TY - JOUR
T1 - A hybrid convolutional neural network for intelligent wear particle classification
AU - Peng, Yeping
AU - Cai, Junhao
AU - Wu, Tonghai
AU - Cao, Guangzhong
AU - Kwok, Ngaiming
AU - Zhou, Shengxi
AU - Peng, Zhongxiao
PY - 2019
Y1 - 2019
N2 - For the purpose of automatic wear debris classification, a hybrid convolution neural network (CNN) is used with transfer learning (TL) and support vector machine (SVM) to identify four types of wear debris including cutting, sphere, fatigue and severe sliding particles. Experimental results indicate that image features extracted from the CNN is more distinguishable than that acquired from the local binary pattern, the histogram of oriented gradients and the color-based methods. The classification accuracy and efficiency of the proposed hybrid CNN with TL and SVM is also higher than that of the CNN, the CNN with TL, and the CNN with SVM. This work provides an effective solution for automatic wear debris identification applicable for machine wear mechanism analysis.
AB - For the purpose of automatic wear debris classification, a hybrid convolution neural network (CNN) is used with transfer learning (TL) and support vector machine (SVM) to identify four types of wear debris including cutting, sphere, fatigue and severe sliding particles. Experimental results indicate that image features extracted from the CNN is more distinguishable than that acquired from the local binary pattern, the histogram of oriented gradients and the color-based methods. The classification accuracy and efficiency of the proposed hybrid CNN with TL and SVM is also higher than that of the CNN, the CNN with TL, and the CNN with SVM. This work provides an effective solution for automatic wear debris identification applicable for machine wear mechanism analysis.
UR - https://hdl.handle.net/1959.7/uws:63818
U2 - 10.1016/j.triboint.2019.05.029
DO - 10.1016/j.triboint.2019.05.029
M3 - Article
SN - 0301-679X
VL - 138
SP - 166
EP - 173
JO - Tribology International
JF - Tribology International
ER -