Combined Input Training and Radial Basis Function Neural Networks based Nonlinear Principal Components Analysis Model Applied for Process Monitoring

Messaoud Bouakkaz, Mohamed-Faouzi Harkat

2012

Abstract

In this paper a novel Nonlinear Principal Component Analysis (NLPCA) is proposed. Generally, a NLPCA model is performed by using two sub-models, mapping and demapping. The proposed NLPCA model consists of two cascade three-layer neural networks for mapping and demapping, respectively. The mapping model is identified by using a Radial Basis Function (RBF) neural networks and the demapping is performed by using an Input Training neural networks (IT-Net). The nonlinear principal components, which represents the desired output of the first network, are obtained by the IT-NET. The proposed approach is illustrated by a simulation example and then applied for fault detection and isolation of the TECP process.

References

  1. Dong, D. and McAvoy, T. (1996). Nonlinear principal component analysis based on principal curves and neural networks. Computers and Chemical Engineering 20, 65 78.
  2. Downs, J. and Vogel, E. (1993). A plant-wide industrial control problem. Computers and chemical engineering Journal 17, 245-255.
  3. Dunia, R., Qin, S., Ragot, J., and McAvoy, T. (1996). Identification of faulty sensors using principal component analysis. AIChE Journal 42, 2797-2812.
  4. Harkat, M., Djellel, S., Doghmane, N., and Benouareth, M. (2007). Sensor fault detection, isolation and reconstruction using nonlinear principal component analysis. Intarnational Journal of Automation and Computing, 4,.
  5. Harkat, M., Mourot, G., and Ragot, J. (2003). Variable reconstruction using rbf-nlpca for process monitoring. In IFAC Symposium on Fault Detection, Supervision and Safety for Technical Process, SAFEPROCESS. Washington, USA.
  6. Hastie, T. and Stuetzle, W. (1989). Principal curves. Journal of the American Statistical Association 84, 502-516.
  7. Hsieh, W. and Li, C. (2001). Nonlinear principal component analysis by neural networks. Tellus Journal 53A, 599- 615.
  8. Kramer, M. (1991). Nonlinear principal component analysis using auto-associative neural networks. AIChE Journal 37, 233-243.
  9. LeBlanc, M. and Tibshirani, R. (1994). Adaptive principal surfaces. Journal of American Statistical Association 89(425), 53-64.
  10. Tan, S. and Mavrovouniotis, M. (1995). Reduction data dimensionality through optimizing neural network inputs. AIChE Journal 41, 1471-1480.
  11. Verbeek, J. (2001). A k-segments algorithm for finding principal curves. IAS Technical Journal.
  12. Vogel, N. R. E. (1994). Optimal steady-state operation of the tennessee eastman challenge process. Computers and chemical engineering Journal 19, 949-959.
  13. Webb, A., Vlassis, N., and Krose, B. (1999). A loss function to model selection in nonlinear principal components. Neural Networks Journal 12, 339-345.
  14. Zhu, Q. and Li, C. (2006). Dimensionality reduction with input training neural network and its application in chemical process modeling. Chinese Journal.
Download


Paper Citation


in Harvard Style

Bouakkaz M. and Harkat M. (2012). Combined Input Training and Radial Basis Function Neural Networks based Nonlinear Principal Components Analysis Model Applied for Process Monitoring . In Proceedings of the 4th International Joint Conference on Computational Intelligence - Volume 1: NCTA, (IJCCI 2012) ISBN 978-989-8565-33-4, pages 483-492. DOI: 10.5220/0004152304830492


in Bibtex Style

@conference{ncta12,
author={Messaoud Bouakkaz and Mohamed-Faouzi Harkat},
title={Combined Input Training and Radial Basis Function Neural Networks based Nonlinear Principal Components Analysis Model Applied for Process Monitoring},
booktitle={Proceedings of the 4th International Joint Conference on Computational Intelligence - Volume 1: NCTA, (IJCCI 2012)},
year={2012},
pages={483-492},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004152304830492},
isbn={978-989-8565-33-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 4th International Joint Conference on Computational Intelligence - Volume 1: NCTA, (IJCCI 2012)
TI - Combined Input Training and Radial Basis Function Neural Networks based Nonlinear Principal Components Analysis Model Applied for Process Monitoring
SN - 978-989-8565-33-4
AU - Bouakkaz M.
AU - Harkat M.
PY - 2012
SP - 483
EP - 492
DO - 10.5220/0004152304830492