Neural network-based software sensor: Training set design and application to a continuous pulp digester

被引：31

作者：

Dufour, P ^{[1
]}

Bhartiya, S ^{[1
]}

Dhurjati, PS ^{[1
]}

Doyle, FJ ^{[1
]}

机构：

[1] Univ Delaware, Dept Chem Engn, Newark, DE 19716 USA

来源：

CONTROL ENGINEERING PRACTICE | 2005年 / 13卷 / 02期

关键词：

artificial neural network; fault detection; soft-sensing; pulp digester; fundamental model;

D O I：

10.1016/j.conengprac.2004.02.013

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

A neural network-based strategy for detection of feedstock variations in a continuous pulp digester is presented. A feedforward two-layer perceptron network is trained to detect and isolate unmeasured variations in the feedstock. Training and validation data sets are generated using a rigorous first principles model. The most important issue discussed here is the design of the data set required to train the artificial neural network. Efficiency and limitation of such an approach are demonstrated using simulations. (C) 2004 Elsevier Ltd. All rights reserved.

引用

页码：135 / 143

页数：9

共 28 条

[1] Modeling nuclear reactor core dynamics with recurrent neural networks
Adali, T
Bakal, B
Sonmez, MK
Fakory, R
Tsaoi, CO
[J]. NEUROCOMPUTING, 1997, 15 (3-4) : 363 - 381
[2] Selecting an artificial neural network for efficient modeling and accurate simulation of the milling process
Bricenco, JF
El-Mounayri, H
Mukhopadhyay, S
[J]. INTERNATIONAL JOURNAL OF MACHINE TOOLS & MANUFACTURE, 2002, 42 (06) : 663 - 674
[3] Carlson R., 1992, Design and Optimization in Organic Synthesis
[4] Challenges in the industrial applications of fault diagnostic systems
Dash, S
Venkatasubramanian, V
[J]. COMPUTERS & CHEMICAL ENGINEERING, 2000, 24 (2-7) : 785 - 791
[5] Reaction profile control of the continuous pulp digester
Doyle, FJ
Kayihan, F
[J]. CHEMICAL ENGINEERING SCIENCE, 1999, 54 (13-14) : 2679 - 2688
[6] Deterministic nonlinear observer-based approaches to fault diagnosis: A survey
Garcia, EA
Frank, PM
[J]. CONTROL ENGINEERING PRACTICE, 1997, 5 (05) : 663 - 670
[7] Model structure determination in neural network models
Henrique, HM
Lima, EL
Seborg, DE
[J]. CHEMICAL ENGINEERING SCIENCE, 2000, 55 (22) : 5457 - 5469
[8] Progress in supervised neural networks
Hush, Don R.
Horne, Bill G.
[J]. IEEE SIGNAL PROCESSING MAGAZINE, 1993, 10 (01) : 8 - 39
[9] On fuzzy logic applications for automatic control, supervision, and fault diagnosis
Isermann, R
[J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART A-SYSTEMS AND HUMANS, 1998, 28 (02): : 221 - 235
[10] COMPUTER AIDED DESIGN OF EXPERIMENTS
KENNARD, RW
STONE, LA
[J]. TECHNOMETRICS, 1969, 11 (01) : 137 - &

← 1 2 3 →