A technique for detecting materials characteristics using mechanical impacts and a multilayer neural network
Por:
Molino-Minero-Re E., López-Garcia M., Mánuel-Lázaro A., Carlosena A., Shariat-Panahi S.
Publicada:
1 ene 2008
Categoría:
Electrical and Electronic Engineering
Resumen:
In this paper, we propose a method for detecting the characteristics of different materials that have similar properties, by classifying their responses when impacted with small hard spheres. First, a signal conditioning and data compression stage are described. Then a multilayer neural network is used to detect the individual patterns of the samples, and classify the signal. The results of this study indicate that it is possible to identify different materials propertied when the signals are correctly acquired and preprocessed, and the network is adequately trained. ©2008 IEEE.
Filiaciones:
Molino-Minero-Re E.:
Polytechnic University of Catalonia, 08800 Vilanova i la Geltrú (Catalonia), Spain
López-Garcia M.:
Polytechnic University of Catalonia, 08800 Vilanova i la Geltrú (Catalonia), Spain
Mánuel-Lázaro A.:
Polytechnic University of Catalonia, 08800 Vilanova i la Geltrú (Catalonia), Spain
Carlosena A.:
Public University of Navarre, Campus de Arrosadía, 31006 Pamplona (Navarra), Spain
Shariat-Panahi S.:
Polytechnic University of Catalonia, 08800 Vilanova i la Geltrú (Catalonia), Spain
|