Research on fault diagnosis of underwater vehicle based on kernel principal component analysis

Hailian Du; Shiyuan Hao; Wenxia Du; Tao Xin

doi:10.1117/12.2619365

29 November 2021 Research on fault diagnosis of underwater vehicle based on kernel principal component analysis

Hailian Du, Shiyuan Hao, Wenxia Du, Tao Xin

Proceedings Volume 12080, 4th International Symposium on Power Electronics and Control Engineering (ISPECE 2021); 120803H (2021) https://doi.org/10.1117/12.2619365
Event: 4th International Symposium on Power Electronics and Control Engineering (ISPECE 2021), 2021, Nanchang, China

Abstract

The working environment of underwater vehicle is very bad, so it is necessary to diagnose its fault effectively in time. Underwater vehicle system has the characteristics of nonlinear and time delay, it is difficult to establish accurate mathematical model. On the basis of the sensor data, such as velocity of underwater vehicle,propeller speed,the motor temperature,the motor current ,the voltage and current of the master battery and Power cell, a fault diagnosis method for underwater vehicle based on Kernel Principal Component Analysis（KPCA）is proposed. Linearly indivisible data in the original low-dimensional space are mapped to high-dimensional space by the radial basis (Gaussian) kernel function. Simulation results show that the fault variables can be identified and separated more accurately and quickly by KPCA. Compared with traditional principal component analysis, KPCA has more advantages in fault diagnosis of underwater vehicle system.

Citation Download Citation

Hailian Du, Shiyuan Hao, Wenxia Du, and Tao Xin "Research on fault diagnosis of underwater vehicle based on kernel principal component analysis", Proc. SPIE 12080, 4th International Symposium on Power Electronics and Control Engineering (ISPECE 2021), 120803H (29 November 2021); https://doi.org/10.1117/12.2619365

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available