A method for early RUL prediction of lithium batteries based on transfer learning and unscented particle filter (UPF) fusion model

Abstract

The present invention provides a method for predicting the early life expectancy (RUL) of lithium batteries based on a fusion model of transfer learning and an unscented particle filter (UPF), belonging to the field of power batteries and energy storage technology. The present invention uses a moving average method and residual analysis method to smooth and denoise the original data set, and divides the processed data into source domain data and target domain data. The source domain data is input into a Mogrifier LSTM neural network for training to obtain a pre-trained model, and the pre-trained model is fine-tuned using a small amount of target domain data to achieve RUL prediction for other batteries of the same type but under different experimental environments. To further improve prediction accuracy, a double-exponential capacity decay empirical model is sampled to establish a state equation. The RUL prediction value output by the fine-tuned model is used as the observation value of the UPF, and the posterior capacity prediction value is obtained through each iterative update. It is then determined whether it reaches the capacity threshold, thereby achieving the remaining service life prediction of the lithium battery.

Description

Technical Field

[0001] The present invention belongs to the field of power batteries and energy storage technology, and specifically relates to a lithium battery early run-of-life (RUL) prediction method based on a transfer learning and unscented particle filter (UPF) fusion model. Background Art

[0002] In recent years, lithium batteries have been widely used in power batteries and energy storage due to their advantages such as high energy density, long life, and low self-discharge rate. However, as usage increases, lithium battery performance gradually declines and the probability of failure increases, which can lead to huge economic losses and even safety hazards. Therefore, the research of advanced battery prognostic and health management (PHM) methods, especially remaining useful life (RUL) prediction, has become an important topic to ensure battery safety and reliability. However, lithium battery capacity decay is affected by many factors, such as lithium ion loss in electrochemical reactions, structural changes in positive and negative electrode materials, and usage conditions such as charge and discharge cycles, current, voltage, and temperature. These complex factors make accurately predicting lithium battery RUL a challenge.

[0003] Existing RUL estimation methods can be divided into model-based and data-driven methods; model-based methods make predictions by establishing mathematical models of the chemical reactions or degradation mechanisms inside the battery, including electrochemical models, semi-empirical models, and statistical filters; electrochemical models can more accurately describe the chemical reactions inside lithium batteries and have relatively clear physical meanings, but they require a large number of battery parameters, which are difficult to obtain in practice; semi-empirical models are modeled by combining battery attenuation laws and measurement data. The advantage is that the construction and implementation are relatively simple and do not require a lot of prior knowledge; but because the model relies on simple mathematical formulas, it is difficult to accurately capture complex battery dynamics processes; the statistical filter method first models the battery and performs parameter estimation or state correction through filtering methods; its advantage is that it can update the system state and RUL estimation in real time, which is suitable for applications in dynamic environments. The disadvantage is that it relies on an accurate system model;

[0004] Unlike model-based approaches, data-driven approaches do not rely on detailed analysis of internal battery reactions. Instead, they use data mining to reveal the inherent correlations between inputs and outputs, thereby learning and capturing the patterns of lithium battery capacity degradation. In the field of battery capacity prediction, a large amount of research has been devoted to exploring various machine learning methods to infer capacity change trends and predict future capacity curves. These methods include support vector machines (SVMs), Gaussian process regression (GPR), long short-term memory networks (LSTMs), and gated recurrent unit networks (GRUs). These models typically rely on large-scale data training to capture the complex nonlinear mapping relationships between input and output variables, thereby accurately fitting the dynamic changes in battery capacity in time series prediction.

[0005] Different batteries have significant differences in the aging process. However, traditional machine learning methods usually assume that the data distribution of the training set and the test set should be consistent. In practical applications, this assumption is often difficult to hold due to the wide variety of lithium batteries and different working environments. In order to obtain cycle data for new batteries, a large number of experiments are usually required, which is time-consuming and costly. Fortunately, different batteries tend to follow similar degradation patterns. During the charge and discharge cycle, the structural changes and wear of the positive and negative electrode materials will gradually reduce their efficiency in inserting and deintercalating lithium ions, thereby causing battery capacity decay. Therefore, how to effectively transfer the degradation characteristics of one battery to another becomes the key to improving the accuracy of lithium battery aging prediction, and transfer learning provides a practical solution to this problem. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to overcome the shortcomings of the existing technology and provide a lithium battery early RUL prediction method based on transfer learning and unscented particle filter (UPF) fusion model, which solves the problems raised in the above background technology.

[0007] In order to solve the above technical problems, the basic concept of the technical solution adopted by the present invention is:

[0008] A method for predicting the early RUL of lithium batteries based on a transfer learning and unscented particle filter (UPF) fusion model includes the following steps:

[0009] Step 1: Data preprocessing: First, the lithium battery is cycled at different temperatures and charge / discharge rates, and samples are taken regularly to obtain the original capacity data set. Second, the raw data is smoothed using the moving average method to reduce random fluctuations. Subsequently, residual analysis is performed by calculating the standard residual between the raw data and the smoothed data (i.e., (raw data - smoothed data) / standard deviation of the raw data). The specific formula for calculating the standard residual is:

[0010] The specific formula for calculating the standardized residual is:

[0011]

[0012] where Q i and They represent the original capacity data and the smoothed data respectively. RMSE represents the root mean square error between the original data and the smoothed data. Sample values ​​outside the 99% confidence interval are marked as outliers. Then, linear interpolation is used to correct the outliers and the outliers are estimated and replaced based on the adjacent normal values. In order to eliminate data bias and improve model training efficiency, the Z-Score normalization method is used to process the capacity values ​​after removing outliers. The specific normalization formula is:

[0013]

[0014] in μ represents the average value of the processed data. σ represents the standard deviation of the processed data, X Represents the processed data, Z represents the normalized capacity data;

[0015] Step 2: The neural network implements RUL prediction, which includes:

[0016] Step 2.1: Single-step prediction: Train the Mogrifier-LSTM network to predict the capacity value of the next cycle based on the capacity values ​​of the previous m cycles. The sliding window method is used to construct the training samples of the Mogrifier-LSTM network. The specific operation is: set the window length to m+1 (the first m cycles as input, the m+1th cycle as output), and slide it step by step along the entire capacity value sequence to obtain input and output pairs. Each training sample is constructed based on this, which can be expressed as:

[0017] Q=[Q1,…Q t ,…Q N ]

[0018] where Q t represents the capacity value of the t-th cycle, N represents the sequence length, the entire battery capacity value sequence, from any continuous sequence of m+1 capacity values ​​[Q i , Q i+1 ,…Q i+m ] to obtain an input-output pair, the input of the network is represented as x i =[Q i , Q j ,…Q i+m-1 ], the output is represented by y i =Q i+m , the relationship is written as y i =f(x i ), namely Q i+m =f([Q i ,…Q j ,…Q i+m-1 ]), where f(·) is the mapping relationship learned by the neural network through training;

[0019] Step 2.2: Iterative prediction: Based on the single-step prediction, the prediction results of the previous step are continuously used as input to gradually calculate the capacity change trajectory of the lithium battery until it reaches 75% of the rated capacity. The specific implementation method is as follows:

[0020] Given input x1 = [Q1, ...Q i,…Q m ], the capacity value predicted by the model is

[0021]

[0022] The predicted results To update x1 to get the new input x2:

[0023] x2=[Q2,…Q i ,… m+1 ]

[0024] Then the predicted capacity value of x2 is:

[0025]

[0026] By analogy, the predicted value of the kth step is expressed as:

[0027]

[0028] By performing iterative prediction according to the above recursive steps, the capacity change trajectory of the lithium battery can be obtained until the capacity reaches the set threshold, that is, 75% of the rated capacity;

[0029] Step 2.3: Transfer learning: Divide the preprocessed data from step 1 into source domain data and target domain data. Use the source domain data as the input for pre-training the Mogrifier-LSTM model. Fine-tune the model using the target domain data to achieve transfer learning, resulting in a fine-tuned transfer learning model TL-Mogrifier-LSTM. During the fine-tuning process, freeze the Mogrifier-LSTM layer and only use the target domain data to optimize the parameters of the fully connected layer.

[0030] Step 3: RUL prediction method based on fusion model: The unscented particle filter (UPF) is introduced to dynamically correct the predicted value of the neural network. The capacity value predicted by the TL-Mogrifier-LSTM neural network obtained in step 2 is used as the observation value of the UPF. The capacity prediction value is updated in each iteration of the prediction phase. The specific steps of using the capacity value predicted by the TL-Mogrifier-LSTM neural network as the observation value of the UPF include:

[0031] Step 3.1: Use the double exponential capacity decay model to construct the state-space equation. The specific formula for constructing the state-space equation includes:

[0032]

[0033] Where a, b, c, and d represent model parameters, respectively. k represents the kth cycle of the lithium battery, and Q represents the estimated capacity of the battery. N(0, σ) represents Gaussian white noise with a mean of 0 and a standard deviation of σ, w represents process noise, and v represents observation noise.

[0034] Step 3.2: Use the UPF algorithm to track and determine the parameters of the double exponential capacity decay model in step 3.1; where the double exponential capacity decay model parameter is a k , b k , c k , d k , the UPF algorithm specifically includes the following steps:

[0035] Step 3.21: Initialize UPF related parameters: initial value of state vector, initial covariance matrix, number of particles N;

[0036] Step 3.22: Importance sampling phase: Use the UKF algorithm combined with the state space equation to calculate the state and observation distribution of each particle;

[0037] Step 3.23: Weight correction: Calculate the weight update factor of each particle and normalize the particle weight so that the weight sum is 1.

[0038] Step 3.24: Resampling: Resampling according to particle weight;

[0039] Step 3.25: Estimate output: Use the updated particles and weights to get an estimate of the system state.

[0040] Step 3.26: Repeat steps 3.21 to 3.25 until the prediction starting point T is reached;

[0041] Step 3.27: Output the double exponential capacity decay model parameter a k , b k , c k , d k ;

[0042] Step 3.3: Starting from the prediction starting point, use the equation in step 3.1 as the state equation, take the capacity prediction value of the TL-Mogrifier-LSTM model as the observation value, apply the UPF algorithm to dynamically update the model parameters, obtain the posterior capacity estimate, and use this posterior capacity estimate as the input of the neural network model to predict the capacity value of the next cycle. Repeat this cycle iteratively to gradually predict the battery capacity change until the set capacity threshold is reached.

[0043] After adopting the above technical solution, the present invention has the following beneficial effects compared with the prior art. Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described below at the same time:

[0044] 1. By applying transfer learning and improving the long short-term memory (LSTM) network, the TL-Mogrifier-LSTM model constructed in this paper has stronger feature capture and nonlinear modeling capabilities than traditional models. This model can flexibly adapt to the characteristics of different batteries and still achieve good RUL prediction accuracy even in the absence of sufficient data, significantly reducing the required amount of target battery data.

[0045] 2. The introduction of the Unscented Particle Filter (UPF) algorithm provides real-time dynamic correction of the neural network's predictions, significantly improving prediction accuracy. The UPF updates the capacity predictions at each iteration, effectively suppressing the potential for error accumulation when relying solely on neural networks for long-term predictions, thereby ensuring the accuracy and reliability of RUL predictions.

[0046] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The drawings described below are only some embodiments. A person skilled in the art can derive other drawings based on these drawings without inventive effort. In the drawings:

[0048] Figure 1 It is a schematic diagram of the data set preprocessing process of the present invention;

[0049] Figure 2 This is a schematic diagram of the Mogrifier-LSTM neural network structure used in the present invention;

[0050] Figure 3 This is a schematic diagram of the overall process of the method for predicting the remaining useful life of a lithium battery based on transfer learning and UPF fusion model provided by the present invention;

[0051] Figure 4 It is a battery capacity curve diagram predicted by different sampling methods of the present invention;

[0052] Figure 5 It is a curve diagram of battery capacity error predicted by different sampling methods of the present invention.

[0053] It should be noted that these drawings and textual descriptions are not intended to limit the conceptual scope of the present invention in any way, but rather to illustrate the concept of the present invention for those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0054] The present invention will now be described in further detail with reference to the accompanying drawings.

[0055] Example 1: Please refer to Figure 1-5 As shown, in this embodiment, a method for predicting the early RUL of lithium batteries based on a transfer learning and unscented particle filter (UPF) fusion model is provided, including the following steps:

[0056] Step 1: Data preprocessing: First, the lithium battery is cycled at different temperatures and charge / discharge rates, and samples are taken regularly to obtain the original capacity data set. Second, the raw data is smoothed using the moving average method to reduce random fluctuations. Subsequently, residual analysis is performed by calculating the standard residual between the raw data and the smoothed data (i.e., (raw data - smoothed data) / standard deviation of the raw data). The specific formula for calculating the standard residual is:

[0057]

[0058] where Q i and Q i They represent the original capacity data and the smoothed data respectively. RMSE represents the root mean square error between the original data and the smoothed data. Sample values ​​outside the 99% confidence interval are marked as outliers. Then, linear interpolation is used to correct the outliers and the outliers are estimated and replaced based on the adjacent normal values. In order to eliminate data bias and improve model training efficiency, the Z-Score normalization method is used to process the capacity values ​​after removing outliers. The specific normalization formula is:

[0059]

[0060] Where μ represents the mean of the processed data, σ represents the standard deviation of the processed data, X represents the processed data, and Z represents the normalized capacity data;

[0061] Step 2: The neural network implements RUL prediction, which includes:

[0062] Step 2.1: Single-step prediction: Train the Mogrifier-LSTM network to predict the capacity value of the next cycle based on the capacity values ​​of the previous m cycles. The sliding window method is used to construct the training samples of the Mogrifier-LSTM network. The specific operation is: set the window length to m+1 (the first m cycles as input, the m+1th cycle as output), and slide it step by step along the entire capacity value sequence to obtain input and output pairs. Each training sample is constructed based on this, which can be expressed as:

[0063] Q=[Q1,…Q t ,…Q N ]

[0064] where Q t represents the capacity value of the t-th cycle, N represents the sequence length, the entire battery capacity value sequence, from any continuous sequence of m+1 capacity values ​​[Q i , Q i+1 ,…Q i+m ] to obtain an input-output pair, the input of the network is represented as x i =[Q i ,…Q j ,…Q i+m-1 ], the output is represented by y i =Q i+m , the relationship is written as y i =f(x i ), namely Q i+m =f([Q i ,…Q j ,…Q i+m-1 ]), where f(·) is the mapping relationship learned by the neural network through training;

[0065] Step 2.2: Iterative prediction: Based on the single-step prediction, the prediction results of the previous step are continuously used as input to gradually calculate the capacity change trajectory of the lithium battery until it reaches 75% of the rated capacity. The specific implementation method is as follows:

[0066] Given input x1=[Q1,…Q i ,…Q m ], the capacity value predicted by the model is

[0067]

[0068] The predicted results To update x1 to get the new input x2:

[0069] x2=[Q2,…Q i ,…Q m+1 ]

[0070] Then the predicted capacity value of x2 is:

[0071]

[0072] By analogy, the predicted value of step k is expressed as:

[0073]

[0074] By performing iterative prediction according to the above recursive steps, the capacity change trajectory of the lithium battery can be obtained until the capacity reaches the set threshold, that is, 75% of the rated capacity;

[0075] Step 2.3: Transfer learning: Divide the preprocessed data from step 1 into source domain data and target domain data. Use the source domain data as the input for pre-training the Mogrifier-LSTM model. Fine-tune the model using the target domain data to achieve transfer learning, resulting in a fine-tuned transfer learning model TL-Mogrifier-LSTM. During the fine-tuning process, freeze the Mogrifier-LSTM layer and only use the target domain data to optimize the parameters of the fully connected layer.

[0076] Step 3: RUL prediction method based on fusion model: The unscented particle filter (UPF) is introduced to dynamically correct the predicted value of the neural network. The capacity value predicted by the TL-Mogrifier-LSTM neural network obtained in step 2 is used as the observation value of the UPF. The capacity prediction value is updated in each iteration of the prediction phase. The specific steps of using the capacity value predicted by the TL-Mogrifier-LSTM neural network as the observation value of the UPF include:

[0077] Step 3.1: Use the double exponential capacity decay model to construct the state-space equation. The specific formula for constructing the state-space equation includes:

[0078]

[0079] Where a, b, c, and d represent model parameters, respectively. k represents the kth cycle of the lithium battery, and Q represents the estimated capacity of the battery. N(0, σ) represents Gaussian white noise with mean 0 and standard deviation σ, ω represents process noise, and ν represents observation noise.

[0080] Step 3.2: Use the UPF algorithm to track and determine the parameters of the double exponential capacity decay model in step 3.1; where the double exponential capacity decay model parameter is a k , b k , c k , d k , the UPF algorithm specifically includes the following steps:

[0081] Step 3.21: Initialize UPF related parameters: initial value of state vector, initial covariance matrix, number of particles N;

[0082] Step 3.22: Importance sampling phase: Use the UKF algorithm combined with the state space equation to calculate the state and observation distribution of each particle;

[0083] Step 3.23: Weight correction: Calculate the weight update factor of each particle and normalize the particle weight so that the weight sum is 1.

[0084] Step 3.24: Resampling: Resampling according to particle weight;

[0085] Step 3.25: Estimate output: Use the updated particles and weights to get an estimate of the system state;

[0086] Step 3.26: Repeat steps 3.21 to 3.25 until the prediction starting point T is reached;

[0087] Step 3.27: Output the double exponential capacity decay model parameter a k , b k , c k , d k ;

[0088] Step 3.3: Starting from the prediction starting point, use the equation in step 3.1 as the state equation, take the capacity prediction value of the TL-Mogrifier-LSTM model as the observation value, apply the UPF algorithm to dynamically update the model parameters, obtain the posterior capacity estimate, and use this posterior capacity estimate as the input of the neural network model to predict the capacity value of the next cycle. Repeat this cycle iteratively to gradually predict the battery capacity change until the set capacity threshold is reached.

[0089] 1. By applying transfer learning and improving the long short-term memory (LSTM) network, the TL-Mogrifier-LSTM model constructed in this paper has stronger feature capture and nonlinear modeling capabilities than traditional models. This model can flexibly adapt to the characteristics of different batteries and still achieve good RUL prediction accuracy even in the absence of sufficient data, significantly reducing the required amount of target battery data.

[0090] 2. The introduction of the Unscented Particle Filter (UPF) algorithm provides real-time dynamic correction of the neural network's predictions, significantly improving prediction accuracy. The UPF updates the capacity predictions at each iteration, effectively suppressing the potential for error accumulation when relying solely on neural networks for long-term predictions, thereby ensuring the accuracy and reliability of RUL predictions.

[0091] Example 2: Figure 1 The data set preprocessing process of the present invention is shown. Figure 1 It can be seen that there is a certain amount of noise in the original data. After smoothing and outlier processing, data suitable for further analysis is obtained. Figure 2 The neural network structure model used in the present invention is shown. Figure 2 It can be seen that compared with the traditional LSTM structure, Mogrifier-LSTM enhances the information interaction ability of the input gate and the forget gate, thus having stronger nonlinear expression performance. Figure 3Describes the lithium battery RUL prediction process based on transfer learning and UPF fusion model. Figure 3 As can be seen, the preprocessed data is divided into two parts: one part is input into the Mogrifier-LSTM network for training to obtain a pretrained model. The model is then fine-tuned using target domain data to generate the target model TL-Mogrifier-LSTM, from which the capacity prediction value is obtained; the other part is used to obtain the initial parameter values ​​of the double exponential model. The capacity prediction value of the transfer learning model is used as the observation value of the UPF prediction model and is updated during each iteration of the UPF algorithm to obtain the posterior capacity prediction value. Finally, the RUL prediction is achieved by comparing the posterior capacity prediction value to see if it meets the capacity prediction threshold. The specific steps are as follows:

[0092] Step 1, data preprocessing: First, the lithium battery is subjected to cyclic charge and discharge experiments at different temperatures and charge and discharge rates, and regular sampling is performed to obtain the original capacity data set; second, the raw data is smoothed using the moving average method to reduce random fluctuations; then, residual analysis is performed by calculating the standard residual between the raw data and the smoothed data (i.e., (raw data - smoothed data) / standard deviation of the raw data). The specific formula for calculating the standard residual is:

[0093]

[0094] where Q i and represents the raw capacity data and the smoothed data, respectively, and RMSE represents the root mean square error between the raw and smoothed data. Sample values ​​outside the 99% confidence interval are marked as outliers. Outliers are then corrected using linear interpolation, estimating and replacing them based on adjacent normal values.

[0095] In addition, in order to eliminate data bias and improve model training efficiency, the present invention uses the Z-Score normalization method to process the capacity value after removing outliers, thus obtaining preprocessed data. The normalization strategy is as follows:

[0096]

[0097] Where μ represents the mean of the processed data, σ represents the standard deviation of the processed data, X represents the processed data, and Z represents the normalized capacity data.

[0098] Step 2: Neural network realizes RUL prediction

[0099] Step 2.1, single-step prediction. In this invention, we train the Mogrifier-LSTM network to predict the capacity value of the next cycle based on the capacity values ​​of the previous m cycles. The sample is constructed by the sampling sliding window method, with the window length set to m+1 (where the first m cycles are used as input and the m+1th cycle is used as output), and the entire capacity value sequence is scanned step by step to obtain input-output pairs. Each training sample can be expressed as, Q = [Q1, ...Q t ,…Q N ], where Q t represents the capacity value of the t-th cycle, and N represents the sequence length. Extending to the entire battery capacity value sequence, we can obtain the capacity value of any continuous sequence of m+1 capacity values ​​[Q i , Q i+1 ,…Q i+m ] to obtain an input-output pair. The input of the network can be expressed as x i =[Q i ,…Q j ,…Q i+m-1 ], the output is represented by y i =Q i+m , the relationship can be written as i =f(x i ), namely Q i+m =f([Q i ,…Q j ,…Q i+m-1 ]), where f(·) is the mapping relationship learned by the neural network through training. This method can predict the capacity value of the next cycle based on the capacity values ​​of the previous m cycles.

[0100] Step 2.2 Iterative Prediction: In Step 2.1, we implemented single-step prediction using the Mogrifier-LSTM network. Next, we will describe how to use this model for long-term iterative prediction to obtain the battery capacity change trajectory before reaching the threshold capacity. The specific steps are as follows:

[0101] Given input x1 = [Q1, ...Q i ,…Q m ], the capacity value predicted by the model is

[0102]

[0103] Next, the prediction results To update x1 to get the new input x2:

[0104] x2=[Q2,…Q i …Q m+1 ]

[0105] Then the predicted capacity value of x2 is:

[0106]

[0107] By analogy, the predicted value of step k can be expressed as:

[0108]

[0109] By performing iterative prediction according to the above recursive steps, the capacity change trajectory of the lithium battery can be obtained until the capacity reaches the set threshold, that is, 75% of the rated capacity.

[0110] In step 2.3, transfer learning, the neural network model used in this invention consists of a Mogrifier LSTM layer and a fully connected layer. First, the data preprocessed in step 1 is divided into source domain data and target domain data. Next, the source domain data is used as input for pre-training of the Mogrifier-LSTM model. Subsequently, the model is fine-tuned using target domain data to achieve transfer learning. During the fine-tuning process, the Mogrifier-LSTM layer is frozen, and only the target domain data is used to optimize the parameters of the fully connected layer, resulting in the fine-tuned transfer learning model TL-Mogrifier-LSTM.

[0111] Step 3: RUL prediction method based on the fusion model. By introducing an unscented particle filter (UPF), the neural network's predicted value is dynamically corrected. The capacity value predicted by the TL-Mogrifier-LSTM neural network obtained in Step 2 is used as the UPF observation value, and the capacity prediction value is updated at each iteration of the prediction phase. Furthermore, the posterior capacity prediction value output by the UPF algorithm is input into the TL-Mogrifier-LSTM model to iteratively predict the capacity value of the next sampling point, significantly improving the prediction accuracy.

[0112] Step 3.1 Construct the state space equation using the double exponential capacity decay model

[0113]

[0114] Where a, b, c, and d represent model parameters, respectively. k represents the kth cycle of the lithium battery, and Q represents the estimated capacity of the battery. N(0, σ) represents Gaussian white noise with mean 0 and standard deviation σ, ω represents process noise, and ν represents observation noise.

[0115] Step 3.2 Use the UPF algorithm to track and determine the double exponential capacity decay model parameter a in step 3.1 k , b k , c k , d k, specifically the following steps:

[0116] a. Initialize UPF related parameters: initial value of state vector, initial covariance matrix, number of particles N;

[0117] b. Importance sampling stage: Use the UKF algorithm combined with the state space equation to calculate the state and observation distribution of each particle;

[0118] c. Weight correction: Calculate the weight update factor of each particle and normalize the particle weight so that the sum of the weights is 1, that is,

[0119] d. Resampling: Resampling according to particle weights;

[0120] e. Estimated output: Use the updated particles and weights to obtain an estimated value of the system state;

[0121] f. Repeat steps ae until the prediction starting point T;

[0122] g. Output double exponential capacity decay model parameter a k , b k , c k , d k .

[0123] Step 3.3 begins at the prediction starting point T. Using the equation in step 3.1 as the state equation and the capacity prediction value from the TL-Mogrifier-LSTM model as the observation value, the UPF algorithm is applied to dynamically update the model parameters to obtain a posterior capacity estimate. This posterior capacity estimate is then used as input to the neural network model to predict the capacity value for the next cycle. This cycle is repeated, gradually predicting the battery capacity change until the set capacity threshold is reached.

[0124] In order to verify the effect of the present invention, experiments were conducted.

[0125] The experimental data of this invention uses the NCA battery data set, and the effectiveness of different methods in RUL prediction is evaluated by three indicators: RMSE (root mean square error), MAE (mean absolute error) and PE (prediction error). The experimental results are detailed in Table 1. Figure 4 and Figure 5Among them, Mogrifier-LSTM represents the experimental results of iterative prediction using the Mogrifier-LSTM network; TL-Mogrifier-LSTM represents the experimental results of the TL-Mogrifier-LSTM model obtained by first training the pre-trained model with source domain data and then fine-tuning the model with target domain data; TL-Mogrifier-LSTM-UPF represents the experimental results of the transfer learning and UPF fusion model proposed in this paper.

[0126] Table 1 Comparison of prediction results

[0127] Real RUL Predicting RUL PE RMSE MAE Mogrifier-LSTM 527 597 70 0.05947 0.05231 TL-Mogrifier-LSTM 527 548 21 0.3265 0.03239 TL-Mogrifier-LSTM-UPF 527 523 4 0.01800 0.01775

[0128] Table 1 compares the long-term prediction results of different methods. It can be seen that the method using only a single neural network model has large RMSE, MAE, and PE errors. The TL-Mogrifier-LSTM method using transfer learning has significantly reduced these errors, demonstrating that transfer learning can effectively improve battery RUL prediction. The last row of Table 1 shows the fusion model method proposed in this paper. Clearly, this method can achieve better RUL prediction results, demonstrating its effectiveness.

[0129] Figure 4 and Figure 5 The capacity curves and prediction errors of the lithium battery RUL prediction results using different methods used in this invention are shown. As can be seen from the figure, the method proposed in this invention has a smaller capacity prediction error and a higher degree of agreement between the prediction curve and the actual value, indicating that this method has a significant advantage in accuracy.

[0130] The present invention is not limited to the above-described embodiments. Any structural changes made under the guidance of the present invention, which have the same or similar technical solutions as the present invention, should be understood to fall within the scope of protection of the present invention. The technologies, shapes, and structural parts not described in detail in the present invention are all well-known technologies.

Claims

1. A lithium battery early RUL prediction method based on transfer learning and unscented particle filter (UPF) fusion model, characterized in that: The steps include: Step 1: Data preprocessing: Perform cyclic charge-discharge experiments on lithium batteries at different temperatures and charge-discharge rates, and regularly sample the lithium batteries to obtain a raw data set. Use the moving average method and residual analysis method to smooth and reduce noise on the raw data set to reduce the impact of noise on subsequent model training. Step 2: The neural network implements RUL prediction, which includes: Step 2.1: Single-step prediction: Train the Mogrifier-LSTM network to predict the capacity value of the next cycle based on the capacity values ​​of the previous m cycles; Among them, in step 2.1, the sliding window method is used to construct the training samples of the Mogrifier-LSTM network. The specific operation is: set the window length to m+1, the first m cycles as input, the m+1th cycle as output, and gradually slide along the entire capacity value sequence to obtain input and output pairs. Each training sample is constructed accordingly, which can be specifically expressed as: ； in represents the capacity value of the t-th cycle, Indicates the sequence length, the entire battery capacity value sequence, from any continuous Sequence of capacity values Get an input-output pair from the network. The input of the network is represented as , the output is expressed as , the relationship is written as ,Right now ,in It is the mapping relationship learned by the neural network through training; Step 2.2: Iterative prediction: Based on the single-step prediction, the prediction results of the previous step are continuously used as input to gradually calculate the capacity change trajectory of the lithium battery until it reaches 75% of the rated capacity; Among them, in step 2.2, the prediction formula is: Given input The capacity value predicted by the model is : The predicted results To update To get new input : ； but The capacity forecast value is: ； By analogy, the The predicted value of the step is expressed as: ； By performing iterative prediction according to the above recursive steps, the capacity change trajectory of the lithium battery can be obtained until the capacity reaches the set threshold, which is 75% of the rated capacity; Step 2.3: Transfer learning: Divide the preprocessed data in step 1 into source domain data and target domain data. Use the source domain data as the input of the Mogrifier-LSTM model for pre-training. Use the target domain data to fine-tune the model to achieve transfer learning, and obtain the fine-tuned transfer learning model TL-Mogrifier-LSTM. Step 3: RUL prediction method based on fusion model: The predicted value of the neural network is dynamically corrected by introducing the unscented particle filter (UPF). The capacity value predicted by the TL-Mogrifier-LSTM neural network obtained in step 2 is used as the observation value of the UPF, and the capacity prediction value is updated in each iteration of the prediction stage.

2. The method for predicting early RUL of lithium batteries based on transfer learning and unscented particle filter (UPF) fusion model according to claim 1, characterized in that: In step 1, the data is pre-processed by first smoothing the initial capacity data using a moving average method, and then performing residual analysis to calculate the standard residual using the smoothed data and the original capacity data.

3. The method for predicting early RUL of lithium batteries based on transfer learning and unscented particle filter (UPF) fusion model according to claim 2, characterized in that: The specific formula for calculating the standardized residual is: ； in and They represent the original capacity data and the smoothed data respectively, RMSE represents the root mean square error of the original data and the smoothed data, and the sample values ​​outside the 99% confidence interval are marked as outliers. Then the outliers are corrected by linear interpolation and estimated based on the adjacent normal values.

4. The method for predicting early RUL of lithium batteries based on transfer learning and unscented particle filter (UPF) fusion model according to claim 3, characterized in that: In order to eliminate data bias and improve model training efficiency, the Z-Score normalization method is used to process the capacity value after removing outliers. The specific normalization formula is: ； in represents the average value of the processed data. represents the standard deviation of the processed data, Represents the processed data, Represents normalized capacity data.

5. The method for predicting early RUL of lithium batteries based on transfer learning and unscented particle filter (UPF) fusion model according to claim 1, characterized in that: In step 2.3, during the fine-tuning process, the Mogrifier-LSTM layer is frozen and only the target domain data is used to optimize the parameters of the fully connected layer.

6. The method for predicting early RUL of lithium batteries based on transfer learning and unscented particle filter (UPF) fusion model according to claim 1, characterized in that: In step 3, the specific steps of using the capacity value predicted by the TL-Mogrifier-LSTM neural network as the observed value of the UPF include: Step 3.1: Construct the state-space equation using the double exponential capacity decay model; Step 3.2: Use the UPF algorithm to track and determine the parameters of the double exponential capacity decay model in step 3.1; Step 3.3: Starting from the prediction starting point, use the equation in step 3.1 as the state equation, take the capacity prediction value of the TL-Mogrifier-LSTM model as the observation value, apply the UPF algorithm to dynamically update the model parameters, obtain the posterior capacity estimate, and use this posterior capacity estimate as the input of the neural network model to predict the capacity value of the next cycle. Repeat this cycle iteratively to gradually predict the battery capacity change until the set capacity threshold is reached.

7. The method for predicting early RUL of lithium batteries based on transfer learning and unscented particle filtering (UPF) fusion model according to claim 6, characterized in that: In step 3.1, the specific formula for constructing the state space equation includes: ； Where a, b, c, and d represent model parameters, respectively; k represents the kth cycle of the lithium battery, and Q represents the estimated capacity of the battery; The mean is 0 and the standard deviation is Gaussian white noise, represents the process noise, represents the observation noise.

8. The method for predicting early RUL of lithium batteries based on transfer learning and unscented particle filter (UPF) fusion model according to claim 6, characterized in that: In step 3.2, the parameters of the double exponential capacity decay model are , the UPF algorithm specifically includes the following steps: Step 3.21: Initialize UPF related parameters: initial value of state vector, initial covariance matrix, number of particles N; Step 3.22: Importance sampling phase: Use the UKF algorithm combined with the state space equation to calculate the state and observation distribution of each particle; Step 3.23: Weight correction: Calculate the weight update factor of each particle and normalize the particle weight so that the weight sum is 1. ; Step 3.24: Resampling: Resampling according to particle weight; Step 3.25: Estimate output: Use the updated particles and weights to get an estimate of the system state; Step 3.26: Repeat steps 3.21 to 3.25 until the prediction starting point T is reached; Step 3.27: Output the parameters of the double exponential capacity decay model .

Images