DocumentCode :
393691
Title :
Impact sound analysis by answer-in-weights neural network for damping ratio estimation
Author :
Takahashi, Yoshikazu ; Ogawa, Takehiko ; Kanada, Hajime ; Mori, Kiyomi
Author_Institution :
Dept. of Electron. & Comput. Syst., Takushoku Univ., Tokyo, Japan
Volume :
4
fYear :
2002
fDate :
5-7 Aug. 2002
Firstpage :
2301
Abstract :
The method has been studied for evaluating the damping ratio of composite material by impact sound. So far, the method was examined for obtaining the damping ratio from the change of the vibration. However, it was difficult to estimate accurately by this method, because of the attenuation tendency might be uncertain. In this paper, we propose to use a neural network for impact sound analysis. We examined this neural network method through the computer simulation using the data of actual impact sound. As the result, we confirmed the effectiveness of using the neural network for estimating the damping ratio.
Keywords :
acoustic emission testing; composite materials; damping; impact testing; neural nets; physics computing; answer-in-weights neural network; attenuation tendency; composite material; computer simulation; damping ratio estimation; impact sound analysis; neural network; vibration change; Chaos; Composite materials; Computer networks; Damping; Economic indicators; Magnetooptic recording; Neural networks; Optical wavelength conversion; Steel; Vibration measurement;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
SICE 2002. Proceedings of the 41st SICE Annual Conference
Print_ISBN :
0-7803-7631-5
Type :
conf
DOI :
10.1109/SICE.2002.1195762
Filename :
1195762
Link To Document :
بازگشت