Abstract
Currently gear fault diagnosis is mainly based on vibration signals with a few studies on acoustic signal analysis. However, vibration signal acquisition is limited by its contact measuring while traditional acoustic-based gear fault diagnosis relies heavily on prior knowledge of signal processing techniques and diagnostic expertise. In this paper, a novel deep learning-based gear fault diagnosis method is proposed based on sound signal analysis. By establishing an end-to-end convolutional neural network (CNN), the time and frequency domain signals can be fed into the model as raw signals without feature engineering. Moreover, multi-channel information from different microphones can also be fused by CNN channels without using an extra fusion algorithm. Our experiment results show that our method achieved much better performance on gear fault diagnosis compared with other traditional gear fault diagnosis methods involving feature engineering. A publicly available sound signal dataset for gear fault diagnosis is also released and can be downloaded as instructed in the conclusion section.
Highlights
As a necessary component of most mechanical equipment, gears are widely used in the system of engineering machinery, aerospace, and ship vehicles for its advantage of power transmission
Li et al [1] proposed a method of planetary gear fault diagnosis via feature extraction based on multi-central frequencies and vibration signal frequency spectrum
The near-field acoustic holography (NAH) technology was used to reconstruct sound files of different bearing conditions, grey-level gradient co-occurrence matrix (GLGCM) features were extracted from the acoustic images and support vector machines were used for rolling bearing fault diagnosis
Summary
As a necessary component of most mechanical equipment, gears are widely used in the system of engineering machinery, aerospace, and ship vehicles for its advantage of power transmission. The NAH technology was used to reconstruct sound files of different bearing conditions, GLGCM features were extracted from the acoustic images and support vector machines were used for rolling bearing fault diagnosis. These methods overcame the limitations of traditional single channel measurement-based ABD methods and solved the local diagnosis problem in ABD. Convolutional neural networks (CNN) are established to adaptively mine available fault characteristics by directly using time and frequency domain signals without other manually constructed features and automatically detect the fault modes of gears. (D-S) evidence evidence theory, theory, to fuse multi-channel acoustical signals
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
