Early-stage lifetime prediction for lithium-ion batteries: A deep learning framework jointly considering machine-learned and handcrafted data features. (15th August 2022)

• Record Type: Journal Article
• Authors: Fei, Zicheng; Zhang, Zijun; Yang, Fangfang; Tsui, Kwok-Leung; Li, Lishuai
• Is Part Of: Journal of energy storage. Volume 52:Part B(2022)
• Publication Date: 2022-08-15
• Subjects: Lithium-ion battery -- Lifetime prediction -- Early stage -- Health feature extraction -- Convolutional neural networks -- Data-driven models; Energy storage -- Periodicals; Energy storage -- Research -- Periodicals; 621.3126
• DOI: 10.1016/j.est.2022.104936
• Languages: English
• ISSNs: 2352-152X

Abstract

Abstract: Predicting the battery lifetime at its early stage is a promising technology for accelerating the battery development, production, and design optimization. However, it is a challenging task for most existing prediction methods because information is too limited in early life cycles, and the early-cycle capacity data exhibits a weak correlation with the target battery lifetime. In this paper, to realize an accurate battery lifetime prediction via data obtained from just first few life cycles, we propose a three-stage deep learning framework. First, we develop an emerging two-channel data feature engineering process, which jointly consider a convolutional neural network based latent feature extraction and domain knowledge based handcrafted features. Next, a wrapper feature selection method is adopted to further compress the dimension of developed features via eliminating linearly correlated ones. Finally, processed data features are fed into a data-driven model to realize the early-stage battery lifetime prediction. Results of computational experiments show that our proposed joint consideration of machine-learned features and handcrafted features can improve early-stage battery lifetime predictions via comparing with state-of-the-art benchmarks. We also show that the proposed framework can be generalized to batteries cycled under different operation conditions. Highlights: Data-driven prediction of the battery lifetime at its early stage is studied A three-stage deep learning based modeling framework is developed A novel input structure and battery data feature engineering paradigm is presented Accurate early stage battery lifetime prediction performance is realized