Fuzzy-Based Statistical Feature Extraction for Detecting Broken Rotor Bars in Line-Fed and Inverter-Fed Induction Motors

Abstract

This paper presents the use of a fuzzy-based statistical feature extraction from the air gap disturbances for diagnosing broken rotor bars in large induction motors fed by line or an inverter. The method is based on the analysis of the magnetic flux density variation in a Hall Effect Sensor, installed between two stator slots of the motor. The proposed method combines a fuzzy inference system and a support vector machine technique for time-domain assessment of the magnetic flux density, in order to detect a single fault or multiple broken bars in the rotor. In this approach, it is possible to detect not only the existence of failures, but also its severity. Moreover, it is not necessary to estimate the slip of the motor, usually required by other methods and the damaged rotor detection was also evaluated for oscillating load conditions. Thus, the present approach can overcome some drawbacks of the traditional MCSA method, particularly in operational cases where false positive and false negative indications are more frequently. The efficiency of this approach has been proven using some computational simulation results and experimental tests to detect fully broken rotor bars in a 7.5 kW squirrel cage induction machine fed by line and an inverter.