基于Wiener结构的软测量模型及辨识算法

曹鹏飞; 罗雄麟

doi:10.3724/SP.J.1004.2014.02179

基于Wiener结构的软测量模型及辨识算法

doi: 10.3724/SP.J.1004.2014.02179

1.
中国石油大学(北京)自动化系北京 102249

基金项目:

国家重点基础研究发展计划项目(973计划) (2012CB720500), 国家自然科学基金(21006127, 61104218), 中国石油大学 (北京)科研基金资助项目(YJRC-2013-12)

详细信息

作者简介:
曹鹏飞中国石油大学(北京) 自动化系博士生. 主要研究方向为多率系统分析,软测量理论与技术.E-mail: cpf200888@126.com

计量
- 文章访问数: 1502
- HTML全文浏览量: 99
- PDF下载量: 1084
- 被引次数: 0
出版历程
- 收稿日期: 2013-10-22
- 修回日期: 2014-01-27
- 刊出日期: 2014-10-20

Wiener Structure Based Modeling and Identifying of Soft Sensor Systems

1.
Department of Automation, China University of Petroleum, Beijing 102249

Funds:

Supported by National Basic Research Program of China (973 Program) (2012CB720500), National Natural Science Foundation of China (21006127, 61104218), and the Science Foundation of China University of Petroleum (YJRC-2013-12)

摘要

摘要: Wiener模型结构能有效地表征系统的动态和静态特性, 因此这里首先基于这一结构建立软测量模型, 利用动态与静态子模型分别建立辅助变量与主导变量间的动态与静态关系, 并说明该软测量模型的可行性, 给出模型具体表达式. 其次, 针对所提模型, 提出分步辨识方式获得最优模型参数, 说明其可行性. 再次, 为了减少计算和实现模型在线更新, 这里提出参数辨识递推算法, 并给出软测量模型参数的收敛性结论. 通过实例仿真, 可以看出本文提出模型的可行性, 以及分步辨识方式与递推算法的有效性.
- 软测量 /
- Wiener结构 /
- 建模 /
- 分步辨识 /
- 递推算法 /
- 收敛性
Abstract: The dynamic and static characteristics of system can be effectively described by Wiener model structure. Therefore, a new soft sensor model using this structure is proposed. The dynamic and static relationships between secondary and primary variables are built respectively by dynamic and static submodels. For this soft sensor model, a feasibility analysis is conducted, and a specific model expression is also given. Then, a substep way for identifying the soft sensor model is proposed. In order to reduce the calculation amount and update the model online, a recursive algorithm for identifying the parameters of dynamic and static submodels is proposed, and followed by the convergence conclusion for parameter estimations is shown later. Case study results confirm the effectiveness of the proposed model, substep identification, and recursive algorithm.
- Soft sensor /
- Wiener structure /
- modeling /
- substep identification /
- recursive algorithm /
- convergence

HTML全文

参考文献(31)

[1]	Kadlec P, Gabrys B, Strandt S. Data-driven soft sensors in the process industry. Computer and Chemical Engineering, 2009, 33(4): 795-814
[2]	Wu Yao, Luo Xiong-Lin. Robustness analysis of Kalman filtering algorithm for multirate systems. Acta Automatica Sinca, 2012, 38(2): 156-174 (吴瑶, 罗雄麟. 多率Kalman滤波算法的鲁棒性分析. 自动化学报,38(2): 156-174)
[3]	[3] Wu Y, Luo X L. A novel calibration approach of soft sensor based on multirate data fusion technology. Journal of Process Control, 2010, 20(10): 1252-1260
[4]	[4] Lee D S, Lee M W, Woo S H, Kim Y J, Park J M. Nonlinear dynamic partial least squares modeling of a full-scale biological wastewater treatment plant. Process Biochemistry, 2006, 41(9): 2050-2057
[5]	[5] Peng H, Ozaki T, Toyoda Y, Shioya H, Nakano K, Haggan-Ozaki V, Mori M. RBF-ARX model-based nonlinear system modeling and predictive control with application to a NOx decomposition process. Control Engineering Practice, 2004, 12(1): 191-203
[6]	Cao Peng-Fei, Luo Xiong-Lin. Modeling of soft sensor for chemical process. CIESC Journal, 2013, 64(3): 788-800 (曹鹏飞, 罗雄麟. 化工过程软测量建模方法研究进展. 化工学报, 2013, 64(3): 788-800)
[7]	[7] Galicia Hector J, He Q P, Wang J. A reduced order soft sensor approach and its application to a continuous digester. Journal of Process Control, 2011, 21(4): 489-500
[8]	[8] Pan T H, Wong D S H, Jang S S. Development of a novel soft sensor using a local model network with an adaptive subtractive clustering approach. Industrial Engineering Chemistry Research, 2010, 49(10): 4738-4747
[9]	[9] Luo Jian-Xu, Shao Hui-He. Developing dynamic soft sensors using multiple neural networks. Journal of Chemical Industry and Engineering, 2003, 54(12): 1770-1773
[10]	Domlan E, Huang B, Xu F W, Espejo A. A decoupled multiple model approach for soft sensors design. Control Engineering Practice, 2011, 19(2): 126-134
[11]	Hong B S, Fan L T, Schlup J R. Monitoring the process of curing of epoxy/graphite fiber composites with a recurrent neural network as a soft sensor. Artificial Intelligence, 1998, 11(2): 293-306
[12]	Dai X Z, Wang W C, Ding Y H, Sun Z Y. ''Assumed inherent sensor'' inversion based ANN dynamic soft-sensing method and its application in erythromycin fermentation process. Computers Chemical Engineering, 2006, 30(8): 1203-1225
[13]	Ma Yong, Huang De-Xian, Jin Yi-Hui. Discussion about dynamic soft-sensing modeling. Journal of Chemical Industry and Engineering, 2005, 56(8): 1516-1519 (马勇, 黄德先, 金以慧. 动态软测量建模方法初探. 化工学报, 2005, 56(8): 1516-1519)
[14]	Wu J F, He X R, Chen B Z. Back-propagation neural network model of dynamic system and its application. Journal of Chemical Industry and Engineering, 2000, 51(3): 378-382
[15]	Gmez J C, Baeyens E. Identification of block-oriented nonlinear systems using orthonormal. Journal of Process Control, 2004, 14(6): 685-697
[16]	Figueroa J L, Biagiola S I, Agamennoni O E. An approach for identification of uncertain Wiener systems. Mathematical and Computer Modelling, 2008, 48(1-2): 305-315
[17]	Kozek M, SinanovićS. Identification of Wiener models using optimal local linear models. Simulation Modelling Practice and Theory, 2008, 16(8): 1055-1066
[18]	Pearson R K, Pottmann M. Gray-box identification of block-oriented nonlinear models. Journal of Process Control, 2000, 10(4): 301-315
[19]	Ding Feng, Xiao De-Yun, Ding Tao. Multi-innovation stochastic gradient identification method. Control Theory Applications, 2003, 20(6): 870-874 (丁锋, 萧德云, 丁韬. 多新息随机梯度辨识方法. 控制理论与应用, 2003, 20(6): 870-874)
[20]	Ding Feng, Yang Jia-Ben. Hierachical identification of large scale systems. Acta Automatica Sinca, 1999, 25(5): 647-654 (丁锋, 杨家本. 大系统的递阶辨识. 自动化学报, 1999, 25(5): 647-654)
[21]	Fang Chong-Zhi, Xiao De-Yun. Process Identification. Beijing: Tsinghua University Press, 2007. (方崇智, 萧德云. 过程辨识. 北京: 清华大学出版社, 2007.)
[22]	Eykhoff P. System Identification-Parameter and State Estimation. New York: John Wiley Sons, 1974.
[23]	Strejc V. Least squares parameter estimation. Automatica, 1980, 16(5): 535-550
[24]	Qin S J. Neural Networks for Intelligent Sensors and Control-Practical Issues and Some Solutions. New York: Academic Press, 1996.
[25]	Principe J C, Euliano N R, Lefebvre W C. Neural and Adaptive Systems. New York: Wiley, 2000.
[26]	Cervantes A L, Agamennoni O E, Figueroa J L. A nonlinear model predictive control system based on Wiener piecewise linear models. Journal of Process Control, 2003, 13(7): 655-666
[27]	Ttterman S, Toivonen H T. Support vector method for identification of Wiener models. Journal of Process Control, 2009, 19(7): 1174-1181
[28]	Ding Feng, Ding Tao, Yang Jia-Ben. Xu Yong-Mao. Convergence of forgetting gradient estimation algorithm for time-varying parameters. Acta Automatica Sinca, 2002, 28(6): 962-968 (丁锋, 丁韬, 杨家本, 徐用懋. 时变参数遗忘梯度估计算法的收敛性. 自动化学报, 2002, 28(6): 962-968)
[29]	Ljung L. Consistency of the least-squares identification method. IEEE Transcations on Automatic Control, 1976, 21(5): 779-781
[30]	Ding Feng, Yang Jia-Ben. Remarks on martingale hyperconvergence theory and the convergence analysis of the forgetting factor least squares algorithms. Control Theory and Applications, 1999, 16(4): 569-572 (丁锋, 杨家本. 关于鞅超收敛定理与遗忘因子最小二乘算法的收敛性分析. 控制理论与应用, 1999, 16(4): 569-572)
[31]	Li Juan, Cui Wen-Quan. Extension of Cauchy-Schwarz inequality. College Mathematics, 2006, 22(6): 144-147 (李娟, 崔文泉. Cauchy-Schwarz 不等式的推广. 大学数学, 2006,22(6): 144-147)