Lithium battery digital twin model with incremental learning

作     者：Xinyu Wang Junfu Li Runze Wang Yi Wu 

作者机构：School of Automotive EngineeringHarbin Institute of TechnologyWeihaiShandong 264209China College of Automation and College of Artificial IntelligenceNanjing University of Posts and TelecommunicationsNanjing 210023China 

出 版 物：《Chain》 (链(英文))

年 卷 期：2024年第1卷第3期

页      面：249-262页

学科分类：0808[工学-电气工程] 08[工学] 

基　　金：the Shandong Province National Natural Science Foundation of China(No.ZR2023QE036) the Natural Science Foundation of Jiangsu Province(No.BK20210600)for their financial support 

主　　题：lithium battery digital twin incremental learning mechanism-data model full life cycle 

摘      要：Digital twin technology used to realize the interactive mapping between digital model and physical entity in virtual space plays a crucial role in promoting the transformation of battery management to digitalization and *** key to achieving a digital twin is developing a virtual model that can accurately reflect the physical ***,the intricate time-varying and nonlinear reaction characteristics within the battery often pose challenges in simulating complex operational conditions and maintaining high accuracy throughout the full life *** learning algorithms are suitable for online streaming data processing and can adapt to concept drift of the data stream by receiving new data online without retraining the entire model from *** paper employs a simplified electrochemical model of the battery and integrates an Aggregated Mondrian Forest with incremental learning capabilities to con­struct a hybrid mechanism-data battery *** developed hybrid model can acquire battery data and train in real time during battery operation to realize co-evolution with the physical battery to ensure the voltage prediction accuracy during the full life cycle of the battery.