Article
Thermodynamics
Lisen Yan, Jun Peng, Dianzhu Gao, Yue Wu, Yongjie Liu, Heng Li, Weirong Liu, Zhiwu Huang
Summary: This paper proposes a hybrid framework combining a model-based method and a data-driven method for accurately predicting the remaining useful life of lithium-ion batteries. The method improves prediction accuracy by dynamically updating parameters with particle filters and optimizing the performance of the support vector regression model using an artificial bee colony algorithm. Experimental results demonstrate the effectiveness of the proposed method, particularly in the early stage.
Article
Computer Science, Artificial Intelligence
Wei Guo, Mao He
Summary: Predicting the remaining useful life (RUL) of lithium-ion batteries (LIBs) is crucial for ensuring the safety and reliability of battery-powered systems. This paper proposes an integrated RUL prediction method based on optimal relevance vectors (RVs) and a modified degradation model (MDM) with the Hausdorff distance (HD), which improves the accuracy of long-term predictions.
APPLIED SOFT COMPUTING
(2022)
Article
Energy & Fuels
Tiezhou Wu, Tong Zhao, Siyun Xu
Summary: This article introduces an improved particle filter algorithm to enhance the accuracy of remaining useful life (RUL) prediction for lithium-ion batteries. The algorithm re-weights the particles using the unscented Kalman algorithm. Simulation and verification on battery sample data demonstrate that the improved algorithm provides more accurate RUL prediction results.
FRONTIERS IN ENERGY RESEARCH
(2022)
Article
Thermodynamics
Qiuhui Ma, Ying Zheng, Weidong Yang, Yong Zhang, Hong Zhang
Summary: This study combines particle filter and Mann-Whitney U test to detect the capacity regeneration point of lithium batteries, using autoregressive model and PF algorithm for RUL prediction. The method is validated through experiments, showing improved prediction accuracy and reduced error rate.
Article
Chemistry, Analytical
Sadiqa Jafari, Yung-Cheol Byun
Summary: The instability and variable lifetime of lithium-ion batteries contribute to their benefits in terms of high efficiency and low-cost issues. Accurate prediction of the remaining useful life of these batteries is crucial for requirement-based maintenance and cost reduction. However, assessing the working capacity of a battery is challenging, and existing prediction methods fail to account for uncertainty. This paper presents a novel prediction technique combining particle filters with extreme gradient boosting for lithium-ion battery RUL estimation, which demonstrates improved accuracy compared to other methods.
Article
Thermodynamics
Fang Yao, Wenxuan He, Youxi Wu, Fei Ding, Defang Meng
Summary: This paper proposes a hybrid prediction model PSO-ELM-RVM for accurately predicting the remaining useful life (RUL) of lithium-ion batteries. The model integrates particle swarm optimization (PSO), an extreme learning machine (ELM), and relevance vector machine (RVM) to provide prediction results with uncertainty expression. Experimental results validate the effectiveness of the proposed model.
Article
Engineering, Multidisciplinary
Mo'ath El-Dalahmeh, Maher Al -Greer, Ma'd El-Dalahmeh, Imran Bashir
Summary: This work proposes a physics-informed smooth particle filter (SPF) framework for accurately predicting the remaining useful life (RUL) of lithium-ion batteries. The framework utilizes a single particle model (SPM) to estimate degradation parameters and quantifies degradation mechanisms for more accurate RUL predictions. It is demonstrated to be dependable and robust, even in the presence of noise and dynamic discharging profiles.
Article
Energy & Fuels
Hailin Feng, Dandan Song
Summary: In this paper, a new health indicator (HI) is proposed to predict the remaining useful life (RUL) of lithium-ion batteries from the discharge surface temperature, which is convenient for real-time measurement and online estimation. The results show that the new HI is effective for degradation modeling, with a RUL prediction error of less than 5 cycles for 5#, 6# and 7# batteries.
JOURNAL OF ENERGY STORAGE
(2021)
Article
Thermodynamics
Lin Chen, Yunhui Ding, Bohao Liu, Shuxiao Wu, Yaodong Wang, Haihong Pan
Summary: This paper proposes a method that combines grey model and neural network for predicting the remaining useful life of lithium-ion batteries. The method is able to accurately predict with limited data and has strong practicality and universality.
Review
Energy & Fuels
Liyuan Shao, Yong Zhang, Xiujuan Zheng, Xin He, Yufeng Zheng, Zhiwei Liu
Summary: This paper reviews the progress of domestic and international research on RUL prediction methods for energy storage components, with a focus on lithium-ion batteries. The failure mechanism of energy storage components is clarified, and RUL prediction methods are summarized. The application of data-model fusion-based methods to RUL prediction of lithium-ion batteries is discussed, along with the challenges and future research outlook.
Article
Energy & Fuels
Jing-Song Qiu, Yong-Cun Fan, Shun-Li Wang, Xiao Yang, Jia-Lu Qiao, Dong-Lei Liu
Summary: An improved multi-kernel relevance vector machine model is proposed for predicting the remaining useful life of lithium-ion batteries, utilizing aging features extracted through gray relation analysis and kernel function combination coefficients determined by an improved gray wolf constrained optimization algorithm. The model shows higher prediction accuracy and more robust long-term prediction capability compared to other models.
INTERNATIONAL JOURNAL OF ENERGY RESEARCH
(2022)
Article
Energy & Fuels
Joonchul Kim, Eunsong Kim, Jung-Hwan Park, Kyoung-Tak Kim, Joung-Hu Park, Taesic Kim, Kyoungmin Min
Summary: This study investigated the impact of data partitioning methods on predicting the remaining useful life (RUL) of batteries. Results showed that the method of adding predicted data from a surrogate model to the training set had the highest accuracy, with an average mean absolute error (MAE) of 47 cycles. In contrast, the slide BOX method, which used only certain cycles before the test set as the training set, had the worst MAE value of 60 cycles. Therefore, this data partitioning method can be implemented to predict the RUL of batteries and aid in the development of next-generation cathode materials with improved performance and stability, as well as achieve reliable predictive maintenance.
INTERNATIONAL JOURNAL OF ENERGY RESEARCH
(2023)
Article
Computer Science, Artificial Intelligence
Liming Deng, Wenjing Shen, Hongfei Wang, Shuqiang Wang
Summary: This paper introduces a novel empirical model for predicting the remaining useful life of lithium-ion batteries by modeling both global and local degradation processes. The model outperforms state-of-the-art methods in capturing degradation and regeneration phenomena.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Ivan Sanz-Gorrachategui, Pablo Pastor-Flores, Milutin Pajovic, Ye Wang, Philip Orlik, Carlos Bernal-Ruiz, Antonio Bono-Nuez, Jesus Sergio Artal-Sevil
Summary: This article explores the estimation of battery remaining useful life (RUL) and proposes health indicators and effective estimation algorithms. The algorithms show satisfactory results on a recent dataset from Toyota Research Institute.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Energy & Fuels
Yeong-Hwa Chang, Yu-Chen Hsieh, Yu-Hsiang Chai, Hung-Wei Lin
Summary: This paper aims to establish a predictive model for battery lifetime using data analysis. The procedure of model establishment is illustrated in detail, including the data pre-processing, modeling, and prediction. The characteristics of lithium-ion batteries are introduced. In this study, data analysis is performed with MATLAB, and the open-source battery data are provided by NASA. The addressed models include the decision tree, nonlinear autoregression, recurrent neural network, and long short-term memory network. In the part of model training, the root-mean-square error, integral of the squared error, and integral of the absolute error are considered for the cost functions. Based on the defined health indicator, the remaining useful life of lithium-ion batteries can be predicted. The confidence interval can be used to describe the level of confidence for each prediction. According to the test results, the long short-term memory network provides the best performance among all addressed models.