The Application of Improved SVM in Mixed Circuit

Huai Long Wang; Qiang Pan; Hong Liu

doi:10.4028/www.scientific.net/AMM.224.493

Paper Titles

Control-Relevant Discretization of Nonlinear State Delay Systems Using the Matrix Exponential Algorithm
p.475

Adaptive Fuzzy SMC Control for Nonlinear System of Dual Arm Robot
p.480

The Safety Research for Face Recognition System Based on Image Feature and Digital Watermarking
p.485

Training Mode Reform of Application Excellence Engineer in Mechatronics Subject Field for Local University
p.489

The Application of Improved SVM in Mixed Circuit
p.493

Using Design of Experiment and Genetic Algorithm to Obtain the Optimum Gear Shifting Strategy for a Real Driving Cycles
p.497

Singularity Analysis of a New 2-DOF Parallel Tilter
p.504

Dynamic Analysis of a Ducted Fan UAV in Forward Flight
p.510

Control System Design and Modeling for Compensation Wheel
p.514

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 224The Application of Improved SVM in Mixed Circuit

The Application of Improved SVM in Mixed Circuit

Abstract:

In order to improve the speed and the rate of fault diagnosis in mixed circuit, this paper introduces a new fault diagnosis method. Through extracting fault features of current characteristics effectively and applying to Improved SVM, the ability of pattern recognition will be better than the traditional BP Neural Network and Single SVM, especially in small samples or non-linear cases. Meanwhile, this paper presents the lifting wavelet transform in order to obtain the feature information accurately. The accuracy of fault diagnosis can greatly enhance by discussing the Improved SVM combined with lifting wavelet transform in a specific monostable trigger. That points out a new direction for the fault diagnosis of mixed circuit.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volume 224)

Pages:

493-496

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.224.493

Citation:

Cite this paper

Online since:

November 2012

Authors:

Huai Long Wang, Qiang Pan, Hong Liu

Keywords:

Fault Diagnosis, Lifting Wavelet Transform, Mixed Circuit, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Zhang Qi-long, Shan Gan-lin. the fault diagnosis of analog circuit based on SVM [J]. Journal of Electricity and Control, 2010, 17（5）：66~69.

Google Scholar

[2] Vapnik V. The Nature of Statistical Learning Theory [M]. New York: Springer-Verlag, (1999).

Google Scholar

[3] Shen Yu-hao, Meng-Chen. the fault diagnosis of simulated circuit based on Improved Support Vector Machine [J]. Computer Simulation, 2010, 27（1）：346~350.

Google Scholar

[4] C W HSU. A Comparison of Methods for Multi-class Support Vector Machines[C]. IEEE Transactions on Neural Networks, 2002, 13(2): 415~425.

DOI: 10.1109/72.991427

Google Scholar

[5] Zhang Jin-ze. the application of Improved Support Vector Machine in the fault diagnosis[J]. Journal of Electricity and Control, 2006, 13（6）：97~100.

Google Scholar

[6] Yang-Qing, Tian-Feng. the real-time fault diagnosis based on lifting wavelet transform and recursive LSSVM[J]. Chinese Journal of Scientific Instrument, 2011. 32（3）：596~602.

Google Scholar

[7] Wang Feng-li, Zhao De-you. the extraction of fault features based on lifting wavelet transform and local wave[J]. Chinese Journal of Scientific Instrument, 2010, 31（4）：789~793.

Google Scholar