CIESC Journal ›› 2019, Vol. 70 ›› Issue (2): 678-686.doi: 10.11949/j.issn.0438-1157.20181035

Previous Articles     Next Articles

Nonlinear predictive control strategies of pH neutralization process based on neural networks

Zhizhen WANG(),Zhiyun ZOU()   

  1. Research Institute of Chemical Defense, Military Academy of Sciences, Beijing 102205, China
  • Received:2018-09-12 Revised:2018-10-18 Online:2019-02-05 Published:2018-09-21
  • Contact: Zhiyun ZOU E-mail:tianlan0370@163.com;zouzhiyun65@163.com

Abstract:

To solve the control problems of nonlinear process systems, nonlinear model-predictive control algorithms are studied. pH neutralization process is a typical nonlinear process in chemical process systems. In view of the characteristic of pH neutralization process, the entire model of pH neutralization process system and the inverse model of static nonlinear block are established by neural networks. Then two novel nonlinear predictive control strategies are studied based on model-predictive control and Hammerstein model. The neural networks model predictive control (NNMPC), which is a global solution strategy for nonlinear predictive control systems and nonlinear Hammerstein model predictive control (NLHMPC), which is a strategy based on two steppes separation control are developed and simulated by MATLAB. Control simulation results show that the NNMPC and NLHMPC control strategies have better performances on set-point tracking and anti-interference control response than PID control. They can give effective control performance to nonlinear processes.

Key words: model-predictive control, neural networks, process control, Hammerstein model, pH neutralization process, nonlinear system

CLC Number: 

  • TP 273

Fig.1

Control system of pH neutralization process"

Fig.2

Structure of Hammerstein model"

Fig.3

Structure of NNMPC"

Fig.4

Model establishment and training process of NNMPC"

Fig.5

Structure of BP neural network"

Fig.6

Flow chart of NNMPC"

Fig.7

Structure of NLHMPC"

Fig.8

Structure of neural network inverse system modeling"

Fig.9

Neural network model training process in NNMPC"

Fig.10

Neural network model training results in NNMPC"

Fig.11

Neural network training process of nonlinear inverse model in NLHMPC"

Fig.12

Neural network training results and model error of nonlinear inverse model in NLHMPC"

Fig.13

Simulation experimental results of set value tracking"

Fig.14

Simulation experiment results of variable setting value tracking"

Fig.15

Responses of anti-disturbance"

1 钱锋, 杜文莉, 钟伟民, 等. 石油和化工行业智能优化制造若干问题及挑战[J]. 自动化学报, 2017, 43(6): 893-901.
QianF, DuW L, ZhongW M, et al. Problems and challenges of smart optimization manufacturing in petrochemical industries[J]. Acta Automatica Sinica, 2017, 43(6): 893-901.
2 柴天佑. 工业过程控制系统研究现状与发展方向[J]. 中国科学:信息科学, 2016, 46(8): 1003-1015.
ChaiT Y. Industrial process control systems: research status and development direction[J]. Scientia Sinica, 2016, 46(8): 1003-1015.
3 MotaA S, MenezesM R, SchmitzJ E, et al. Identification and online validation of a pH neutralization process using an adaptive network-based fuzzy inference system[J]. Chemical Engineering Communications, 2016, 203(4): 516-526.
4 ChenX, XueA K, PengD L, et al. Modeling of pH neutralization process using fuzzy recurrent neural network and DNA based NSGA-Ⅱ[J]. Journal of the Franklin Institute, 2014, 351(7): 3847-3864.
5 ZhangY J, JiaY, ChaiT Y, et al. Data-driven PID controller and its application to pulp neutralization process[J]. IEEE Transactions on Control Systems Technology, 2018, 26(3): 828-841.
6 VatankhahB, FarrokhiM. Nonlinear model-predictive control with disturbance rejection property using adaptive neural networks[J]. Journal of the Franklin Institute, 2017, 354(13): 5201-5220.
7 SinghP K, BhanotS, MohantaH K. Genetic optimization based adaptive fuzzy logic control of a pH neutralization process[J]. International Journal of Control & Automation, 2014, 7(11): 233-248.
8 李泽龙, 杨春节, 刘文辉, 等. 基于LSTM-RNN模型的铁水硅含量预测[J]. 化工学报, 2018, 69(3): 992-997.
LiZ L, YangC J, LiuW H, et al. Research on hot metal Si-content prediction based on LSTM-RNN[J]. CIESC Journal, 2018, 69(3): 992-997.
9 SchmidhuberJ. Deep learning in neural networks: an overview[J]. Neural Networks, 2015, 61: 85-117.
10 焦李成, 杨淑媛, 刘芳, 等. 神经网络七十年: 回顾与展望[J]. 计算机学报, 2016, 39(8): 1697-1716.
JiaoL C, YangS Y, LiuF, et al. Seventy years beyond neural networks: retrospect and prospect[J]. Chinese Journal of Computers, 2016, 39(8): 1697-1716.
11 王康成, 尚超, 柯文思,等. 化工过程深度神经网络软测量的结构与参数自动调整方法[J]. 化工学报, 2018, 69(3): 900-906.
WangK C, ShangC, KeW S, et al. Automatic structure and parameters tuning method for deep neural network soft sensor in chemical industries[J]. CIESC Journal, 2018, 69(3): 900-906.
12 席裕庚. 预测控制[M]. 北京: 国防工业出版社, 2013.Xi Y G. Predictive Control [M]. Beijing: National Defense Industry Press, 2013.
13 MayneD Q. Model predictive control: recent developments and future promise[J]. Automatica, 2014, 50(10): 2967-2986.
14 Anang, SutantoH, EdiL. Model predictive control design and performance analysis of a pasteurization process plant[C]// International Conference on Instrumentation, Control and Automation. Bandung, Indonesia:IEEE, 2017: 81-87.
15 QinS J, BadgwellT A. A survey of industrial model predictive control technology[J]. Control Engineering Practice, 2003, 11(7): 733-764.
16 AllgöwerF, FindeisenR, NagyZ K. Nonlinear model predictive control: from theory to application[J]. Journal of the Chinese Institute of Chemical Engineers, 2004, 35(3): 299-315.
17 席裕庚, 李德伟, 林姝. 模型预测控制——现状与挑战[J]. 自动化学报, 2013, 39(3): 222-236.Xi Y G, Li D W, Lin S. Model predictive control—status and challenges[J]. Acta Automatica Sinica, 2013, 39(3): 222-236.
18 何德峰, 丁宝苍, 于树友. 非线性系统模型预测控制若干基本特点与主题回顾[J]. 控制理论与应用, 2013, 30(3): 273-287.
HeD F, DingB C, YuS Y. Review of fundamental properties and topics of model predictive control for nonlinear systems[J]. Control Theory & Applications, 2013, 30(3): 273-287.
19 孔小兵, 刘向杰. 基于输入输出线性化的连续系统非线性模型预测控制[J]. 控制理论与应用, 2012, 29(2): 217-224.
KongX B, LiuX J. Continuous-time nonlinear model predictive control with input/output linearization[J]. Control Theory & Applications, 2012, 29(2): 217-224.
20 盖俊峰, 赵国荣, 周大旺. 一种基于线性近似的非线性系统模型预测控制方法[J]. 航天控制, 2015, 33(5): 3-7.
GaiJ F, ZhaoG R, ZhouD W. Nonlinear model predictive control scheme based on linearization approximation[J]. Aerospace Control, 2015, 33(5): 3-7.
21 YeQ, LouX Y, ShengL. Generalized predictive control of a class of MIMO models via a projection neural network[J]. Neurocomputing, 2017, 234: 192-197.
22 ZhaoJ M. NN-adaptive predictive control for a class of discrete-time nonlinear systems with input-delay[J]. Neurocomputing, 2016, 173: 1832-1838.
23 KillianM, MayerB, SchirrerA, et al. Cooperative fuzzy model predictive control[J]. Elektrotechnik Und Informationstechnik, 2015, 132(8): 474-480.
24 王书斌, 单胜男, 罗雄麟. 基于T-S模糊模型与粒子群优化的非线性预测控制[J]. 化工学报, 2012, 63(S1): 176-187.
WangS B, ShanS N, LuoX L. Nonlinear predictive control based on T-S fuzzy model and particle-swarm optimization[J]. CIESC Journal, 2012, 63(S1) : 176-187.
25 YusufZ, WahabN A, AbusamA. Neural network-based model predictive control with CPSOGSA for SMBR filtration[J]. International Journal of Electrical & Computer Engineering, 2017, 7(3): 1538-1545.
26 KittisupakornP, SomsongP, HussainM A, et al. Improving of crystal size distribution control based on neural network-based hybrid model for purified terephthalic acid batch crystallizer[J]. Engineering Journal, 2017, 21(7): 319-331.
27 KumarD, BudmanH. Robust nonlinear MPC based on Volterra series and polynomial chaos expansions[J]. Journal of Process Control, 2014, 24(1): 304-317.
28 FigueroaJ L, BiagiolaS I, AlvarezM P, et al. Robust model predictive control of a Wiener-like system[J]. Journal of the Franklin Institute, 2013, 350(3): 556-574.
29 ŁawryńczukM. Nonlinear predictive control for Hammerstein-Wiener systems[J]. ISA Transactions, 2015, 55(1): 49-62.
30 AlamirM. Contraction-based nonlinear model predictive control formulation without stability-related terminal constraints[J]. Automatica, 2017, 75: 288-292.
31 GrüneL, StielerM. Asymptotic stability and transient optimality of economic MPC without terminal conditions[J]. Journal of Process Control, 2014, 24(8): 1187-1196.
32 邹志云, 郭宇晴, 王志甄, 等. 非线性Hammerstein模型预测控制策略及其在pH中和过程中的应用[J]. 化工学报, 2012, 63(12): 3965-3970.
ZouZ Y, GuoY Q, WangZ Z, et al. Nonlinear Hammerstein model predictive control strategy and its application to pH neutralization process[J]. CIESC Journal, 2012, 63(12): 3965-3970.
33 周洪煜, 梁东义, 周松杰. 废水中和过程的RBF神经网络预测控制[J]. 控制工程, 2014, 21(1): 79-83.
ZhouH Y, LiangD Y, ZhouS J. RBFNN predictive control of wastewater neutralization process[J]. Control Engineering of China, 2014, 21(1): 79-83.
34 安爱民, 刘云利, 张浩琛, 等. 微生物燃料电池的动态性能分析及其神经网络预测控制[J]. 化工学报, 2017, 68(3): 1090-1098.
AnA M, LiuY L, ZhangH C, et al. Dynamic performance analysis and neural network predictive control of microbial fuel cell [J]. CIESC Journal, 2017, 68(3): 1090-1098.
35 李明河, 周磊, 王健. 基于LM算法的溶解氧神经网络预测控制[J]. 农业机械学报, 2016, 47(6): 297-302.
LiM H, ZhouL, WangJ. Neural network predictive control for dissolved oxygen based on Levenberg-Marquardt algorithm[J]. Transactions of the Chinese Society for Agricultural Machinery, 2016, 47(6): 297-302.
[1] Enwei ZHI, Fei YAN, Mifeng REN, Gaowei YAN. Soft sensor of wet ball mill load parameters based on transfer variational autoencoder - label mapping [J]. CIESC Journal, 2019, 70(S1): 150-157.
[2] Dong HUANG, Xionglin LUO. Judgement of process transition control strategies for large-range conditions change of chemical processes [J]. CIESC Journal, 2019, 70(5): 1848-1857.
[3] Shipin YANG, Zhen HUANG, Lijuan LI, Jianquan SONG, Jing YE, Hui WANG. A deep dive diagnostic and correction algorithm for mismatched sub-models in complicated chemical processes [J]. CIESC Journal, 2019, 70(4): 1485-1493.
[4] Bowen SHI, Yanyan YIN, Fei LIU. Optimal control strategies combined with PSO and control vector parameterization for batchwise chemical process [J]. CIESC Journal, 2019, 70(3): 979-986.
[5] Baochang XU, Hua ZHANG, Jinshan WANG. Partial approximate least absolute deviation for nonlinear system identification based on radial basis function [J]. CIESC Journal, 2019, 70(2): 653-660.
[6] Shan DOU, Guangyu ZHANG, Zhihua XIONG. Anomaly detection of process unit based on LSTM time series reconstruction [J]. CIESC Journal, 2019, 70(2): 481-486.
[7] Zhiqiang GENG, Shaoxing JING, Ju BAI, Zhongkai WANG, Qunxiong ZHU, Yongming HAN. Improved intelligent warning method based on MWSPCA-CBR and its application in petrochemical industries [J]. CIESC Journal, 2019, 70(2): 572-580.
[8] Zhiqiang GENG, Meng XU, Qunxiong ZHU, Yongming HAN, Xiangbai GU. Research and application of soft measurement model for complex chemical processes based on deep learning [J]. CIESC Journal, 2019, 70(2): 564-571.
[9] Xiaohan ZHANG, Pingjiang WANG, Xiangbai GU, Yuan XU, Yanlin HE, Qunxiong ZHU. Research on principal components extraction based robust extreme learning machine(PCE-RELM) and its application to modeling chemical processes [J]. CIESC Journal, 2019, 70(2): 475-480.
[10] Haisheng CHEN, Tengfei WANG, Kejin HUANG, Yang YUAN, Xing QIAN, Liang ZHANG. Decentralized control system designs for reactive distillation columns with external recycle [J]. CIESC Journal, 2019, 70(2): 440-449.
[11] Wenjing LI, Meng LI, Junfei QIAO. Effluent BOD soft measurement based on mutual information and self-organizing RBF neural network [J]. CIESC Journal, 2019, 70(2): 687-695.
[12] Limin WANG, Libin LU, Furong GAO, Donghua ZHOU. Infinite horizon linear quadratic hybrid fault-tolerant control for multi-phase batch process [J]. CIESC Journal, 2019, 70(2): 541-547.
[13] LI Fan, XU Feng, LUO Xionglin. Control configuration design with genetic algorithm for decentralized control system [J]. CIESC Journal, 2018, 69(S2): 266-273.
[14] YANG Qing, YANG Yubing, LI Jianmin, FENG Hongli, ZHOU Xueyang, LIU Xiuhong. Partial nitrification coupled anaerobic ammonia oxidation process to treat low C/N domestic sewage [J]. CIESC Journal, 2018, 69(8): 3635-3642.
[15] FENG Liwei, ZHANG Cheng, LI Yuan, XIE Yanhong. DLNS-PCA-based fault detection for multimode batch process [J]. CIESC Journal, 2018, 69(7): 3159-3166.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] LING Lixia, ZHANG Riguang, WANG Baojun, XIE Kechang. Pyrolysis Mechanisms of Quinoline and Isoquinoline with Density Functional Theory[J]. , 2009, 17(5): 805 -813 .
[2] LEI Zhigang, LONG Aibin, JIA Meiru, LIU Xueyi. Experimental and Kinetic Study of Selective Catalytic Reduction of NO with NH3 over CuO/Al2O3/Cordierite Catalyst[J]. , 2010, 18(5): 721 -729 .
[3] SU Haifeng, LIU Huaikun, WANG Fan, LÜXiaoyan, WEN Yanxuan. Kinetics of Reductive Leaching of Low-grade Pyrolusite with Molasses Alcohol Wastewater in H2SO4[J]. , 2010, 18(5): 730 -735 .
[4] WANG Jianlin, XUE Yaoyu, YU Tao, ZHAO Liqiang. Run-to-run Optimization for Fed-batch Fermentation Process with Swarm Energy Conservation Particle Swarm Optimization Algorithm[J]. , 2010, 18(5): 787 -794 .
[5] SUN Fubao, MAO Zhonggui, ZHANG Jianhua, ZHANG Hongjian, TANG Lei, ZHANG Chengming, ZHANG Jing, ZHAI Fangfang. Water-recycled Cassava Bioethanol Production Integrated with Two-stage UASB Treatment[J]. , 2010, 18(5): 837 -842 .
[6] Gao Ruichang, Song Baodong and Yuan Xiaojing( Chemical Engineering Research Center, Tianjin University, Tianjin 300072). LIQUID FLOW DISTRIBUTION IN GAS - LIQUID COUNTER - CONTACTING PACKED COLUMN[J]. , 1999, 50(1): 94 -100 .
[7] Su Yaxin, Luo Zhongyang and Cen Kefa( Institute of Thermal Power Engineering , Zhejiang University , Hangzhou 310027). A STUDY ON THE FINS OF HEAT EXCHANGERS FROM OPTIMIZATION OF ENTROPY GENERATION[J]. , 1999, 50(1): 118 -124 .
[8] Luo Xiaoping(Department of Industrial Equipment and Control Engineering , South China University of Technology, Guangzhou 510641)Deng Xianhe and Deng Songjiu( Research Institute of Chemical Engineering, South China University of Technology, Guangzhou 5106. RESEARCH ON FLOW RESISTANCE OF RING SUPPORT HEAT EXCHANGER WITH LONGITUDINAL FLUID FLOW ON SHELL SIDE[J]. , 1999, 50(1): 130 -135 .
[9] Jin Wenzheng , Gao Guangtu , Qu Yixin and Wang Wenchuan ( College of Chemical Engineering, Beijing Univercity of Chemical Technology, Beijing 100029). MONTE CARLO SIMULATION OF HENRY CONSTANT OF METHANE OR BENZENE IN INFINITE DILUTE AQUEOUS SOLUTIONS[J]. , 1999, 50(2): 174 -184 .
[10]

LI Qingzhao;ZHAO Changsui;CHEN Xiaoping;WU Weifang;LI Yingjie

.

Combustion of pulverized coal in O2/CO2 mixtures and its pore structure development

[J]. , 2008, 59(11): 2891 -2897 .