Dynamic Extreme Learning Machine Identification for Nonlinear System with Long Time Delay
详细信息 查看官网全文
- 英文论文题名：Dynamic Extreme Learning Machine Identification for Nonlinear System with Long Time Delay
- 论文作者：Dazi Li ; Tianjiao Kang ; Jinglin Zhou ; Qibing Jin
- 英文论文作者：Dazi Li ; Tianjiao Kang ; Jinglin Zhou ; Qibing Jin ; Institute of Automation ; Beijing University of Chemical Technology
- 年：2017
- 作者机构：Institute of Automation,Beijing University of Chemical Technology;
- 英文论文关键词：Extreme learning machine ; System identification ; pH neutralization ; Long time delay ; Particle swarm optimization
- 会议召开时间：2017-07-26
- 会议录名称：第36届中国控制会议论文集（B）
- 英文会议录名称：Proceedings of the 36th Chinese Control Conference（B）
- 语种：英文
- 分类号：N945.14
- 学会代码：KZLL
- 会议名称：第36届中国控制会议
- 会议地点：中国辽宁大连
- 主办单位：中国自动化学会控制理论专业委员会
- 学会名称：中国自动化学会控制理论专业委员会
- 页数：5
- 文件大小：211k
- 原文格式：D
- 会议级别：全国
摘要
In this paper, a new method is presented for identification of single-input single-output(SISO) nonlinear systems with long time delay. The proposed dynamic extreme learning machine(DELM) is different from extreme learning machine in that it adds adaptive delay parameters in the output layer of the network, and the delay parameter is optimized by use of particle swarm algorithm. The dynamic extreme learning machine has two main advantages: First, for any system, it needs only two input nodes. Second, it does not need to know the specific delay time. A pH neutralization process and a nonlinear dynamic system process are used to evaluate the performance of the proposed method. Simulation results demonstrate the effectiveness of the proposed identification algorithm for a class of nonlinear system with long time delay.
In this paper, a new method is presented for identification of single-input single-output(SISO) nonlinear systems with long time delay. The proposed dynamic extreme learning machine(DELM) is different from extreme learning machine in that it adds adaptive delay parameters in the output layer of the network, and the delay parameter is optimized by use of particle swarm algorithm. The dynamic extreme learning machine has two main advantages: First, for any system, it needs only two input nodes. Second, it does not need to know the specific delay time. A pH neutralization process and a nonlinear dynamic system process are used to evaluate the performance of the proposed method. Simulation results demonstrate the effectiveness of the proposed identification algorithm for a class of nonlinear system with long time delay.
In this paper, a new method is presented for identification of single-input single-output(SISO) nonlinear systems with long time delay. The proposed dynamic extreme learning machine(DELM) is different from extreme learning machine in that it adds adaptive delay parameters in the output layer of the network, and the delay parameter is optimized by use of particle swarm algorithm. The dynamic extreme learning machine has two main advantages: First, for any system, it needs only two input nodes. Second, it does not need to know the specific delay time. A pH neutralization process and a nonlinear dynamic system process are used to evaluate the performance of the proposed method. Simulation results demonstrate the effectiveness of the proposed identification algorithm for a class of nonlinear system with long time delay.
引文
[1]L.Pekar,F.Neri,An Introduction to the Special Issue on Time Delay Systems:Modelling,Identification,Stability,Control and Applications.Wseas Transaction on Systems,2012.
[2]E.Sitompul,Adaptive Neural Networks for Nonlinear Dynamic Systems Identification,Fifth International Conference on Computational Intelligence,Modelling and Simulation,8-13,2013.
[3]S.Bedoui,M.Ltaief,K.Abderrahim,A new recursive algorithm for simultaneous identification of discrete time delay systems,IFAC Proceedings Volumes,45(16):1502-1507,2012.
[4]S.Chen,S.A.Billings,Neural networks for nonlinear dynamic system modelling and identification,International Journal of Control,56(2):319–46,1992.
[5]G.P.Moss,T.Kyriacou,S.C.Wilkinson,The Application of non-linear auto-regressive moving average with exogenous input(Narmax)to modelling the absorption across human skin.International Journal of Cosmeticence,34(4):377-377,2013.
[6]G.Kouba,R.M.Botez,N.Boely,Fuzzy logic method use in F/A-18 aircraft model identification,Journal of Aircraft,47(1):1-17,2012.
[7]R.Babuska,H.Verbruggen,Neuro-fuzzy methods for nonlinear system identification,Annual Reviews in Control,27(1):73–85,2003.
[8]A.Kalafatis,N.Arifin,L.Wang,Cluett W,A new approach to the identification of ph processes based on the Wiener model,Chemical Engineering Science,50(23):3693–701,1995.
[9]V.Arto,P.Hannu,A.Halme,Modeling of chromatographic separation process with Wiener-MLP representation,Journal of Process Control,11(5):443–58,2001.
[10]T.Wigren,Recursive prediction error identification using the nonlinear wiener model,Automatic,29(4):1011–25,1993.
[11]I.W.Hunter,M.J.Korenberg,The identification of nonlinear biological systems:Wiener and Hammerstein cascade models,Biological Cybernetics,55:135–44,1986.
[12]R.K.Pearson,Outliers in process modeling and identification,IEEE Transactions on Control Systems Technology,10(1):55-63,2002.
[13]J.C.Gomez,A.Jutan,E.Baeyens,Wiener model identification and predictive control of a p H neutralization process,IEE Proceedings-Control Theory and Applications151(3):329-338,2001.
[14]P.Wang,S.Y.LI,Multiple model-based predictive control for a class of nonlinear systems,Control and Decision,22(10),2007.
[15]L.Yuan,T.S.Wen,C.Sen,Research and application of predictive control algorithm based on fuzzy model,International Conference on Advanced Mechatronic Systems,IEEE,2015:244-248.
[16]D.Q.Zhao,C.X.Li,S.N.Lan,Least squares support vector machine based time-delay control algorithm for reducing seismic responses of structures,Journal of Vibration&Shock,32(9):165-172,2013.
[17]I.Cherif,F.Fnaiech,Nonlinear System Identification with a Real–Coded Genetic Algorithm(RCGA),International Journal of Applied Mathematics&Computer Science,25(4):863-875,2015.
[18]A.Balestrino,F.B.Verona,A.Landi,On-line process estimation by ANNs and Smith controller dedign,IEE Proceedings-Control Theory and Application,145(2):231-235,1998.
[19]X.M.Ren,A.B.Rad,Identification of nonlinear systems with unknown time delay based on time-delay neural networks,IEEE Transactions on Neural Networks,18(5):1536-1541,2007.
[20]M.Han,B.Han,W.Guo,Process control of p H neutralization based on adaptive algorithm of universal learning network,Journal of Process Control,16(1),2006.
[21]J.Kennedy and R.Eberhart,“Particle swarm optimization”in Proceedings of the IEEE International Conference on Neural Networks,vol.4,pp.1942–1948,1995.
[22]Y.Xu and Y.Shu,Evolutionary extreme learning machineBased on particle swarm optimization,Lecture Notes in Computer Science,vol.3971,2006.
[23]G.B.Huang,Q.Y.Zhu,C.K.Siew,Extreme learning machine:A new learning scheme of feed forward neural networks,in Proceedings of the 2004 IEEE international joint conference on neural networks,vol.2,p.985–90,2004.
[24]M.Luo,K.Zhang,A hybrid approach combining extreme learning machine and sparse representation for image classification,Engineering Applications of Artificial Intelligence,27,228-235,2014.
[25]L.J.Zhao,D.C.Yuan,J.Tang,Ball mill load state recognition based on kernel PCA and probabilistic PLS-ELM,in 2012 International Conference on Information Technology and Management Innovation,pp.398-401,2012.
[26]G.B.Huang,Q.Y.Zhu,C.K.Siew,Extreme learning machine:theory and applications,Neurocomputing 70(1)489–501,2006.
[27]L.Zhang,N.Wang,Double neuron model-free control for p H processes,Control and Decision Conference.IEEE:2867-2871,2010.
[28]Y.L.Hsu,J.S.Wang,A wiener-type recurrent neural network and its control strategy for nonlinear dynamic applications,Process Control,19(6):942–53,2009.
[29]P.A.Mastorocostas,J.B.Theocharis,A recurrent fuzzy-neural model for dynamic system identification,IEEE Transactions on Systems Man&Cybernetics Part B Cybernetics A Publication of the IEEE Systems Man&Cybernetics Society,32(2):176-90,2002.
[2]E.Sitompul,Adaptive Neural Networks for Nonlinear Dynamic Systems Identification,Fifth International Conference on Computational Intelligence,Modelling and Simulation,8-13,2013.
[3]S.Bedoui,M.Ltaief,K.Abderrahim,A new recursive algorithm for simultaneous identification of discrete time delay systems,IFAC Proceedings Volumes,45(16):1502-1507,2012.
[4]S.Chen,S.A.Billings,Neural networks for nonlinear dynamic system modelling and identification,International Journal of Control,56(2):319–46,1992.
[5]G.P.Moss,T.Kyriacou,S.C.Wilkinson,The Application of non-linear auto-regressive moving average with exogenous input(Narmax)to modelling the absorption across human skin.International Journal of Cosmeticence,34(4):377-377,2013.
[6]G.Kouba,R.M.Botez,N.Boely,Fuzzy logic method use in F/A-18 aircraft model identification,Journal of Aircraft,47(1):1-17,2012.
[7]R.Babuska,H.Verbruggen,Neuro-fuzzy methods for nonlinear system identification,Annual Reviews in Control,27(1):73–85,2003.
[8]A.Kalafatis,N.Arifin,L.Wang,Cluett W,A new approach to the identification of ph processes based on the Wiener model,Chemical Engineering Science,50(23):3693–701,1995.
[9]V.Arto,P.Hannu,A.Halme,Modeling of chromatographic separation process with Wiener-MLP representation,Journal of Process Control,11(5):443–58,2001.
[10]T.Wigren,Recursive prediction error identification using the nonlinear wiener model,Automatic,29(4):1011–25,1993.
[11]I.W.Hunter,M.J.Korenberg,The identification of nonlinear biological systems:Wiener and Hammerstein cascade models,Biological Cybernetics,55:135–44,1986.
[12]R.K.Pearson,Outliers in process modeling and identification,IEEE Transactions on Control Systems Technology,10(1):55-63,2002.
[13]J.C.Gomez,A.Jutan,E.Baeyens,Wiener model identification and predictive control of a p H neutralization process,IEE Proceedings-Control Theory and Applications151(3):329-338,2001.
[14]P.Wang,S.Y.LI,Multiple model-based predictive control for a class of nonlinear systems,Control and Decision,22(10),2007.
[15]L.Yuan,T.S.Wen,C.Sen,Research and application of predictive control algorithm based on fuzzy model,International Conference on Advanced Mechatronic Systems,IEEE,2015:244-248.
[16]D.Q.Zhao,C.X.Li,S.N.Lan,Least squares support vector machine based time-delay control algorithm for reducing seismic responses of structures,Journal of Vibration&Shock,32(9):165-172,2013.
[17]I.Cherif,F.Fnaiech,Nonlinear System Identification with a Real–Coded Genetic Algorithm(RCGA),International Journal of Applied Mathematics&Computer Science,25(4):863-875,2015.
[18]A.Balestrino,F.B.Verona,A.Landi,On-line process estimation by ANNs and Smith controller dedign,IEE Proceedings-Control Theory and Application,145(2):231-235,1998.
[19]X.M.Ren,A.B.Rad,Identification of nonlinear systems with unknown time delay based on time-delay neural networks,IEEE Transactions on Neural Networks,18(5):1536-1541,2007.
[20]M.Han,B.Han,W.Guo,Process control of p H neutralization based on adaptive algorithm of universal learning network,Journal of Process Control,16(1),2006.
[21]J.Kennedy and R.Eberhart,“Particle swarm optimization”in Proceedings of the IEEE International Conference on Neural Networks,vol.4,pp.1942–1948,1995.
[22]Y.Xu and Y.Shu,Evolutionary extreme learning machineBased on particle swarm optimization,Lecture Notes in Computer Science,vol.3971,2006.
[23]G.B.Huang,Q.Y.Zhu,C.K.Siew,Extreme learning machine:A new learning scheme of feed forward neural networks,in Proceedings of the 2004 IEEE international joint conference on neural networks,vol.2,p.985–90,2004.
[24]M.Luo,K.Zhang,A hybrid approach combining extreme learning machine and sparse representation for image classification,Engineering Applications of Artificial Intelligence,27,228-235,2014.
[25]L.J.Zhao,D.C.Yuan,J.Tang,Ball mill load state recognition based on kernel PCA and probabilistic PLS-ELM,in 2012 International Conference on Information Technology and Management Innovation,pp.398-401,2012.
[26]G.B.Huang,Q.Y.Zhu,C.K.Siew,Extreme learning machine:theory and applications,Neurocomputing 70(1)489–501,2006.
[27]L.Zhang,N.Wang,Double neuron model-free control for p H processes,Control and Decision Conference.IEEE:2867-2871,2010.
[28]Y.L.Hsu,J.S.Wang,A wiener-type recurrent neural network and its control strategy for nonlinear dynamic applications,Process Control,19(6):942–53,2009.
[29]P.A.Mastorocostas,J.B.Theocharis,A recurrent fuzzy-neural model for dynamic system identification,IEEE Transactions on Systems Man&Cybernetics Part B Cybernetics A Publication of the IEEE Systems Man&Cybernetics Society,32(2):176-90,2002.