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


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.



Edited by:

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




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





[1] Z. Peng, T. B. Kirk, Wear partial classification in a fuzzy grey system, Wear, 1999, 225-229: 1238-1247.

DOI: https://doi.org/10.1016/s0043-1648(98)00400-1

[2] B. J. Rodance, S. Raadnui, The morphological attributes of wear particle � their role in identifying wear mechanisms, Wear, 1994, 175: 115-121.

DOI: https://doi.org/10.1016/0043-1648(94)90174-0

[3] Roylance B. J and S. Raadnui, The Morphological Attributes of Wear Particle-Their Role in Identifying Wear echanisms, Wear, 1994, 175: 115-121.

DOI: https://doi.org/10.1016/0043-1648(94)90174-0

[4] Luerkens D. W, Beddow J. K, Vetter A. F, Morphological Fourier descriptors, Powder Technology, 1982, 31: 209-215.

DOI: https://doi.org/10.1016/0032-5910(82)89006-2

[5] KANG Jianli, CHEN Gang, MAO Jinming, Novel Method of Wear Debris Recognition Based on Gabor Wavelet Texture Feature, Laser and Infrared, Vol. 35, No. 3, March, (2005).

[6] Lu Yonggeng, Zhao Chunsheng, Ge Shiron, Study on the Calculation of Particle Image Fractal Parameter, China Mechanical Engineering, Vol. 15, No. 7, April (2004).

[7] JIA Yonghong, Digital Images Processing, Wuhan University Press, September (2003).

[8] YANG wanhai, multi-sensor data-fusion and application, Xian Dian University Press, (2004).

[9] KANG jianli, LU yaping, ZHOU yinsheng, Wear Particle Recognition with Improved BP Algorithm, Lubrication Engineering, No. 2, Mar. (2005).

[10] Kolmgorov's, On the representation of continuous Functions of many variables by superposition of continuous functions of one variable and condition, Dok1, Akad. Nauk, USSR, 114, pp.953-956, (1957).

[11] HUANG deshuang, Patten Recognition System Based on Neural Network, Electronic Industry, (1996).

[12] Daniel P. Anderson, "Wear particle Atlas, � Lakehurst, New Jersey, 28, June (1982).

Fetching data from Crossref.
This may take some time to load.