Adaptive Nonlinear Model Predictive Control Using an On-line Support Vector Regression Updating Strategy

doi:10.1016/j.cjche.2014.05.004

›› 2014, Vol. 22 ›› Issue (7): 774-781.DOI: 10.1016/j.cjche.2014.05.004

• PROCESS CONTROL • 上一篇下一篇

Adaptive Nonlinear Model Predictive Control Using an On-line Support Vector Regression Updating Strategy

Ping Wang^1,2, Chaohe Yang¹, Xuemin Tian², Dexian Huang ³

1. State Key Laboratory of Heavy Oil Processing, China University of Petroleum, Qingdao 266580, China;
2. College of Information and Control Engineering, China University of Petroleum, Qingdao 266580, China;
3. Department of Automation, Tsinghua University, Beijing 100084, China

收稿日期:2013-06-24 修回日期:2013-11-16 出版日期:2014-07-28 发布日期:2014-08-23
通讯作者: Xuemin Tian
基金资助:
Supported by the National Basic Research Program of China (2012CB720500), Postdoctoral Science Foundation of China (2013M541964) and Fundamental Research Funds for the Central Universities (13CX05021A).

Adaptive Nonlinear Model Predictive Control Using an On-line Support Vector Regression Updating Strategy

Ping Wang^1,2, Chaohe Yang¹, Xuemin Tian², Dexian Huang ³

1. State Key Laboratory of Heavy Oil Processing, China University of Petroleum, Qingdao 266580, China;
2. College of Information and Control Engineering, China University of Petroleum, Qingdao 266580, China;
3. Department of Automation, Tsinghua University, Beijing 100084, China

Received:2013-06-24 Revised:2013-11-16 Online:2014-07-28 Published:2014-08-23
Supported by:
Supported by the National Basic Research Program of China (2012CB720500), Postdoctoral Science Foundation of China (2013M541964) and Fundamental Research Funds for the Central Universities (13CX05021A).

摘要/Abstract

摘要： The performance of data-drivenmodels relies heavily on the amount and quality of training samples, so itmight deteriorate significantly in the regions where samples are scarce. The objective of this paper is to develop an online SVR model updating strategy to track the change in the process characteristics efficiently with affordable computational burden. This is achieved by adding a new sample that violates the Karush-Kuhn-Tucker conditions of the existing SVR model and by deleting the old sample that has the maximum distance with respect to the newly added sample in feature space. The benefits offered by such an updating strategy are exploited to develop an adaptive model-based control scheme, where model updating and control task perform alternately. The effectiveness of the adaptive controller is demonstrated by simulation study on a continuous stirred tank reactor. The results reveal that the adaptive MPC scheme outperforms its non-adaptive counterpart for largemagnitude set point changes and variations in process parameters.

关键词: Adaptive control, Support vector regression, Updating strategy, Model predictive control

Abstract: The performance of data-drivenmodels relies heavily on the amount and quality of training samples, so itmight deteriorate significantly in the regions where samples are scarce. The objective of this paper is to develop an online SVR model updating strategy to track the change in the process characteristics efficiently with affordable computational burden. This is achieved by adding a new sample that violates the Karush-Kuhn-Tucker conditions of the existing SVR model and by deleting the old sample that has the maximum distance with respect to the newly added sample in feature space. The benefits offered by such an updating strategy are exploited to develop an adaptive model-based control scheme, where model updating and control task perform alternately. The effectiveness of the adaptive controller is demonstrated by simulation study on a continuous stirred tank reactor. The results reveal that the adaptive MPC scheme outperforms its non-adaptive counterpart for largemagnitude set point changes and variations in process parameters.

Key words: Adaptive control, Support vector regression, Updating strategy, Model predictive control

Ping Wang, Chaohe Yang, Xuemin Tian, Dexian Huang . Adaptive Nonlinear Model Predictive Control Using an On-line Support Vector Regression Updating Strategy[J]. , 2014, 22(7): 774-781.

参考文献

[1] S.J. Qin, T.A. Badgwell, A survey of industrial model predictive control technology, Control. Eng. Pract. 11 (7) (2003) 733-764.
[2] S. Engell, Feedback control for optimal process operation, J. Process Control 17 (3) (2007) 203-219.
[3] L. Magni, M.D. Raimondo, F. Allgower, Nonlinear model predictive control: towards new challenging applications, Lecture Notes in Control and Information Sciences, vol. 384, Springer-Verlag, Berlin, 2009.
[4] J.A.K. Suykens, Support vector machines and kernel-based learning for dynamical systemsmodelling, Proceedings of the 15th IFAC Symposium on System Identification, Saint-Malo, France, 2009, pp. 1029-1037.
[5] S.B. Chitralekha, S.L. Shah, Application of support vector regression for developing soft sensors for nonlinear processes, Can. J. Chem. Eng. 88 (5) (2010) 696-709.
[6] J.L.Wang, T. Yu, C.Y. Jin, On-line estimation of biomass in fermentation process using support vector machine, Chin. J. Chem. Eng. 14 (3) (2006) 383-388.
[7] S.N. Zhang, F.L. Wang, D.K. He, R.D. Jia, Real-time product quality control for batch processes based on stacked least-squares support vector regressionmodels, Comput. Chem. Eng. 36 (10) (2012) 217-226.
[8] J.A. Yu, Bayesian inference based two-stage support vector regression framework for soft sensor development in batch bioprocesses, Comput. Chem. Eng. 41 (11) (2012) 134-144.
[9] P. Kadlec, R. Grbic, B. Gabrys, Review of adaptation mechanisms for data-driven soft sensors, Comput. Chem. Eng. 35 (1) (2011) 1-24.
[10] J.l. Liu, Development of self-validating soft sensors using fast moving window partial least squares, Ind. Eng. Chem. Res. 49 (22) (2010) 11530-11546.
[11] Y. Liu, H.Q. Wang, J. Yu, Selective recursive kernel learning for online identification of nonlinear systems with NARX form, J. Process Control 20 (2) (2010) 181-194.
[12] L.J. Li, H.Y. Su, J. Chu, Modeling of isomerization of C8 aromatics by online least squares support vector machine, Chin. J. Chem. Eng. 17 (3) (2009) 437-444.
[13] K. Chen, J. Ji, H.Q.Wang, Adaptive local kernel-based learning for soft sensor modeling of nonlinear processes, Chem. Eng. Res. Des. 89 (10) (2011) 2117-2124.
[14] D. Li, H. Li, T. Si, On-line robust modeling of nonlinear systems using support vector regression, Proceedings of 2nd International Conference on Advanced Computer Control (ICACC), Shenyang, China, 2010, pp. 204-208.
[15] J. Ma, J. Theiler, S. Perkins, Accurate online support vector regression, Neural Comput. 15 (11) (2003) 2683-2704.
[16] S. Iplikci, Online trained support vector machines-based generalized predictive control of non-linear systems, Int. J. Adapt. Control Sig. Process 20 (10) (2006) 599-621.
[17] H. Wang, D.Y. Pi, Y.X. Su, Online SVM regression algorithm-based adaptive inverse control, Neurocomputing 70 (4-6) (2007) 952-959.
[18] S.R. Sergio,M.J. Fuente, Fault tolerance in the framework of support vectormachines based model predictive control, Eng. Appl. Artif. Intell. 23 (7) (2010) 1127-1139.
[19] P. Wang, H.G. Tian, X.M. Tian, D.X. Huang, A new approach for online adaptive modeling using incremental support vector regression, CIESC J. 61 (8) (2010) 2040-2045.
[20] J. Zhan,M. Ishida, Themulti-step predictive control of nonlinear SISO processes with a neural model predictive control (NMPC) method, Comput. Chem. Eng. 21 (2) (1997) 201-210.
[21] W.D. Zhou, L. Zhang, L.C. Jiao, An analysis of SVMs generalization performance, Acta Electron. Sin. 29 (5) (2001) 590-594.
[22] Y. Liu, Y.C. Gao, Z.L. Gao, H.Q.Wang, P. Li, Simple nonlinear predictive control strategy for chemical processes using sparse kernel learning with polynomial form, Ind. Eng. Chem. Res. 49 (17) (2010) 8209-8218.
[23] E. Wael, K. Mehmed, Local properties of RBF-SVM during training for incremental learning, Proceedings of International Joint Conference on Neural Networks, Atlanta, Georgia, USA, 2009, pp. 779-786.
[24] W.M. Zhang, G.L. He, D.Y. Pi, Y.X. Su, SVM with polynomial kernel function based nonlinear model one-step-ahead predictive control, Chin. J. Chem. Eng. 13 (3) (2005) 373-379.
[25] E. Hernandez, Y. Arkun, Study of the control-relevant properties of back propagation neural network models of nonlinear dynamical systems, Comput. Chem. Eng. 16 (4) (1992) 227-240.

Adaptive Nonlinear Model Predictive Control Using an On-line Support Vector Regression Updating Strategy

Adaptive Nonlinear Model Predictive Control Using an On-line Support Vector Regression Updating Strategy

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	Shan Liu, Wenqi Zhong, Xi Chen, Li Sun, Lukuan Yang. Multiobjective economic model predictive control using utopia-tracking for the wet flue gas desulphurization system[J]. 中国化学工程学报, 2023, 54(2): 343-352.
[2]	Zhen Wang, Aimin An, Qianrong Li. Distributed model predictive control based on adaptive sampling mechanism[J]. 中国化学工程学报, 2021, 39(11): 193-204.
[3]	Lukuan Yang, Wenqi Zhong, Li Sun, Xi Chen, Yingjuan Shao. Dynamic optimization oriented modeling and nonlinear model predictive control of the wet limestone FGD system[J]. 中国化学工程学报, 2020, 28(3): 832-845.
[4]	Li Jia, Wendan Tan. Just-in-time learning based integrated MPC-ILC control for batch processes[J]. Chinese Journal of Chemical Engineering, 2018, 26(8): 1713-1720.
[5]	Jianxin Wang, Na Yu, Mengqi Chen, Lin Cong, Lanyi Sun. Composition control and temperature inferential control of dividing wall column based on model predictive control and PI strategies[J]. Chinese Journal of Chemical Engineering, 2018, 26(5): 1087-1101.
[6]	Pengfei Cao, Xionglin Luo, Xiaohong Song. Feasibility analysis and online adjustment of constraints in model predictive control integrated with soft sensor[J]. , 2017, 25(9): 1230-1237.
[7]	Haokun Wang, Zuhua Xu, Jun Zhao, Aipeng Jiang. An optimal filter based MPC for systems with arbitrary disturbances[J]. , 2017, 25(5): 632-640.
[8]	Mahmoud M. Saafan, Mohamed M. Abdelsalam, Mohamed S. Elksas, Sabry F. Saraya, Fayez F. G. Areed. An adaptive neuro-fuzzy sliding mode controller for MIMO systems with disturbance[J]. , 2017, 25(4): 463-476.
[9]	Ping Yuan, Bi Zhang, Zhizhong Mao. A self-tuning control method for Wiener nonlinear systems and its application to process control problems[J]. , 2017, 25(2): 193-201.
[10]	Cuimei Bo, Jun Li, Lei Yang, Hui Yi, Jihai Tang, Xu Qiao. MPC of distillation column with side reactors for methyl acetate[J]. Chinese Journal of Chemical Engineering, 2017, 25(12): 1798-1804.
[11]	Hongguang Pan, Weimin Zhong, Zaiying Wang. An on-line constraint softening strategy to guarantee the feasibility of dynamic controller in double-layered MPC[J]. Chinese Journal of Chemical Engineering, 2017, 25(12): 1805-1811.
[12]	Baocang Ding, Hongguang Pan. Output feedback robust model predictive control with unmeasurable model parameters and bounded disturbance[J]. , 2016, 24(10): 1431-1441.
[13]	Kai Feng, Jiangang Lu, Jinshui Chen. Nonlinearmodel predictive control based on support vectormachine and genetic algorithm[J]. Chinese Journal of Chemical Engineering, 2015, 23(12): 2048-2052.
[14]	Zhe Dong. Adaptive output-feedback power-level control for modular high temperature gas-cooled reactors[J]. Chinese Journal of Chemical Engineering, 2015, 23(12): 2092-2097.
[15]	Defeng He, Shiming Yu, Li Yu. Multi-objective nonlinear model predictive control through switching cost functions and its applications to chemical processes[J]. Chinese Journal of Chemical Engineering, 2015, 23(10): 1662-1669.