Rough Neuron network for Fault Diagnosis

Full Text (PDF, 357KB), PP.51-58

Views: 0 Downloads: 0

Author(s)

Yueling ZHAO 1,* Hui jin 1 Lihong Wang 1 Shuang WANG 1

1. College of Electrical Engineering , Liaoning University of Technology, Jinzhou, P.R.China

* Corresponding author.

DOI: https://doi.org/10.5815/ijigsp.2011.02.08

Received: 2 Dec. 2010 / Revised: 11 Jan. 2011 / Accepted: 15 Feb. 2011 / Published: 8 Mar. 2011

Index Terms

Rough Set, rough neuron, particle swarm, rough neuron BP neural network, fault diagnosis

Abstract

Considering training time of traditional BP neural network is too long and it cannot solve the problems in the input vector with multiple-valued, a new method of BP neural network based on rough neuron is presented. A rough neuron can be viewed as a pair of neurons. One neuron corresponds to the upper boundary and the other corresponds to the lower boundary. Upper and lower neuron exchange information with each other during the calculation of their outputs. Firstly, the continuous attributes in diagnostic decision system are discretized with particle swarm optimization. Then, the reducts are found based on attribute dependence of rough set, and the optimal diagnostic decision is determined. Lastly, according to the optimal decision system, rough neuron network is designed for fault diagnosis. A practical example is given , the method is feasible and available.

Cite This Paper

Yueling ZHAO,Hui jin,Lihong Wang,Shuang WANG,"Rough Neuron network for Fault Diagnosis", IJIGSP, vol.3, no.2, pp.51-58, 2011. DOI: 10.5815/ijigsp.2011.02.08

Reference

[1]ZHENG X X, QIAN F. Research and development of fault diagnosis methods for dynamic system. Control and Instruments in Chemical Industry, 2005, 32(4): 1-7.

[2]FENG J, LIAO Y, WANG J Q. Fault diagnosis based on ANN in water circulation system. Journal of Hunan Institute of Engineering, 2005.3, 15(1): 47-50.

[3]SHI H F, LIU J R, MA Y F. The application of neuralnetwork-based fault diagnosis expert system for sluice. Chinese Journal of Scientific, 2005.8, 26(8): 769-778.

[4]LIAO J J. Research on data mining system for failure diagnosis based on neural network. Information Technology, 2009, 4: 31-33.

[5]HUANG D, SONG X. Application of neural network to chemical fault diagnosis . Control Engineering of China, 2006.1, 13(1): 6-9.

[6]GAO Y, YANG H ZH. Fault diagnosis method for chemical polymeric process based on neural networks. Control Engineering of China, 2005.5, 12: 52-54.

[7]Pawlak Z, Rough Sets. Informational Journal of Information and Computer Sciences, 1982, 11(5): 341-356.

[8]CHEN T, LUO J Q. Fuzzy pattern recognition for radar signals based on rough set fixed weight. Computer Applications and Software, 2009.1, 26(1): 25-27.

[9]GUO Q L, ZHENG L. A novel approach for fault diagnosis of steam turbine unit based on fuzzy rough set data mining theory. Proceedings of the CSEE, 2007.3, 27(8): 81-87.

[10]GUO X H, MA X P. Fault diagnosis feature subset selection using rough set. Computer Engineering and Applications, 2007, 43(1): 221-224.

[11]GUO X H, MA X P. Fault diagnosis based on rough set and neural network ensemble. Control Engineering of China, 2007.1, 14(1): 53-56.

[12]DONG J K, LI Y, GENG H. Research on airborne equipment fault diagnosis method based on rough setneural network. Avionics Technology, 2008.3, 39(1): 37-41.

[13]P.J. Lingras, Rough neural networks, Proceedings of Sixth International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems, Granada, Spain, 1996, pp. 1445-1450.

[14]Lin, T.Y.: Introduction to the special issue on rough sets. International Journal of Ap-proximate Reasoning. Vo.15. (1996) 287-289

[15]Dai, J.H., Li Y.X.: Study on discretization based on rough set theory. Proc. of the first Int. Conf. on Machine Learning and Cybernetics. (2002) 1371-1373

[16]Roy, A., Pal, S.K.: Fuzzy discretization of feature space for a rough set classifier. Pattern Recognition Letter. Vol.24. (2003) 895-902

[17]usmaga, R.: Analyzing discretizations of continuous attributes given a monotonic dis-crimination function. Intelligent Data Analysis. Vol.1. (1997) 157-179

[18]Eberhart R C, Kennedy J. Particles swarm optimization [C]. IEEE International Conference on Neural Network, Perth, Australia, 1995: 1942-1948.

[19]Eberhart R C, Kennedy J. A new optimizer using particles swarm theory [C]. Proc. of Sixth International Symposium on Micro Machine and Human Science, Nagoya, Japan, 1995: 39-43.

[20]YANG SH Z, DING H, SHI T L. Diagnose reasoning based on knowledge [M]. Beijing: Tsinghua University Press, 1993: 30-31.