Performance Assessment on Two Kinds of GA-Based Neural Networks in Fault Diagnosis

Xiao Gang Jian; Jian Gxin Huang

doi:10.4028/www.scientific.net/AMR.403-408.3090

Paper Titles

A Practical Tool for Multiple Simulation Tasks of Gas Engine
p.3071

Wireless Transfer Mode Based on the Environmental Detection System
p.3077

Predicting Seepage of Earth Dams Using Neural Network and Genetic Algorithm
p.3081

Research and Implementation of Management System of Laboratory
p.3086

Performance Assessment on Two Kinds of GA-Based Neural Networks in Fault Diagnosis
p.3090

Dynamical Assembly for Naked-Eye-Stereoscopic LCD Screen
p.3095

The Research on 4WS Vehicle Steering Stability by Modeling and Simulation
p.3099

The Ideas of Building Information Platform for Fujian Cross-Strait Information Industrial Cooperation
p.3104

A Simple and Effective NDA Carrier Frequency Estimation Method for MPSK Signals in Unknown Fading Channel
p.3108

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 403-408Performance Assessment on Two Kinds of GA-Based...

Performance Assessment on Two Kinds of GA-Based Neural Networks in Fault Diagnosis

Abstract:

In this paper, we analyze characteristics of two kinds of GA-Based neural networks. For large scale neural networks, it is necessary to optimize the initial network parameters. Using the global optimum ability of GA(Genetic Algorithm), we optimize the initial weights and biases of BPNN (Back-Propagation Neural Networks), which can avoid the local minimum. And we also optimize the spread coefficient of Gaussian Radial Basis Function of PNN (Probabilistic Neural Networks). Then the results in transformer fault diagnosis are compared. Experimental results based on Matlab show that the method of GA-Based greatly increases the reliability of diagnosis.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 403-408)

Pages:

3090-3094

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.403-408.3090

Citation:

Cite this paper

Online since:

November 2011

Authors:

Xiao Gang Jian, Jian Gxin Huang

Keywords:

BP Neural Network (BPNN), Fault Diagnosis, GA, PNN, Transformer

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Judd J S: Proceedings of the 1th IEEE International Conference on Neural Networks Vol. 2 (1987), p.685.

Google Scholar

[2] Yiqin Wan: Transformer fault diagnosis based on PNN (Master Thesis, Nanchang University 2007).

Google Scholar

[3] Houfeng Duan: Transformer fault diagnosis based on BP neural networks optimized by GA (Master Thesis, Peking Jiaotong University 2008).

Google Scholar

[4] Chun Lu, Bingxue Shi and Lu Chen: Proceedings of the 7th IEEE International Conference on Electronics, Circuits and Systems Vol. 2 (2000), p.958.

DOI: 10.1109/icecs.2000.913035

Google Scholar

[5] Tatsuya Hirane, Tetsuya Toryu, Hidehiro Nakano, Arata Miyauchi: Lecture Notes in Computer Science Vol. 3696 (2005), p.323.

Google Scholar

[6] Eiko Sugawara, Masaru Fukushi, Susurnu Horiguchi: Proceedings of the 18th IEEE International Symposium on Defect and Fault Tolerance in VLSI Systems (2003), p.328.

DOI: 10.1109/dftvs.2003.1250128

Google Scholar