基于稳定Hammerstein模型的在线软测量建模方法及应用

doi:10.11949/j.issn.0438-1157.20141210

化工学报 ›› 2015, Vol. 66 ›› Issue (4): 1378-1387.DOI: 10.11949/j.issn.0438-1157.20141210

基于稳定Hammerstein模型的在线软测量建模方法及应用

丛秋梅^1,2,3, 苑明哲^2,3, 王宏^2,3,4

1. 辽宁石油化工大学信息与控制工程学院, 辽宁抚顺 113001;
2. 中国科学院沈阳自动化研究所信息服务与智能控制技术研究室, 辽宁沈阳 110016;
3. 中国科学院院重点实验室网络化控制系统重点实验室, 辽宁沈阳 110016;
4. 沈阳中科博微自动化有限公司, 辽宁沈阳 110179

收稿日期:2014-08-11 修回日期:2014-12-22 出版日期:2015-04-05 发布日期:2015-04-05
通讯作者: 丛秋梅
作者简介:丛秋梅(1978-),女,博士,讲师。
基金资助:
国家自然科学基金项目(61034008);中国博士后科学基金项目(2013M530953);中国科学院网络化控制系统重点实验室自主课题(WLHKZ2014005)。

On-line soft sensor based on stable Hammerstein model and its applications

CONG Qiumei^1,2,3, YUAN Mingzhe^2,3, WANG Hong^2,3,4

1. School of Information and Control Engineering, Liaoning Shihua University, Fushun 113001, Liaoning, China;
2. Deptartment of Information Service & Intelligent Control, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, Liaoning, China;
3. Key Laboratory of Networked Control System, Chinese Academy of Sciences, Shenyang 110016, Liaoning, China;
4. Microcyber Incorporated, Shenyang 110179, Liaoning, China

Received:2014-08-11 Revised:2014-12-22 Online:2015-04-05 Published:2015-04-05
Supported by:
supported by the National Natural Science Foundation of China (61034008), the China Postdoctoral Science Foundation (2013M530953) and the Independent Subject Sponsored by Key Laboratory of Control Network System, Chinese Academy of Sciences (WLHKZ2014005).

摘要/Abstract

摘要：

针对复杂工业过程中由于存在未建模动态和不确定干扰,导致关键变量的软测量精度下降的问题,提出了一种基于稳定Hammerstein模型(H模型)的在线软测量建模方法。H模型的非线性增益采用带有时变稳定学习算法的小波神经网络模型,线性系统部分采用基于递推最小二乘的ARX模型,基于输入到状态稳定性理论证明了H模型辨识误差的有界性。其中小波神经网络具有表征强非线性的特性,稳定学习算法可抑制未建模动态和不确定干扰的影响,改善了模型的预测精度和自适应能力。以典型非线性系统和实际污水处理过程为例进行了仿真研究,结果表明,基于稳定H模型的软测量方法具有较高的在线软测量精度。

关键词: Hammerstein模型, 在线建模, 软测量, 预测, 稳定学习, 污水处理过程, 稳定性

Abstract:

Aiming at the problem that the soft sensing precision of key variables deteriorates when unmodeled dynamics and uncertain disturbances exist in the complex industrial process, an on-line soft sensor based on stable Hammerstein model (H model) was presented. H model was composed of wavelet neural network with time-varying stable learning algorithm as nonlinear gain and ARX model with RLS (recursive least square) algorithm as linear part. The boundedness of identification error for H model was proved according to the Input-to-State Stability theory. Wavelet neural network could represent strong nonlinearity of the process, and the stable learning algorithm could restrain the influences of unmodeled dynamics and uncertain disturbances and improve prediction precision and self-adaptability. Simulations based on a nonlinear system and the wastewater treatment process showed that the soft sensing method presented in this paper possessed high prediction precision.

Key words: Hammerstein model, on-line modeling, soft sensor, prediction, stable learning, wastewater treatment process, stability

中图分类号:

TP391.9

丛秋梅, 苑明哲, 王宏. 基于稳定Hammerstein模型的在线软测量建模方法及应用[J]. 化工学报, 2015, 66(4): 1378-1387.

CONG Qiumei, YUAN Mingzhe, WANG Hong. On-line soft sensor based on stable Hammerstein model and its applications[J]. CIESC Journal, 2015, 66(4): 1378-1387.

参考文献 21

[1]	Chai Tianyou (柴天佑). Operational optimization and feedback control for complex industrial processes [J]. Acta Automatics Sinica (自动化学报), 2013, 39 (11): 1744-1757
[2]	Cao Pengfei (曹鹏飞), Luo Xionglin (罗雄麟). Modeling of soft sensor for chemical process[J]. CIESC Journal(化工学报), 2013, 64 (3): 788-800
[3]	Yu W, Li X. Discrete-time neuro identification without robust modification [J]. IEE Proceedings -Control Theory and Applications, 2003, 150 (3): 311-316
[4]	Zhang N M. An online gradient method with momentum for two-layer feedforward neural networks [J]. Applied Mathematics and Computation, 2009, 212 (2): 488-498
[5]	Chen Y J, Huang T C, Hwang R C. An effective learning of neural network by using RFBP learning algorithm [J]. Information Sciences, 2004, 167 (1): 77-86
[6]	Narendra K S, Gallman P G. An iterative method for the identification of nonlinear systems using a Hammerstein model [J]. IEEE Transactions on Automatic Control, 1966, 11 (3): 546-550
[7]	Lakshminarayanan S, Shah S L, Nandakumar K. Modeling and control of multivariable processes: dynamic PLS approach [J]. AIChE Journal, 1997, 43 (9): 2307-2322
[8]	Wlodzimierz G. Stochastic approximation in nonparametric identification of Hammerstein systems [J]. IEEE Transactions on Automatic Control, 2002, 47 (11): 1800-1811
[9]	Zhao W X. Parametric identification of Hammerstein systems with consistency results using stochastic inputs [J]. IEEE Transactions on Automatic Control, 2010, 55 (2): 474-480
[10]	Jia Li (贾立), Li Xunlong (李训龙). Identification of Hammerstein model: review and prospect [J]. Control Theory & Applications (控制理论与应用), 2014, 31 (1): 1-10
[11]	Jia L, Yang A H, Chiu M S. Special input signals based neurofuzzy Hammerstein-Wiener model and its application [J]. International Journal of System Control and Information Processing, 2012, 1 (2): 199-218
[12]	Hunt K J, Sbarbaro D, Zbikowski R, Gawthrop P J. Neural networks for control systems-a survey [J]. Automatica, 1992, 28 (6): 1083-1112
[13]	Chen Senfa (陈森发). Theory and Method of Complex System Modeling (复杂系统建模理论与方法) [M]. Nanjing: Southeast University Press, 2005
[14]	Yu W. Nonlinear system identification using discrete-time recurrent neural networks with stable learning algorithms [J]. Information Sciences, 2004, 158 (1): 131-147
[15]	Sontag, E D, Wang Y. On characterizations of the input-to-state stability property [J]. Systems and Control Letters, 1995, 24 (5): 351-359
[16]	Feng Peidi (冯培悌). System Identification (系统辨识) [M]. Hangzhou: Zhejiang University Press, 1999
[17]	Wang Shuangjian (王双剑), Chu Jizheng (楚纪正). Hammerstein model identification method based on the new improved neural dynamics and its application to hybrid modeling [J]. Information and Control (信息与控制), 2012, 41 (3): 384-390
[18]	Kreinovich V S O, Cabmn S. Wavelet neural networks are asymptotically optimal approximators for function of one variable// Proceeding of IEEE ICNN [C]. Florida, USA, 1994: 299-304
[19]	Ye Lingjian (叶凌箭), Ma Xiushui (马修水), Song Zhihuan (宋执环). Real-time optimization for chemical processes based on on-line modeling of controlled variables [J]. CIESC Journal (化工学报), 2013, 64 (8): 2918-2923
[20]	Sontag E D. Input to state stability: basic concepts and results [J]. Lecture Notes in Mathematics, 2008, 1932: 163-200
[21]	Narendra K S, Li S M. Neural networks in control systems// Smolensky P, Mozer M C, Rumelhart D E, Mathematical Perspectives on Neural Networks [M]. New Jersey: Lawrence Erlbaum Associates, 1996: 347-394

基于稳定Hammerstein模型的在线软测量建模方法及应用

On-line soft sensor based on stable Hammerstein model and its applications

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献 21

相关文章 15

编辑推荐

Metrics

本文评价

[1]	江河, 袁俊飞, 王林, 邢谷雨. 均流腔结构对微细通道内相变流动特性影响的实验研究[J]. 化工学报, 2023, 74(S1): 235-244.
[2]	孟令玎, 崇汝青, 孙菲雪, 孟子晖, 刘文芳. 改性聚乙烯膜和氧化硅固定化碳酸酐酶[J]. 化工学报, 2023, 74(8): 3472-3484.
[3]	闫琳琦, 王振雷. 基于STA-BiLSTM-LightGBM组合模型的多步预测软测量建模[J]. 化工学报, 2023, 74(8): 3407-3418.
[4]	尹刚, 李伊惠, 何飞, 曹文琦, 王民, 颜非亚, 向禹, 卢剑, 罗斌, 卢润廷. 基于KPCA和SVM的铝电解槽漏槽事故预警方法[J]. 化工学报, 2023, 74(8): 3419-3428.
[5]	郑玉圆, 葛志伟, 韩翔宇, 王亮, 陈海生. 中高温钙基材料热化学储热的研究进展与展望[J]. 化工学报, 2023, 74(8): 3171-3192.
[6]	郭雨莹, 敬加强, 黄婉妮, 张平, 孙杰, 朱宇, 冯君炫, 陆洪江. 稠油管道水润滑减阻及压降预测模型修正[J]. 化工学报, 2023, 74(7): 2898-2907.
[7]	邵伟明, 韩文学, 宋伟, 杨勇, 陈灿, 赵东亚. 基于分布式贝叶斯隐马尔可夫回归的动态软测量建模方法[J]. 化工学报, 2023, 74(6): 2495-2502.
[8]	蔡斌, 张效林, 罗倩, 党江涛, 左栗源, 刘欣梅. 导电薄膜材料的研究进展[J]. 化工学报, 2023, 74(6): 2308-2321.
[9]	李艳辉, 丁邵明, 白周央, 张一楠, 于智红, 邢利梅, 高鹏飞, 王永贞. 非常规服役超临界锅炉的微纳尺度腐蚀动力学模型建立及应用[J]. 化工学报, 2023, 74(6): 2436-2446.
[10]	毛磊, 刘冠章, 袁航, 张光亚. 可捕集CO₂的纳米碳酸酐酶粒子的高效制备及性能研究[J]. 化工学报, 2023, 74(6): 2589-2598.
[11]	于源, 陈薇薇, 付俊杰, 刘家祥, 焦志伟. 几何相似涡流空气分级机环形区流场变化规律研究及预测[J]. 化工学报, 2023, 74(6): 2363-2373.
[12]	徐文超, 孙志高, 李翠敏, 李娟, 黄海峰. 静态条件下表面活性剂E-1310对HCFC-141b水合物生成的影响[J]. 化工学报, 2023, 74(5): 2179-2185.
[13]	王子健, 柯明, 李佳涵, 李舒婷, 孙巾茹, 童燕兵, 赵治平, 刘加英, 任璐. 短b轴ZSM-5分子筛制备方法及应用研究进展[J]. 化工学报, 2023, 74(4): 1457-1473.
[14]	刘润竹, 储甜甜, 张孝阿, 王成忠, 张军营. α，ω-端羟基亚苯基氟硅聚合物的合成及性能[J]. 化工学报, 2023, 74(3): 1360-1369.
[15]	陈向上, 马振杰, 任希华, 贾悦, 吕晓龙, 陈华艳. 三维网络萃取膜的制备及传质效率研究[J]. 化工学报, 2023, 74(3): 1126-1133.