Recent Advances in Vibration Signal Processing Techniques for Gear Fault Detection-A Review

Abstract

This paper provides a review of the literature, progress and changes over the years on fault detection of gears using vibration signal processing techniques. Analysis of vibration signals generated by gear in mesh has shown its usefulness in industrial gearbox condition monitoring. Vibration measurement provides a very efficient way of monitoring the dynamic conditions of a machine such as gearbox. Various vibration analysis methods have been proposed and applied to gear fault detection. Most of the traditional signal analysis techniques are based on the stationary assumption. Such techniques can only provide analyses in terms of the statistical average in the time or frequency domain, but can not reveal the local features in both time and frequency domains simultaneously. Frequency/quefrency analysis, time/statistical analysis, time-frequency analysis and cyclostationarity analysis are reviewed in regard for stationary and nonstationary operation. The use of vibration signal processing detection techniques is classified and discussed. The capability of each technique, fundamental principles, advantages and disadvantages and practical application for gear faults detection have been examined by literature review.

Integration of Nonlinear Dynamics and Machine learning for Diagnostics of a Single-Stage Gear Box

“…Vibration and acoustic techniques are a primary emphasis in current fault diagnostics of gears because of the valuable insights they offer about the state of rotating equipment (Bajric, Zuber, & Isic, 2013). Due to the extremely nonlinear nature of faults and the intricate nonstationary dynamics, diagnosing gear problems is still a difficult task (Jardine, Lin, & Banjevic, 2006).…”

Fault Diagnosis for Reducers Based on a Digital Twin

“…Reducers are commonly used in various transmission systems, such as robots [ 1 , 2 , 3 ], cars, rolling mills, and so on. The condition monitoring and fault diagnosis of gearboxes has been attracting considerable attention [ 4 , 5 , 6 ]. The existing fault diagnosis methods mainly rely on machine learning algorithms [ 7 ] and deep learning models [ 8 , 9 , 10 , 11 ], where Convolutional Neural Networks (CNNs) [ 12 , 13 ], Long Short-term Memory (LSTM) Networks [ 14 ], and Autoencoders [ 15 ] have shown good performance in terms of feature extraction, although with application restrictions in some fields.…”

Gear Fault Diagnostics Using Extended Phase Space Topology

“…nonlinearity of faults in gears which makes abnormality diagnostics difficult (Randall, 1982;Chad, 1998;Jardine, Lin, & Banjevic, 2006;Serridge, 1990). Vibration and acoustic methods contain valuable information about the condition of the rotating machines such as gears, and therefore, they are the most widely used for fault diagnostics of gears (Bajric, Zuber, & Isic, 2013;Hussain & A.Gabbar, 2011; W. Q. Wang, Ismail, & Farid Golnaraghi, 2001;Dalpiaz, Rivola, & Rubini, 2000).…”