Analysing the Eccentricity of the Air Gap in an Induction Motor Using a Decision Tree Algorithm

Abstract

This present study presents an air Gap Eccentricity Analysis in Induction Motor using Decision Tree Algorithm. In this study, vibration monitoring system applied to bearing fault analysis and experimental result shows that vibration and current is spectra of and rotating machine like induction motor for different bearing faults. The industry is very similar to the induction motor. Due to its simple control quality, it is also widely used. The eccentricity of three-phase induction motors is mismatched. We experienced speed pulsation, vibration-induced acoustic noise, and friction issues between the stator and rotor as a result of the eccentricity issue. The proposed methodology is useful on Real- time data and achieves 90% true Value. The installation of various Sensors in order to maintain the Good condition of the induction motor is very costly. Decision tree algorithm identifier detects 90% accurate value of air gap which is a gap between rotor and stator, in addition, the LabVIEW tools and power analyzer library is used for searching the maximum accurate parameter for achieving the result.