A lithium-ion battery remaining useful life prediction method based on the incremental capacity analysis and Gaussian process regression. (December 2021)

• Record Type: Journal Article
• Authors: Pang, Xiaoqiong; Liu, Xiaoyan; Jia, Jianfang; Wen, Jie; Shi, Yuanhao; Zeng, Jianchao; Zhao, Zhen
• Is Part Of: Microelectronics and reliability. Volume 127(2021)
• Publication Date: 2021-12
• Subjects: Lithium-ion batteries -- Remaining useful life -- Incremental capacity curve -- Gaussian process regression; Electronic apparatus and appliances -- Reliability -- Periodicals; Miniature electronic equipment -- Periodicals; Appareils électroniques -- Fiabilité -- Périodiques; Équipement électronique miniaturisé -- Périodiques; Electronic apparatus and appliances -- Reliability; Miniature electronic equipment; Periodicals; 621.3815
• DOI: 10.1016/j.microrel.2021.114405
• Languages: English
• ISSNs: 0026-2714

Abstract

Abstract: Remaining useful life (RUL) is a critical metric of lithium-ion battery prognostic and health management. Accurate prediction of RUL is of great significance to the safety and reliability of lithium-ion batteries, which is able to provide useful reference information for maintenance. In this work, a novel method fusing the incremental capacity analysis (ICA) and Gaussian process regression (GPR) for RUL prediction of lithium-ion batteries is proposed. Firstly, the IC curve, which has higher sensitivity than the traditional charge/discharge curve, is used to analyze the performance degradation process of the lithium-ion battery. Then the peak value of the IC curve and the regional area under the peak value of the IC curve are extracted as health indicators (HIs). Secondly, the RUL prediction framework of lithium-ion batteries based on ICA and GPR is established, and the uncertainty expression of the prediction results is given. Finally, the experimental results show that the HIs extracted in this paper can effectively reflect the degradation state of the battery, and the proposed method has high accuracy in predicting RUL. Highlights: A novel fusion method based on ICA and GPR is proposed to predict the RUL of battery. The IC curve of discharge process is used to extract health indicators. Qualitative and quantitative analysis of health indicators is made. Four batteries are used to verify the effectiveness of the proposed method.