Method and system for indirectly predicting battery health status based on expansion stress

Abstract

The embodiment of the present application relates to the technical field of battery performance prediction, and discloses a method for indirectly predicting the health status of a battery based on expansion stress, including: collecting the time series values ​​of expansion stress, current, voltage, operating temperature, SOC, and RUL during several charge and discharge processes of the battery, and indirectly calculating the SOH data of each time series through SOC and RUL; establishing a data set containing the expansion stress, current, voltage, operating temperature, and SOH under different time series; constructing a prediction model based on a sparse hybrid expert model; using the data set to train and verify the prediction model; using the trained prediction model to predict the health status SOH of the battery and output the prediction result. The solution of the present application solves at least the technical problems of traditional prediction methods such as single dimension, lack of dynamic and real-time performance, limited prediction accuracy, and low efficiency.

Description

Technical Field

[0001] The present application relates to the technical field of battery performance prediction, and in particular to a method and system for indirectly predicting the health status of a battery based on expansion stress. Background Art

[0002] A battery's state of health (SOH) is a measure of its performance relative to its new state. SOH describes the percentage of a battery's maximum capacity relative to its original capacity after a period of use and aging. A battery's SOH is a critical parameter for battery management systems (BMS) because it directly impacts battery reliability and safety. With the advancement of battery technology, accurately monitoring and predicting SOH is becoming increasingly important.

[0003] However, traditional battery health prediction methods mainly rely on monitoring the battery's current, voltage, and temperature (U / I / T). Although these methods can reflect the basic status of the battery to a certain extent, they have obvious limitations and cannot comprehensively and accurately assess the battery's health. Traditional methods have the following shortcomings:

[0004] Single Dimension: This method primarily relies on data from the three dimensions of U, I, and T. However, these data do not vary significantly across different stages of the battery lifecycle and only experience significant fluctuations during emergencies. This monitoring method fails to capture subtle changes in the battery's internal structure and electrochemical performance, making it difficult to provide a comprehensive, real-time assessment of battery health.

[0005] Lack of dynamism and real-time performance: Battery aging is a dynamic and complex process involving multiple physical and chemical changes. Traditional methods can only provide static or phased assessment results, making it difficult to track changes in battery health status in real time.

[0006] Limited prediction accuracy: Due to the complexity of the battery's internal structure and chemical reactions, traditional methods often have difficulty establishing accurate degradation mechanism models to predict the battery's remaining life and health status. As a result, the prediction results often have large uncertainties.

[0007] Inefficiency: Traditional machine learning models often use a single model to fit the entire dataset, which is inadequate when faced with complex and highly heterogeneous data. Such models have limited generalization capabilities, are prone to overfitting, and are inefficient when processing large amounts of data.

[0008] In view of the above shortcomings, a more comprehensive and accurate battery health status prediction method is urgently needed. Summary of the Invention

[0009] One purpose of this application is to provide a method and system for indirectly predicting the health status of a battery based on expansion stress, at least to solve the technical problems of traditional prediction methods such as single dimension, lack of dynamics and real-time performance, limited prediction accuracy, and low efficiency.

[0010] To achieve the above objectives, some embodiments of the present application provide the following aspects:

[0011] In a first aspect, an embodiment of the present application provides a method for indirectly predicting battery health status based on expansion stress, comprising:

[0012] Collect the time series values ​​of expansion stress, current, voltage, operating temperature, state of charge (SOC) and remaining service life (RUL) of the battery during several charge and discharge processes, and indirectly calculate the battery health status (SOH) data of each time series through the SOC and RUL data;

[0013] Establishing a data set containing the expansion stress, current, voltage, operating temperature and battery health status SOH in different time series;

[0014] Constructing a prediction model based on a sparse mixture of expert models, wherein the prediction model includes multiple expert sub-models and a gating network model;

[0015] Each of the expert sub-models has a 5-layer structure, where the input layer receives input data, the middle layer has 3 layers with dimensions of 128, 64, and 32, respectively, and the output layer outputs a 16-dimensional vector;

[0016] The gated network model is a three-layer network structure, with an input layer receiving input data, a middle layer being a 32-dimensional vector, and an output layer being a three-dimensional vector, corresponding to the weights of three expert sub-models, with the sum of the three weights being 1. Each expert sub-model is a multi-layer perceptron, and the gated network model is a multi-layer perceptron, with sparse activation implemented using the Gumbel-Softmax algorithm.

[0017] Using the data set to train and verify the prediction model;

[0018] The trained prediction model is used to predict the battery's state of health (SOH) and output a prediction result.

[0019] Furthermore, the indirect calculation of battery health status SOH data of each time series through state of charge SOC and remaining useful life RUL data includes:

[0020] The batteries are grouped by remaining useful life (RUL), and the maximum state of charge (SOC) value is calculated within each group. This maximum value is used as the SOH value for each data record within the corresponding remaining useful life (RUL) cycle. The entire battery health state (SOH) sequence is then filtered and padded for outliers to obtain normal battery health state (SOH) sequence data.

[0021] Furthermore, the number of the expert sub-models is N, and the outputs of the N expert sub-models are output_1, output_2, ..., output_N, and these N outputs are all high-dimensional vectors;

[0022] The output of the gating network model is an N-dimensional vector, which corresponds to the weights of the N expert sub-models, and the sum of the N weights is 1.

[0023] Furthermore, the N-dimensional vector output by the gating network model is used as the input of the Gumbel-Softmax algorithm. The Gumbel-Softmax algorithm re-outputs an N-dimensional vector as the weight of the expert sub-model by adding Gumbel noise and Softmax mapping, thereby achieving sparse activation of the expert sub-model;

[0024] Performing a weighted summation on the expert sub-model weight and the output of the corresponding expert sub-model to obtain a comprehensive feature representation;

[0025] Connecting the comprehensive features to a fully connected layer;

[0026] Through the linear regression layer, the battery's state of health (SOH) is output.

[0027] Furthermore, N is 3.

[0028] Furthermore, the steps of the Gumbel-Softmax algorithm are as follows:

[0029] (1) Initial logits

[0030] Assume a logits vector z containing M elements, which represents the pre-activation score for each expert, corresponding to the weight vector of the expert sub-model output by the gating network model;

[0031] (2) Add Gumbel noise

[0032] Add a noise g sampled from a Gumbel(0, 1) distribution to each logit:

[0033] z′=z+g

[0034] Among them, z′ is the logits vector with Gumbel noise added, , u is a vector sampled from the uniform distribution U(0,1);

[0035] (3) Softmax mapping

[0036] Applying the Softmax function to the logits z′ with Gumbel noise added gives a probability distribution π:

[0037]

[0038] in, represents the i-th element in the probability distribution π, that is, the probability of the i-th category; Represents the i-th element of the logits vector after adding Gumbel noise; is the temperature parameter, which controls the sharpness of the softmax distribution; when When it approaches 0, the distribution becomes very sharp, close to the one-hot vector. As it approaches infinity, the distribution approaches a uniform distribution.

[0039] In a second aspect, an embodiment of the present application further provides a system for indirectly predicting battery health status based on expansion stress, comprising:

[0040] The acquisition unit is used to collect the time series values ​​of expansion stress, current, voltage, operating temperature, state of charge (SOC) and remaining service life (RUL) of the battery during several charge and discharge processes, and indirectly calculate the battery health status (SOH) data of each time series through the state of charge (SOC) and remaining service life (RUL) data;

[0041] An establishing unit, configured to establish a data set including the expansion stress, current, voltage, operating temperature, and battery health status SOH in different time series;

[0042] A construction unit, configured to construct a prediction model based on a sparse mixture of expert models, wherein the prediction model includes a plurality of expert sub-models and a gating network model;

[0043] A training unit, configured to train and verify the prediction model using the data set;

[0044] The prediction unit is used to predict the health state SOH of the battery using the trained prediction model and output the prediction result.

[0045] Compared with the existing technology, this application achieves the following beneficial effects:

[0046] The present invention supplements the traditional current, voltage and temperature characteristics based on the expansion stress characteristics.

[0047] The present invention proposes a battery health status prediction method based on multi-dimensional monitoring. By introducing a new health factor, expansion stress, together with voltage, current, and temperature, a four-dimensional health assessment system is constructed. By real-time monitoring of the expansion stress changes during battery operation and combining the battery management system to realize signal processing and analysis, a comprehensive and real-time assessment of the battery health status is achieved, thereby improving the accuracy of SOH prediction. This innovative method not only makes up for the shortcomings of the traditional three-dimensional assessment system, but also improves the accuracy and long-term stability of battery health status prediction, providing a more reliable basis for battery maintenance and replacement. When indirectly predicting battery SOH through a sparse hybrid expert model, the model's expressive power and prediction accuracy can be improved, the robustness and generalization ability of the overall model are improved, the risk of overfitting is reduced, the computational cost is greatly reduced, and the model's operational efficiency is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] One or more embodiments are exemplarily illustrated by pictures in the corresponding drawings. These exemplifications do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings are represented as similar elements. Unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0049] Figure 1 A flow chart of a method for indirectly predicting battery health status based on expansion stress provided in the first embodiment of the present application;

[0050] Figure 2 A diagram showing the structure of a prediction model provided in the first embodiment of the present application;

[0051] Figure 3 This is a structural diagram of the expert sub-model in the prediction model provided in the first embodiment of the present application;

[0052] Figure 4 This is a structural diagram of a gated network model in the prediction model provided in the first embodiment of the present application;

[0053] Figure 5 This is a trend chart of the preliminary calculation results of SOH in the first stage of the method provided in the first embodiment of the present application;

[0054] Figure 6 This is a trend chart of the SOH correction calculation results in the first stage of the method provided in the first embodiment of the present application;

[0055] Figure 7 This is a sample diagram of the battery SOH indirect prediction results in the second stage of the method provided in the first embodiment of the present application;

[0056] Figure 8 A module diagram of a system unit for indirectly predicting battery health status based on expansion stress, provided in the second embodiment of the present application;

[0057] Figure 9 This is a schematic diagram of an exemplary structure of an electronic device provided in the third embodiment of the present application. DETAILED DESCRIPTION

[0058] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0059] In some scenarios, the BMS only collects data such as the battery's State of Charge (SOC) and Remaining Useful Life (RUL), but does not have direct SOH data. In this case, it is necessary to indirectly calculate the SOH through certain methods and build a prediction model to predict the SOH. This invention calls this the indirect SOH prediction method.

[0060] During battery operation, the following data can be measured:

[0061] 1. Expansion stress: The internal pressure generated by the chemical reaction during the battery charging and discharging process.

[0062] 2. Current: The current during the battery charging and discharging process, which can be charging or discharging.

[0063] 3. Voltage: The voltage across the battery.

[0064] 4. Temperature: The operating temperature of the battery.

[0065] Expansion stress, current, voltage and temperature are key factors affecting battery performance, which are closely related to the internal chemical reactions and physical state of the battery.

[0066] Expansion stress, current, voltage and temperature can be used to predict battery SOH, mainly reflected in the following points:

[0067] 1. Expansion stress:

[0068] Batteries expand and contract during charge and discharge. This accumulated mechanical stress can cause structural damage, such as electrode delamination and separator rupture. Excessive expansion stress can lead to internal micro-short circuits or capacity loss, thereby reducing the battery's SOH. By monitoring the extent of battery expansion, we can indirectly assess the accumulation of internal stress and predict the battery's health status.

[0069] 2. Current:

[0070] The magnitude and duration of current flow affect the cycle life of a battery. High-current discharges generate more heat and stress within the battery. Prolonged, high-current discharges accelerate battery aging, reducing its effective capacity and, consequently, lowering its SOH. By analyzing the current waveform and statistical characteristics, we can assess the battery's charge and discharge behavior and predict its health.

[0071] 3. Voltage:

[0072] Battery voltage changes reflect the state of the battery's internal chemical reactions. As a battery ages, its full charge and full discharge voltages decrease. This voltage drop may indicate an increase in the battery's internal impedance, a sign of battery aging. By monitoring the battery's voltage curve and voltage stability, the battery's state of health (SOH) can be inferred.

[0073] 4. Temperature:

[0074] Battery temperature significantly impacts its performance and lifespan. Both high and low temperatures accelerate battery aging. Temperature fluctuations affect the rate of chemical reactions within the battery, which in turn affects its capacity and power output. By monitoring battery temperature fluctuations, we can assess the battery's thermal management and predict its health status.

[0075] These parameters can be used to predict SOH because they are closely related to the chemical and physical processes within the battery, which determine its performance and lifespan. By comprehensively analyzing these parameters, predictive models for battery health can be developed. These models are typically based on machine learning algorithms and can be trained using historical data to predict future battery performance. Predicting SOH helps identify potential battery degradation issues in advance, allowing appropriate maintenance measures to be taken and extending the battery's service life.

[0076] The Sparse Mixture of Experts (SMoE) model is a machine learning architecture designed for complex prediction and classification problems. The model's core lies in the use of multiple "expert" sub-models, each specialized for processing a specific portion of the dataset or a specific type of input. The predictions of these sub-models are weighted and aggregated through a gating network to produce the final prediction. The "sparse" nature of SMoE lies in the fact that, for each prediction, not all expert sub-models are activated; only a subset are selected for participation. This selective activation mechanism significantly reduces computational costs and improves the model's operational efficiency. Sparse strategies can be implemented using algorithms such as the Gumbel algorithm, which selects a few experts from multiple sub-models for activation while keeping the majority inactive.

[0077] This paper proposes a method and system for indirectly predicting the battery state of health (SOH) based on expansion stress and a sparse hybrid expert model. By introducing expansion stress as a new health factor, a four-dimensional health assessment system is constructed together with voltage, current, and temperature. This method monitors the changes in expansion stress during battery operation in real time and combines it with a battery management system to process and analyze signals, thereby achieving a comprehensive, real-time assessment of the battery's state of health. This innovative method not only overcomes the shortcomings of traditional three-dimensional assessment systems, but also improves the accuracy and long-term stability of battery state of health predictions, providing a more reliable basis for battery maintenance and replacement.

[0078] First embodiment

[0079] Figure 1 A flow chart of a method for indirectly predicting battery health status based on expansion stress provided in the first embodiment of the present application is as follows: Figure 1 As shown, a method 100 for indirectly predicting battery health status based on expansion stress includes:

[0080] S110: collecting time series values ​​of expansion stress, current, voltage, operating temperature, state of charge (SOC), and remaining useful life (RUL) of the battery during several charge and discharge processes, and indirectly calculating battery state of health (SOH) data of each time series based on the SOC and RUL data;

[0081] Expansion stress is a novel and unique indicator of the battery's internal state of health, reflecting changes in internal pressure caused by chemical reactions during the charge and discharge process. Utilizing this characteristic can provide a new perspective on the battery's state of health, which can help more accurately predict SOH. Expansion stress can complement traditional current, voltage, and temperature characteristics to provide more comprehensive battery health information, thereby improving the accuracy of SOH prediction.

[0082] In step S110 , collecting the battery's expansion stress, current, voltage, temperature, SOC, and RUL data requires the use of specific sensors and measuring equipment. The following are some basic steps and methods:

[0083] 1. Expansion stress collection

[0084] Pressure sensors: During battery design, miniature pressure sensors can be installed inside or outside the battery to measure expansion stress. These sensors can directly measure the internal pressure changes caused by chemical reactions during the battery's charge and discharge processes.

[0085] Data logger: Connect the pressure sensor signal to the data logger to record real-time data.

[0086] 2. Current acquisition

[0087] Current sensor: Use a current sensor such as a Hall effect sensor or a shunt resistor to measure the current flowing through the battery.

[0088] Data acquisition system: Connect the current sensor to a data acquisition system (such as a data acquisition card or battery management system) to record the current data.

[0089] 3. Voltage acquisition

[0090] Voltmeter: Use a high-precision voltmeter or the voltage measurement circuit built into the battery management system to measure the terminal voltage of the battery.

[0091] Data acquisition system: Similar to the current sensor, voltage data can also be recorded through the data acquisition system.

[0092] 4. Temperature collection

[0093] Temperature sensor: You can use a thermocouple, thermistor (NTC or PTC), or infrared sensor to measure the temperature of the battery.

[0094] Data acquisition system: Connect the temperature sensor to the data acquisition system to monitor and record temperature changes in real time.

[0095] 5. SOC and RUL data collection

[0096] Battery Management System (BMS): SOC and RUL are usually calculated by the battery management system, which combines current, voltage and other sensor data to estimate SOC and RUL.

[0097] The specific collection steps are as follows:

[0098] (1) Design sensor layout: Ensure that the sensors are placed in a location that can accurately reflect the battery status.

[0099] (2) Install the sensor: Install the sensor on the battery or battery management system.

[0100] (3) Calibrate the sensor: Calibrate the sensor to ensure that its readings are accurate and reliable.

[0101] (4) Connect the data acquisition system: Connect all sensors to the data acquisition system.

[0102] (5) Data synchronization: Ensure that all sensor data are synchronized during collection to enable accurate correlation analysis.

[0103] (6) Data recording: Real-time data recording during the battery charging and discharging process.

[0104] (7) Data processing: Preprocess the collected data, such as filtering and normalization, for subsequent analysis.

[0105] Through the above steps, relevant data of the battery under normal working conditions can be effectively collected.

[0106] The model of the present invention is divided into two stages, wherein step S110 relates to the first stage (stage 1) of the model, namely indirectly calculating the battery state of health SOH through the state of charge SOC and the remaining service life data RUL.

[0107] Specifically, the indirect SOH calculation method is: during a complete charge and discharge cycle, the SOC and RUL data are also complete. Within a cycle, the maximum SOC value is the SOH value corresponding to that cycle. Therefore, the calculation process groups the data by RUL, calculates the maximum SOC value within each group, and uses this maximum value as the SOH value for each data record within the corresponding RUL cycle. The entire SOH sequence is then filtered out of outliers and padded with data to obtain a normal SOH sequence data.

[0108] The steps of SOH outlier removal and data filling in the present invention are as follows:

[0109] (1) Identify outliers: Use a sliding window to identify points that are significantly different from the surrounding values. The window size of the sliding window is 10,000. The sliding mean and standard deviation are calculated within each window. Outliers are those values ​​that differ from the sliding mean by more than 2 times the sliding standard deviation;

[0110] (2) Eliminate outliers: set the identified outliers to NaN;

[0111] (3) Interpolation supplement: Use linear interpolation to fill in the data of outliers.

[0112] S120: Establishing a data set including the expansion stress, current, voltage, operating temperature, and battery health status SOH in different time series;

[0113] In step S120, based on the data obtained in step S110, a dataset containing the expansion stress, current, voltage, operating temperature, and battery state of health (SOH) at different time series is established. This dataset is used as training data and is divided into a training set and a test set in a ratio of 8:2.

[0114] S130: Build a prediction model based on a sparse mixture of experts (SMoE) model, where the prediction model includes multiple expert sub-models and a gating network model;

[0115] Figure 2 This is a diagram of the prediction model structure provided in the embodiment of this application. Figure 2 As shown, the Sparse Mixture of Experts model is a machine learning architecture designed for complex prediction and classification problems. SMoE allows different experts to learn specific aspects of the data. For example, some experts may focus on current changes, while others may focus on expansion stress patterns. This multi-expert model can improve prediction accuracy. Through a sparse selection mechanism, only a portion of the expert network is activated, significantly reducing computational effort and improving model training and prediction efficiency.

[0116] The SMoE model includes a multi-expert model and a gating network model.

[0117] Each expert sub-model is a multi-layer perceptron (MLP) model, and each expert sub-model has a multi-layer structure. If there are N expert sub-models, the outputs of these N expert sub-models are output 1 (output_1), output 2 (output_2), ..., output N (output_N), and these N outputs are all high-dimensional vectors.

[0118] The gated network model adopts a multi-layer perceptron (MLP) model. The output of the gated network model is an N-dimensional vector, which corresponds to the weights of N expert sub-models, and the sum of the N weights is 1.

[0119] The output of the gating network is further weighted using the Gumbel-Softmax algorithm to achieve sparse activation of the expert sub-model. That is, sparse activation is achieved using the Gumbel-Softmax algorithm.

[0120] The Gumbel-Softmax algorithm is a technique for implementing differentiable sampling in neural networks, allowing us to use gradient descent to optimize discretely selected parameters during training. The Gumbel-Softmax algorithm combines the Gumbel distribution and the Softmax function, making the previously non-differentiable discrete sampling process differentiable. The Gumbel distribution is a continuous distribution used for sampling indices or rankings, while the Softmax function is used to convert real-valued vectors into probability distributions.

[0121] Specifically, the steps of the Gumbel-Softmax algorithm are as follows:

[0122] (1) Initial logits

[0123] Assume a logits vector z containing M elements, which represents the pre-activation score for each expert, corresponding to the weight vector of the expert sub-model output by the gating network model;

[0124] (2) Add Gumbel noise

[0125] Add a noise g sampled from a Gumbel(0, 1) distribution to each logit:

[0126] z′=z+g

[0127] Among them, z′ is the logits vector with Gumbel noise added, , u is a vector sampled from the uniform distribution U(0,1);

[0128] (3) Softmax mapping

[0129] Applying the Softmax function to the logits z′ with Gumbel noise added gives a probability distribution π:

[0130]

[0131] in, represents the i-th element in the probability distribution π, that is, the probability of the i-th category; Represents the i-th element of the logits vector after adding Gumbel noise; is the temperature parameter, which controls the sharpness of the softmax distribution; when When it approaches 0, the distribution becomes very sharp, close to the one-hot vector. As it approaches infinity, the distribution approaches a uniform distribution.

[0132] Furthermore, the weighted summation process includes:

[0133] The N-dimensional vector output by the gating network model is used as the input of the Gumbel-Softmax algorithm. The Gumbel-Softmax algorithm re-outputs an N-dimensional vector as the weight of the expert sub-model by adding Gumbel noise and Softmax mapping, thereby achieving sparse activation of the expert sub-model;

[0134] Performing a weighted summation on the expert sub-model weight and the output of the corresponding expert sub-model to obtain a comprehensive feature representation;

[0135] Connecting the comprehensive features to a fully connected layer;

[0136] Through the linear regression layer, the battery's state of health (SOH) is output.

[0137] Preferably, in some embodiments, N is 3, such as Figure 3As shown in , the expert sub-models are all 5-layer structures. The input layer receives input data, the middle layer has 3 layers, and the dimensions are 128, 64, and 32 respectively. The output layer outputs a 16-dimensional vector. Figure 4 As shown in the figure, the gated network model is a three-layer network structure. The input layer receives input data, the middle layer is a 32-dimensional vector, the activation function is the ReLU function, and the output layer is a 3-dimensional vector. The activation function is softmax, corresponding to the weights of the three expert sub-models, and the sum of the three weights is 1.

[0138] The input data are fed into three expert sub-models respectively to extract corresponding features from different perspectives.

[0139] The outputs of the three expert sub-models are output 1 (output1), output 2 (output2) and output 3 (output3). These three outputs are all high-dimensional vectors. This invention takes 32 dimensions as an example to represent the feature representation of each sub-expert model for the input data; the output of the gating network is a 3-dimensional vector, which corresponds to the weights of the three expert sub-models, and the sum of the three weights is 1.

[0140] The output 3D vector of the gated network model is used as the input of the Gumbel-Softmax algorithm. The Gumbel-Softmax algorithm re-outputs a 3D vector by adding Gumbel noise and Softmax mapping, which serves as the weight of the expert sub-model. The weight of the expert sub-model is then weighted and summed with the output of the corresponding expert sub-model to obtain a comprehensive feature representation. The comprehensive feature is then connected to a fully connected layer. Finally, the SOH is output through a linear regression layer.

[0141] S140: Using the data set to train and verify the prediction model;

[0142] In step S140 , the input data of the model are Current, Voltage, Expansion, and Temperature, which respectively represent the current, voltage, expansion stress, and temperature of the battery; the output data of the model is SOH, which represents the state of health of the battery.

[0143] 1. Prediction data display

[0144] This paper tested its effectiveness on a public dataset available at https: / / deepblue.lib.umich.edu / data / concern / file_sets / gq67jr501. The current, voltage, expansion stress, and temperature in the cycling_wExpansion.csv file in the folder numbered 01 were used to indirectly predict the battery's state of health (SOH). Table 1 shows a sample (partial) dataset of battery characteristics such as expansion stress, state of charge (SOC), and limit (RUL). Current represents current, Voltage represents voltage, Expansion represents expansion stress, Temperature represents temperature, Capacity represents battery capacity (SOC), and Cycle number represents the number of remaining cycles (RUL).

[0145] Table 1. Battery expansion stress and other characteristics, SOC, and RUL data set examples (partial)

[0146]

[0147] 2. Display of SOH calculation results

[0148] Group by Cycle number, calculate the maximum value of the SOC sequence in each group, and use it as the SOH value corresponding to each data in the group. The SOH sequence calculation results are as follows: Figure 5 As shown. Figure 5 From the SOH trend graph, we can see that the overall trend of SOH is steadily decreasing, which is in line with the law of SOH change. However, there are a few outliers, namely the two places where the figure suddenly drops, which require outlier processing and data filling. After SOH outlier removal and data filling, the calculation result of SOH is as follows: Figure 6 shown.

[0149] A sample (partial) of specific SOH calculation results is shown in Table 2. Table 2 contains the current, voltage, expansion stress, and temperature data in Table 1 as well as the SOH calculation results.

[0150] Table 2. Battery expansion stress and other characteristics and SOH data set examples (partial)

[0151]

[0152] The present invention implements the prediction model code and trains it on the Keras platform, with epochs = 1000 and batch size = 1024. The optimizer for model training is the Adam algorithm, and the loss function is mean square error (MSE).

[0153] The training set and test set in Table 2 are used to train and verify the model respectively.

[0154] S150: Predicting the battery's state of health (SOH) using the trained prediction model and outputting a prediction result.

[0155] After the prediction model training is completed in step S140, if the model effect is good, the model can be deployed and used to predict the SOH of the battery.

[0156] In step S150, the prediction model is fed with the following input data: Current, Voltage, Expansion, and Temperature, representing the battery's current, voltage, expansion stress, and temperature, respectively. The prediction model's target is the battery's state of health (SOH). The model's loss function is the mean square error (MSE); the optimizer is adam; and the evaluation metric is the mean absolute error (MAE), which is the sum of the absolute values ​​of the differences between the target and predicted values.

[0157] 3.SOH prediction results display

[0158] The mean of the test set of SOH is 4.2739 and the standard deviation is 0.38516, while the mean of the prediction set is 4.2759 and the standard deviation is 0.38521, which shows that the data distribution of the prediction results is basically consistent with the data distribution of the real data.

[0159] The root mean square error between the predicted and tested battery SOH values ​​is only 0.01236, indicating that the model performs well. The prediction results are shown in Table 3 below.

[0160] Table 3. Example of indirect prediction results of battery SOH

[0161]

[0162] The prediction results are as follows Figure 7 shown. Figure 7 The solid line in the upper middle represents the true value, the dotted line represents the predicted value, and the solid square represents the error value. The numbers represent the true values. Figure 7 It can be seen that the prediction effect is good.

[0163] According to the above embodiment of the present invention, the method introduces a new health factor, expansion stress, to construct a four-dimensional health assessment system together with voltage, current and temperature. By real-time monitoring of the changes in expansion stress during battery operation and combining the battery management system to realize signal processing and analysis, a comprehensive and real-time assessment of the battery health status is achieved, which not only makes up for the shortcomings of the traditional three-dimensional assessment system, but also improves the accuracy and long-term stability of battery health status prediction, and provides a more reliable basis for battery maintenance and replacement. The SOH is indirectly calculated through data such as SOC and RUL, and the SOH is predicted, making the monitoring indicators of the BMS system more complete. When indirectly predicting the battery SOH, the SMoE model can improve the expression ability and prediction accuracy of the model, improve the robustness and generalization ability of the overall model, and reduce the risk of overfitting.

[0164] The steps of the above method are divided only for the purpose of clear description. During implementation, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this application; adding insignificant modifications or introducing insignificant designs to the algorithm or process without changing the core design of the algorithm and process are all within the scope of protection of this application.

[0165] Second embodiment

[0166] Figure 8 A system unit module diagram for indirectly predicting battery health status based on expansion stress is provided in the second embodiment of the present application, such as Figure 8 As shown, a system 200 for indirectly predicting battery health status based on expansion stress includes:

[0167] The acquisition unit 210 is used to collect the time series values ​​of expansion stress, current, voltage, operating temperature, state of charge (SOC), and remaining useful life (RUL) of the battery during several charge and discharge processes, and indirectly calculate the battery health status (SOH) data of each time series based on the state of charge (SOC) and remaining useful life (RUL) data;

[0168] An establishing unit 220 is configured to establish a data set including the expansion stress, current, voltage, operating temperature, and battery health status SOH in different time series;

[0169] A construction unit 230 is configured to construct a prediction model based on a sparse hybrid expert model, wherein the prediction model includes a plurality of expert sub-models and a gating network model;

[0170] A training unit 240 is configured to train and verify the prediction model using the data set;

[0171] The prediction unit 250 is configured to predict the battery state of health (SOH) using the trained prediction model and output a prediction result.

[0172] It is not difficult to find that this embodiment is a system embodiment corresponding to the first embodiment, and this embodiment can be implemented in conjunction with the first embodiment. The relevant technical details mentioned in the first embodiment are still valid in this embodiment, and to reduce repetition, they are not repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied to the first embodiment.

[0173] It is worth mentioning that all modules involved in this embodiment are logical modules. In actual applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, to highlight the innovation of this application, this embodiment does not include units that are not closely related to solving the technical problems proposed by this application. However, this does not mean that other units do not exist in this embodiment.

[0174] Third embodiment

[0175] In addition, some embodiments of the present application further provide an electronic device. The electronic device may be various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, etc. The electronic device may also be various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices.

[0176] The electronic device includes: one or more processors; and a memory storing computer program instructions, wherein the computer program instructions, when executed, enable the processor to perform the steps of the method provided in any one or more of the above embodiments. Figure 9 An exemplary structural diagram of the electronic device is disclosed. Figure 9As shown, the electronic device includes: one or more processors 1101, memory 1102, and interfaces for connecting various components, including high-speed and low-speed interfaces. The various components are interconnected using different buses and can be mounted on a common motherboard or in other ways as needed. The processor can process instructions executed within the electronic device, including instructions stored in or on the memory for displaying graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some other embodiments, if desired, multiple processors and / or multiple buses can be used with multiple memories and multiple storage devices. Similarly, multiple electronic devices can be connected, with each device providing some of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or claimed herein.

[0177] The electronic device may further include: an input device 1103 and an output device 1104. The processor 1101, the memory 1102, the input device 1103 and the output device 1104 may be connected via a bus or other means. Figure 9 The bus connection is taken as an example.

[0178] Input device 1103 can receive input digital or character information and generate key signal input related to user settings and function control of the electronic device. Examples include a touch screen, keypad, mouse, trackpad, touchpad, pointing stick, one or more mouse buttons, trackball, joystick, and other input devices. Output device 1104 may include a display device, auxiliary lighting devices (e.g., LEDs), and tactile feedback devices (e.g., vibration motors). The display device may include, but is not limited to, a liquid crystal display (LCD), a light-emitting diode (LED) display, and a plasma display. In some embodiments, the display device may be a touch screen.

[0179] To provide user interaction, the electronic device may be a computer. The computer includes a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user, as well as a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices may also be used to provide user interaction; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback), and input from the user may be received in any form, including acoustic input, voice input, or tactile input.

[0180] In the embodiments of the present application, a computer program / instruction is stored on a computer-readable medium. When executed by a processor, the computer program / instruction implements the steps of the method provided in any one or more of the above embodiments. The computer-readable medium may be included in the electronic device described in the above embodiments, or it may exist independently and not be incorporated into the device. The computer-readable medium carries one or more computer-readable instructions.

[0181] The memory 1102 can be used as a non-transitory computer-readable storage medium to store non-transitory software programs, non-transitory computer executable programs, and modules. The processor 1101 executes the non-transitory software programs, instructions, and modules stored in the memory 1102 to execute various functional applications and data processing of the server, thereby implementing the program instructions / modules corresponding to the method provided in any one or more of the above embodiments of the present application.

[0182] The memory 1102 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and applications required for at least one function; the data storage area may store data created based on the use of the electronic device, etc. In addition, the memory 1102 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 1102 may optionally include a memory remotely located relative to the processor 1101, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0183] It should be noted that the computer-readable medium described in this application may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. Computer-readable media may include, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this application, a computer-readable medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or component.

[0184] Computer-readable media includes both permanent and non-permanent, removable and non-removable media, and can be implemented using any method or technology for information storage. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc-read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0185] Computer program code for performing the operations of the present application can 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 can be executed entirely on the user's computer, partially on the user's computer, as a stand-alone 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 can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0186] In the above embodiments, all or part of the embodiments may be implemented using software, hardware, firmware, or any combination thereof. For example, implementation may be achieved using an application-specific integrated circuit (ASIC), a general-purpose computer, or any other similar hardware device. In some embodiments, the software program of the present application may be executed by a processor to implement the above steps or functions. Similarly, the software program of the present application (including related data structures) may be stored in a computer-readable recording medium, such as a RAM memory, a magnetic or optical drive, a floppy disk, or the like. In addition, some steps or functions of the present application may be implemented using hardware, for example, as a circuit that cooperates with a processor to perform the various steps or functions.

[0187] The computer program product provided in the embodiments of the present application includes one or more computer programs / instructions, which, when executed by a processor, generate, in whole or in part, the processes or functions described in the embodiments of the present application. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state disk (SSD)).

[0188] The flowcharts or block diagrams in the accompanying drawings illustrate the possible architectures, functions and operations of the devices, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment or part of code, and the module, program segment or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two 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 box in the block diagram and / or flowchart, as well as the combination of boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-specific system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0189] The scope of this application is defined by the appended claims rather than the foregoing description and is therefore intended to encompass within this application all changes that come within the meaning and range of equivalents of the claims. Any reference signs in the claims should not be construed as limiting the claims to which they relate. In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in a device claim may also be implemented by one unit or device through software or hardware. Words such as "first" and "second" are only used to distinguish the description and do not indicate any particular order, nor should they be understood as indicating or implying relative importance.

[0190] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art may easily propose variations or substitutions within the technical scope disclosed in the present application, and such variations or substitutions shall be encompassed within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the scope of protection of the claims, and the above embodiments shall be regarded as exemplary and non-limiting.

Claims

1. A method for indirectly predicting battery health status based on expansion stress, characterized in that: include: Collect the time series values ​​of expansion stress, current, voltage, operating temperature, state of charge (SOC) and remaining service life (RUL) of the battery during several charge and discharge processes, and indirectly calculate the battery health status (SOH) data of each time series through the SOC and RUL data; The indirect calculation of the battery state of health (SOH) data of each time series through the state of charge (SOC) and remaining useful life (RUL) data includes: Group the batteries by remaining useful life (RUL), calculate the maximum state of charge (SOC) value within each group, and use this maximum value as the SOH value for each data record within the corresponding RUL cycle. Remove and fill abnormal values ​​from the entire SOH sequence to obtain normal SOH sequence data. Establishing a data set containing the expansion stress, current, voltage, operating temperature and battery health status SOH in different time series; Constructing a prediction model based on a sparse mixture of expert models, wherein the prediction model includes multiple expert sub-models and a gating network model; Each of the expert sub-models has a 5-layer structure, where the input layer receives input data, the middle layer has 3 layers with dimensions of 128, 64, and 32, respectively, and the output layer outputs a 16-dimensional vector; The gating network model is a three-layer network structure. The input layer receives input data, the middle layer is a 32-dimensional vector, and the output layer is a 3-dimensional vector, which corresponds to the weights of the three expert sub-models, and the sum of the three weights is 1. The gating network outputs a 3-dimensional weight vector and is sparsely activated through Gumbel-Softmax. Each expert sub-model is a multi-layer perceptron, the gated network model is a multi-layer perceptron, and sparse activation is implemented using the Gumbel-Softmax algorithm; Using the data set to train and verify the prediction model; The trained prediction model is used to predict the battery's state of health (SOH) and output a prediction result.

2. The method according to claim 1, characterized in that in, The number of the expert sub-models is N, and the outputs of the N expert sub-models are output_1, output_2, ..., output_N, and these N outputs are all high-dimensional vectors; The output of the gating network model is an N-dimensional vector, which corresponds to the weights of the N expert sub-models, and the sum of the N weights is 1.

3. The method according to claim 2, characterized in that in, The N-dimensional vector output by the gating network model is used as the input of the Gumbel-Softmax algorithm. The Gumbel-Softmax algorithm re-outputs an N-dimensional vector as the weight of the expert sub-model by adding Gumbel noise and Softmax mapping, thereby achieving sparse activation of the expert sub-model; Performing a weighted summation on the expert sub-model weight and the output of the corresponding expert sub-model to obtain a comprehensive feature representation; Connecting the comprehensive features to a fully connected layer; Through the linear regression layer, the battery's state of health (SOH) is output.

4. The method according to claim 3, characterized in that in, N is 3.

5. The method according to claim 3, characterized in that in, The steps of the Gumbel-Softmax algorithm are as follows: (1) Initial logits Assume a logits vector z containing M elements, which represents the pre-activation score for each expert, corresponding to the weight vector of the expert sub-model output by the gating network model; (2) Add Gumbel noise Add a noise g sampled from a Gumbel(0, 1) distribution to each logit: z′=z+g Among them, z′ is the logits vector with Gumbel noise added, , u is a vector sampled from the uniform distribution U(0,1); (3) Softmax mapping Applying the Softmax function to the logits z′ with Gumbel noise added gives a probability distribution π: ； in, represents the i-th element in the probability distribution π, that is, the probability of the i-th category; Represents the i-th element of the logits vector after adding Gumbel noise; is the temperature parameter, which controls the sharpness of the softmax distribution; when When it approaches 0, the distribution becomes very sharp, close to the one-hot vector. As it approaches infinity, the distribution approaches a uniform distribution.

6. A system for indirectly predicting the state of health of a battery based on expansion stress, for implementing the method for indirectly predicting the state of health of a battery based on expansion stress according to any one of claims 1 to 5, characterized in that: include: The acquisition unit is used to collect the time series values ​​of expansion stress, current, voltage, operating temperature, state of charge (SOC) and remaining service life (RUL) of the battery during several charge and discharge processes, and indirectly calculate the battery health status (SOH) data of each time series through the state of charge (SOC) and remaining service life (RUL) data; An establishing unit, configured to establish a data set including the expansion stress, current, voltage, operating temperature, and battery health status SOH in different time series; A construction unit, configured to construct a prediction model based on a sparse mixture of expert models, wherein the prediction model includes a plurality of expert sub-models and a gating network model; A training unit, configured to train and verify the prediction model using the data set; The prediction unit is used to predict the health state SOH of the battery using the trained prediction model and output the prediction result.

Images