Identification defect character of MMM signals based on wavelet singular entropy and RBFNN

Lan Zhang; Yongrui Zhao; Chong Tian

doi:10.1117/12.886053

31 December 2010 Identification defect character of MMM signals based on wavelet singular entropy and RBFNN

Lan Zhang, Yongrui Zhao, Chong Tian

Proceedings Volume 7544, Sixth International Symposium on Precision Engineering Measurements and Instrumentation; 75443G (2010) https://doi.org/10.1117/12.886053
Event: Sixth International Symposium on Precision Engineering Measurements and Instrumentation, 2010, Hangzhou, China

Abstract

Metal magnetic memory is a novel NDT method that can be used to detect residual stress distribution of ferromagnetic components.Wavelet decomposition and entropy theory are used and wavelet singular entropy is introduced to extract characteristic from abnormal signals of defect. Furthermore, RBF neural network is utilized to identify defect character. Experimental results showed that, compared to the traditional gradient value, the proposed new method can be used to effectively reflect defect character and it is immune to the effect of noises.

Citation Download Citation

Lan Zhang, Yongrui Zhao, and Chong Tian "Identification defect character of MMM signals based on wavelet singular entropy and RBFNN", Proc. SPIE 7544, Sixth International Symposium on Precision Engineering Measurements and Instrumentation, 75443G (31 December 2010); https://doi.org/10.1117/12.886053

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