A method to locate loose metal parts with FFT and support vector machine

Yuanfeng He; Yanlong Cao; Jiangxin Yang

doi:10.1117/12.819741

31 December 2008 A method to locate loose metal parts with FFT and support vector machine

Yuanfeng He, Yanlong Cao, Jiangxin Yang

Proceedings Volume 7130, Fourth International Symposium on Precision Mechanical Measurements; 713051 (2008) https://doi.org/10.1117/12.819741
Event: Fourth International Symposium on Precision Mechanical Measurements, 2008, Anhui, China

Abstract

The position of loose part can be located by analyzing the impact signal generated by the steel plate and the metal part which strikes the plate or falls to it from a certain height. A new method utilizing Fast Fourier transform (FFT) and Support Vector Machine (SVM) is proposed in this paper to locate positions of loose parts. FFT changes signals into frequency domain from time domain. While trained by the eigenvalues (i.e. Feature values) of impact signals from simulant device, SVM can distinguish locations of loose parts in an acceptable bias. Experiments proved that the above mentioned method is feasible.

Citation Download Citation

Yuanfeng He, Yanlong Cao, and Jiangxin Yang "A method to locate loose metal parts with FFT and support vector machine", Proc. SPIE 7130, Fourth International Symposium on Precision Mechanical Measurements, 713051 (31 December 2008); https://doi.org/10.1117/12.819741

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