Fault Diagnosis of AUV’s Thrusters Based on SVM

Article Preview

Abstract:

An autonomous underwater vehicle (AUV) should have the ability of adapting the complexity and unpredictability of the marine environment, which means that the technology of AUV’s fault diagnosis is very significant, especially the part of thrusters. In order to make it possible, one fault diagnosis strategy of AUV’s thrusters is proposed, which is based on the support vector machine (SVM). SVM has many unique advantages in solving small-sample, nonlinear and high dimensional problems. In this paper, different character signal is inputted SVM to train and test it. The simulation results show that the fault diagnosis of AUV’s thrusters based on offline SVM can classify the fault styles successfully, which proves its feasibility and effectiveness. This method offers a new way to solve the fault diagnosis of AUVs.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

858-862

Citation:

Online since:

March 2015

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2015 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

* - Corresponding Author

[1] LIU Qian and ZHU Da-qi: Journal of System Simulation Vol. 22 (2010), p.96.

Google Scholar

[2] WANG Yu-jia ZHANG Ming-jun and GUO Yong: Journal of Huazhong University of Science and Technology (Nature Science Edition) Vol. 37 (2009), p.135.

Google Scholar

[3] WANG Li-rong, GAN Yong, XU Yu-ru and WAN Lei: Journal of Harbin Engineering University Vol. 26 (2005), p.425.

Google Scholar

[4] E. Juhan, D. Richard, P. Miles: Automatic fault detection and execution monitoring for AUV missions, AUV 2010, Monterey, CA, United states.

Google Scholar

[5] V. N. Vapnik: Statistical Learning Theory (Publishing House of Electronics Industry, China, 2009).

Google Scholar

[6] WANG Wen-jian: Modeling and Application of Support Vector Machines (Science Press,China, 2014).

Google Scholar