Fusion Identification for Wear Particles Based on Dempster-Shafter Evidential Reasoning and Back-Propagation Neural Network

Abstract:

Article Preview

Based on Back-Propagation neural network and Dempster-Shafter evidential reasoning, a fuse classification method for identifying wear particles is putted forward. Firstly, digital wear debris images are dealt with images processing methods. Then from the wear particles images, wear particles characters can be obtained by means of statistical analysis and Fourier analysis. Later, an integrated neural network made of two sub-neural networks based on statistical analysis and Fourier analysis is established, and some typical wear particles features as training samples are provided. After each sub-BP neural network has been trained successfully, the preliminary diagnosis of each sub-neural network is achieved. By using of the dempster-shafter evidential reasoning, the finial fusion diagnosis results are obtained. In the end, a practical example is given to show that the fusion results are more accurate than those with a single method only.

Info:

Periodical:

Edited by:

Dongming Guo, Tsunemoto Kuriyagawa, Jun Wang and Jun’ichi Tamaki

Pages:

341-346

DOI:

10.4028/www.scientific.net/KEM.329.341

Citation:

Y.B. Cao and X.P. Xie, "Fusion Identification for Wear Particles Based on Dempster-Shafter Evidential Reasoning and Back-Propagation Neural Network", Key Engineering Materials, Vol. 329, pp. 341-346, 2007

Online since:

January 2007

Authors:

Export:

Price:

$35.00

In order to see related information, you need to Login.

In order to see related information, you need to Login.