Spur gears are one of the widely used gears in a gearbox assembly. They often require lubrication and replacement of pinion and gears as prone to damage in high speed shafts with heavy loads and adverse working conditions. These creates spalling and breakage of gear tooth due to material fatigue from excessive loads and also forms pitting corrosion due to reduced lubrication and higher input shaft speeds. Vibrational analysis of these rolling elements is necessary for monitoring the health of gears periodically. These graphs provide a pattern waveform over time to study the characteristic high frequency impact noise signal peaks due to increased vibrations from faulty sections. This paper depicts about the implementation of convolutional neural networks to analyze the vibrational graphs obtained at different rotating speed of shafts for various gear ratios to plot the high frequency impact noise and train the neural networks to identify the peaks and classify among the faulty and healthy spur gears and pinions for a better way to reduce time in estimating the remaining average working life of gears and perform adequate maintenance of components.
