Proceedings ArticleDOI
Lithium-Ion Battery Remaining Useful Life Prediction Based on GRU-RNN
TLDR
A battery RUL prediction approach based on a new recurrent neural network (RNN), i.e. the RNN with Gated Recurrent Unit (GRU) is proposed which overcomes the drawback on dealing with long term relationship of RNN.Abstract:
Lithium-ion battery has been widely applied as an energy storage component in various industrial applications including electric vehicles, distributed grids and space crafts. However, the battery performance degrades gradually due to the SEI growth, li-plating and other irreversible electro-chemical reactions. These inevitable reactions directly influence the reliability of the energy storage system and may further cause catastrophic consequences to the host system. Remaining useful life (RUL) is one of critical indicators to evaluate the battery performance. This paper proposes a battery RUL prediction approach based on a new recurrent neural network (RNN), i.e. the RNN with Gated Recurrent Unit (GRU). The proposed method overcomes the drawback on dealing with long term relationship of RNN. The structure of the RNN-GRU is much simpler which contributes to a higher computational complexity. The experiments based on the NMC lithium-ion battery cycle life testing data are conducted and the results indicate that the mean error of different battery cells are both less than 3% which means the proposed method is accurate and robust for battery RUL predictions.read more
Citations
More filters
Journal ArticleDOI
LSTM-Based Battery Remaining Useful Life Prediction With Multi-Channel Charging Profiles
TL;DR: Novel RUL prediction techniques based on long short-term memory (LSTM) to estimate RUL even in the presence of capacity regeneration phenomenon, which considers multiple measurable data from battery management system such as voltage, current and temperature charging profiles whose patterns vary as aging.
Journal ArticleDOI
Remaining Useful Life Prediction Using a Novel Feature-Attention-Based End-to-End Approach
TL;DR: A novel feature-attention-based end-to-end approach for RUL prediction that gives greater attention weights to more important features dynamically in the training process and outperforms other latest existing approaches.
Journal ArticleDOI
Prognostics and health management of Lithium-ion battery using deep learning methods: A review
Yong Zhang,Yan-fu Li +1 more
TL;DR: In this paper , the authors provide a comprehensive view of deep learning-based PHM of Li-ion battery, and provide a conclusion and presents the prospects of PHM with deep learning techniques, including deep belief network, convolutional neural network, recurrent neural network and generative adversarial network.
Journal ArticleDOI
Transformer Network for Remaining Useful Life Prediction of Lithium-Ion Batteries
TL;DR: A Transformer-based neural network is designed that combines denoising and prediction tasks into a unified framework for predicting Remaining Useful Life (RUL) of a Li-ion battery.
Journal ArticleDOI
Recent advances and trends of predictive maintenance from data-driven machine prognostics perspective
TL;DR: In this article, an extensive review of recent advances and trends of data-driven machine prognostics, with a focus on their applications in practice, is presented, and a discussion on the challenges, opportunities, and future trends of predictive maintenance is presented.
References
More filters
Journal ArticleDOI
A review on lithium-ion battery ageing mechanisms and estimations for automotive applications
Anthony Barré,Benjamin Deguilhem,Sebastien Grolleau,Mathias Gerard,Frédéric Suard,Delphine Riu +5 more
TL;DR: In this paper, the authors present a summary of techniques, models, and algorithms used for battery ageing estimation, going from a detailed electrochemical approach to statistical methods based on data, and their respective characteristics are discussed.