Share Email Print

Proceedings Paper

Intelligent online quality control using discrete wavelet analysis features and likelihood classification
Author(s): S. Goumas; M. Zervakis; A. Pouliezos; G. S. Stavrakakis; Enrico Primo Tomasini; Nicola Paone; Lorenzo Scalise
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper presents a method for extracting features in the wavelet domain of vibration velocity transient signals of washing machines, that are then used for classification of the state (acceptable-faulty) of the product. The Discrete Wavelet Transform in conjunction with Statistical Digital Signal Processing techniques are used for feature extraction. The performance of this feature set is compared to features obtained through standard Fourier analysis of the stationary part of the signal. Minimum distance Bayes classifiers are used for classification purposes. Measurements from a variety of defective/non-defective washing machines taken in the laboratory as well as from the production line are used to illustrate the applicability of the proposed method.

Paper Details

Date Published: 22 May 2000
PDF: 12 pages
Proc. SPIE 4072, Fourth International Conference on Vibration Measurements by Laser Techniques: Advances and Applications, (22 May 2000); doi: 10.1117/12.386766
Show Author Affiliations
S. Goumas, Technical Univ. of Crete (Greece)
M. Zervakis, Technical Univ. of Crete (Greece)
A. Pouliezos, Technical Univ. of Crete (Greece)
G. S. Stavrakakis, Technical Univ. of Crete (Greece)
Enrico Primo Tomasini, Univ. degli Studi di Ancona (Italy)
Nicola Paone, Univ. degli Studi di Ancona (Italy)
Lorenzo Scalise, Univ. degli Studi di Ancona (Italy)

Published in SPIE Proceedings Vol. 4072:
Fourth International Conference on Vibration Measurements by Laser Techniques: Advances and Applications
Enrico Primo Tomasini, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?