Transformer Fault Diagnosis of Rough-Neural Network Based on MEA

Jin Lan Gao

doi:10.4028/www.scientific.net/AMM.217-219.2585

Paper Titles

Propagation Characteristic in 2D Phononic Crystals with Bending Linear Defect
p.2566

System of Premixed Abrasive Jet Cleaning and Derusting on Steel Tube Inwall
p.2571

On-Line Detection Distribution Strategy Research of Complex Surface Based on Bayesian Networks
p.2575

Method of Identifying Key Quality Characteristics in Multistage Manufacturing Process Based on PLSR
p.2580

Transformer Fault Diagnosis of Rough-Neural Network Based on MEA
p.2585

Hydrodynamic Noise and Radiated Mechanism of 3D Cavity
p.2590

The Study on the Ultrasonic Testing and Defects in Quantitative Analysis for the Scroll-Type Profile
p.2594

Concurrent Tolerancing Design Based on Time Value of Manufacture-Quality Loss Cost
p.2598

Survey and Analyze the Line Output Characteristics in Inkjet Printing
p.2603

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 217-219Transformer Fault Diagnosis of Rough-Neural...

Transformer Fault Diagnosis of Rough-Neural Network Based on MEA

Abstract:

Combining mind evolutionary algorithm with rough set and neural network, this paper proposed a rough set neural network based on MEA for transformer fault diagnosis. Rough set attribute reduction as the front-processor of neural network diagnostic device, and using MEA to search rough set discrete breakpoints and optimize neural network weights and thresholds, it avoided complex manual trial of the conventional rough set attribute reduction and slow convergence speed and low precision of BP neural network, then faster convergence to the global optimum solution and improves the diagnosis speed and accuracy. Simulation results show that this method is effective.

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:

2585-2589

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.217-219.2585

Citation:

Cite this paper

Online since:

November 2012

Authors:

Jin Lan Gao

Keywords:

Attribute Reduction, BP Neural Network (BPNN), MEA, Rough Set Theory (RST), Transformer Fault Diagnosis

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] JU Q, YU Z B, HAO Z C, et al. Division-based rainfall-runoff simulations with BP neural networks and Xinanjiang model[J]. Neural computing, 2009, 72(13): 2873-2883.

DOI: 10.1016/j.neucom.2008.12.032

Google Scholar

[2] Song Yibin. Quick training method for multi-layer perception and its application. Control and decision, 2000, 12(1): 125-127.

Google Scholar

[3] Shu Hongchun; Sun Xiangfei; Si Dajun. A RS approach to founding and maintaining ES knowledge base for fault diagnosis of power transformer [J]. Proceedings of the Csee, 2002, 22(2): 31-35.

Google Scholar

[4] Jelonek J, et al. Rough set reduction of attributes and their domains for neural networks[J]. Computational Intelligence, 1995, 11(2)：339-347.

DOI: 10.1111/j.1467-8640.1995.tb00036.x

Google Scholar

[5] Zeng Huanglin. Rough set theory and application[M]. Chongqing: Chongqing University Press, 1998.

Google Scholar

[6] Xie, Keming, Du, Yonggui, Sun, Chengyi, Application of the mind-evolution-based machine learning in mixture-ratio calculation of raw materials cement[J], The World Congress on Intelligent Control and Automation (WCICA), 2000, v1, pp.132-134.

DOI: 10.1109/wcica.2000.859932

Google Scholar

[7] Wang Fang, Xie Ke-ming, Liu Jian-xia, Swarm intelligence based MEA design[J]. Control and Decision, Jan. 2010, Vol.25, No.1: 145-148.

Google Scholar

[8] Miao Duoqian, Li Daoguo. Rough set theory, algorithms and applications [M]. Beijing: Qinghua University Press, 2007.

Google Scholar