Industrial gearbox fault diagnosis based on multi-scale convolutional neural networks and thermal imaging

Yongbo Li; Xiaoqiang Du; Xianzhi Wang; Shubin Si

doi:10.1016/j.isatra.2022.02.048

Industrial gearbox fault diagnosis based on multi-scale convolutional neural networks and thermal imaging

ISA Trans. 2022 Oct;129(Pt B):309-320. doi: 10.1016/j.isatra.2022.02.048. Epub 2022 Mar 10.

Authors

Yongbo Li¹, Xiaoqiang Du², Xianzhi Wang², Shubin Si²

Affiliations

¹ School of Aeronautics, Northwestern Polytechnical University, Xian, Shanxi, 710072, China. Electronic address: yongbo@nwpu.edu.cn.
² School of Mechanical Engineering, Polytechnical University, Xian, Shanxi, 710072, China.

PMID: 35305817
DOI: 10.1016/j.isatra.2022.02.048

Abstract

Infrared thermal technology plays a vital role in the health condition monitoring of gearbox. In the traditional infrared thermal technology-based methods, Gaussian pyramid is applied as the feature extraction approach, which has disadvantages of noise influence and information missing. Focus on such disadvantages, an improved multi-scale decomposition method combined with convolutional neural network is proposed to extract the fault features of the multi-scale infrared images in this paper. It can enlarge the data length at large scales, and thus reduce the fluctuations of feature values and reserve the fault information. The effectiveness of the proposed method is validated using the experiment infrared data of one industrial gearbox. Results demonstrate that our proposed method has the best performance comparing with five methods.

Keywords: Convolutional neural networks; Fault diagnosis; Gearbox; Multi-scale; Thermal imaging.