Shing-chiang TAN1, Chee-peng LIM2
(1. Faculty of Information Science & Technology, Multimedia University, Bukit Beruang, Melaka 75450, Malaysia; 2. School of Computer Science of University of Science Malaysia, Gelugor Penang 11700, Malaysia)
Abstract-Accurate fault detection and diagnosis is important for secure and profitable operation of modern power systems. In this paper, an ensemble of conflict-resolving Fuzzy ARTMAP classifiers, known as Probabilistic Multiple Fuzzy ARTMAP with Dynamic Decay Adjustment (PMFAMDDA), for accurate discrimination between normal and faulty operating conditions of a Circulating Water (CW) system in a power generation plant is proposed. The decisions of PMFAMDDA are reached through a probabilistic plurality voting strategy that is in agreement with the Bayesian theorem. The results of the proposed PMFAMDDA model are compared with those from an ensemble of Probabilistic Multiple Fuzzy ARTMAP (PMFAM) classifiers. The outcomes reveal that PMFAMDDA, in general, outperforms PMFAM in discriminating operating conditions of the CW system.
Key words-fault detection and diagnosis; fuzzy ARTMAP; dynamic decay adjustment algorithm; plurality voting; circulating water system
Manuscript Number; 1674-8042(2011)04-0371-07
doi: 11.3969/j.issn.1674-8042.2011.04.016
References
[1] T. Minakawa, Y. Ichikawa, M. Kunugi, et al., 1995. Development and implementation of a power system fault diagnosis expert system. IEEE Trans. Power Syst., 10: 932-940.
[2] B. Yazici, G.B. Kliman, W.J. Premerlani, et al., 1997. An adaptive, on-line, statistical method for detection of broken bar in motors using stator current and torque estimation. Proc. of IEEE Ind. Applicat. Soc. Annu. Meeting, 1: 221-226.
[3] W. M. Lin, C. H. Lin, Z. C. Sun, 2004. Adaptive multiple fault detection and alarm processing for loop system with probabilistic network. IEEE Trans. Power Deliver, 19: 64-69.
[4] V. Venkatasubramanian, R. Rengaswamy, K. Yin, et al., 2003. A review of process fault detection and diagnosis: Part I: Quantitative model-based methods. Comput. Chem. Eng., 27: 293-311.
[5] F. Kimura, Z. Chen, M. Shridhar, 1990. An integrated character recognition algorithm for locating and recognizing zip codes. Proc. of U.S. Postal Service Advanced Technology Conf., p.605-619.
[6] C.Y. Suen, C. Nadal, T.A. Mai, et al., 1992. Computer recognition of unconstrained handwritten numerals. Proc. of IEEE, 80: 1162-1180.
[7] J. Franke, E. Mandler, 1992. A comparison of two approaches for combining the votes of cooperating classifiers. Proc. of 11th Int. Conf. Pattern Recognition, The Hague,The Netherlands, 2: 611-614.
[8] B. Grofman, G. Owen, S. Field, 1983.Thirteen theorems in search of the truth. Theory Decis, 15: 261-278.
[9] G. A. Carpenter, S. Grossberg, 1987. A massively parallel architecture for a self-organizing neural pattern recognition machine. Computer Vision, Graphics and Image Processing, 37: 54-115.
[10] G. A. Carpenter, S. Grossberg, 1987. Stable self-organisation of pattern recognition codes for analog input patterns. Appl. Opt., 26: 4919-4930.
[11] G. A. Carpenter, S. Grossberg, 1988. The art of adaptive pattern recognition by a self-organizing neural network. Computer, 21:77-88.
[12] G.A. Carpenter, S. Grossberg, D. Rosen, 1991. Fuzzy art: fast stable learning and categorization of analog patterns by an adaptive resonance system. Neural Netw., (4): 759-771.
[13] G.A. Carpenter, S. Grossberg, J. Reynolds, 1991. ARTMAP: Supervised real-learning and classification of nonstationary data by a self-organizing neural network. Neural Netw., 4: 565-588.
[14] G.A. Carpenter, S. Grossberg, N. Markuzon, et al., 1992. Fuzzy ARTMAP: a neural network architecture for incremental supervised learning of analog multidimensional maps. IEEE Trans. Neural Netw., 3: 698-712.
[15] G.A. Carpenter, W. Ross, 1995. ART-EMAP: a neural network architecture for object recognition by evidence accumulation. IEEE Trans. Neural Netw., 6: 805-818.
[16] G.A. Carpenter, 1997. Distributed learning, recognition, and prediction by art and artmap neural networks. Neural Netw., 10: 1473-1494.
[17] S.C. Tan, M.V.C. Rao., C.P. Lim, 2006. On the reduction of complexity in the architecture of fuzzy ARTMAP with dynamic decay adjustment, Neurocomputing, 69: 2456-2460.
[18] X. Lin, S. Yacoub, J. Burns, et al., 2003. Performance analysis of pattern classifier combination by plurality voting. Pattern Recognition Letters, 24: 1959-1969.
[19] S.C. Tan , C.P. Lim, 2004. Application of an adaptive neural network with symbolic rule extraction to fault detection and diagnosis in a power generation plant. IEEE Trans. Energy Conver., 19: 369-377.
[20] G.A. Carpenter , A.H. Tan, 1995. Rule extraction: from neural architecture to symbolic representation. Connection Sci., 7: 3-27.
[21] K.P. Huber, M.R. Berthold, 1995. Building precise classifiers with automatic rule extraction. Proc. of IEEE Int. Conf. Neural Networks, 3: 1263-1268.
[22] L. Zadeh, 1965. Fuzzy sets. Information and Control, 8: 338-353.
[23] C.P. Lim, R.F. Harrison, 1997. An incremental adaptive network for on-line supervised learning and probability estimation. Neural Netw., 10: 925-939.
[24] G. Auda, M. Kamel, H. Raafat, 1995. Voting schemes for cooperative neural network classifiers. Proc. of IEEE Int. Conf. Neural Netw., 3: 1240-1243.
[25] L. Lam , C.Y. Suen, 1997. Application of majority voting to pattern recognition: an analysis of the behavior and performance. IEEE Trans. Syst, Man, and Cybern., 27: 553-567.
[26] Tenaga Nasional Sdn Bhd (TNB): System description and operating procedures. Prai Power Station Stage 3, 1999.
[27] B. Efron, 1979. Bootstrap methods: another look at the Jackknife. The Annals of Statistics, 7: 1-26.
[full text view]
