Deep learning enhanced lithium-ion battery nonlinear fading prognosis  

作　　者：Shanling Ji Jianxiong Zhu Zhiyang Lyu Heze You Yifan Zhou Liudong Gu Jinqing Qu Zhijie Xia Zhisheng Zhang Haifeng Dai 

机构地区：[1]School of Mechanical Engineering,Southeast University,Nanjing 211189,Jiangsu,China [2]Guangdong Provincial Key Lab of Green Chemical Product Technology,South China University of Technology,Guangzhou 510006,Guangdong,China [3]Engineering Research Center of New Light Sources Technology and Equipment,Ministry of Education,Nanjing 211189,Jiangsu,China [4]Clean Energy Automotive Engineering Center,School of Automotive Engineering,Tongji University,Shanghai 201804,China [5]School of Mathematics,Southeast University,Nanjing 211189,Jiangsu,China

出　　处：《Journal of Energy Chemistry》2023年第3期565-573,I0015,共10页能源化学（英文版）

基　　金：supported by the financial support from the National Key Research and Development Program of China(2022YFB3807200);the Fundamental Research Funds for the Central Universities(2242022K330047);the dual creative talents from Jiangsu Province(JSSCBS20210152,JSSCBS20210100);the National Natural Science Foundation of Jiangsu Province(BK20221456,BK20200375);the Natural Science Foundation of China with(22109021);the Research Fund Program of Guangdong Provincial Key Lab of Green Chemical Product Technology(6802008024)。

摘　　要：With the assistance of artificial intelligence,advanced health prognosis technique plays a critical role in the lithium-ion(Li-ion) batteries management system.However,conventional data-driven early aging prediction exhibited dramatic drawbacks,i.e.,volatile capacity nonlinear fading trajectories create obstacles to the accurate multistep ahead prediction due to the complex working conditions of batteries.Herein,a novel deep learning model is proposed to achieve a universal and accurate Li-ion battery aging prognosis.Two battery datasets with various electrode types and cycling conditions are developed to validate the proposed approaches.Knee-point probability(KPP),extracted from the capacity loss curve,is first proposed to detect knee points and improve state-of-health(SOH) predictive accuracy,especially during periods of rapid capacity decline.Using one-cycle data of partial raw voltage as the model input,the SOH and KPP can be simultaneously predicted at multistep ahead,whereas the conventional method showed worse accuracy.Furthermore,to explore the underlying characteristics among various degradation tendencies,an online model update strategy is developed by leveraging the adversarial adaptationinduced transfer learning technique.This work gains new sights into the comprehensive Li-ion battery management and prognosis framework through decomposing capacity degradation trajectories and adversarial learning on the unlabeled samples.

关 键 词：Battery aging prognosis Deep learning Knee-point probability Sate-of-health 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TM912[自动化与计算机技术—控制科学与工程]