.

7. The battery health status prediction method according to claim 6, characterized in that: The step of inputting the charge and discharge cycle data into a trained battery health state prediction model to obtain a battery life result output by the battery health state prediction model specifically includes: Inputting the charge-discharge cycle data into the identity mapping layer to obtain an identity mapping feature outputted by the identity mapping layer after identity processing; Inputting the charge-discharge cycle data into the convolutional neural network layer to obtain a first output feature output by the convolutional neural network layer; Inputting the first output feature into a long short-term memory network layer to obtain a third abstract feature output by the long short-term memory network layer; The identity mapping feature and the third abstract feature are input into the feature fusion layer for feature fusion, and the battery life result is obtained after being processed by the corrected linear layer.

8. A battery health status prediction device, characterized in that: The device comprises: A data acquisition module, used to acquire the charge and discharge cycle data of the lithium battery to be tested; A battery prediction module, used to input the charge and discharge cycle data into a trained battery health state prediction model to obtain a battery life result output by the battery health state prediction model; The battery health status prediction model is based on the sample fusion features of the sample lithium battery and the battery health status of each sample charge and discharge cycle, and is trained using a supervised deep learning method. The sample fusion features are the input data used for training, and the battery health status of each sample charge and discharge cycle is the label used for training; The sample fusion feature is extracted from the sample charge and discharge cycle data of the sample lithium battery based on the time-voltage decay relationship to identify the inflection point in the charge and discharge cycle process and to mine the differential features implicit in the data. The battery health status of each sample charge and discharge cycle is determined based on the ratio of the battery capacity of the sample charge and discharge cycle to the battery capacity of the initial sample charge and discharge cycle.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the battery health status prediction method according to any one of claims 1 to 7 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the battery health status prediction method as claimed in any one of claims 1 to 7 are implemented.

Images