Auxiliary error and probability density function based neuro-fuzzymodel and its application in batch processes

doi:10.1016/j.cjche.2015.11.010

Chin.J.Chem.Eng. ›› 2015, Vol. 23 ›› Issue (12): 2013-2019.DOI: 10.1016/j.cjche.2015.11.010

Previous Articles Next Articles

Auxiliary error and probability density function based neuro-fuzzymodel and its application in batch processes

Li Jia, Kai Yuan

Shanghai Key Laboratory of Power Station Automation Technology, Department of Automation, College ofMechatronics Engineering and Automation, ShanghaiUniversity, Shanghai 200072, China

Received:2015-05-19 Revised:2015-07-10 Online:2016-01-19 Published:2015-12-28
Contact: Li Jia
Supported by:
Supported by the National Natural Science Foundation of China (61374044), Shanghai Science Technology Commission (12510709400), Shanghai Municipal Education Commission (14ZZ088), and Shanghai Talent Development Plan.

Auxiliary error and probability density function based neuro-fuzzymodel and its application in batch processes

Li Jia, Kai Yuan

Shanghai Key Laboratory of Power Station Automation Technology, Department of Automation, College ofMechatronics Engineering and Automation, ShanghaiUniversity, Shanghai 200072, China

通讯作者: Li Jia
基金资助:
Supported by the National Natural Science Foundation of China (61374044), Shanghai Science Technology Commission (12510709400), Shanghai Municipal Education Commission (14ZZ088), and Shanghai Talent Development Plan.

Abstract

Abstract: This paper focuses on resolving the identification problemof a neuro-fuzzymodel (NFM) applied in batch processes. A hybrid learning algorithm is introduced to identify the proposed NFM with the idea of auxiliary error model and the identification principle based on the probability density function (PDF). The main contribution is that the NFM parameter updating approach is transformed into the shape control for the PDF ofmodeling error.More specifically, a virtual adaptive control systemis constructed with the aid of the auxiliary errormodel and then the PDF shape control idea is used to tune NFM parameters so that the PDF of modeling error is controlled to follow a targeted PDF, which is in Gaussian or uniform distribution. Examples are used to validate the applicability of the proposed method and comparisons are made with the minimum mean square error based approaches.

Key words: Batch process, Auxiliary error model, Probability density function, Neuro-fuzzy model

摘要： This paper focuses on resolving the identification problemof a neuro-fuzzymodel (NFM) applied in batch processes. A hybrid learning algorithm is introduced to identify the proposed NFM with the idea of auxiliary error model and the identification principle based on the probability density function (PDF). The main contribution is that the NFM parameter updating approach is transformed into the shape control for the PDF ofmodeling error.More specifically, a virtual adaptive control systemis constructed with the aid of the auxiliary errormodel and then the PDF shape control idea is used to tune NFM parameters so that the PDF of modeling error is controlled to follow a targeted PDF, which is in Gaussian or uniform distribution. Examples are used to validate the applicability of the proposed method and comparisons are made with the minimum mean square error based approaches.

关键词: Batch process, Auxiliary error model, Probability density function, Neuro-fuzzy model

Li Jia, Kai Yuan. Auxiliary error and probability density function based neuro-fuzzymodel and its application in batch processes[J]. Chin.J.Chem.Eng., 2015, 23(12): 2013-2019.

Li Jia, Kai Yuan. Auxiliary error and probability density function based neuro-fuzzymodel and its application in batch processes[J]. Chinese Journal of Chemical Engineering, 2015, 23(12): 2013-2019.

References

[1] Linyun Lu, Fuli Wang, Furong Gao, Statistical modeling and online monitoring of batch processes, Acta Autom. Sin. 32 (3) (2006) 400-410.

[2] Li Jia, Jiping Shi, Minsen Chiu, An iterative learning control algorithm with convergence analysis for batch processes, J. Chem. Ind. Eng. 61 (1) (2010) 116-123.

[3] Jie Zhang, Batch-to-batch optimal control of a batch polymerization process based on stacked neural network models, Chem. Eng. Sci. 63 (2008) 1273-1281.

[4] R.D. Zhang, A.K. Xue, J.Z. Wang, Neural network based iterative learning predictive control design for mechatronic systems with isolated nonlinearity, J. Process Control 19 (2009) 68.

[5] Li Jia, Tian Yang, An Integrated Iterative Learning Control Strategy with ModelModification and Dynamic R-Parameter for Batch Processes, J. Process Control 23 (2013) 1332-1341.

[6] Li Jia, Kai Yuan, The probability density function based neuro-fuzzy model and its application in batch processes, Neurocomputing 148 (2015) 216-221.

[7] Li Jia, Kai Yuan, Time-varying Neuro-fuzzy Model Using Probability Density Function Techniques for Batch Processes, Journal of Statistical Computation and Simulation 84 (2014) 1249-1260.

[8] Z.H. Xiong, J. Zhang, Neural networkmodel-based on-line re-optimization control of fed-batch processes using a modified iterative dynamic programming algorithm, Chem. Eng. Process. 44 (4) (2005) 477-484.

[9] Y. Tian, J. Zhang, J. Morris, Optimal control of a fed-batch bioreactor based upon an augmented recurrent neural network model, Neurocomputing 48 (2002) 919-936.

[10] J. Zhang, Modeling and optimal control of batch processes using recurrent neurofuzzy networks, IEEE Trans. Fuzzy Syst. 13 (4) (2005) 417-427.

[11] Jinliang Ding, Tianyou Chai, Offline modeling for product quality prediction of mineral processing using modeling error PDF shaping and entropy minimization, IEEE Trans. Neural Netw. 22 (3) (2011) 408-419.

[12] Li Jia, Jiping Shi, Minsen Chiu, Research on fuzzy neural model with global convergence for batch process, Inf. Control. 38 (6) (2009) 683-691.

[13] M. Karny, Towards fully probabilistic control design, Automatic 32 (1996) 1719-1722.

[14] H. Wang, H. Yue, Output PDF control of stochastic distribution systems: modeling, control and applications, Control Eng. China 10 (3) (2003) 193-197.

[15] L. Guo, H. Wang, PID controller design for output PDFs of stochastic systems using linear matrix inequalities, IEEE Trans. Syst. Man Cybern. B Cybern. 35 (1) (2005) 65-71.

[16] S.H. Tan, J.B. Hao, J. Vandewalle, Efficient identification of RBF neural net models for nonlinear discrete-time multivariable dynamical systems, Neurocomputing 9 (1995) 11-26.

[17] E. Parzen, On estimation of a probability density function and mode, Ann. Math. Stat. 33 (1962) 1065-1076.

[18] Z.H. Xiong, J. Zhang, X. Wang, Y.M. Xu, Run-to-run iterative optimization control of batch processes based on recurrent neural network, Adv. Neural Netw. 3174 (2004) 97-103.

Auxiliary error and probability density function based neuro-fuzzymodel and its application in batch processes

Auxiliary error and probability density function based neuro-fuzzymodel and its application in batch processes

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Racheal Aigbe, Doga Kavaz. Unravel the potential of zinc oxide nanoparticle-carbonized sawdust matrix for removal of lead (II) ions from aqueous solution [J]. Chinese Journal of Chemical Engineering, 2021, 29(1): 92-102.
[2]	Aihong Li, Changzhan Liu, Zhiyong Liu. A heuristic design method for batch water-using networks of multiple contaminants with regeneration unit [J]. Chinese Journal of Chemical Engineering, 2019, 27(5): 1103-1112.
[3]	Li Jia, Wendan Tan. Just-in-time learning based integrated MPC-ILC control for batch processes [J]. Chin.J.Chem.Eng., 2018, 26(8): 1713-1720.
[4]	Yongyong Hui, Xiaoqiang Zhao. Batch process monitoring based on WGNPE-GSVDD related and independent variables [J]. Chin.J.Chem.Eng., 2018, 26(12): 2549-2561.
[5]	Xuan Yang, Xiao'e Ruan. Robustness of reinforced gradient-type iterative learning control for batch processes with Gaussian noise [J]. Chin.J.Chem.Eng., 2016, 24(5): 623-629.
[6]	Dazi Li, Ningjia Meng, Tianheng Song. Learning control of fermentation process with an improved DHP algorithm [J]. , 2016, 24(10): 1399-1405.
[7]	Saima Noor, Shamsul Qamar. The space time CE/SE method for solving one-dimensional batch crystallization model with fines dissolution [J]. , 2015, 23(2): 337-341.
[8]	Chen Chen, Zhihua Xiong, Yisheng Zhong. Design and Analysis of Integrated Predictive Iterative Learning Control for Batch Process Based on Two-dimensional System Theory [J]. , 2014, 22(7): 762-768.
[9]	YANG Guojun, LI Xiuxi, QIAN Yu. A Real-time Updated Model Predictive Control Strategy for Batch Processes Based on State Estimation [J]. Chin.J.Chem.Eng., 2014, 22(3): 318-329.
[10]	WANG Limin, CHEN Xi, GAO Furong . An LMI Method to Robust Iterative Learning Fault-tolerant Guaranteed Cost Control for Batch Processes [J]. Chin.J.Chem.Eng., 2013, 21(4): 401-411.
[11]	CHI Ronghu, ZHANG Dexia, LIU Ximei, HOU Zhongsheng, JIN Shangtai. An Anticipatory Terminal Iterative Learning Control Approach with Applications to Constrained Batch Processes [J]. Chin.J.Chem.Eng., 2013, 21(3): 271-275.
[12]	GUO Hui, LI Hongguang. On-line Batch Process Monitoring with Improved Multi-way Independent Component Analysis [J]. Chin.J.Chem.Eng., 2013, 21(3): 263-270.
[13]	ZHANG Yuliang, ZHANG Beike, MA Xin, CAO Liulin, WU Chongguang. Consequence Identification for Maloperation in Batch Process [J]. Chin.J.Chem.Eng., 2013, 21(12): 1347-1359.
[14]	ZHAO Luping, ZHAO Chunhui, GAO Furong. Phase Transition Analysis Based Quality Prediction for Multi-phase Batch Processes^* [J]. Chin.J.Chem.Eng., 2012, 20(6): 1191-1197.
[15]	DONG Weiwei, YAO Yuan, GAO Furong. Phase Analysis and Identification Method for Multiphase Batch Processes with Partitioning Multi-way Principal Component Analysis (MPCA) Model^* [J]. Chin.J.Chem.Eng., 2012, 20(6): 1121-1127.