A hybrid convolutional neural network for intelligent wear particle classification

Yeping Peng, Junhao Cai, Tonghai Wu, Guangzhong Cao, Ngaiming Kwok, Shengxi Zhou, Zhongxiao Peng

Research output: Contribution to journalArticlepeer-review

Abstract

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.
Original languageEnglish
Pages (from-to)166-173
Number of pages8
JournalTribology International
Volume138
DOIs
Publication statusPublished - 2019

Fingerprint

Dive into the research topics of 'A hybrid convolutional neural network for intelligent wear particle classification'. Together they form a unique fingerprint.

Cite this