Fault Diagnosis System of Tennessee-Eastman Process Based on RBF Networks and Wavelet

Abstract:

BP neural networks requires for the predicted number of hidden layer neurons and the corresponding predicted function. RBF distributed organizations can effectively address a large number of fault information. RBF algorithm is combined with the wavelet. The diagnosis system is simulated for multi-variable nonlinear Tennessee-Eastman Process (Tennessee - Eastman TE process).The results show that the fault diagnosis system based on wavelet RBF algorithm is better than the traditional BP neural networks and improved wavelet BP algorithm, and can effectively solve the problem of fault diagnosis.

• Periodical: Advanced Materials Research (Volumes 546-547)
• Pages: 828-832
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.546-547.828
• Online since: July 2012
• Authors: Xiao Qin Liu, Hai Jun Sun, Shu Xian Deng, Tai Dong Ji
• Keywords: Fault Diagnosis, Radial Basis Function (RBF), Tennessee-Eastman Process, Wavelet

References

[1] Russel E.L., Chiang L.H., and Braatz R.D. Fault detection in industrial processes using canonical variate analysis and dynamic Principal component analysis[J], Chemometrics and Intel. Lab. Sysr. 2000, 51: 81-93.

DOI: 10.1016/s0169-7439(00)00058-7

[2] Kano, M., Hasebe,S. and Hashimoto, I. A new multivariate statistical process monitoring method using principal component analysis[J], Computers and Chemical Engineering, 2001, 25: 1103-1113.

DOI: 10.1016/s0098-1354(01)00683-4

[3] Gertler,J., Li,W., Huang.Y., and McAvoy, T.J. Isolation enhanced principal component analysis[J], AICHE J., 1999, 45: 323-334.

DOI: 10.1002/aic.690450213

[4] Chiang L.H., Russel E.L., and Braatz R.D. Fault diagnosis in chemical processes using Fisher discriminant analysis, discriminant partial least squares, and principal component analysis[J], Chemometrics and Intel. Lab. Syst., 2000, 50: 243-252.

DOI: 10.1016/s0169-7439(99)00061-1

[5] Kano, M., Nagao, K., Hasebe, S. etal. Comparison of multivariate statistical process monitoring methods with applications to the Eastman challenge problem[J], Computers and Chemical Engineering, 2002, 26: 161-174.

DOI: 10.1016/s0098-1354(01)00738-4

[6] Bi Tian-shu, Ni Yi-xin, Wu Fu-li, Yang Qi-xun. Hybrid Fault Section EstimationSystemWith Radial Baisis Function Neural Network And Fuzzy System. Proceedings of the CSEE. 2005, Vol. 25, No. 14: 12-18.

[7] Szu H, etal. Neural network adaptive wavelets neural for signal representation and classification, Optical Engineering , 1992, 31(9): 1907-(1916).

DOI: 10.1117/12.59918

[8] Downs, J.J. and Vogel, E.F. A plant-wide industrial process control problem[J]. Computers and chemical Engineering, 1993, 17(3): 245-255.

DOI: 10.1016/0098-1354(93)80018-i

[9] McAvoy, T.J. and Ye, N. Base control for the Tennessee Eastman problem [J]. Computers and Chemical Engineering, 1994, 18: 383-413.

DOI: 10.1016/0098-1354(94)88019-0