Fault Diagnosis of Drills using Artificial Neural Networks
Machine fault diagnosis recovers all the studies that aim to detect automatically faults or damages on machines
using the signals generated by these machines. This study aims to develop an automatic machine fault diagnosis system that
uses pattern recognition techniques such as artificial neural networks. The sounds emitted by the healthy and faulty drills are
obtained and analyzed. Unlike the conventional methods that focus on the time domain, we explore here the effectiveness of
the frequency domain components and demonstrate in the same time the ineffectiveness of the time domain analysis of the
sounds produced by drills. First, the power spectrum of the sounds are extracted as the features of the signals. Secondly, the
extracted power spectrum components are given to a neural network based classifier to perform the diagnosis. The results
show that the proposed method can be used for the sounds based automatic diagnosis system.
Index terms- Fault diagnosis, Machine learning, Artificial neural network, Sound processing.