Diagnosis of Faults in Electro-Mechanical Devices from Vibration Measurements

With new enhancements and developments, mechanical engineering got into a new stage of enhancement where the combination of artificial intelligence technology. We frequently see mechanical and electronic engineering's perception of artificial intelligence. This can utilize computers’ sophisticated data processing capabilities, solving a variety of complicated problems while also increasing the amount of automation in mechanical and electronic engineering. The main issue with traditional mechanical fault detection is that, because technical circumstances are so difficult and complex, only minor errors can be recognized by machines. As a result, the usage procedure is inconvenient. This research work combines some machine learning algorithms to analyze the rate of diagnosis of faults in Electro-Mechanical devices from vibration measurements. The main aim of this study is to employ ML techniques for the classification of mechanical failure analysis. The obtained dataset will be used to analyze the ML techniques. According to the results obtained, the Decision Tree algorithm has achieved the highest rate of 87.4%.