Young Scholar Forum



 


Title: 基于可解释性数据科学技术的电池智能制造

Panelist: Kailong Liu

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.

Personal Profile刘凯龙,山东大学教授、博士生导师,国家四青人才、英国未来领袖学者、IEEE高级会员。长期从事电池与储能系统建模、管理、控制研究。以第一/通讯作者发表SCI一区论文40余篇,其中ESI高被引论文20篇、热点论文6篇,出版专著4部,第一发明人授权国内外发明专利5项。主持国自然面上基金、Innovate UK、HVM Catapult等英国科研项目并结题优秀,获英国未来领袖基金提名(160万英镑)。以第一作者获IEEE TIE、Springer LSMS 2021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。成果应用于德国储能龙头企业Varta Storage、英国汽车龙头企业阿斯顿马丁、英国最大电池制造中心UKBIC等,并受到英国科技部重点关注。担任IEEE Trans. on Transportation Electrification、IEEE/CAA Journal of Automatica Sinica、Renewable and Sustainable Energy Reviews、Applied Energy、Control Engineering Practice等自动化或能源应用SCI Top国际期刊编委,担任 Energy、IJEPES、IEEE JESTPE 等期刊客座编辑。


****************************************************************************************************************************************************************

 

Title: Modeling and state estimation of Lithium-ion batteries based on fractional calculus

Panelist: Liping Chen

Abstract: State of Charge (SOC) estimation is one of the most basic and core functions in battery management system. The accuracy of SOC values affects the drive performance, battery life and safety performance of electric vehicles. How to accurately characterize the physical dynamic process of lithium batteries and establish a high-precision SOC estimation algorithm is the focus of current research. In recent years, many studies have shown that fractional calculus has great advantages in describing the dynamic characteristics of lithium-ion batteries, and the research on equivalent circuit modeling and state estimation of lithium batteries based on fractional microproduct method has received more attention. This report will introduce the lithium-ion equivalent circuit modeling and charge state estimation method based on fractional calculus theory, and discuss the application of fractional calculus in energy storage system.

Personal ProfileChen Liping, Professor. His research interests include modeling, analysis and control of complex systems, energy management of energy storage systems, digital twins and machine learning. He has presided over more than 10 projects including National Natural Science Foundation of China, Anhui Provincial Key Research and Development Program. He is a reviewer of AMS (No. 120446), a reviewer of zbMATH (No.18830), a member of the Chinese Society of Automation Fractional Systems and Control Committee, a member of the Chinese Society of Automation Vehicle Control and Intelligence Committee, and a member of the Computer Society Industrial Control Computer Committee. He is serviced as Associate editor of SCI Journal of Nonlinear, Complex and Data Science, Associate Editor of International Journal of Dynamics and Control, Editorial Board of Journal of Machine Design and Automation Intelligence. He is a member of the 2017CAC Procedure Committee, the Publishing Chair of ICCMA in 2021 and 2022, and the Publishing Chair of Publicity in 2022 CCC. He has published more than 100 SCI papers, and 8 papers were selected as 1% ESI. Authorized or applied for more than 10 invention patents. He has been cited more than 2,500 times by SCI and 3300 times by Google Scholar. H-index 28. The research results won the second prize of Natural Science Award of Anhui Province in 2020 (ranked first), the second prize of Natural Science Award of Chongqing in 2015 (ranked third), and the second prize of Natural Science Award of Chongqing in 2022 (ranked third).


****************************************************************************************************************************************************************


Title: AI在动力总成数字研发中的作用

Panelist: Ji Li

Abstract: 在当今竞争激烈的市场环境中,企业迫切需要提高研发效率以在创新和产品开发方面取得成功。与此同时,全球关注的研究热点之一是可持续性和环境保护,这些问题对企业的研发和运营提出了新的挑战和机会。本报告将探讨如何应对这些挑战,通过数字工具的巧妙应用,加速产品创新,降低环境影响,并提高资源效率。特别关注的是新兴数字技术,如人工智能,将如何在动力系统研发中发挥关键作用,推动可持续性和绿色技术的发展。报告将展示人工智能在设计优化、能源管理和协作驾驶等方面的作用,以帮助企业更好地满足不断增长的社会和法规要求,同时保持竞争力。

Personal Profile李季博士,系英国伯明翰大学研究员,伯明翰CASE车辆研究及教育中心秘书,国际汽车工程师学会(SAE Committee)委员,美国电气电子工程师学会(IEEE)会员。2020年毕业于英国伯明翰大学,师从世界著名车辆动力系统专家、国际汽车工程学会会士(SAE Fellow)英国机械工程师学会会士(IMechE)徐宏明教授。主研英国EPRSC, Innovate UK等重大科研项目若干。与比亚迪等公司展开深入合作,领导开发了基于工业数据驱动的建模框架。发表国际期刊会议论文30余篇,其中一作发表在IEEE Trans on Fuzzy Systems,IEEE Trans on Industrial Informatics,IEEE Trans on Industrial Electronics, IEEE/CAA Journal of Automatica Sinica, Applied Energy等顶刊十余篇。从事车辆工程方向研究,主要研究包括人机系统,数据表征与软传感器,共享绿色出行等。多次获得国际最佳论文奖,以及欧盟卓越奖章。担任《Chemosphere》,《Sensors》,《International Journal of Powertrains》等客座编辑。

 

****************************************************************************************************************************************************************

Title: 超大型重载车辆智能控制与应用

Panelist: Manjiang Hu

Abstract: 百吨级以上超大型重载车辆是高端工程机械领域的大国重器,智能控制技术可有效提升超大型重载车辆作业安全与效率。报告首先描述智能控制系统的科学内涵与重点任务,介绍矿山环境下超大型重载车辆智能控制的迫切需求以及关键挑战。然后详细介绍课题组近几年在整车运动控制、牵引驱动控制、集群协同控制等方面科研工作。基于以上学术成果,介绍超大型重载车辆智能控制系统在工程实践领域的核心应用,包括无人驾驶矿卡、智能新能源大轿车以及跨场景中央指挥控制系统装备等。最后,分析目前车辆构型对于超大型重载车辆的性能约束,展望下一代基于正向构型与协调控制的超大型重载车辆。


Personal Profile胡满江博士,主要研究方向为运载装备智能网联系统集成与架构设计、多传感器信息融合。发表学术论文20余篇,申请专利18项,授权软件著作权5项。主持/参与国家自然科学基金、国际合作项目、校企合作项目17项。目前主要从事智慧矿山无人运输系统和智慧车列系统技术平台的研发与产业应用工作。


****************************************************************************************************************************************************************

Title: 自动驾驶汽车安全性等效加速测试

Panelist: Shuo Feng

Abstract: 自动驾驶汽车安全性测试的低效率难题是阻碍其研发落地的重要瓶颈。本研究针对该难题背后的“稀疏度灾难”(Curse of Rarity)问题,提出了等效加速测试理论与方法,在大规模自然驾驶数据集的基础上,利用密集强化学习方法(Dense Deep Reinforcement Learning)生成测试交通环境,等效加速了测试过程多个数量级,显著提升了自动驾驶汽车的测试研发效率。


undefined

Personal Profile封硕,博士,清华大学自动化系助理教授、博士生导师,曾任美国密西根大学助理研究员,从事自动驾驶汽车智能等效加速测试理论与方法研究,以通讯作者或第一作者在《自然》(封面论文)、《自然·通讯》等高水平期刊发表论文,曾获IEEE智能交通系统学会“最佳博士学位论文奖”、美国运筹与管理协会“2021年度智能交通系统最佳论文奖”。


****************************************************************************************************************************************************************

Title: 网联矿运电机车智能优化运行技术

Panelist: Xizheng Zhang

Abstract: 智慧矿山装备已经列入国家“十四五”规划和“中国制造2025”行动纲领,我国矿山数量达到 11.25万座,露天开采不到1万座,绝大多数为地下开采,正在面临人力成本、安全和管理各方面压力。报告以网联矿运电机车智能运行为主题,阐述矿运电机车的电动化、网联化和智能化等关键技术。报告矿运电机车电机系统的服役可靠性及退化规律、机车驱动系统效率优化方法和故障诊断、锂电池状态评估以及复合储能系统协调控制。介绍多特征融合矿运交通标志语义分类方法、车辆自主感知方法和视觉障碍物检测算法。阐述基于改进卡尔曼滤波算法的车辆位置UWB定位技术、电机车突发状况脱轨检测方法、基于C-V2X网联信息的车辆层次化车速优化方法,并给出应用实例。


undefined

Personal Profile张细政,教授、博士生导师,机器人视觉感知与控制技术国家工程研究中心研究员,湖南工程学院计算机与通信学院院长。湖南省芙蓉学者入选者,湖南省智慧物流无人驾驶技术工程研究中心主任,湖南省人工智能现代产业学院院长,湖南省仪器仪表学会副理事长。先后主持完成国家自然科学基金、湖南省科技攻关计划等多个项目,发表权威期刊论文20余篇。获中国发明学会发明创业奖、教育部科学研究科技进步奖、湖南省自然科学奖等奖励等5项。目前主要从事人工智能技术、车辆智能化等方面研究。