ARX-NNPLS Model Based Optimization Strategy and Its Application in Polymer Grade Transition Process*

Chinese Journal of Chemical Engineering ›› 2012, Vol. 20 ›› Issue (5): 971-979.

ARX-NNPLS Model Based Optimization Strategy and Its Application in Polymer Grade Transition Process^*

费正顺, 胡斌, 叶鲁彬, 梁军

State Key Lab of Industrial Control Technology, Institute of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China

收稿日期:2011-05-20 修回日期:2011-09-12 出版日期:2012-10-28 发布日期:2012-11-06
通讯作者: LIANG Jun,E-mail:jliang@iipc.zju.edu.cn
基金资助:
Supported by the National Natural Science Foundation of China (61174114);the National High Technology Research and Development Program of China (2007AA04Z168, 2009AA04Z154);the Research Fund for the Doctoral Program of Higher Education in China (20050335018)

ARX-NNPLS Model Based Optimization Strategy and Its Application in Polymer Grade Transition Process^*

FEI Zhengshun, HU Bin, YE Lubin, LIANG Jun

State Key Lab of Industrial Control Technology, Institute of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China

Received:2011-05-20 Revised:2011-09-12 Online:2012-10-28 Published:2012-11-06
Supported by:
Supported by the National Natural Science Foundation of China (61174114);the National High Technology Research and Development Program of China (2007AA04Z168, 2009AA04Z154);the Research Fund for the Doctoral Program of Higher Education in China (20050335018)

摘要/Abstract

摘要： Since it is often difficult to build differential algebraic equations (DAEs) for chemical processes, a new data-based modeling approach is proposed using ARX (AutoRegressive with eXogenous inputs) combined with neural network under partial least squares framework (ARX-NNPLS), in which less specific knowledge of the process is required but the input and output data. To represent the dynamic and nonlinear behavior of the process, the ARX combined with neural network is used in the partial least squares (PLS) inner model between input and output latent variables. In the proposed dynamic optimization strategy based on the ARX-NNPLS model, neither parameterization nor iterative solving process for DAEs is needed as the ARX-NNPLS model gives a proper representation for the dynamic behavior of the process, and the computing time is greatly reduced compared to conventional control vector parameterization method. To demonstrate the ARX-NNPLS model based optimization strategy, the polyethylene grade transition in gas phase fluidized-bed reactor is taken into account. The optimization results show that the final optimal trajectory of quality index determined by the new approach moves faster to the target values and the computing time is much less.

关键词: partial least squares, ARX-NN structure, dynamic optimization, grade transition, polymerization

Abstract: Since it is often difficult to build differential algebraic equations (DAEs) for chemical processes, a new data-based modeling approach is proposed using ARX (AutoRegressive with eXogenous inputs) combined with neural network under partial least squares framework (ARX-NNPLS), in which less specific knowledge of the process is required but the input and output data. To represent the dynamic and nonlinear behavior of the process, the ARX combined with neural network is used in the partial least squares (PLS) inner model between input and output latent variables. In the proposed dynamic optimization strategy based on the ARX-NNPLS model, neither parameterization nor iterative solving process for DAEs is needed as the ARX-NNPLS model gives a proper representation for the dynamic behavior of the process, and the computing time is greatly reduced compared to conventional control vector parameterization method. To demonstrate the ARX-NNPLS model based optimization strategy, the polyethylene grade transition in gas phase fluidized-bed reactor is taken into account. The optimization results show that the final optimal trajectory of quality index determined by the new approach moves faster to the target values and the computing time is much less.

Key words: partial least squares, ARX-NN structure, dynamic optimization, grade transition, polymerization

费正顺, 胡斌, 叶鲁彬, 梁军. ARX-NNPLS Model Based Optimization Strategy and Its Application in Polymer Grade Transition Process^*[J]. Chinese Journal of Chemical Engineering, 2012, 20(5): 971-979.

FEI Zhengshun, HU Bin, YE Lubin, LIANG Jun. ARX-NNPLS Model Based Optimization Strategy and Its Application in Polymer Grade Transition Process^*[J]. Chin.J.Chem.Eng., 2012, 20(5): 971-979.

参考文献

1 Biegler,L.T.,Grossmann,I.E.,"Retrospective on optimization",Comput.Chem.Eng.,28 (8),1169-1192 (2004).
2 Qin,S.J.,"Recursive PLS algorithms for adaptive data modeling",Comput Chem Eng,22 (4-5),503-514 (1998).
3 Wold,S.,Ruhe,A.,Wold,H.,Dunn,W.J.,"The collinearity problem in linear-regression-The partial least-squares (PLS) approach to generalized inverses",Siam Journal on Scientific and Statistical Computing,5 (3),735-743 (1984).
4 Wold,S.,Kettanehwold,N.,Skagerberg,B.,"Nonlinear PLS modeling",Chemometrics and Intelligent Laboratory Systems,7 (1-2),53-65 (1989).
5 Qin,S.J.,McAvoy,T.J.,"Nonlinear PLS modeling using neural networks",Comput Chem Eng,16 (4),379-391 (1992).
6 Sharmin,R.,Sundararaj,U.,Shah,S.,Griend,L.V.,Sun,Y.J.,"Inferential sensors for estimation of polymer quality parameters: Industrial application of a PLS-based soft sensor for a LDPE plant",Chem.Eng.Sci.,61 (19),6372-6384 (2006).
7 Baffi,G.,Morris,J.,Martin,E.,"Non-linear model based predictive control through dynamic non-linear partial least squares",Chem Eng Res Des,80 (A1),75-86 (2002).
8 Hu,B.,Zheng,P.Y.,Liang,J.,"Multi-loop internal model controller design based on a dynamic PLS framework",Chin.J.Chem.Eng.,18 (2),277-285 (2010).
9 Hu,B.,Zhao,Z.,Liang,J.,"Multi-loop nonlinear internal model controller design under nonlinear dynamic PLS framework using ARX-neural network model",Journal of Process Control,22 (1),207-217 (2012).
10 Vassiliadis,V.S.,Sargent,R.W.H.,Pantelides,C.C.,"Solution of a class of multistage dynamic optimization problems (1) Problems without path constraints",Ind.Eng.Chem.Res.,33 (9),2111-2122 (1994).
11 Wang,Y.,Seki,H.,Ohyama,S.,Akamatsu,K.,Ogawa,M.,Ohshima,M.,"Optimal grade transition control for polymerization reactors",Comput.Chem.Eng.,24 (2-7),1555-1561 (2000).
12 Geladi,P.,Kowalski,B.R.,"Partial least-squares regression-A tutorial",Anal.Chim.Acta,185,1-17 (1986).
13 Basheer,I.A.,Hajmeer,M.,"Artificial neural networks: Fundamentals,computing,design,and application",J.Microbiol.Meth.,43 (1),3-31 (2000).
14 McAuley,K.B.,MacGregor,J.F.,"Online inference of polymer properties in an industrial polyethylene reactor",AIChE J,37 (6),825-835 (1991).
15 Bonvin,D.,Bodizs,L.,Srinivasan,B.,"Optimal grade transition for polyethylene reactors via NCO tracking",Chem.Eng.Res.Des.,83 (A6),692-697 (2005).
16 Mostoufi,N.,Kiashemshaki,A.,Sotudeh-Gharebagh,R.,"Two-phase modeling of a gas phase polyethylene fluidized bed reactor",Chemical Engineering Science,61 (12),3997-4006 (2006).
17 Padhiyar,N.,Bhartiya,S.,Gudi,R.D.,"Optimal grade transition in polymerization reactors: A comparative case study",Ind.Eng.Chem.Res.,45 (10),3583-3592 (2006).
18 McAuley,K.B.,MacGregor,J.F.,"Optimal grade transitions in a gas-phase polyethylene reactor",AIChE J,38 (10),1564-1576 (1992).
19 Wang,J.D.,Yang,Y.R.,"Study on optimal strategy of grade transition in industrial fluidized bed gas-phase polyethylene production process",Chin.J.Chem.Eng.,11 (1),1-8 (2003).
20 Chatzidoukas,C.,Perkins,J.D.,Pistikopoulos,E.N.,Kiparissides,C.,"Optimal grade transition and selection of closed-loop controllers in a gas-phase olefin polymerization fluidized bed reactor",Chemical Engineering Science,58 (16),3643-3658 (2003).
21 Flores-Tlacuahuac,A.,Biegler,L.T.,Saldivar-Guerra,E.,"Optimal grade transitions in the high-impact polystyrene polymerization process",Ind.Eng.Chem.Res.,45 (18),6175-6189 (2006).

[1]	Haike Li, Xindong Li, Guozai Ouyang, Lang Li, Zhaohuang Zhong, Meng Cai, Wenhao Li, Wanfu Huang. Tannic acid/Fe³⁺ interlayer for preparation of high-permeability polyetherimide organic solvent nanofiltration membranes for organic solvent separation[J]. 中国化学工程学报, 2023, 57(5): 17-29.
[2]	Yongbo Liu, Zhihao Si, Cong Ren, Hanzhu Wu, Peng Zhan, Yuqing Peng, Peiyong Qin. Ultrathin polyamide nanofiltration membrane prepared by triazine-based porous organic polymer as interlayer for dye removal[J]. 中国化学工程学报, 2023, 57(5): 193-201.
[3]	Bowen Jiang, Jia Liu, Guoqiang Yang, Zhibing Zhang. Efficient conversion of CO₂ into cyclic carbonates under atmospheric by halogen and metal-free poly(ionic liquid)s[J]. 中国化学工程学报, 2023, 55(3): 202-211.
[4]	Xingzheng Liu, Chuanbo Fu, Manting Wang, Jiexin Wang, Haikui Zou, Yuan Le, Jianfeng Chen. High-gravity technology intensified Knoevenagel condensation-Michael addition polymerization of poly (ethylene glycol)-poly (n-butyl cyanoacrylate) for blood-brain barrier delivery[J]. 中国化学工程学报, 2022, 46(6): 94-103.
[5]	Zongyao Zhou, Zhen Li, Lubna M. Rehman, Zhiping Lai. Conjugated microporous polymer membranes for chemical separations[J]. 中国化学工程学报, 2022, 45(5): 1-14.
[6]	Jing Dou, Shuo Han, Saisai Lin, Zhikan Yao, Lian Hou, Lin Zhang. Highly permeable reverse osmosis membranes incorporated with hydrophilic polymers of intrinsic microporosity via interfacial polymerization[J]. 中国化学工程学报, 2022, 45(5): 194-202.
[7]	Haoqing Xu, Wenyan Feng, Menglong Sheng, Ye Yuan, Bo Wang, Jixiao Wang, Zhi Wang. Covalent organic frameworks-incorporated thin film composite membranes prepared by interfacial polymerization for efficient CO₂ separation[J]. 中国化学工程学报, 2022, 43(3): 152-160.
[8]	Pingwei Liu, Jigang Du, Yuting Ma, Qingyue Wang, Khak Ho Lim, Bo-Geng Li. Progress of polymer reaction engineering: From process engineering to product engineering[J]. 中国化学工程学报, 2022, 50(10): 3-11.
[9]	Fenghao Guo, Yuanyuan Ding, Yanyan Wang, Xiao Gao, Zhiyong Chen. Functional monodisperse microspheres fabricated by solvothermal precipitation co-polymerization[J]. 中国化学工程学报, 2021, 34(6): 323-331.
[10]	Lei Ma, Hongxia Lv, Haonan Yu, Lingtong Kong, Rongyue Zhang, Xiaoyan Guo, Haibo Jin, Guangxiang He, Xiaoyan Liu. In-depth investigation on the factors affecting the performance of high oil-absorption resin by response surface method[J]. 中国化学工程学报, 2021, 33(5): 286-296.
[11]	Ying Xu, Pengru Chen, Wei Lv, Chenguang Wang, Longlong Ma, Qi Zhang. Hydrogenolysis of organosolv hydrolyzed lignin over high-dispersion Ni/Al-SBA-15 catalysts for phenolic monomers[J]. 中国化学工程学报, 2021, 32(4): 307-314.
[12]	Shuaifeng Zhang, Qinghua Zhang, Jianzhuang Shang, Zaisha Mao, Chao Yang. Measurement methods of particle size distribution in emulsion polymerization[J]. 中国化学工程学报, 2021, 39(11): 1-15.
[13]	Abdullah A. Basaleh, Muhammad H. Al-Malack, Tawfik A. Saleh. Polyamide-baghouse dust nanocomposite for removal of methylene blue and metals: Characterization, kinetic, thermodynamic and regeneration[J]. 中国化学工程学报, 2021, 39(11): 112-125.
[14]	Muhammad A. Imran, Tiantian Li, Xuemei Wu, Xiaoming Yan, Abdul-Sammed Khan, Gaohong He. Sulfonated polybenzimidazole/amine functionalized titanium dioxide (sPBI/AFT) composite electrolyte membranes for high temperature proton exchange membrane fuel cells usage[J]. 中国化学工程学报, 2020, 28(9): 2425-2437.
[15]	Shuguang Xiang, Jiye Wang. Quantum chemical descriptors based QSAR modeling of neodymium carboxylate catalysts for coordination polymerization of isoprene[J]. 中国化学工程学报, 2020, 28(7): 1805-1808.

ARX-NNPLS Model Based Optimization Strategy and Its Application in Polymer Grade Transition Process^*

ARX-NNPLS Model Based Optimization Strategy and Its Application in Polymer Grade Transition Process^*

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