International Journal of Information Engineering and Electronic Business(IJIEEB)

ISSN: 2074-9023 (Print), ISSN: 2074-9031 (Online)

Published By: MECS Press

IJIEEB Vol.2, No.1, Nov. 2010

Comparison of Two Methods Basing on Artificial Neural Network and SVM in Fault Diagnosis

Full Text (PDF, 590KB), PP.23-29

Views:71   Downloads:7


Chunming Li,Huiling Li

Index Terms

Neural network;SVM;fault diagnosis


Two diagnosis methods based on a neural network classifier and SVM are proposed for a pulse width modulation voltage source inverter. They are used to detect and identify the transistor open-circuit fault. BP neural network (BPNN) is capable of recognition. However, it has shortcomings obviously. These are just advantages of SVM, which has ability of global search. As an alternative to ANN, SVM can offer higher detection efficiency and reliability.

Cite This Paper

Chunming Li,Huiling Li,"Comparison of Two Methods Basing on Artificial Neural Network and SVM in Fault Diagnosis", IJIEEB, vol.2, no.1, pp.23-29, 2010.


[1]Kastha,K,and Majundar,A.K.“An improved starting strategy for voltage source inverter fed three phase induction motor drive under inverterfaultconditions”,IEEE Transactions on Power Electron,2000,vol 15,pp.726-732.

[2]Bellinni,A.“Closed-loop control impact on the diagnosis of induction motor faults”.Conf.Rec.of IEEE-IAS Annual Mtg,October 1999,pp.1913-1921.

[3]K.Mohammadi, S.J.Seyyed Mahdavi.On improving training time of neural networks in mixed signal circuit fault diagnosis applications. Microelectronics Reliability, 2008.

[4]M. Abdel-Salami. Y. M.Y. Hasani.Neural networks recognition of weak points in power systems based on wavelet fearures.18thInternational Conference on Electricity Distribution, 2005.

[5]Yanghong Tan, Yigang He. A Novel Method for Analog Fault Diagnosis Based on Neural Networks and Genetic Algorithms. Instrumentation and Measurement, IEEE Transactions on Volume 57, Issue11, Nov.2008 Page(s):2631 – 2639.

[6]Chien-Yu Huang, Long-Hui Chen, Yueh-Li Chen, Fengming M.Chang.Evaluating the process of a genetic algorithm to improve the back-propagation network: A Monte Carlo study. Expert Systems with Applications, Volume 36, Issue 2, Part 1, March 2009, Pages 1459-1465.