Adaptive neuro-fuzzy inference system for bearing fault detection in induction motors using temperature, current, vibration data

Abstract

In this study the features for bearing fault diagnosis is investigated based on the analysis of temperature, vibration and current measurements of a 3 phase, 4 poles, 5 HP induction motors which are chemically, thermally and electrically aged by artificial aging methods. Then three adaptive neuro-fuzzy inference systems which takes the temperature, current and vibration measurements as inputs and the condition of the motors as output are established, and the performances of these networks are compared.