A reduced order soft sensor approach and its application to a continuous digester

被引:90
作者
Galicia, Hector J. [2 ]
He, Q. Peter [1 ]
Wang, Jin [2 ]
机构
[1] Tuskegee Univ, Dept Chem Engn, Tuskegee, AL 36088 USA
[2] Auburn Univ, Dept Chem Engn, Auburn, AL 36849 USA
基金
美国国家科学基金会;
关键词
Soft sensor; Partial least squares; Process dynamics; Transport delay; Reduced order model; Pulp digester; LOOP SUBSPACE IDENTIFICATION; NONLINEAR INFERENTIAL CONTROL; BATCH DISTILLATION; DYNAMIC PLS; PREDICTIVE CONTROL; MODEL; STATE; ALGORITHMS; PARAMETERS; DIAGNOSIS;
D O I
10.1016/j.jprocont.2011.02.001
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In many industrial processes, the primary product variable(s) are not measured online but are required for feedback control. To address this challenge, there has been increased interest toward developing data-driven soft sensors using secondary measurements based on multivariate regression techniques. Among different data-driven approaches, the dynamic partial least squares (DPLS) soft sensor approach has been applied to several industrial processes. However, despite its successful applications, there is a lack of theoretical understanding on the properties of the DPLS soft sensor. Specifically, whether it can adequately capture process dynamics and whether it can provide unbiased estimate under closed-loop operation have not been examined rigorously. In this work, we provide a theoretical analysis to answer these questions. In addition, we propose a reduced-order DPLS (RO-DPLS) soft sensor approach to address the limitation of the traditional DPLS soft sensor when applied to model processes with large transport delay, i.e., large number of lagged variables are required to be include in the regressor matrix in order to capture process dynamics adequately. Compared to the traditional DPLS soft sensor, the proposed RO-DPLS approach not only reduces model size and improves prediction but also provides multiple-step-ahead prediction. The performance of the proposed RO-DPLS is demonstrated using both a simulated single-vessel digester and an industrial Kamyr digester. (C) 2011 Elsevier Ltd. All rights reserved.
引用
收藏
页码:489 / 500
页数:12
相关论文
共 67 条
[1]   Subspace identification based inferential control applied to a continuous pulp digester [J].
Amirthalingam, R ;
Lee, JH .
JOURNAL OF PROCESS CONTROL, 1999, 9 (05) :397-406
[2]  
Amirthalingam R, 1997, COMPUT CHEM ENG, V21, pS1143
[3]   Two-step procedure for data-based modeling for inferential control applications [J].
Amirthalingam, R ;
Sung, SW ;
Lee, JH .
AICHE JOURNAL, 2000, 46 (10) :1974-1988
[4]  
[Anonymous], PRACTICAL DISTILLATI
[5]  
BEQUETTE BW, 1984, AICHE ANN M SAN FRAN
[6]   A pulp mill benchmark problem for control: application of plantwide control design [J].
Castro, JJ ;
Doyle, FJ .
JOURNAL OF PROCESS CONTROL, 2004, 14 (03) :329-347
[7]   Consistency analysis of some closed-loop subspace identification methods [J].
Chiuso, A ;
Picci, G .
AUTOMATICA, 2005, 41 (03) :377-391
[8]   Subspace algorithms for the identification of multivariable dynamic errors-in-variables models [J].
Chou, CT ;
Verhaegen, M .
AUTOMATICA, 1997, 33 (10) :1857-1869
[9]   Recursive exponentially weighted PLS and its applications to adaptive control and prediction [J].
Dayal, BS ;
MacGregor, JF .
JOURNAL OF PROCESS CONTROL, 1997, 7 (03) :169-179
[10]  
DeKing N., 2004, PULP PAPER GLOBAL FA