Experimental study and nonlinear modelling by artificial neural networks of a distillation column

被引：4
作者：
Chetouani Y. [1 ]
机构：
[1] Département Génie Chimique, Université de Rouen, Rue Lavoisier
来源：
International Journal of Reliability and Safety | 2010年 / 4卷 / 2-3期
关键词：
ANNs; Artificial neural network; Distillation column; Modelling; Monitoring; Product quality; Reliability;
D O I：
10.1504/IJRS.2010.032448
中图分类号：
学科分类号：
摘要：
Chemical industries are characterised by complex nonlinear processes. A suitable class of Non-linear Auto-Regressive Moving Average with eXogenous (NARMAX) models is considered which captures most of the system dynamics. The use of this model should reflect the normal behaviour of the process and be used for developing a cost-effective Fault Detection and Diagnosis (FDD) method. An Artificial Neural Network (ANN) is used to model plant input-output data by means of a NARMAX model. Three statistical criteria are used for the validation of the experimental data. A realistic and complex application as a distillation column is presented in order to illustrate the proposed ideas concerning the dynamics modelling and model reduction. Satisfactory agreement between identified and experimental data is found and results show that the reduced neural model successfully predicts the evolution of the product composition. Copyright © 2010 Inderscience Enterprises Ltd.
引用
收藏
页码：265 / 284
页数：19
相关论文
共 47 条
  • [1] Al-Enezi G., Elkamel A., Predicting the effect of feedstock on product yields and properties of the FCC process, Petroleum Science and Technology, 18, 3-4, pp. 407-128, (2000)
  • [2] Bhagwat A., Srinivasan R., Krishnaswamy P.R., Fault detection during process transitions: A model-based approach, Chemical Engineering Science, 58, 2, pp. 309-325, (2003)
  • [3] Billings S.A., Voon W.S.F., Correlation based model validity tests for nonlinear models, International Journal of Control, 44, pp. 235-244, (1986)
  • [4] Cammarata L., Fichera A., Pagano A., Neural prediction of combustion instability, Applied Energy, 72, 2, pp. 513-528, (2002)
  • [5] Chen S., Billings S.A., Representation of nonlinear systems-the NARMAX model, International Journal of Control, 49, pp. 1013-1032, (1989)
  • [6] Chetouani Y., Modeling and prediction of the dynamic behavior in a reactor-exchanger using NARMAX neural structure, Chemical Engineering Communications, 194, 5, pp. 691-705, (2007)
  • [7] Chetouani Y., Use of cumulative sum (CUSUM) test for detecting abrupt changes in the process dynamics, International Journal of Reliability, Quality and Safety Engineering, 14, pp. 65-80, (2007)
  • [8] Chouai A., Laugier S., Richon D., Modeling of thermodynamic properties using neural networks: Application to refrigerants, Fluid Phase Equilibria, 199, 1-2, pp. 53-62, (2002)
  • [9] Cybenko G., Approximation by superpositions of a sigmoidal function, Mathematics of Control, Signals, and Systems, 4, pp. 303-312, (1989)
  • [10] Deng W.-J., Chen W.-C., Pei W., Back-propagation neural network based importance-performance analysis for determining critical service attributes, Expert Systems with Applications, 34, 2, pp. 1115-1125, (2008)
12345