Fault Diagnosis of Chemical Process Based on ACO-BP Neural Network

Jian Xue Chen

doi:10.4028/www.scientific.net/AMM.217-219.2722

Paper Titles

Prediction of Top Coal Caving Ability Based on Support Vector Machine
p.2702

Adaptive Interpolation of Tool Posture Vector in Five-Axis Flank Milling
p.2706

Effect of Structure Parameters on Dynamic Characteristics of Piezoelectric Vibrator in Ultrasonic EDM Processing
p.2711

Improved Atomic Force Microscopic Inspection Process of Liquid Crystal Display
p.2716

Fault Diagnosis of Chemical Process Based on ACO-BP Neural Network
p.2722

Fault Diagnosis for AP1000 Plant Feed Water System Based on the Fault Petri Net
p.2726

Application Study on Automatic Particle Count Technology Used in Fuel Filtration Efficiency Test
p.2731

Multiaperture Connection Method for Three-Dimensional Mesasurement Based on Quaternion
p.2736

The Analysis on Controllability of Angular Ball Bearings with Considering the Installation Errors
p.2740

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 217-219Fault Diagnosis of Chemical Process Based on...

Fault Diagnosis of Chemical Process Based on ACO-BP Neural Network

Abstract:

Fault diagnosis is an important problem in the process of chemical industry and the artificial neural network is widely applied in fault diagnosis of chemical process. A hybrid algorithm combining ant colony optimization (ACO) algorithm with back-propagation (BP) algorithm, also referred to as ACO-BP algorithm, is proposed to train the neural network weights and thresholds. The basic theory and steps of ACO-BP algorithm are given, and applied in fault diagnosis of the continuous stirred-tank reactor (CSTR). Experimental results prove that ACO-BP algorithm has good fault diagnosis precision, and it can detect the fault in CSTR promptly and effectively.

You might also be interested in these eBooks

Advanced Materials and Process Technology

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 217-219)

Pages:

2722-2725

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.217-219.2722

Citation:

Cite this paper

Online since:

November 2012

Authors:

Jian Xue Chen

Keywords:

Ant Colony Optimization Algorithm (ACOA), Back Propagation Algorithm (BPA), CSTR, Fault Diagnosis, Neural Network (NN)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] T.Sorsa, and H.H. Koiva: Neural Networks in Process Fault Diagnosis, IEEE Trans on SMC Vol. 22 (1999), pp.19-22

Google Scholar

[2] S.Haykin: Neural Networks: A Comprehensive Foundation. Macmillan College Publishing (1994)

Google Scholar

[3] Marco Gori,Alberto Tesi: On the problem of local minima in back-propagation, IEEE Trans, Pattern Anal.Mach.Intell, Vol 14 (1992), p.76–86

DOI: 10.1109/34.107014

Google Scholar

[4] A.van Ooyen and B.Nienhuis: Improving the convergence of the back-propagation algorithm, Neural Network, Vol 4 (1922), p.465–471

DOI: 10.1016/0893-6080(92)90008-7

Google Scholar

[5] M.Dorigo and G.Di Caro: The Ant Colony Optimization meta-heuristic, in: D.Corne, M. Dorigo, and F. Glover, editors, New Ideas in Optimization, McGraw Hill, London, UK (1999)

DOI: 10.1109/cec.1999.782657

Google Scholar

[6] M.Dorigo, G. Di Caro, and L.M. Gambardella: Ant algorithms for discrete optimization, Artificial Life, Vol 5 (1999), p.137–172

DOI: 10.1162/106454699568728

Google Scholar

[7] Wang Ge and Pu Peng-bo: Application of ACO-BP in Neural Network Training, Computer Simulation, Vol 26 (2009), pp.136-140

Google Scholar

[8] Zhong-Wen, Jin-Shou Yu and Xiang-Ming Hua: On-line Quality Control of CSTR Concentration, Journal of East China University of Science & Technology, Vol 23 (1997), p.232~236

Google Scholar