哈尔滨工业大学（深圳）学术讲座

演讲人Speaker：刘凯龙教授

题目Title: 基于可解释性数据科学技术的电池智能管控

时间Date：2023年11月23日      Time：上午 10:30~11:30

地点Venue： A 栋 505  室  

内容摘要Abstract：

Lithium-ion batteries have become one of the most promising sources for accelerating the development of transportation electrification, where effective electrode manufacturing plays a key role in determining battery performance. Due to the highly complicated process and strongly coupled interdependencies of electrode production, a data-science solution that can analyze feature variables within the manufacturing chain and achieve reliable prediction is urgently needed. This work proposes two feasible data-science solutions, through using interpretable machine learning techniques, for effectively quantifying the importance and correlations of battery manufacturing features and their effects on the predictions of electrode properties. Illustrative results demonstrate that the proposed data-science frameworks not only achieve reliable predictions of electrode properties but also leads to the effective quantification of both manufacturing feature importance and correlations. This is the first time to design the systematic data-driven frameworks for directly quantifying battery production feature importance and correlations by various evaluation criteria, paving a promising solution to reduce model dimension and conduct efficient sensitivity analysis of battery manufacturing.

个人简介(About the speaker):

刘凯龙，山东大学教授、博导，科睿唯安全球高被引科学家、IEEE高级会员。长期从事电池与储能系统建模、管理、控制研究。第一或通讯作者发表一区论文50余篇，出版专著4部，授权国内外发明专利10项。获英国未来领袖基金提名（160万英镑），主持国自然面上基金、英国Innovate UK项目并结题优秀。排一获IEEE TIE、CEP等国际期刊/会议最佳论文奖6项；获中国仿真学会自然科学一等奖1项。成果应用于Varta Storage、阿斯顿马丁、UKBIC等龙头企业。任IEEE TIE、IEEE TTE、RSER期刊副编辑，IEEE/CAA JAS、APEN、CEP期刊首届青年编委。