A lithium-ion battery SOC estimation method based on battery capacity

Abstract

The present invention provides a method for estimating the SOC of a lithium-ion battery based on battery capacity, which belongs to the technical field of lithium-ion batteries. The method solves the technical problem that the SOC of the current battery capacity is difficult to estimate. The technical solution is as follows: comprising the following steps: step 1) measuring the terminal voltage, current, temperature of the lithium-ion battery with SOC ranging from 1 to 0, as well as the voltage and current of the load; step 2) pre-processing the measured data, constructing a 2DCNN training data set and a test data set for estimating the battery capacity, and then constructing a new data set; step 3) realizing the final real-time estimation of the SOC. The beneficial effects of the present invention are as follows: the present invention obtains various battery parameters through battery charge and discharge experiments at different temperatures, and after estimating the battery capacity, it can finally be used for real-time estimation of the SOC of the lithium battery.

Description

Technical Field

[0001] The present invention relates to the technical field of lithium-ion batteries, and in particular to a method for estimating the state of charge (SOC) of a lithium-ion battery based on battery capacity. Background Art

[0002] Electric vehicles have become a key trend in the automotive industry, and lithium batteries, with their numerous advantages, have become a key energy storage material for electric vehicles. In automotive battery management systems, accurate state-of-charge (SOC) estimation is crucial for providing feedback to the driver on remaining battery capacity and enabling more efficient management and control of the vehicle battery.

[0003] Currently, there are three categories of SOC estimation techniques. The first is the ampere-hour integration method. This method is difficult to apply in practice, but it can be used to define SOC values ​​and achieve high accuracy. The second category is model-based methods, mainly including electrochemical models and equivalent circuit methods. Electrochemical models have clear physical meanings and can reflect various electrochemical phenomena in batteries. However, due to their complex structure and excessive number of parameters, they are not very advantageous in practical applications. Equivalent circuit model-based methods, which include both online and offline methods, can estimate SOC after identifying parameters and combining filtering algorithms. Although they can achieve high accuracy through algorithmic improvements, they struggle to account for changes in temperature and aging over time. The third category is data-driven methods, mainly including support vector machines and neural networks. Because data-driven models do not require specific models, they can comprehensively consider multiple factors and achieve high accuracy. Battery capacity, a key indicator of aging, is difficult to measure directly. Therefore, in the application of data-driven methods, SOC estimation that takes battery capacity into account is a technical challenge.

[0004] How to solve the above technical problems is the subject faced by the present invention. Summary of the Invention

[0005] The purpose of the present invention is to provide a lithium-ion battery SOC estimation method based on battery capacity. The method obtains various battery parameters through battery charge and discharge experiments at different temperatures, then processes the data and constructs a training data set. The trained data set is imported into a 2DCNN convolutional neural network for training. After estimating the battery capacity, a new data set is constructed using the estimated battery capacity, and the 2DCNN is used for training again. Ultimately, it can be used for real-time estimation of the lithium battery SOC.

[0006] The present invention is achieved by the following measures: a method for estimating the SOC of a lithium-ion battery based on battery capacity, comprising the following steps:

[0007] Step 1) Fully charge a new lithium-ion battery under varying temperatures, then repeatedly measure the terminal voltage, current, and temperature of the lithium-ion battery as the SOC changes from 1 to 0, as well as the voltage and current of the load, through a constant current discharge test, a DST discharge test, a FUDS discharge test, and a US06 discharge test;

[0008] Step 2) Preprocessing the measured data to construct a 2DCNN training dataset and a test dataset for estimating battery capacity, and constructing a new dataset using the battery capacity estimated by the 2DCNN convolutional neural network;

[0009] Step 3) Use the 2DCNN convolutional neural network to train and test the new dataset to achieve the final SOC real-time estimation;

[0010] As a further optimization solution of the lithium-ion battery SOC estimation method based on battery capacity provided by the present invention, the step 2) specifically includes the following steps:

[0011] Step 2-1) The lack of uniform data dimensions will lead to slow convergence and high errors when fitting the neural network algorithm, so the measured data needs to be normalized. The battery objects of various working condition experiments are the same, but the range of variation of voltage and current is different. Therefore, the data of various working conditions need to be pre-processed separately first. The following formula is used to normalize the input data:

[0012]

[0013] Among them, a ij is the jth data point of the i-th input, a min is the minimum value of the i-th input data, a max is the maximum value of the i-th input data, x in_ij is a ij The data after normalization.

[0014] The output is the SOC of the lithium battery. The SOC range is between 0 and 1, so normalization is not required.

[0015] Step 2-2) After data normalization, the following method is used to construct a data set. First, the measured values ​​in a discharge cycle are truncated into several data of length n, as shown below:

[0016]

[0017] Among them, x ij represents the jth data in the i-th cycle of the input data set, x ij The corresponding output is t nThe battery capacity value at the moment. U represents the voltage across the battery, I represents the current flowing through the battery, T represents the temperature of the battery during operation, t represents the discharge time, and U represents the battery capacity value at the moment. l Indicates the load current, I l In the present invention, n is set to 10.

[0018] Step 2-3) For a discharge experiment with a total number of charge and discharge cycles N and a single discharge cycle t = m, we use the padding method to expand the edge data to fully explore the relationship between the input data before and after each discharge cycle. This generates a total of N × m groups of input data of size 6 × 10, and the corresponding N × m battery capacity values ​​as output data. The input and output data of different operating conditions are combined into a total data set.

[0019] In steps 2-4, the training and test datasets are extracted without shuffling the dataset to ensure that the training and test datasets are not affected. The first 80% of the data from a discharge condition is used as the training dataset, and the last 20% of the data is used as the test dataset. These are used as training and test data for the 2DCNN.

[0020] Step 2-5) The 2DCNN convolutional neural network architecture developed for lithium-ion battery capacity estimation includes: an input layer (Input), four convolutional layers (C), two fully connected layers (F) and an output layer (Output).

[0021] Step 2-6) The convolutional layers and fully connected layers are all activated using the relu function, and the output layer is activated using the tanh function and mapped.

[0022] After the battery capacity is estimated in step 2-7), a new input data set of size 5×10 is constructed by taking U, I, T, t and the estimated battery capacity in formula (2). The corresponding output data is t n The battery SOC value at the moment.

[0023] As a further optimization solution of the lithium-ion battery SOC estimation method based on battery capacity provided by the present invention, the step 3) specifically includes the following steps:

[0024] Step 3-1) The 2DCNN convolutional neural network architecture developed for lithium-ion battery SOC estimation includes: an input layer, three convolutional layers, two fully connected layers, and an output layer.

[0025] Step 3-2) The convolutional layers and fully connected layers are all activated using the relu function, and the output layer is activated using the tanh function and mapped.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] (1) The present invention uses a fusion neural network algorithm based on battery capacity, which adds estimated battery capacity data to the data set and can achieve higher estimation accuracy.

[0028] (2) The length of historical data used by the present invention is 10 or even less, and the historical data can be memorized; and a short historical data length can also have a faster estimation speed.

[0029] (3) The 2DCNN used in the present invention to estimate SOC can reduce the amount of computation and unnecessary error input compared to using 3DCNN to estimate SOC, according to the definition of SOC, thereby achieving higher accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0031] Figure 1 It is the overall framework flow chart of the present invention.

[0032] Figure 2 Schematic diagram of the new dataset construction method in the present invention.

[0033] Figure 3 This is a curve diagram of the estimated battery capacity of the present invention. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. Of course, the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0035] Example 1

[0036] See also Figures 1 to 3 The present invention provides a method for estimating the state of charge (SOC) of a lithium-ion battery based on battery capacity. This embodiment utilizes a Panasonic NCR-18650B lithium-ion battery with a nominal voltage of 3.7V and a capacity of 3400mAh. The battery is fully charged using a constant current / constant voltage charging method and allowed to rest for 1 hour until it reaches full charge. Discharge tests are then repeated using constant current discharge, DST, FUDS, and US06 conditions until the voltage drops to the discharge cutoff voltage.

[0037] In order to better achieve the purpose of the present invention, this embodiment is a lithium-ion battery SOC estimation method based on a fusion neural network, which specifically includes the following steps:

[0038] Step 1) Fully charge a new lithium-ion battery under varying temperatures, then repeatedly measure the terminal voltage, current, and temperature of the lithium-ion battery as the SOC changes from 1 to 0, as well as the voltage and current of the load, through a constant current discharge test, a DST discharge test, a FUDS discharge test, and a US06 discharge test;

[0039] Step 2) Preprocessing the measured data to construct a 2DCNN training dataset and a test dataset for estimating battery capacity, and constructing a new dataset using the battery capacity estimated by the 2DCNN convolutional neural network;

[0040] Step 3) Use the 2DCNN convolutional neural network to train and test the new dataset to achieve the final SOC real-time estimation.

[0041] Preferably, the step 2) specifically includes the following steps:

[0042] Step 2-1) The lack of uniform data dimensions will lead to slow convergence and high errors when fitting the neural network algorithm, so the measured data needs to be normalized. The battery objects of various working condition experiments are the same, but the range of variation of voltage and current is different. Therefore, the data of various working conditions need to be pre-processed separately first. The following formula is used to normalize the input data:

[0043]

[0044] Among them, a ij is the jth data point of the i-th input, a min is the minimum value of the i-th input data, a max is the maximum value of the i-th input data, x in_ij is a ij The data after normalization.

[0045] The output is the SOC of the lithium battery. The SOC range is between 0 and 1, so normalization is not required.

[0046] Step 2-2) After data normalization, the following method is used to construct a data set. First, the measured values ​​in a discharge cycle are truncated into several data of length n, as shown below:

[0047]

[0048] Among them, x ij represents the jth data in the i-th cycle of the input data set, x ij The corresponding output is t n The battery capacity value at the moment. U represents the voltage across the battery, I represents the current flowing through the battery, T represents the temperature of the battery during operation, t represents the discharge time, and U represents the battery capacity value at the moment.l Indicates the load current, I l In the present invention, n is set to 10.

[0049] Step 2-3) For a discharge experiment with a total number of charge and discharge cycles N and a single discharge cycle t = m, we use the padding method to expand the edge data to fully explore the relationship between the input data before and after each discharge cycle. This generates a total of N × m groups of input data of size 6 × 10, and the corresponding N × m battery capacity values ​​as output data. The input and output data of different operating conditions are combined into a total data set.

[0050] In steps 2-4, the training and test datasets were extracted without shuffling the dataset to ensure that the training data would not be affected. The first 80% of the data from a discharge condition was used as the training dataset, and the last 20% of the data was used as the test dataset. These were used as training and test data for the 3DCNN.

[0051] Step 2-5) The 2DCNN convolutional neural network architecture developed for lithium-ion battery capacity estimation includes: an input layer (Input), four convolutional layers (C), two fully connected layers (F), and an output layer (Output). Specifically: in the convolutional layer, the first three layers are 32 2×2 two-dimensional convolution kernels, and the fourth layer is 64 3×3 two-dimensional convolution kernels; the number of fully connected layers is 64 and 32, and the estimation results are as follows: Figure 3 shown.

[0052] Step 2-6) The convolutional layers and fully connected layers are all activated using the relu function, and the output layer is activated using the tanh function and mapped.

[0053] After the battery capacity is estimated in step 2-7), a new input data set of size 5×10 is constructed by taking U, I, T, t and the estimated battery capacity in formula (2). The corresponding output data is t n The battery SOC value at the moment.

[0054] Preferably, the step 3) specifically comprises the following steps:

[0055] Step 3-1) The 2DCNN convolutional neural network architecture developed for lithium-ion battery SOC estimation consists of an input layer, three convolutional layers, two fully connected layers, and an output layer. Specifically, the first two convolutional layers have 32 2×2 convolution kernels, and the third layer has 64 3×3 convolution kernels. The number of fully connected layers is 64 and 32, respectively.

[0056] Step 3-2) The convolutional layers and fully connected layers are all activated using the relu function, and the output layer is activated using the tanh function and mapped.

[0057] The present invention uses a fusion neural network algorithm based on battery capacity, which adds estimated battery capacity data to the data set, thereby achieving higher estimation accuracy.

[0058] The length of the historical data used by the present invention is 10 or even less, and the historical data can be memorized; moreover, the short length of the historical data can also have a faster estimation speed.

[0059] The 2DCNN used in the present invention to estimate SOC can reduce the amount of computation and unnecessary error input compared to using 3DCNN to estimate SOC, based on the definition of SOC, thereby achieving higher accuracy.

[0060] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for estimating SOC of a lithium-ion battery based on battery capacity, characterized in that: The following steps are involved: Step 1) Fully charge a new lithium-ion battery under varying temperatures, then repeatedly measure the terminal voltage, current, and temperature of the lithium-ion battery as the SOC changes from 1 to 0, as well as the voltage and current of the load, through a constant current discharge test, a DST discharge test, a FUDS discharge test, and a US06 discharge test; Step 2) Preprocessing the measured data to construct a 2DCNN training dataset and a test dataset for estimating battery capacity, and constructing a new dataset using the battery capacity estimated by the 2DCNN convolutional neural network; The step 2) comprises the following steps: Step 2-1) Normalize the measured data. The battery objects of various working condition experiments are the same, but the voltage and current variation ranges are different. First, pre-process the data of various working conditions separately and use the following formula to normalize the input data: Among them, a ij is the jth data point of the i-th input, a min is the minimum value of the i-th input data, a max is the maximum value of the i-th input data, x in_ij is a ij The data after normalization; The output is the SOC of the lithium battery. The SOC range is between 0 and 1 and does not require normalization. Step 2-2) After data normalization, the following method is used to construct a data set. First, the measured values ​​in a discharge cycle are truncated into several data of length n, as shown below: Among them, x ij represents the jth data in the i-th cycle of the input data set, x ij The corresponding output is t n The battery capacity value at the moment, U represents the voltage across the battery, I represents the current flowing through the battery, T represents the temperature of the battery during operation, t represents the discharge time, U represents the ... l Indicates the load current, I l Indicates the load current; Step 2-3) For a discharge experiment with a total number of charge and discharge cycles N and a single discharge cycle t = m, the edge data is expanded using the padding method to make the connection between the previous and next input data in each discharge cycle. Then, a total of N × m groups of input data with a size of 6 × 10 are generated, and the corresponding N × m battery capacity values ​​are output data. The input and output data of different working conditions are merged into a total data set; Step 2-4) Select the first 80% of the data of a discharge condition as the training data set, and the last 20% of the data as the test data set, which are used as training and test data for 2DCNN; Step 2-5) The 2DCNN convolutional neural network architecture developed for lithium-ion battery capacity estimation includes: an input layer (Input), four convolutional layers (C), two fully connected layers (F), and an output layer (Output); Step 2-6) All convolutional layers and fully connected layers are activated using the relu function, and the output layer is activated using the tanh function and mapped; After the battery capacity is estimated in step 2-7), a new input data set of size 5×10 is constructed by taking U, I, T, t and the estimated battery capacity in formula (2). The corresponding output data is t n Battery SOC value at the moment; Step 3) Use the 2DCNN convolutional neural network to train and test the new dataset to achieve the final SOC real-time estimation.

2. The method for estimating SOC of a lithium-ion battery based on battery capacity according to claim 1, wherein: The step 3) specifically comprises the following steps: Step 3-1) The 2DCNN convolutional neural network architecture developed for lithium-ion battery SOC estimation includes: an input layer, three convolutional layers, two fully connected layers, and an output layer; Step 3-2) The convolutional layers and fully connected layers are all activated using the relu function, and the output layer is activated using the tanh function and mapped.

Images