博士生导师

导师介绍
姓      名 刘德荣
性     别
职称/职务 教授
所属专业 控制科学与工程
研究领域 智能控制理论及应用、复杂工业系统建模与控制、计算智能、智能信息处理、自适应动态规划、强化学习
个人主页

http://derongliu.org

电子邮箱 derongliu@foxmail.com

个人简述

自从201011日入选千人计划以来,刘德荣教授建立了一个研究团队,目前团队每年发表20多篇高水平SCI论文。自1992年起刘德荣教授共出版了18部学术著作、170SCI期刊论文、239篇国际会议论文。目前在SCI数据库里面总引用4794次,H-index39。在GoogleScholar里面总引用10441次,H-index58。刘德荣教授自1992年以来的主要研究成果总结如下。(1)早期研究饱和非线性系统,从事非线性系统稳定性方面的研究工作,其成果被国际学术界命名为“Liu-Michel”判据,解决了饱和非线性作用下系统的稳定性问题。(2)在神经网络方面,开创了递归神经网络的稀疏结构研究工作并成功将成果应用于联想记忆和细胞神经网络。(3)10年来,主要从事自适应动态规划理论和应用研究工作,在该领域出版了三本书,100多篇SCI论文,是国际上该研究领域的领军人物之一。自适应动态规划方法跟强化学习是同类方法,是智能控制、优化、信息处理、人工智能和机器学习领域的热点研究方向,近期Google旗下人工智能围棋AlphaGo采用的算法就是强化学习跟深度学习算法的结合。

学科领域

l科学学位:控制科学与工程

l专业学位:控制工程  

教育背景

l1990–1993年,美国圣母大学(University of Notre Dame),电气工程系,获电气工程博士学位

l1984–1987年,中国科学院自动化研究所,获工学硕士学位

l1978–1982年,华东工学院 (现南京理工大学),机电工程系,获工学学士学位

工作经历

l1982–1984年,北方工业公司国营向阳仪表厂技术员

l1987–1990年,中国科学院研究生院无线电电子学部助教

l1993–1995年,美国通用汽车公司研究开发中心StaffFellow

l1995–1999年,美国斯蒂文斯理工学院电气与计算机工程系助教授

l1999年开始,美国芝加哥伊利诺伊大学电气与计算机工程系助教授、终身职副教授、2006年起任终身职正教授

l2008–2015年,中国科学院自动化研究所研究员、博士生导师

l2015–2016年,北京科技大学自动化学院教授、博士生导师

l2017–今,广东工业大学自动化学院百人计划特聘教授、博士生导师

学术兼职          

l2016–2018年,亚太神经网络学会,副主席

l2016–2018年,IEEE计算智能学会DistinguishedLecturer

l2015–2017年和2006–2008年,IEEE计算智能学会理事(AdComMember

l2014–今,ArtificialIntelligence Review (Springer),主编

l2014–今,IEEE/CAAJournal of Automatica Sinica,副主编

l2014–2017年,IFAC理事会成员(CouncilMember

l2013–今,自动化学报,副主编

l2012–2014年,IEEE计算智能学会DistinguishedLecturer

l2012–2014年,IEEE计算智能学会北京分会主席

l2011–今,中国自动化学会常务理事

l2011–2015年,亚太神经网络联合会理事(BoG)和2016–今,亚太神经网络学会理事(BoG

l2010–2015年,IEEETransactions on Neural Networks and Learning Systems,主编

l2010–2012年,国际神经网络学会理事(BoG

l2008年起,在24个国际会议上做过大会报告和邀请报告

l2005–2008年,IEEE计算智能学会芝加哥分会主席

l24thInternational Conference on Neural Information Processing (ICONIP 2017),总主席

l12thWorld Congress on Intelligent Control and Automation (WCICA 2016),总主席

l2014IEEE World Congress on Computational Intelligence (WCCI 2014),总主席

lInternationalJoint Conference on Neural Networks (IJCNN 2008),程序主席          

主要荣誉    

lFellow,国际模式识别学会(IAPR2016

lFellow,国际神经网络学会(INNS2013

lFellow,电气与电子工程学会(IEEE2005

l中国科学院优秀研究生指导教师奖,2013

l亚太神经网络联合会(APPNA)杰出成就奖,2014

l神经信息处理国际大会(ICONIP)最佳论文奖:20152013,两次获奖

l国家特聘专家(中组部和人社部)2011

l国家自然科学基金委  海外杰出青年合作研究基金2008  

l伊利诺伊大学UniversityScholar奖,2006

l美国国家科学基金会教授早期事业发展奖(NSFCAREER Award1999  

l斯蒂文斯理工学院HarveyN. Davis杰出教学奖,1997

代表性论著

主要论文

[1]D. Liu and A.N. Michel, “Asymptotic stability of discrete-time systems with saturationnonlinearities with applications to digital filters,” IEEE Transactions on Circuits and Systems-I: Fundamental Theory andApplications, vol. 39, no. 10, pp. 798–807, Oct. 1992.  

[2]D. Liu and A.N. Michel, “Cellular neural networks for associative memories,” IEEE Transactions on Circuits andSystems-II: Analog and Digital Signal Processing, vol. 40, no. 2, pp.119–121, Feb. 1993.

[3]D. Liu and A.N. Michel, “Stability analysis of state-space realizations for two-dimensionalfilters with overflow nonlinearities,” IEEETransactions on Circuits and Systems-I: Fundamental Theory and Applications,vol. 41, no. 2, pp. 127–137, Feb. 1994.

[4]D. Liu and A.N. Michel, “Sparsely interconnected neural networks for associative memorieswith applications to cellular neural networks,” IEEE Transactions on Circuits and Systems-II: Analog and Digital SignalProcessing, vol. 41, no. 4, pp. 295–307, Apr. 1994.  

[5]D. Liu and Z.Lu, “A new synthesis approach for feedback neural networks based on theperceptron training algorithm,” IEEETransactions on Neural Networks, vol. 8, no. 6, pp. 1468–1482, Nov.1997.  

[6]D. Liu , E. I.Sara, and W. Sun, “Nested auto-regressive processes for MPEG-encoded video trafficmodeling,” IEEE Transactions on Circuitsand Systems for Video Technology, vol. 11, no. 2, pp. 169–183, Feb. 2001.

[7]D. Liu and A.Molchanov, “Criteria for robust absolute stability of time-varying nonlinearcontinuous-time systems,” Automatica,vol. 38, no. 4, pp. 627–637, Apr. 2002.

[8]D. Liu, T.-S.Chang, and Y. Zhang, “A constructive algorithm for feedforward neural networkswith incremental training,” IEEETransactions on Circuits and Systems-I: Fundamental Theory and Applications,vol. 49, no. 12, pp. 1876–1879, Dec. 2002.

[9]D. Liu, S. Hu,and J. Wang, “Global output convergence of a class of continuous-time recurrentneural networks with time-varying thresholds,” IEEE Transactions on Circuits and Systems-II: Express Briefs, vol.51, no. 4, pp. 161–167, Apr. 2004.

[10]  D. Liu, Y.Zhang, and H. Zhang, “A self-learning call admission control scheme for CDMAcellular networks,” IEEE Transactions onNeural Networks, vol. 16, no. 5, pp. 1219–1228, Sept. 2005.  

[11]  D. Liu and Y.Cai, “Taguchi method for solving the economic dispatch problem with nonsmoothcost functions,” IEEE Transactions onPower Systems, vol. 20, no. 4, pp. 2006–2014, Nov. 2005.  

[12]  D. Liu, X.Xiong, B. DasGupta, and H. Zhang, “Motif discoveries in unaligned molecularsequences using self-organizing neural networks,” IEEE Transactions on Neural Networks, vol. 17, no. 4, pp. 919–928,July 2006.[13]  D. Liu, S. Hu,and H. Zhang, “Simultaneous blind separation of instantaneous mixtures witharbitrary rank,” IEEE Transactions onCircuits and Systems-I: Regular Papers, vol. 53, no. 10, pp. 2287–2298,Oct. 2006.

[14]  D. Liu, Z.Pang, and S. R. Lloyd, “A neural network method for detection of obstructivesleep apnea and narcolepsy based on pupil size and EEG,” IEEE Transactions on Neural Networks, vol. 19, no. 2, pp. 308–318,Feb. 2008.

[15]  D. Liu, H.Javaherian, O. Kovalenko, and T. Huang, “Adaptive critic learning techniquesfor engine torque and air-fuel ratio control,” IEEE Transactions on Systems, Man and Cybernetics-Part B: Cybernetics,vol. 38, no. 4, pp. 988–993, Aug. 2008.

[16]  D. Liu, D.Wang, D. Zhao, Q. Wei, and N. Jin, “Neural-network-based optimal control for aclass of unknown discrete-time nonlinear systems using globalized dualheuristic programming,” IEEE Transactionson Automation Science and Engineering, vol. 9, no. 3, pp. 628–634, July2012.

[17]  D. Liu and Q.Wei, “Finite-approximation-error-based optimal control approach fordiscrete-time nonlinear systems," IEEETransactions on Cybernetics, vol. 43, no. 2, pp. 779–789, Apr. 2013.

[18]  D. Liu, D.Wang, and H. Li, “Decentralized stabilization for a class of continuous-timenonlinear interconnected systems using online learning optimal controlapproach,” IEEE Transactions on NeuralNetworks and Learning Systems, vol. 25, no. 2, pp. 418–428, Feb. 2014.

[19]  D. Liu and Q.Wei, “Policy iteration adaptive dynamic programming algorithm for discrete-timenonlinear systems,” IEEE Transactions onNeural Networks and Learning Systems, vol. 25, no. 3, pp. 621–634, Mar.2014.

[20]  D. Liu, H. Li,and D. Wang, “Online synchronous approximate optimal learning algorithm formultiplayer nonzero-sum games with unknown dynamics,” IEEE Transactions on Systems, Man and Cybernetics: Systems, vol.44, no.8, pp. 1015–1027, Aug. 2014.

[21]  D. Liu, D.Wang, F. Wang, H. Li, and X. Yang, “Neural-network-based online HJB solutionfor optimal robust guaranteed cost control of continuous-time uncertainnonlinear systems,” IEEE Transactions onCybernetics, vol. 44, no. 12, pp. 2834–2847, Dec. 2014.

[22]  D. Liu, H. Li,and D. Wang, “Error bounds for adaptive dynamic programming algorithms forsolving undiscounted optimal control problems,” IEEE Transactions on Neural Networks and Learning Systems, vol. 26,no. 6, pp. 1323–1334, June 2015.

[23]  D. Liu, X.Yang, D. Wang, and Q. Wei, “Reinforcement-learning-based robust controllerdesign for continuous-time uncertain nonlinear systems subject to inputconstraints,” IEEE Transactions onCybernetics, vol.45, no.7, pp.1372–1385, July 2015.

[24]  D. Liu, Q.Wei, and P. Yan, “Generalized policy iteration adaptive dynamic programming fordiscrete-time nonlinear systems,” IEEETransactions on Systems, Man, and Cybernetics: Systems, vol. 45, no. 12,pp. 1577–1591, Dec. 2015.

主要著作

[1]D. Liu and A.N. Michel, Dynamical Systems withSaturation Nonlinearities: Analysis and Design. New York: Springer-Verlag,1993 (ISBN: 0-387-19888-1).

[2]A. N. Micheland D. Liu, Qualitative Analysis andSynthesis of Recurrent Neural Networks. New York: Marcel Dekker, 2002(ISBN: 0-8247-0767-2).

[3]D. Liu and P.J. Antsaklis, Editors, Stability andControl of Dynamical Systems with Applications. Boston, MA: Birkhauser,2003 (ISBN: 0-8176-3233-6).

[4]F.-Y. Wang andD. Liu, Editors, Advances inComputational Intelligence: Theory and Applications. Singapore: WorldScientific, 2006 (ISBN: 981-256-734-8).

[5]H. Zhang andD. Liu, Fuzzy Modeling and Fuzzy Control.Boston, MA: Birkhauser, 2006 (ISBN: 0-8176-4491-1).

[6]A. N. Michel,L. Hou, and D. Liu, Stability of DynamicalSystems: Continuous, Discontinuous and Discrete Systems. Boston, MA:Birkh¨auser, 2007 (ISBN: 978-0-8176-4486-4)

[7]F.-Y. Wang andD. Liu, Editors, Networked ControlSystems: Theory and Applications. London, UK: Springer, 2008 (ISBN:978-1-84800-214-2).

[8]H. Zhang, D.Liu, and Z. Wang, Controlling Chaos:Suppression, Synchronization and Chaotification. London, UK: Springer, 2009(ISBN: 978-1-84882-522-2).

[9]H. Zhang, D.Liu, Y. Luo, and D. Wang, AdaptiveDynamic Programming for Control: Algorithms and Stability. London, UK:Springer, 2013 (ISBN: 978-1-4471-4757-2).

[10]  F. L. Lewisand D. Liu, Editors, ReinforcementLearning and Approximate Dynamic Programming for Feedback Control. Hoboken,NJ: Wiley, 2013 (ISBN: 978-1-118-10420-0).

[11]  D. Liu, C.Alippi, D. Zhao, and H. Zhang, Editors, Frontiersof Intelligent Control and Information Processing. Singapore: WorldScientific, 2014 (ISBN: 978-981-4616-87-4).

[12]  J. Keller, D.Liu, and D. Fogel, Fundamentals ofComputational Intelligence–Neural Networks, Fuzzy Systems, and EvolutionaryComputation. New York: IEEE/Wiley, 2016 (ISBN: 978-1-119-21434-2).

[13]  D. Liu, Q.Wei, D. Wang, X. Yang, and H. Li, AdaptiveDynamic Programming with Applications in Optimal Control, London: Springer,2017 (ISBN: 978-3-319-50813-9).

知识产权

l发明专利:基于回声状态网络的用电预测方法和系统,发明人:刘德荣,石光,魏庆来

l发明专利:办公建筑能耗管理方法,发明人:刘德荣,石光,魏庆来

l发明专利:一种基于可变误差的非线性系统自适应最优控制方法,发明人:刘德荣,魏庆来,林汉权,李超

l发明专利:一种基于神经网络的办公建筑房间分类方法,发明人:刘德荣,石光,魏庆来,刘禹,关强

l发明专利:一种智能微电网分布式储能设备控制优化方法,发明人:刘德荣,魏庆来,石光

l发明专利:一种带有储能设备的智能微电网电能优化控制方法,发明人:刘德荣,魏庆来,石光

l发明专利:一种变换炉系统的炉温自学习控制方法,发明人:刘德荣,魏庆来,李超,徐延才

l发明专利:一种智能微电网双电池电能协同优化方法,发明人:刘德荣,魏庆来,徐延才

l发明专利:一种煤气化炉系统的炉温自学习控制方法,发明人:刘德荣,魏庆来,徐延才

l发明专利:变换炉的控制方法,发明人:刘德荣,魏庆来,黄玉柱,赵冬斌

科研项目

l国家自然科学基金委重点项目:

1.  面向建筑群的分布式能源系统一体化建模与优化调度,2016.1.1–2020.12.31.

2.  复杂系统平行控制基础理论及典型应用,2013.1.1–2017.12.31.
3.  基于数据的非线性控制系统分析与设计,2011.1.1–2014.12.31.

l国家自然科学基金委面上项目:

Ø基于数据的智能电网电能供需自适应优化匹配与调控,2013.1.1–2016.12.31.

l北京市自然科学基金:

Ø基于自适应动态规划的多控制器非线性系统零和博弈控制,2010.1.1–2012.12.31.

l国家自然科学基金委海外青年学者合作研究基金(海外杰青):

Ø智能控制理论,2008.1.1–2010.12.31.

我的团队

魏庆来、王鼎、杨雄、罗彪、谭拂晓、万频、王永华、赵博