Life Prediction Of Lithium-ion Batteries Research Articles

Remaining Useful Life Prediction of Lithium-Ion Batteries: A Temporal and Differential Guided Dual Attention Neural Network

Remaining Useful Life Prediction of Lithium-Ion Batteries: A Temporal and Differential Guided Dual Attention Neural Network

Accurate capacity and remaining useful life prediction of lithium-ion batteries based on improved particle swarm optimization and particle filter

Accurate prediction of capacity and remaining useful life (RUL) for lithium-ion batteries (LIBs) is crucial for ensuring safe and reliable operation of electric vehicles. However, the battery capacity degradation and external environmental disturbances make it still challenging to achieve this goal. In this article, an accurate capacity and RUL prediction method is proposed by combining improved particle swarm optimization (IPSO) with particle filter (PF) algorithms. First, the parameters of particle swarm optimization (PSO) algorithm are adjusted by adaptive weights to avoid the problem of local optimal solution. Subsequently, the optimal particle searched by IPSO is updated continuously by the PF algorithm to achieve a more accurate posterior estimation. Finally, the proposed IPSO-PF method is verified by two independent and public datasets of NASA and CALCE batteries. The results validate that the proposed method has high precision and generalizability in predicting the capacity and RUL of LIBs even at various charging rates and battery types.

AttMoE: Attention with Mixture of Experts for remaining useful life prediction of lithium-ion batteries

For Lithium-ion (Li-ion) batteries, problems such as material aging and capacity decay lead to battery performance degradation or even catastrophic events. Predicting Remaining Useful Life (RUL) is an effective way to indicate the health of Li-ion batteries, which helps to improve the reliability and safety of battery-powered systems. We propose a novel neural network, AttMoE, which combines an attention mechanism with Mixture of Experts (MoE), to capture the capacity fade trend for battery RUL prediction. When facing the problem that raw data collected from sensors are always full of noise, AttMoE uses a dropout mask to denoise the raw data. For RUL prediction, one key idea is that the attention mechanism captures the long-term dependencies between elements in a sequence and more attention is paid to the important features that contain more degradation information; another key idea is that MoE uses many experts to increase model capacity to achieve better representations. Finally, we conducted experiments using two public data sets to show that AttMoE is effective in RUL prediction and achieves up to 10%–20% improvement in terms of Relative Error (RE). Our projects are all open source and are available at https://github.com/XiuzeZhou/RUL.

A hybrid deep learning approach for remaining useful life prediction of lithium-ion batteries based on discharging fragments

Accurate remaining useful life (RUL) estimation is crucial for the normal and safe operations of lithium-ion batteries (LIBs). Traditionally, every cycle’s maximum discharging capacity should be measured and then serve as a model input to predict iteratively the degradation trajectory. Unfortunately, full discharge stages are not always present in practice. Herein, this study presents a hybrid approach consisting of signal decomposition and deep learning to overcome the above limitations. Firstly, for the collected discharging fragments, the convolutional neural networks model predicts every cycle’s maximum discharging capacity which combines to form a predicted capacity degradation curve before the start point of RUL prediction. Then, via empirical mode decomposition, this curve’s global degradation trend is extracted and serves as the subsequent model input. Finally, the entire degradation trajectory and RUL value could be inferred based on the well-trained gated recurrent unit-fully connected model. The superior prediction performance of the proposed method is verified on two open battery datasets. All the estimation errors can be maintained within 7.0% based on the discharging fragment of the ∼20% capacity ratio ranges from 40% to 60% of the degradation data. This result illustrates the promising accuracy and robustness of the developed LIBs RUL estimation method, especially for not full discharge process in practice.

Cycle life and influencing factors of cathode materials for lithium-ion batteries--a case study of lithium-cobalt oxides

Abstract Lithium-cobalt oxide has become a new generation of highly promising anode materials for lithium-ion batteries due to its low price, environmental friendliness, high platform voltage, and high theoretical capacity. In this paper, the working characteristics and related parameters of lithium-ion batteries are sorted out, and the influence factors of the decline mechanism of lithium-ion batteries are investigated from the perspective of chemical composition. Regarding the cycle life of lithium-ion battery cathode materials, this paper establishes a cycle life prediction model for lithium-ion batteries based on the LSTM model. It optimizes the hyperparameters of the model using the PSO algorithm. In addition, this paper also prepared lithium cobalt oxide cathode materials and carried out a validation analysis of the factors affecting their electrochemical performance. It is found that the cycle life prediction of lithium-ion battery based on LSTM has an RMSE of 3.27%, and the capacity of lithium cobalt oxide soft pack full battery decays from 249.81mAh to 137.04mAh at 26°C. The cycle life of its lithium cobalt oxide lithium-ion battery is around 250 cycles, and the average decay is 0.445mAh during one charge/discharge. Different charge/discharge cycles and diversity will have a significant effect on the cycle life of lithium-ion battery cathode materials, and it is necessary to pay attention to the parameter changes in the preparation of lithium cobalt oxide cathode materials in order to increase the cycle life of lithium-ion batteries.

A MLP-Mixer and mixture of expert model for remaining useful life prediction of lithium-ion batteries

Accurately predicting the Remaining Useful Life (RUL) of lithium-ion batteries is crucial for battery management systems. Deep learning-based methods have been shown to be effective in predicting RUL by leveraging battery capacity time series data. However, the representation learning of features such as long-distance sequence dependencies and mutations in capacity time series still needs to be improved. To address this challenge, this paper proposes a novel deep learning model, the MLP-Mixer and Mixture of Expert (MMMe) model, for RUL prediction. The MMMe model leverages the Gated Recurrent Unit and Multi-Head Attention mechanism to encode the sequential data of battery capacity to capture the temporal features and a re-zero MLP-Mixer model to capture the high-level features. Additionally, we devise an ensemble predictor based on a Mixture-of-Experts (MoE) architecture to generate reliable RUL predictions. The experimental results on public datasets demonstrate that our proposed model significantly outperforms other existing methods, providing more reliable and precise RUL predictions while also accurately tracking the capacity degradation process. Our code and dataset are available at the website of github.

Remaining useful life prediction for lithium-ion batteries with an improved grey particle filter model

Accurate prediction of remaining useful life is of great value for the maintenance and replacement of electric vehicles lithium-ion batteries. This paper aims to present a grey particle filter model for improving remaining useful life forecast accuracy. Firstly, a grey particle filter model with recursive least square parameter estimation is built, and the proposed model’s parameters are trained. Secondly, RUL is predicted by using the parameters and proposed model. Finally, NASA lithium-ion battery open data set was used for verification. The model was evaluated from two perspectives of RUL accuracy and mean absolute percentage error. Predictions are also made for lithium-ion batteries under conditions of elevated temperature. The findings demonstrate that the proposed model outperforms the other models.

Transfer learning based remaining useful life prediction of lithium-ion battery considering capacity regeneration phenomenon

Lithium-ion battery (LIB) has been widely used in various energy storage systems, and the accurate remaining useful life (RUL) prediction for LIB is critical to ensure the normal operation of system. However, the capacity regeneration (CR) phenomenon caused by the non-working state of LIB will seriously affect the capacity degradation trajectory of LIB, thus leading to an inaccurate RUL prediction result. To solve this problem, this paper proposes a non-parametric CR detection algorithm to detect the CR phenomenon online and quantitatively correct the prediction errors caused by different CR phenomena. In addition, a data reconstruction algorithm and a parameter update scheme are proposed to solve the problem of unit-to-unit difference among LIBs. Finally, the long and short term memory neural network-based transfer learning model is applied to predict the RUL of target LIB. The effectiveness of the proposed model is verified by the real LIB dataset of NASA. Compared with some existing RUL prediction models considering CR phenomenon, the proposed model exhibits higher accuracy and better universality.

Remaining Useful Life Prediction of Lithium-Ion Battery Based on Adaptive Fractional Lévy Stable Motion with Capacity Regeneration and Random Fluctuation Phenomenon

The capacity regeneration phenomenon is often overlooked in terms of prediction of the remaining useful life (RUL) of LIBs for acceptable fitting between real and predicted results. In this study, we suggest a novel method for quantitative estimation of the associated uncertainty with the RUL, which is based on adaptive fractional Lévy stable motion (AfLSM) and integrated with the Mellin–Stieltjes transform and Monte Carlo simulation. The proposed degradation model exhibits flexibility for capturing long-range dependence, has a non-Gaussian distribution, and accurately describes heavy-tailed properties. Additionally, the nonlinear drift coefficients of the model can be adaptively updated on the basis of the degradation trajectory. The performance of the proposed RUL prediction model was verified by using the University of Maryland CALEC dataset. Our forecasting results demonstrate the high accuracy of the method and its superiority over other state-of-the-art methods.

Remaining useful life prediction for lithium-ion batteries based on sliding window technique and Box-Cox transformation

Accurate remaining useful life (RUL) prediction technique matters in lithium-ion battery use, optimization, and replacement. This article presents an RUL prediction method combining the sliding window (SW) technique and Box-Cox transformation (BCT). This method achieves online RUL prediction with acceptable accuracy, is independent of offline training data, and only brings a low computational burden. The SW technique is employed for gathering a certain amount of capacity data, which is subsequently transformed using BCT-related techniques to construct a capacity degradation model. The identified model is then extrapolated to predict battery RUL, and the prediction uncertainties are calculated through Monte Carlo (MC) simulation. A simple implementation shows that this hybrid method outperforms the history-based polynomial and BCT methods in battery RUL prediction. Given the segmented capacity degradation trend, a constraint can be imposed on the model parameter for optimization purposes. Experimental results demonstrate that the optimized method obtains lower root-mean-square errors (RMSEs) of RUL predictions during the last 20 % of the battery lifetime than the original one, and the precise RULs are predicted with standard deviations mainly within [1, 10] cycles.

Capacity and remaining useful life prediction for lithium-ion batteries based on sequence decomposition and a deep-learning network

Capacity and remaining useful life prediction for lithium-ion batteries based on sequence decomposition and a deep-learning network

Remaining Useful Life Prediction of Lithium-ion Batteries Based on Optimized Prophet Model

In this paper, we propose an algorithm to optimize the Prophet model by combining the improved sparrow search algorithm. Firstly, the original Prophet model is theoretically analyzed and regression fitted in a realistic data set to verify the feasibility of the model for lithium-ion battery RUL prediction. Secondly, the parameters of the Prophet model are optimized by using the modified sparrow search algorithm to enhance its prediction accuracy. The simulation results show that the model proposed in this paper provides better performance in lithium-ion battery RUL prediction and outperforms the methods involved in this paper for comparison in terms of prediction accuracy.

Equivalent circuit simulated deep network architecture and transfer learning for remaining useful life prediction of lithium-ion batteries

Equivalent circuit simulated deep network architecture and transfer learning for remaining useful life prediction of lithium-ion batteries

A data reconstruction-based Monte Carlo method for remaining useful life prediction of lithium-ion battery with few historical samples

Lithium-ion battery (LIB) has been widely used in many energy storage systems, and the accurate remaining useful life (RUL) prediction of LIB is essential to ensure the safe operation of these systems. However, for the LIB installed in a new system, there are only few historical samples available for RUL prediction, which makes it difficult to build accurate RUL prediction model for LIB. Therefore, this paper proposes a data reconstruction-based Monte Carlo method to solve the problems caused by few historical samples. First, a Wiener process-based data reconstruction algorithm is used to reconstruct historical dataset, providing sufficient prior information for the Monte Carlo method. Then, Bayesian theory and a parameter update scheme are proposed to update the reconstructed dataset and the corresponding parameter distributions, so that the training data of RUL prediction model can be closer to the data of target LIB. Finally, long short-term memory neural network is applied for RUL prediction. The effectiveness of our model is verified by two real LIB datasets. Compared with some existing RUL prediction models of LIB, the proposed model has better generality and higher prediction accuracy under the condition of few historical samples.

A data-driven prediction model for the remaining useful life prediction of lithium-ion batteries

Accurate prediction of remaining useful life (RUL) can ensure the safety and reliability of power batteries during operation, reduce the failure rate and operating costs, and enhance user experience. However, battery degradation is a complex, nonlinear dynamic process that is difficult to fully comprehend and predicting RUL remains a significant challenge. To address this issue, the hybrid data-driven prediction model PCA-CNN-BiLSTM was proposed in this paper, which combines principal component analysis (PCA), convolutional neural network (CNN), and bi-directional long short-term memory (Bi-LSTM) network. PCA was applied to downscale and whiten the health factor (HF) to maximize the extraction of important features of lifespan decay, while reducing the correlation between features. The convolution kernel of the CNN was used to explore the local region feature information of the input information and search for the common patterns among the neighboring data. Additionally, the model parameters and computational efforts were reduced through pooling. Finally, battery RUL prediction was achieved using Bi-LSTM, which has the advantages of effectively enhancing model accuracy and reducing the risk of over-fitting by taking into account both past and future data. The performance of the proposed model was evaluated utilizing NASA and CALCE's battery datasets, and the results suggest that it exhibits a high level of accuracy across various datasets. Compared to other methods, the PCA-CNN-BiLSTM method has the best performance indicators for predicting battery RUL, including RMSE, MAE, MAPE, RULe and DOL. This indicates that the proposed model has better fitting performance, accuracy, robustness, and generalization ability.

Uncertainty quantification in machine learning for engineering design and health prognostics: A tutorial

On top of machine learning (ML) models, uncertainty quantification (UQ) functions as an essential layer of safety assurance that could lead to more principled decision making by enabling sound risk assessment and management. The safety and reliability improvement of ML models empowered by UQ has the potential to significantly facilitate the broad adoption of ML solutions in high-stakes decision settings, such as healthcare, manufacturing, and aviation, to name a few. In this tutorial, we aim to provide a holistic lens on emerging UQ methods for ML models with a particular focus on neural networks and the applications of these UQ methods in tackling engineering design as well as prognostics and health management problems. Towards this goal, we start with a comprehensive classification of uncertainty types, sources, and causes pertaining to UQ of ML models. Next, we provide a tutorial-style description of several state-of-the-art UQ methods: Gaussian process regression, Bayesian neural network, neural network ensemble, and deterministic UQ methods focusing on spectral-normalized neural Gaussian process. Established upon the mathematical formulations, we subsequently examine the soundness of these UQ methods quantitatively and qualitatively (by a toy regression example) to examine their strengths and shortcomings from different dimensions. Then, we review quantitative metrics commonly used to assess the quality of predictive uncertainty in classification and regression problems. Afterward, we discuss the increasingly important role of UQ of ML models in solving challenging problems in engineering design and health prognostics. Two case studies with source codes available on GitHub are used to demonstrate these UQ methods and compare their performance in the life prediction of lithium-ion batteries at the early stage (case study 1) and the remaining useful life prediction of turbofan engines (case study 2).

Remaining useful life prediction of lithium-ion batteries based on peak interval features and deep learning

Anticipating the lifespan of a lithium-ion battery is a challenging task due to the unstable external working conditions and complex internal response. To enhance the accuracy of the remaining usable life prediction of lithium-ion batteries, this study proposes a feature extraction method that relies on the peak value of the incremental capacity (IC) curve for a data-driven prediction approach. This method can significantly reduce the amount of data required for training the model. Furthermore, the grey correlation method (GCM) is employed to select features that have a high correlation with the target value, thereby further reducing the amount of data required for training the model. It is explored how well characteristics may be extracted from various peak intervals. The time series prediction-capable long short-term memory (LSTM) network is used to create the data-driven model. Finally, the experimental findings demonstrate that the proposed data-driven model's prediction error is smaller than 1.18 %. The proposed data-driven in this work is found to have a superior prediction impact on the same data set in different deep learning methods when compared to other data-driven approaches.

Remaining useful life prediction of lithium-ion batteries via an EIS based deep learning approach

Reliable life prediction technology is of great significance in ensuring a safe and efficient lifetime of lithium batteries. However, the traditional health factors such as battery capacity are the effects of battery aging rather than the direct causes, which cannot directly reflect the internal degradation mechanism information of the battery, and the prediction accuracy is easily affected by the working environment of the battery. Electrochemical impedance spectroscopy (EIS) data can more directly reflect the internal mechanism information of the battery, which includes a wealth of battery aging information. In order to deeply investigate the mapping relationship between impedance spectrum and remaining useful life (RUL) of lithium batteries, EIS method is employed to obtain the impedance and phase of lithium batteries under different health states and temperatures, as well as explore the visualization and quantification of impedance frequency response of lithium battery. Furthermore, the mapping relationship between RUL and the lithium battery impedance is investigated in a full impedance spectrum at different temperatures. It is found that, as lithium battery aging, its negative imaginary parts impedance increases significantly, especially in the middle of the frequency band, and has no significant dependence on temperature. While the real part impedance shows an obvious dependence on temperature. Therefore, it is found that the negative imaginary parts impedance of impedance spectrum has a well-fit characterization ability for RUL of a lithium battery. In this paper, a fusion neural network model of Conv1d-SAM (one-dimensional convolutional neural network-self-attention mechanism) was established with negative imaginary part impedance as input factor to predict battery RUL. The predicted results show that Conv1d-SAM has improved accuracy and stability in RUL prediction, and the mean absolute error function of the proposed model is increased by 72% compared with the latest published method.

Remaining Useful Life Prediction of Lithium-Ion Battery Using ICC-CNN-LSTM Methodology

In recent years, lithium-ion batteries have gained significant attention due to their crucial role in various applications, such as electric vehicles and renewable energy storage. Accurate prediction of the remaining useful life (RUL) of these batteries is essential for optimizing their performance and ensuring reliable operation. In this paper, we propose a novel methodology for RUL prediction using an individual control chart (ICC) to identify and remove degraded data, a convolutional neural network (CNN) to smooth the noise of sensor data and long short-term memory (LSTM) networks to effectively capture both spatial and temporal dependencies within battery data, enabling accurate RUL estimation. We evaluate our proposed model using a comprehensive dataset, and experimental results demonstrate its superior performance compared to existing methods. Our findings highlight the potential of ICC-CNN-LSTM for RUL prediction in lithium-ion batteries and provide valuable insights for future research.

Optimized data-driven approach for remaining useful life prediction of Lithium-ion batteries based on sliding window and systematic sampling

The prediction of remaining useful life (RUL) in lithium-ion batteries (LIB) serves as a critical health index for evaluating battery parameters, including efficiency, robustness, and accuracy. Existing RUL prediction techniques encounter challenges related to data extraction based on battery parameters and data samples, as well as the selection of appropriate model hyperparameters to achieve accurate outcomes. To address these issues, this article presents a novel framework for RUL prediction using a hybrid optimized data-driven approach, which combines a cascaded forward neural network (CFNN) with the innovative jellyfish optimization (JFO) technique. Initially, a comprehensive 46-data feature-based framework is developed for training the proposed hybrid JFO-CFNN model, employing a mathematical systematic sampling (SS) method. The SS method facilitates the selection of 15 relevant data features, from the LIB parameters such as temperature, current, and voltage, from each charging cycle. Additionally, the developed framework mitigates the capacity regeneration effect present with the capacity degradation profile by employing the overlapping sliding window (OSW) technique. Moreover, the CFNN model parameters, such as hidden neurons and learning rate, are optimized using the newly introduced meta-heuristic JFO technique. To validate the performance of the proposed hybrid JFO-CFNN model, comparisons are made with other models such as the JFO-optimized artificial neural network (ANN) and deep neural network (DNN) model as well as with another battery dataset obtained from the Massachusetts Institute of Technology (MIT) Stanford battery database. The outcomes based on the NASA battery suggested the average RMSE of the proposed JFO-CFNN model below 0.1 and 0.15 for NASA and MIT Stanford battery datasets. The experimental results demonstrate the high prediction accuracy and applicability of the proposed hybrid JFO-CFNN model.