Improved Fault Diagnosis Method Based on Probabilistic Neural Network

Gu Qing Liu; Shu Hua Yin; Xin Tian Wang; Yan Qing Sun

doi:10.4028/www.scientific.net/AMR.433-440.6084

Paper Titles

A Novel Index to Voltage Collapse based on the System Physical Quantities
p.6060

Non-Characteristic Harmonics Analysis of HVDC System Based on Expansion Prony Algorithm
p.6065

On-Line Evaluation of Voltage Transformer Accuracy
p.6071

Experimental Study on Dynamic Characteristics and Seismic Response Analysis of Yingxian Wooden Pagoda
p.6077

Improved Fault Diagnosis Method Based on Probabilistic Neural Network
p.6084

Study on Application of Improved Predictive Current Method in STATCOM
p.6089

Calculation of Iron Loss in Large Hydro-Generator under Non-Load
p.6096

Method of Wavelet Denoising in Harmonic Detection
p.6103

Warranty Costs Assessment for Automotive Applications
p.6108

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 433-440Improved Fault Diagnosis Method Based on...

Improved Fault Diagnosis Method Based on Probabilistic Neural Network

Abstract:

In order to enhancing the accuracy of fault diagnosis system, an improved method based on the probabilistic neural network (PNN) is proposed, in which the synthetic attribute weights of faults are introduced that are obtained by integrating algebra view and information theory view of rough set. The synthetic attribute weights are utilized to training the classical PNN and dealing with the classification of faults so as to improving the PNN model. The new model is more accurate and can represent expertise. This novel approach is applied in digital data network to diagnose failures, and the results of the experiment verify that the method is practical and effective in raising accuracy of diagnosis as well as avoiding misdirection in fault remedy.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 433-440)

Pages:

6084-6088

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.433-440.6084

Citation:

Cite this paper

Online since:

January 2012

Authors:

Gu Qing Liu, Shu Hua Yin, Xin Tian Wang, Yan Qing Sun

Keywords:

Attribute Weights, Fault Diagnosis, Probabilistic Neural Network, Rough Set (RS)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Xu liuyi, Li jianghuang, A kind of CBR for improve breaks down the diagnosis method research, J. Control & Measurement. China, vol. 23, pp.216-218, July (2007).

Google Scholar

[2] Pawlak Z, Rough Sets: Theoretical Aspects of Reasoning About Data[M], Boston: Kluwer Academic Publishers, (1991).

Google Scholar

[3] Lei Lin, Dai Chuantong, Fault Diagnosis of Node in WSN Based on Integration of Rough sets and Neural Network, J. Journal of University of electronic Science and Technology of China, vol. 37, pp.565-568, April (2008).

Google Scholar

[4] Liu Fei, Kong Yuanyuan, A new method based on integration of CBR and BP neural network, J. Journal of lianyungang Technical College. China, vol. 21, pp.15-17, Feb. (2008).

Google Scholar

[5] Jian-Da Wu，Peng-Hsin Chiang，Yo-Wei Chang, An expert system for fault diagnosis in internal combustion engines using probability neural network, J. Expert Systems with Applications. China, vol. 34, pp.2704-2713, (2008).

DOI: 10.1016/j.eswa.2007.05.010

Google Scholar

[6] Wang Xiao-yan, Yang Si-chun, A new algorithm for attribute reduction based on discernible matrix, J. Computer Technology and Development. China, vol. 18, pp.77-79, Feb. (2008).

Google Scholar