Detection of Single and Dual Incipient Process Faults Using an Improved Artificial Neural Network

Document Type: Research Article

Authors

Department of Chemical & Petroleum Engineering, Sharif University of Technology, Tehran, I.R. IRAN

Abstract

Changes in the physicochemical conditions of process unit, even under control, may lead to what are generically referred to as faults. The cognition of causes is very important, because the system can be diagnosed and fault tolerated. In this article, we discuss and propose an artificial neural network that can detect the incipient and gradual faults either individually or mutually. The main feature of the proposed network is including the fault patterns in the input space. The scheme is examined through a sample unit with five probable occurring faults. The simulation results indicate that the proposed algorithm can detect both single and two simultaneous faults properly.

Keywords


[1] Venkatasubramanian, V., Rengaswamy, R., Yin, K.  and Kavuri, S.N., Comp. And Chem. Eng., 27, p. 293 (2003).
[2] Venkatasubramanian, V.,  Rengaswamy,  R.,  and Kavuri, S.N., Comp. And Chem. Eng., 27, p. 313 (2003).
[3] Watanabe, K. and Himmelblau, D.M., AIChE J., 29, p. 250 (1983).
[4] Watanabe, K. and Himmelblau, D.M., Chem. Eng. Sci., 39, p. 491 (1983).
[5] Vedam, H. and Venkatasubramanian, V., Comp. And Chem. Eng., 21, S655 (1997).
[6] Joskins, J.C. and Himmelblau, M., Comp. And Chem. Eng., 12, p. 881 (1988).
[7] Rengaswamy, R. and Venkatasubramanian, V., Comp. And Chem. Eng., 27, p. 431 (2000).
[8] Chen, B.H., Wang, X.Z., Yang, S.H. and Mcgreavy, C., Comp. And Chem. Eng., 23(7), p. 899 (1999).
[9] Vachhani, P.,  Rengaswamy,  R. and Venkatasubra-manian, V., Chem. Eng. Sci., 56 (6), p. 2133 (2001).
[10] Watanabe, K., et al., AIChE J., 35, p. 1803 , (1989).