2021中国车辆控制与智能化大会 (CVCI 2021)暨中国

  内燃机学会内燃动力智能技术分会第二届学术年会

 

赞助商

企业名称：北京西能电子科技发展有限公司

企业简介：

北京西能电子科技发展有限公司，秉志成为中国高端产业自主创新的新动力，专注服务于新能源汽车、ISO26262功能安全、ADAS、发动机动力总成控制、高端工业控制和节能控制等新兴产业。

我司开发工具业务部推广德国INCHRON公司Tool-Suite多核/多ECU实时嵌入式软件架构设计工具、德国PLS公司UDE/UADx系列高速在线调试工具、德国GLIWA公司 T1时间特性测试和分析工具、德国Verifysoft公司CTC++代码覆盖率测试工具、以及意大利Bugseng公司ÉCLAIR 源码MISAR静态代码检查和AUTOSAR C代码检查工具、以及德国emmtrix多核软件并行开发工具ePS；公司嵌入式软件开发和工程服务部提供基于AUTOSAR的软件开发和AUTOSAR工程服务、Tricore/Aurix控制器产品开发、多核嵌入式的软件架构设计和优化、时间特性设计和测试、以及满足ISO26262安全标准软件测试。

我司支持基于 Infineon Tricore/Aurix的嵌入式应用开发，专业于多核应用、功能安全的工程化开发和AUTOSAR软件架构设计，提供Tricore嵌入式开发工具链+集成测试工具链+应用的一条龙服务。

* 应用领域:   

ü 新能源汽车电机驱动、电池管理、整车域控制、自动驾驶

ü 发动机排放控制、发动机节能控制、动力总成域控制

ü 满足AUTOSAR和功能安全（ISO 26262）SIL3多核嵌入式控制

 

企业名称：南京越博动力系统股份有限公司

 

企业简介：

南京越博动力系统股份有限公司是国内领先的新能源汽车动力总成系统产品和解决方案提供商。公司成立于 2012 年，2018 年 5 月 8 日在深交所创业板成功上市（股票代码：300742）。

越博动力始终坚持以自主创新和领先科技为核心驱动力的内涵式发展道路，拥有新能源汽车整车控制技术、驱动电机及控制技术、自动变速器及控制技术、动力系统集成一体化技术等核心技术。目前已与中国一汽、上汽集团、东风汽车、长安汽车、吉利汽车、陕汽集团、宇通集团、三一集团、徐工集团、奇瑞汽车、中通客车等国内一流新能源汽车厂商展开合作。截至目前，公司已申请国内外专利 434 项，其中授权专利 275 项。

公司先后获得国家高新技术企业、工信部品牌培育试点企业、国家智能制造综合标准化与新模式应用项目实施单位、江苏省隐形冠军企业、江苏省科技小巨人企业、江苏省企业技术创新奖等荣誉。承担了国家火炬计划产业化示范项目、江苏省科技成果转化专项等项目 30 余项。

依托越博动力新能源汽车研究院和工程试验中心，公司获批建立了国家企业技术中心、国家级博士后科研工作站、中国合格评定国家认可委员会认可实验室（CNAS）、江苏省新能源汽车动力系统重点实验室、江苏省新能源汽车动力总成工程技术研究中心、江苏省新能源汽车动力总成工程研究中心、江苏省认定企业技术中心、江苏省博士后创新实践基地、江苏省企业研究生工作站等 9 个省级以上研发平台。同时与吉林大学、北京理工大学、南京理工大学等国内外十多家著名高校和科研机构形成了长期战略合作关系。越博动力始终秉持“诚信为本、客户至上、专注品质、追求卓越”的经营理念，致力打造全球最具竞争力的新能源汽车动力系统，推动新能源汽车行业发展。公司将以创新驱动为使命，致力于成为全球新能源汽车动力系统领航者。

 

企业名称：卓品智能科技无锡有限公司

卓品智能科技无锡有限公司，由GJ特聘专家、江苏省双创人才李大明在2017年8月创立，致力于嵌入式软硬件开发。公司拥有嵌入式控制器开发核心技术，具备丰富的产品化经验、开发周期短，响应速度快，维护服务完善，提供全系列电控系统解决方案，助推客户产品转型升级，引领行业发展。

成立以来我们与多家国内知名发动机及零部件厂商开展业务，并保持了长期稳定的合作关系。与供应商建立良好互信的长期合作，达成销售渠道共享的战略同盟，实现共赢。

卓品智能科技，从柴油机电控市场开始，积极开发动力总成全系列电控产品，并致力于完成包括无人机驾驶电控在内的商用车电控产品及外包服务市场布局。为打造世界一流品牌，实现可持续发展而努力。                        成立以来我们与多家国内知名发动机及零部件厂商开展业务，并保持了长期稳定的合作关系。与供应商建立良好互信的长期合作，达成销售渠道共享的战略同盟，实现共赢。      卓品智能科技，从柴油机电控市场开始，积极开发动力总成全系列电控产品，并致力于完成包括无人驾驶电控在内的商用车电控产品及外包服务市场布局。为打造世界一流品牌，实现可持续发展而努力。

 

总览（姓名不分先后）

1. 新能源商用车动力总成技术介绍——罗本进

2. Decision Making and Control for Efficient and Safe Autonomous Vehicles——Dezong Zhao

3. Bridging the Theory to Practice: A Review of the IFAC ECOSM Benchmark Problem——Fuguo Xu 

4. 强化学习赋能混合动力车辆能量管理系统和方法——周泉

5. 基于SOA框架的智能网联APP开发与应用——鄢挺 

6. Extended State Observer based Control and FilterDesign with Applications to Vehicle Control Systems——薛文超

7.Multi-time Scale Uncertainty Observation Based Control of Autonomous Vehicles——宋康 

8.动力电池安全高效管理关键技术——商云龙

9.Deep Learning based Object Detection and Semantic Segmentation for Autonomous Driving——李颖

10.Introduction to The Control and Optimization of Modern Powertrains.——高金武

11. Bridging the Theory to Practice: A Review of the IFAC ECOSM Benchmark Problem——徐福国

12. 满足整车跨域功能融合和失效可操作要求的系统解决方案——丁锋

13.混合动力专用发动机高效清洁技术发展趋势——陆国祥

14The Development and Application of Automotive Fuel Cell Control Unit.——江维海

15.智能网联汽车产业发展态势与百度 Apollo 实践——何鹏

16.矿山无人化关键技术及应用——王健

17.Model-based Estimation Approach for State of Charge of Lithium-ion Battery——贺林

18.面向资源优化和安全的系统辨识——郭金

19.基于集值型测量数据的非线性系统自适应调节控制——赵文虓

20.图像目标智能感知技术及应用——庞彦伟

21.人工智能技术在机场道面安全检测中的应用——孙雷

22.迁移学习及其应用——杨柳

23.数据驱动与自抗扰控制结合设计及在燃煤机组中的应用——吴振龙

24.吉利新一代混动系统智能控制算法的研究与应用——钱鹏飞

25.新能源商用车动力总成技术介绍——罗本进

26.基于SOA框架的智能网联APP开发与应用——鄢挺

27.面向ADAS的新能源汽车动力域控制解决方案——朱仲文

28.高通助力汽车智能化应用——杨安

29.Decision Making and Control for Efficient and Safe 30.Autonomous Vehicles——朱仲文

31.强化学习赋能混合动力车辆能量管理系统和方法——周泉

32.质子交换膜燃料电池动态特性与自抗扰控制——孙立

33.热管理系统的智能附件方案——于海鹏

34.基于时间模型的多核多ECU嵌入式软件架构仿真、优化和测试方案——刘为文

335.孪生模型在发动机控制开发中的应用——陈韬

36.内燃机关重件/运动件服役数据无线实时测量技术研发与应用——杨灿

37.机器学习辅助的碳烟多参数同时诊断——王潜龙

38.数据驱动下预测性维修的几点思考——邓英俊

 

 

大会报告

Karl H. Johansson

Title: Traffic Control Using Automated Truck Platoons:Distributed Sensing, Actuation, and Learning

Abstract: 

While the long-term benefits of introducing connected and automated vehicles into road traffic are widely understood to be revolutionary, there is much debate about whether its early stages will cause an increase in congestion and issues related to human-driven vehicles. Notwithstanding, connected vehicles acting as mobile sensors and actuators could enable traffic predictions and control at a scale never before possible, and thereby a much more efficient use of the available road infrastructure. In this talk, we will present how a new freight transport technology based on automated truck platoons can be the backbone for such a system. Some basic theoretical and experimental results on the control and coordination of truck platoons will be presented. How such platoons influence traffic flows by acting as a moving bottleneck will then be discussed together with traffic models suitable for designing novel traffic control systems. It will also be argued that these models are possible to learn automatically from data gathered by platoons acting as traffic flow sensors. Experiments show that relatively few connected vehicles are enough to mitigate stop-and-go waves and improve traffic conditions significantly. The presentation will be based on joint work with Matthieu Barreau

and Mladen Cicic.

 

 

Karl H. Johansson is Professor with the School of Electrical Engineering and Com- puter Science at KTH Royal Institute of Technology in Sweden and Director of Digital Futures. He received MSc and PhD degrees from Lund University. He has held visiting positions at UC Berkeley, Caltech, NTU, HKUST Institute of Advanced Studies, and NTNU. His research interests are in networked control systems and cyber-physical systems with applications in transportation, energy, and automation networks. He is a member of the Swedish Research Council's Scientific Council for Natural Sciences and Engineering Sciences. He has served on the IEEE   Control Systems Society Board of Governors, the IFAC Executive Board, and is currently Vice-President of the Euro- pean Control Association. He has received several best paper awards and other distinctions from IEEE, IFAC, and ACM. He has been awarded Distinguished Professor with the Swedish Research Council and Wallenberg Scholar with the Knut and Alice Wallenberg Foundation. He has received the Future Research Leader Award from the Swedish Foundation for Strategic Research and the triennial Young Author Prize from IFAC. He is Fellow of the IEEE and the Royal Swedish Academy of Engineering Sciences, and he is IEEE Control Systems Society Distinguished Lecturer.

 

Jie Chen

Title:严格信息-物理约束下的多智能体协同决策与控制

 

Abstract:随着以无人机/无人车等为代表的多智能体系统的大规模应用，实际应用中严格的信息-物理约束将给传统的多智能体协同决策与控制技术带来极大挑战。本报告在简要回顾现有多智能体协同技术的基础上，针 对实际任务中严格的信息-物理约束，从严格时序逻辑约束下的协同行为规划，动态位姿空间约束下的分布式 运动规划，仅基于相对观测信息约束下的仿射编队控制等方面分别介绍了多智能体协同决策与控制的最新研究 进展，分析了其技术内涵，凝练出制约其发展的若干核心关键问题，并给出具有创新性的解决之道。最后对多 智能体协同决策与控制的发展趋势做出预测，以期对相关研究起到借鉴和引导作用。

 

陈杰，同济大学校长，中国工程院院士，IEEE Fellow、IFAC Fellow。“复杂系统智 能控制与决策”国家重点实验室主任、国家杰出青年科学基金获得者、教育部CJ学者奖励计划特聘教授、国家自然科学基金委基础科学中心学术带头人、创新研究群 体学术带头人、973项目首席、新世纪百千万人才工程国家级人才、全国优秀科技 工作者。现担任国务院学位委员会学科评议组控制科学与工程组召集人、教育部科 学技术委员会委员兼专门委员会主任，中国自动化学会副理事长、中国人工智能学 会副理事长、中国指挥与控制学会副理事长、上海市人工智能战略咨询专家委员会 副主任委员，多部国际、国内学术期刊副主编和编委。长期从事控制科学与工程等 相关学科领域的教学与科研工作。在动态环境下复杂系统的多指标优化与控制、多智能体协同控制等研究领域 内进行了深入研究，并面向应用将在该领域的研究与装备系统建设密切结合，所研制出的装备已得到大量应用。近年来，以第一完成人获国家自然科学二等奖1项、国家科技进步二等奖2项、省部级一等奖4项。何梁何利 基金“科学与技术进步奖”获得者。发表SCI收录论文100余篇，以第一发明人获授权发明专利40多项，先后出版 学术专著4部、教材和译著各1部。

 

Timothy Gordon Professor

Title: Flexible Vehicle Automation – Connecting Drivers to Intelligent      Vehicles for Improved Comfort and Safety

 

Abstract: 

To make a fully functional self-driving car means replicating the human driving process inside a com- puter. This includes aspects of human perception, reasoning, and situational awareness that have proved to be too challenging for the current generation of artificial intelligence. A more flexible approach to vehicle auto- mation is therefore required, with special focus on shared control. In this talk, Professor Gordon presents a broad viewpoint of how new functionalities can be achieved by fusing together the best available attributes of human and vehicular intelligence. Three general areas of flexible automation are identified: shared control for mobility, cooperative active safety, and electronic support for driving enjoyment. A deeper analysis is then presented for a layered (hierarchical) optimal control approach to shared human-vehicle control in safety critical situations.

Tim Gordon is Professor of Vehicle Control Engineering at the University of Lincoln and President of the International Association for Vehicle System Dynam- ics (IAVSD). He has a PhD in Theoretical Physics from the University of Cam- bridge and has pursued a career in control systems and control engineering, with primary interests in road vehicles. Previously he held a number of senior academ- ic positions, including Professor of Mechanical Engineering at the University of Michigan (UM, Ann Arbor), and Research Professor at UM’s Transportation Research Institute. He was also Ford Professor at Loughborough University and

has worked extensively with the automotive industry throughout his academic career. He is currently a visiting professor at Tongji University, Shanghai, and is Co-chair of the IEEE Technical Committee on Intelligent Vehic- ular Systems and Control.

 

Devesh Upadhyay

Title: Intelligence in Vehicles, Opportunities and Challenges in an Emerging Landscape

 

Abstract: Machine-Learning,Data-Driven approaches and Connectivity are opening new possibilities for enabling intelligent systems. In the automotive domain this goes well beyond autonomous driving and driver assist systems. The vehicle interior has also become a rich environment for such intelligence and user experi- ence is driving much development. The vehicle control problems are also seeing a multitude of new opportuni- ties driven by connectivity, large and varied data resources, powerful compute and advanced algorithms. In this talk we discuss opportunities, challenges and outlook in a very fast-changing landscape. For illustration we borrow both form general industry and academia as well as from active ongoing works at Ford research.

Devesh joined Ford in 2001 after completing his PhD at The Ohio-State University. Devesh Upadhyay is currently the Sr. Technical leader for the Core AI-ML Methods and Quantum Computing team in Ford research. During his tenure at Ford Devesh has worked on a variety of problems related to control theory, modeling methods, uncertainty quantification, signal processing, diagnostics/prognostics etc. In his current role Devesh is working with the Core AI-ML-QC team to find new solutions to old problems. This work is at the intersection of theoretical and applied research. The focus is to robustly extend AI-ML methods to   engineering and manufacturing problems under constraints imposed by practical applications.

Hui Xie

Title:内燃动力电气化、数字化、智能化现状与机遇

 

Abstract:电气化、数字化和智能化，是内燃动力系统重要的技术发展方向，也为内燃动力的智能控制技术带来了全新的发展机遇。本报告将系统分析该领域的发展现状与趋势，凝练网联内燃动力系统控制的关键问题和挑战，探讨大数据，人工智能，自动控制，通信技术等技术与现代内燃动力系统的融合方法，形成内燃动力系统智 能控制新框架，并以天津大学先进动力与智能车辆控制团队的研究工作为例，具体介绍在燃油系统、空气系统、扭矩系统、热管理系统，以及网联内燃动力总成方面的最新研究进展。

 

谢辉，天津大学长聘教授，天津大学无人驾驶汽车交叉研究中心主任，中国内燃机学会内燃动力智能技术分会主任委员、中国自动化学会车辆控制与智能化专委会副主任委员、国际自动控制联合会先进汽车控制技术委员会（IFAC-AAC）委员、天津市汽车工程学会副理事长。

主要研究方向及成果：主要从事内燃动力智能控制、车辆动力总成智能控制及无人驾驶控制研究。主持国际合作、国家和部委及横向课题50余项。发表SCI/EI论文90余篇，出版著作1本。获授权发明专利和软件著作权30余项。获国家级教学成果奖二等奖1项（排名第1）、中国机械工业科学技术奖一等奖1项（排名第1）、天津市技术发明一等奖1项（排名第1）、中国大坝工程学会技术发明特等奖（排名第4）、国家级技术发明奖二等奖1项（排名第5）。

 

 

青年学者论坛

薛文超 

Title: Extended State Observer based Control and Filter Design with Applications to Vehicle Control Systems

 

Abstract: 

Extended state observer (ESO) has been widely used to deal with various control and filtering prob- lems of uncertain systems. In the frame of ESO, the “total disturbance” in systems can be timely estimated from the input-data and output-data of systems. This talk will discuss the recent progress in design and theory of ESO as well as ESO based control. Firstly, the ESO design method for general uncertain systems will be presented. The estimation error of ESO will be rigorously discussed. Next, I will focus on the ESO based filters for estimating both states and uncertain dynamics, especially for the stochastic systems. Finally, some recent applications to vehicle control systems will be demonstrated.

 

Wenchao Xue received Ph.D. degree in control theory from the Academy of Mathe- matics and Systems Science (AMSS), Chinese Academy of Sciences (CAS) in 2012. He is now an Associate Professor of AMSS, CAS. His research interests include theory and application of active disturbance rejection control, nonlinear uncertain system control and nonlinear uncertain systems filtering. Dr. Xue empha- sizes on the control theory research to solve the real world problems. He has published several papers on Automatica and IEEE transactions. Currently, Dr. Xue is an associate editor of the IFAC Journal of Control Engineering Practice and the Journal of Systems Sciences and Mathematic. He has chaired several NSFC projects including Outstanding Youth Fund. He is the member of Chinese Simulation Federation, and the member of TCCT, Chinese Association of Automation. He is a recipient of server conference best/outstanding paper awards including Best Paper Award of IEEE DDCLS 2018 and SCIS-CCC Poster Paper Award of CCC 2019.

 

宋康 

Title: Multi-time Scale Uncertainty Observation Based Control of Autonomous Vehicles

 

Abstract: Uncertainties, in the vehicle dynamics and the operating environment, are primary challenges in the practical application of autonomous vehicles. In this talk, a multi-time scale uncertainty observation-based control solution is introduced, combining the extended state observer and model parameters online identification algorithm. Application cases in autonomous rollers and buses will be discussed.

 

宋康，博士，天津大学副教授，博士生导师，美国密西根州立大学和美国福特汽车 公司博士后（2015-2018），中国内燃机学会内燃动力智能技术分会秘书长，中国 自动化学会车辆控制与智能化专委会副秘书长，主要从事内燃动力与车辆的建模与 控制研究。 在美国福特连续三年的支持下，建立了面向控制的微型混合动力增压发动机动态预 测模型，提出了 ESO-MPC 增压控制与能量管理算法。与所在课题组研究提出的 内燃动力主动抗扰智能控制技术在国内多家企业得到工程应用。通过团队的共同努 力，开发的无人驾驶压路机在我国某水电大坝投入生产应用 2 年有余，规模 15 台，碾压超 300 万 m³。指导研究生获 2021 年世界智能驾驶挑战赛金奖、2021 中国（沈阳）智能网联汽车大赛 “自动驾驶” 仿真比赛金奖、实车前瞻应用挑战赛银奖。发表 SCI/EI 论文 40 余篇， 授权美国发明专利 2 项，在审中国发明专利 20 余项、PCT 国际发明专利 1 项，获 2018 年中国机械工业联合 会科技一等奖、2019 年天津市技术发明一等奖，2020 年中国大坝工程学会特等奖。

 

商云龙 

Title: 动力电池安全高效管理关键技术

 

Abstract:锂离子动力电池是一类衰退机理不明、环境工况敏感、多个体非均一混联的复杂动态系统，其安全 高效使用面临严峻挑战，严重制约了新能源汽车和储能行业的健康发展。报告将重点介绍动力电池建模估计、 故障诊断、均衡控制、低温预热等关键技术以及山东大学团队取得的研究进展。

 

商云龙，山东大学控制科学与工程学院，教授，博士生导师，泰山学者青年专家。 从事动力电池建模与管理研究，以第一作者发表 SCI 论文 17 篇，授权国家发明专 利 33 件、美国发明专利 1 件、PCT 国际检索报告 4 件，申请美国发明专利 3 件， 获中国自动化学会 CAA 自然科学奖一等奖 ( 排 2)、山东省专利奖一等奖 ( 排 2)、 CAA 优秀博士学位论文奖和山东省优秀博士学位论文奖等，主持国家优青、面上、 山东省杰青以及山东省重大创新工程等项目。

李颖 

Title: Deep Learning based Object Detection and Semantic Segmentation for Autonomous Driving

 

Abstract: Accurate environmental perception is the key for reliable navigation, accurate decision-making, and safe driving of autonomous vehicles in complex environments. This task needs to extract reliable and accurate environmental information using the data acquired by on-board sensors. In recent years, with the break throughs of computing platforms and the publication of high-quality labeled perception datasets, deep learning has achieved a series of remarkable results in environment perception for autonomous driving. How to extract accurate information using deep learning algorithms in different driving scenarios plays an important role in decision-making and planning. Therefore, this report focuses on the research of deep learning based object detection and semantic segmentation in different driving scenarios.

 

Ying Li received the Ph.D. degree from the University of Waterloo, Canada, in 2021. She is currently an Assistant Professor with the School of Mechanical Engineering, Beijing Institute of Technology, China. Her current research focuses on autonomous driving, environmental perception, computer vision, mobile laser scanning, geomet- ric and semantic modeling, and high definition mapping. She has published more than 20 SCI/EI papers. She is also the principal investigator of 4 grants, including the National Science Fund for Youth and the International Postdoctoral Exchange Fellowship Program (Talent-Introduction Program

 

高金武 

Title: Introduction to The Control and Optimization of Modern Powertrains.

 

Abstract: Control systems have come to play an important role in the performance of modern powertrains with regards to meeting goals on low/zero emissions and high energy efficiency. To achieve these goals, various types of powertrain including high efficiency engine, electric motor, hybrid mode combing engine and motor, fuel cell engine are designed to drive vehicle, which also bring more challenges in practice. Therefore, control and optimization technologies have become promising tools for the development of control systems in the automotive industry.

This talk will introduce the work and effort of the speaker’s team on the modern powertrain control in the past years.Jinwu Gao received the B. Eng. degree in the Department of Automation Measure- ment and Control Engineering, and the Ph.D. degree in the Department of Control Science and Engineering from Harbin Institute of Technology, Harbin, China, in 2005 and 2012. From 2012 to 2014, he was an Assistant Professor at Sun Yat-sen University, China. In July 2014, he held postdoctoral position in the Department of Engineering and Applied Science, Sophia University, Japan. From 2016 to 2020, he was an Associate Professor at Jilin University, China, and has been a Professor at Jilin since September 2020. His research interests include control theory and appli- cation in automotive powertrain.

 

徐福国 

Title: Bridging the Theory to Practice: A Review of the IFAC ECOSM Benchmark Problem

 

Abstract:In the 6th IFAC Conference on Engine and Powertrain Control, Simulation and Modeling (ECOSM 2021), Tokyo 2021, we collaborated with scholars from Sweden, Spain, China and Japan and engineers from Toyota Motor Corporation, Japan to propose a benchmark problem for the challengers aiming to energy efficiency control of connected and intelligent hybrid electric vehicles (HEVs). The purpose of this benchmark problem is to provide a platform for the students and younger researchers to challenge the issues of the next generation powertrain control, and exchanging the frontier research results in automotive system control and optimization.

The targeted HEVs are under the connected environment with of real-time information of vehicle-to-everything, including geographic information, vehicle-to-infrastructure information and vehicle-to-vehicle information. The provided high-fidelity simulator consists of an industrial-level HEV model and a traffic scenario database obtained through a commercial traffic simulator, where the running route is generated based on real-world data with slope and intersection position. The benchmark problem to be solved is the HEVs powertrain control using traffic information to fulfil fuel economy improvement while satisfying the constraints of the driving safety and travel time.

This presentation will give an introduction of the benchmark challenging problem and our provided simulator, and discuss the fuel economy performances of the submitted controller results.

 

Fuguo Xu received the M.E. degree in control theory and control engineering from Yanshan University, Qinhuangdao, China, in 2016 and the Ph.D. degree in green science and engineering from Sophia University, Tokyo, Japan, in 2019. Since 2019, he has been a Postdoctoral Fellow with the Department of Engineering and Applied Sciences, Sophia University. He has served as the student activity chair of IFAC Conference on ECOSM 2021 and he is serving as the guest editor of Control Theory and Technology. His research interests include optimal con

 

工业论坛

丁锋

Title: 满足整车跨域功能融合和失效可操作要求的系统解决方案

 

Abstract: 在整车电子电器架构区域融合和功能域融合的发展趋势下，通过跨域功能融合提升系统表现成为了 新的技术要求，同时，智能车辆对系统失效后的可操作性提出了更高的要求，通过系统架构设计满足不同的失 效可操作要求成为了新的技术挑战。为满足整车厂整车跨域功能融合和失效可操作的要求，联合电子可以提供 动力域和车身域的系统和零部件解决方案、区域导向和功能域导向的控制器系统解决方案，以及软件和架构设 计服务。

联合汽车电子有限公司跨域业务技术中台开发总监，高级工程师。毕业于北京航空 航天大学自动控制专业，硕士学位。负责完成了多个控制器软件平台研发工作，在 汽车电子控制器系统软件和软件架构设计方面积累了丰富的专业知识和经验，熟知 相关领域技术现状及前沿动态，造诣颇深。获得过汽车工业和上海市多项科技进步 奖项，在 2019 年获得上汽优秀工程技术带头人等荣誉称号。

 

陆国祥

Title: 混合动力专用发动机高效清洁技术发展趋势

 

Abstract: 通过插电式混合动力汽车及发动机发展趋势、DM-i 超级混动专用高效发动机系统方案、混动专用 高效发动机面临的挑战和应对策略三个方面详细讲解混合动力专用发动机高效清洁技术及发展趋势。

陆国祥，工学博士，比亚迪产品规划及汽车新技术研究院双模中心副主任，DM 平 台技术总监，广东省电子信息行业协会会员，深圳市 “高层次人才聚龙英才”。 长期从事发动机与新能源汽车技术领域研究工作，主导比亚迪 DM-i 超级混动技术 平台的规划及预研，负责插电式混动专用高效发动机的开发，并成功搭载秦、唐、 宋车型；主导三款插电式混动专用发动机开发，其中 1.5L 自吸发动机实现峰值热效 率 43.04%。近 5 年，获 18 项专利授权，发表论文 12 篇，其中 SCI 论文 4 篇。荣获中国汽车工 业科学技术进步奖、中国机械工业科学技术奖、广东省机械工业科学技术奖在内的 10 项奖项。

 

江维海

Title: The Development and Application of Automotive Fuel Cell Control Unit

 

Abstract: 

The Proton Exchange Membrane Fuel Cell(PEMFC) are widely regarded as one of a very important alternative automotive powertrain for the next generation of vehicles, since it has the advantages of high efficiency, zero emission, low noise and short start-up time, etc. However, the electrochemical reaction process of fuel cell in practical application is extremely sensitive to the system conditions such as component variations within fuel cell, temperature, pressure and humidity, etc. What’s more, the system has strong nonlinearity and serious coupling among subsystems. It is a multi-disciplinary complex system, which brings great challenges to the system control design. A reliable Fuel Cell Control Unit (FCU) can improve the working efficiency and prolong the service life of fuel cell at the same time.

This presentation will systematically introduce the development of Fuel Cell Control Unit(FCU) from the aspects of the development process of FCU, hardware development, software development, Hardware in the Loop(HIL) test, the modeling and calibration of fuel cell system, control algorithm development and validation, etc.

 

Weihai Jiang received the M.S. degree in power engineering from Tianjin University, China, in 2016 and the Ph.D. degree in control engineering from Sophia University, Tokyo, Japan, in 2019. From Aug. 2019 to Sep. 2021, he worked in Automotive Engineering Research Institute of China Automotive Technology and Research Center Co.,Ltd. He is now an Associate Professor of Hefei University of Technology. He has published more than 20 papers and 6 invention patents. He won the third prize of the Innovation and Entrepreneurship Competition from the Fifth young member of Jiangsu Association for science and technology, in 2020. He received an excellent scientific and technological achievement award from CATARC and an Advanced individual in scientific research award from the Automotive Engineering Research Institute of CATARC, in 2020. His research interests include advanced control technology of new energy vehicles, Connected and Autonomous vehicles.

 

 

何鹏

Title: 智能网联汽车产业发展态势与百度 Apollo 实践

 

Abstract: 近年来国家高度重视智能网联汽车产业发展，中央政府、主管部委、地方政府密集出台各类支持政 策，保障产业健康发展。智能网联汽车市场渗透率快速提升，高级别自动驾驶由封闭道路测试向开放道路商业 化示范运营推进。百度Apollo在国内20余个城市落地应用项目，在快速提升技术成熟度，降低产品成本的同 时，积极探索自动驾驶、车路协同、智慧交通的商业化运营路径。 

 

何鹏，高级工程师，2010年毕业于北京航空航天大学交通科学与工程学院，获工学 博士学位。从事智能网联汽车行业工作多年，负责百度多项地方政府智慧交通合作 项目规划设计，参与多项自动驾驶、车路协同和智慧交通领域国家和地方政策规划 编制，以及国家、行业和团体标准研制工作。

 

王健

 

Title: 矿山无人化关键技术及应用

 

Abstract: 面向露天及井工矿无人运输与智能化需求，深度融合数字四胞胎理论，设计了虚实融合的 IMOS 架 构；阐述 IMOS 子系统架构与功能，包括：单车作业系统、多车协同系统、车路协同 系统、无人驾驶智能系 统、调度管理系统、平行系统、监管系统、远程接管系统和通讯系统；探讨 IMOS 关键技术，即平行矿山仿 真建模技术、无人驾驶技术、矿区通讯技术和协同作业技术。智慧矿山操作系统是 国内首套露天矿山无人化 与智能化的一体化解决方案，其将社会发展要素作为矿区绿色可持续发展的度量 条件，将有效提高露天矿山 生产效率及安全水平，推进生态矿山建设，对实现能源绿色发展有重要意义。

 

王健，博士，吉林大学计算机学院教授、博士生导师，青岛慧拓智能机器有限公司联 合创始人。中国汽车工程研究院股份有限公司特聘高级专家，启明信息技术股份有限 公司特聘高级专家。国家智能网联汽车(重庆)示范区开放道路测试专家委员会委员， 国家智能网联汽车(北方)示范区开放道路测试专家委员会委员，国家智能网联汽车(广 州)示范区开放道路测试专家委员会委员。先后在加拿大大不列颠哥伦比亚大学、奥 地利因斯布鲁克大学、法国国家信息与自动化研究所、韩国汉阳大学从事博士生、博 士后、访问学者等研究工作。主要研究领域为智能网联汽车的通信协议、MEC应用、模拟仿真与测试等。近5年来作为项目负责人先后承担了国家自然科学基金面上、青年项目、国际合作交流、中国博士后基金特等资助、教育部博士点基金、吉林省发展计划重点项目、吉林省国际合作项目、吉林省 青年基金等纵向项目 13 项，获2018年高等教育国家级教学成果二等奖1次（第5名），2013年吉林省科学技 术进步奖一等奖1 次（第3名），中国商业联合会全国商业科技进步奖二等奖 2 次，以第1责任作者IEEE Transaction on ITS, Scientific Reports, Computer Networks, Computer Communications等国际SCI检 索期刊发表论文50余篇，授权发明专利7项，软件著作权4项，出版中英文专著各1部。

 

贺林

 

Title: Model-based Estimation Approach for State of Charge of Lithium-ion Battery

 

Abstract: The state of charge is a key parameter of lithium-ion battery, whose estimation approaches may be divided into classical control and reinforce learning algorithm. For an accurate SOC of lithium-ion battery by classical control algorithm, we have met with two problems, i.e. the accuracy of model, and the practicability of algorithm. Respect to the practicability of algorithm, it is important that the algorithm should not only match with the characteristics of state of charge, but also be applied into practical engineering. As for the accuracy of model, there are lots of battery models proposed in some literatures. An accurate battery model, which can describe the dynamics characteristics of lithium-ion battery, is one of the most important factors affecting the final estimation result. In this lecture, we will discuss how to respond to the challenge of accurate estimation for the state of charge of lithium-ion battery.

He Lin was born in Nanchong, China, in 1977. He received the Ph.D. degree in automotive engineering from Tongji University, Shanghai, China, in 2010. After that, he entered into the State Key Laboratory of Automotive Safety and Energy, Tsing- hua University, Beijing, China, as an assistant research fellow. He did some researches of advanced engine control technology for Toyota Motor Corporation from Apr. 2010 to Mar. 2011 in Sophia University, Tokyo, Japan. From Jan. 2012 to May 2016, He was a product engineering manager of Foton Motor Group to devel- op new energy vehicle. In the meantime, As a project chief engineer, He developed first fuel cell truck of China and first full platform of battery electric truck for  Foton.

Now, He is a professor of Hefei University of Technology. He has written two books of new energy vehicle, i.e. Electric Vehicle Design, Power Battery. His research interests mainly include vehicle dynamics & control, and automotive powertrain & control, lithium-ion battery management, electric motor control, steer-by-wire, brake-by-wire, intelligent vehicle. Email: helin@hfut.edu.

 

 

智能动力变革性技术论坛（天津大学与中国科学院数学与系统科学研究院联合承办）

 

郭金

 

Title: 面向资源优化和安全的系统辨识

 

Abstract: 网络化环境下的系统辨识面临通信传输率有限、量化误差、信道噪声、传输误码、延时、数据丢包、网络安全等因素带来的挑战。另一方面，诸多系统在时间、空间上相互联系，如何合理有效地调度/共享物理端的测量、执行等硬件资源和远程/云端的计算资源对节约运行成本和保持系统性能至关重要。本报告介绍面向资源优化和安全的系统辨识方法，以及一些初步的应用研究。

 

郭金，教授，博士生导师，中国自动化学会控制理论专业委员会委员和副秘书长。主要从事系统建模与辨识、自适应控制等方向的研究。主持国家级项目3项，省部级项目2项，参与包括重点项目在内的国家级项目10余项。发表学术论文60余篇，出版英文著作1部，授权发明专利3项。目前，担任期刊Asian Journal of Control和Journal of Systems Science and Complexity的编委，以及《工程科学学报》青年编委。

 

赵文虓 

Title: 基于集值型测量数据的非线性系统自适应调节控制

 

Abstract: 针对两类模块化非线性系统（Hammerstein系统和Wiener系统），基于随机逼近算法，给出系统输出调节误差为集值型测量数据情形下的反馈控制器构造以及调节最优性的理论证明，并在仿真模拟和实验验证中测试了算法有效性。

 

赵文虓，毕业于山东大学，在中国科学院数学与系统科学研究院获得博士学位，现任中国科学院数学与系统科学研究院研究员。他的研究方向主要集中在随机系统的建模、估计与控制，包括变量选择与稀疏参数辨识、随机系统的递推估计与适应控制、分布式估计与优化等。赵文虓目前担任《系统科学与数学》编委、IEEE Control Systems Letters编委，IEEE CSS Conference Editorial Board编委以及 IEEE CSS 北京分会秘书长等学术兼职。

 

庞彦伟

Title: 图像目标智能感知技术及应用

 

Abstract:目标感知在无人驾驶、辅助驾驶等智能系统中有着广泛的应用。本报告介绍课题组在一般目标检测、行人目标检测上研究进展。以深度学习智能视觉感知为核心，主要聚焦在被遮挡目标检测、小尺度目标检测、雾霾天气下的目标检测以及基于双目视觉的三维目标检测技术。最后对相关挑战和趋势进行了展望。

 

庞彦伟，博士，天津大学电气自动化与信息工程学院教授、天津市类脑智能技术重点实验室主任。入选科技部中青年科技创新领军人才。曾获天津市科技进步一等奖、中国电子学会自然科学一等奖。担任IEEE NNLS汇刊、中国科学-信息科学等期刊编委。主要研究深度学习、类脑智能、图像目标检测、图像语义分割、医学图像重建、多传感器协同感知等技术及其在智能驾驶、智能视频监控、智能医学成像设备、智能可穿戴健康设备、智能机器人等领域的应用。

 

孙雷 

 

Title: 人工智能技术在机场道面安全检测中的应用

 

Abstract:当前中国正处于从“民航大国”向“民航强国”转变的关键阶段，道面安全是民航运行安全的重中之重。现行道面检测模式越来越难以满足对超高安全与精度、超窄作业时限、超大作业范围等的本质要求。为此，综合各项技术指标的长期历史数据，推演道面适航状态动态演化规律，实现道面适航状态长期安全预警，由静态检测向动态预警的提升是未来机场道面安全检测发展的必然趋势。其中，时间和空间两个维度检测数据的高精度对齐配准是实现道面安全动态演化分析的基础和前提。但是，面向道面结构安全检测中检测数据存在噪声干扰强、形态多样、样本稀缺、环境复杂动态等难题，传统基于模型的方法和基于深度学习的方法均无法实现。针对这一问题，本项目将数据驱动与模型驱动相结合，设计了多层次紧耦合感知技术框架，开展深入的理论方法研究，在此基础上研制地空一体、模块切换、云端智慧、适用于机场道面巡检与定检的多机器人协同作业系统，对相关理论方法在超大型机场进行实验验证。

 

孙雷，男，43岁，博士，南开大学教授、博士生导师。分别于1999年、2002年天津大学获机械电子工程专业学士、硕士学位，2005年于南开大学获控制理论与控制工程专业博士学位。2005年至今于南开大学机器人与信息自动化研究所任教。主要研究方向集中在协作型机器人感知与控制技术，作为项目负责人或主要成员，通过鉴定或验收的国家863计划、国家重点研发计划、国家自然科学基金、天津市自然科学基金等科研成果12项。目前主持的在研课题5项，包括国家重点研发计划“智能机器人”专项、天津市新一代人工智能重大专项、国家自然科学基金项目等。获得天津市技术发明二等奖。发表论文60余篇，获得发明专利10余项，软件著作权登记8项。

 

杨柳 

Title: 迁移学习及其应用

 

Abstract:监督学习方法的性能严重依赖于标注数据的数量。然而，在真实的应用场景中，标注大量数据的代价通常是昂贵的。为了解决标签数据较少的问题，本次报告将介绍迁移学习的方法，以及在自动驾驶、行为识别和人群计数等方面的应用，充分利用其它相关源领域中的有标记数据，进而提高目标领域中未标记数据的识别性能。

 

杨柳，博士，天津大学智能与计算学部副教授，2016年毕业于北京交通大学计算机学院获博士学位，多次去韩国和香港访问交流。主要研究方向为机器学习中迁移学习、联邦学习、多视图学习和多标记学习。主持或参加多个国家级、省部级科研项目（包括国家自然基金重点项目、面上项目和青年基金等）。近年来在国内外重要学术杂志和会议上发表30余篇论文（包括IEEE Trans. on NNLS, IEEE Trans. on IP, IEEE Trans. on Cybernetics, CVPR和IJCAI等），其中一篇论文获得“最佳学生论文奖”。

 

吴振龙

Title: 数据驱动与自抗扰控制结合设计及在燃煤机组中的应用

 

Abstract:具有多源扰动、强非线性、大滞后等特性的燃煤机组脱硝系统面临着控制挑战。为提高脱硝系统的跟踪性能和抗干扰性能，本报告介绍了一种结合改进自抗扰控制与前馈设控制的复合控制策略。通过对大滞后特性的控制难点分析，提出了一种适用于脱硝系统的定量参数整定方法，并利用数据驱动的方法，通过扰动量的相关性分析设计合理的前馈控制策略。现场运行数据表明提出的复合控制策略具有更强的扰动抑制能力和消除反应器两侧出口浓度偏差的能力，显示了很强的应用价值和应用潜力。接下来介绍自抗扰控制在多个电厂的多个关键回路中的应用情况，展示了很强的应用价值。

 

吴振龙，博士，郑州大学电气工程学院副教授。研究兴趣为自抗扰控制和分数阶控制及在能源系统中的应用，工业大数据挖掘及在控制优化中的应用。主持自然科学基金项目、河南省科技攻关项目、电力系统及发电设备控制和仿真国家重点实验室开放基金项目。申请发明专利项20余项，已授权专利7项。以第一作者/通讯作者在Energy、ISA Transactions、Control Engineering Practice等期刊发表论文30余篇。

 

钱鹏飞

Title: 吉利新一代混动系统智能控制算法的研究与应用

 

Abstract:随着汽车“新四化”的推进，动力系统需要更加智能的适应不同工况和驾驶风格。吉利新一代混合动力系统在驾驶性层面通过云平台、高精度地图、车辆环境感知等系统使车辆对每一份能量极致管理，对不同路况控制自由切换，对不同驾驶风格实现千人千面的驾驶体验。吉利新一代混动系统新增智能能量管理，智能能量回收，自适应驾驶模式等先进算法，车辆更加智能。

  

钱鹏飞：2011年毕业于吉林大学（机电一体化）与韩国成均馆大学(车辆工况)，双硕士。长期从事汽油以及柴油发动机的空气系统以及后处理领域控制策略开发；2017年加入吉利动力研究院，领导GHS2.0混动专用发动机以及混动控制系统开发。

 

罗本进

Title: 新能源商用车动力总成技术介绍

 

Abstract:报告描述了商用车新能源动力总成的发展情况，商用车对动力总成的需求特点。对新能源动力总成在商用车上采用的技术应用及发展趋势进行了分析，给出了越博动力系统股份有限公司在新能源动力总成业务上所采用的技术解决方案及提供的产品特点及范围，最后给出越博动力在新能源商用车领域布局的未来发展规划。

 

罗本进 越博动力系统股份有限公司 首席技术官， 研究院院长，斯图加特大学博士，GJ特聘专家，南京越博动力CTO，新能源汽车研究院院长；江苏省产业技术研究院暨长三角国家技术创新中心首席科学家；原德国博世前瞻研发部高级系统工程师；长期从事汽车动力总成及自动变速箱的设计计算、控制及系统集成的研发工作，同时在工业4.0领域持续研究。

 

鄢挺

Title: 基于SOA框架的智能网联APP开发与应用

 

Abstract:近年来随着智能网联产业的高速发展，市面上对智能化功能的需求逐渐旺盛，其中基于SOA软件框架的智能网联APP由于其灵活高效等优点逐渐占据市场主流，联电通过结合自身擅长的动力域控制和智能优化算法，在节能减排、用户体验和基础服务方面开发了一系列智能网联功能包，目前已有若干功能包工程落地，并与多个客户达成项目合作。

 

鄢挺，博士，2018年毕业于上海交通大学机械与动力工程学院，随后进入联合汽车电子公司从事系统功能开发工作。负责完成了多项智能网联功能包开发，包含预测性滑行回收，预测性经济车速规划，驾驶员风格辨识，车速曲线估计等，在与BJEV、GW、SAIC等的合作项目中负责功能方案与场景设计、SOA服务架构定义，测试与验证等工作，另外也参与多项混合动力系统应用层软件开发项目。

 

朱仲文

Title: 面向ADAS的新能源汽车动力域控制解决方案

 

Abstract: 近年来，汽车技术向电动化和智能化发展趋日益明显。本报告介绍一种面向ADAS的新能源汽车动力域控制解决方案，讨论汽车电控系统未来发展趋势。

 

朱仲文，本硕博毕业于天津大学，悉尼科技大学访问学者，现任合肥工业大学汽车工程技术研究院教授级高工，黄山学者优秀青年，主要从事新能源、燃料电池、智能网联汽车控制技术及系统集成研究工作，荣获“天津市优秀科技工作者”、“江苏省六大高峰人才”、“扬州市最美科技工作者”等荣誉称号，获得过天津市科技进步二等奖一项、三等项一项，中国机械工业科学技术奖科技进步三等奖一项，江苏省汽车工程学会汽车工业科学技术三等奖一奖，作为团队负责人所带领团队“新能源电控技术开发创新团队”入选“天津市创新人才推进计划重点领域创新团队”。