文档介绍：Acoustic Diagnosis for Blower with Wavelet Transform and
works
Manabu Kotani*, Yasuo Ueda*, Haruya Matsumoto** and Toshihide Kanagawa***
*Faculty of Engineering, Kobe University
1-1 Rokkodai, Nada, Kobe 657, Japan , ko t ******@in. kobe-u .ac .j p
**Osaka Institute of Technology, 5-16-1 Omiya, Asahi, Osaka 535, Japan
***ProductionTechnology Center, Osaka Gas Co., Ltd.
1-1-16 Hokko, Konohana, Osaka 554, Japan, ******@
ABSTRACT
In this paper, we describe the acoustic diagnosis technique for the blower with the wavelet
transform and the work. It is important for this diagnosis to detect the surging phe-
nomena which lead to the destruction of the blower. Since the surging sound is non-stationary
signal, the wavelet transform is more suitable for the pre-processing method than FFT transform.
The dyadic wavelet transform is used as the pre-processing method. The multi-layered neural
network is used as the discrimination method. The results show that the work with
the wavelet transform can detect the surging sound in perfect.
1. Introduction the pattern recognition are reported recently [4][5].
Arai et al. [4] have studied the application of neu-
Vibration and acoustic are usually used as machine works to the diagnosis pressor’s valve.
condition diagnostic techniques. The vibration di- The applied model is multi-layer