Stochastic dynamic modeling of lithium battery via expectation maximization algorithm

详细信息    查看全文

• 作者：Wu Wang^a ; ^b ; ^{wangwu@fzu.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Xiaocheng Liu^a ; ^bAuthor Vitae ; Fenghuang Cai^a ; ^bAuthor Vitae ; Jianming Wang^a ; ^bAuthor Vitae
• 关键词：Lithium battery ; Data-driven approach ; Expectation maximization algorithm ; Stochastic dynamic model
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：29 January 2016
• 年：2016
• 卷：175
• 期：part_PA
• 页码：421-426
• 全文大小：824 K

文摘

Lithium battery is a reliable source for mobile, computers and electric vehicles. However, the internal chemical reaction of lithium battery is complex and susceptible to external influences, such that the traditional model-driven approach cannot model it accurately. In this paper, based on the data-driven approach, an expectation maximization algorithm is proposed to model a class of lithium battery. By using the expectation maximization algorithm, the model parameters and actual values of test, as well as the noise intensity can be identified simultaneously. The NASA battery data sets are employed to demonstrate the effectiveness of the proposed algorithm. Several indices are presented to evaluate the inferred lithium battery models.