Can I read Capacity and Remaining Useful Life Prediction for Lithium-ion Batteries Based on Sequence Decomposition and a Deep-learning Network on EtoBox?

Capacity and Remaining Useful Life Prediction for Lithium-ion Batteries Based on Sequence Decomposition and a Deep-learning Network by Zili Wang; Yonglu Liu; Fen Wang; Hui Wang; Mei Su is a scholarly article available to read on EtoBox.

What is Capacity and Remaining Useful Life Prediction for Lithium-ion Batteries Based on Sequence Decomposition and a Deep-learning Network about?

Lithium-ion batteries' remaining useful life (RUL) prediction is important for battery management systems, which are essential for ensuring the optimum performance and longevity of batteries used in different industries. However, accurate RUL prediction is challenging due to the complex degradation mechanism of the battery and actual noise operation conditions, particularly the capacity regeneration noise. To address this issue, this paper proposes a new method which combines a deep learning network with a sequence decomposition algorithm. Firstly, complementary ensemble empirical mode decomposition with adaptive noise algorithm is used to decompose the capacity fading sequence into a long-term residual and short-term fluctuations. This reduces the interference of the capacity regeneration phenomenon. Then, Transformer-based network is established to realize prediction for the separate components. This network architecture can handle the long-range dependency of the sequential data through its multi-head attention mechanism. The proposed method is validated through extensive experimentation using two publicly accessible battery datasets. The results show that the proposed method ca

Author

Zili Wang; Yonglu Liu; Fen Wang; Hui Wang; Mei Su

Publisher

Elsevier BV

Published

2023

Language

EN