Abstract
In this paper, a graph-based semi-supervised learning (GSSL) algorithm, greedy-gradient max cut (GGMC), based fault diagnosis method for direct online induction motors is proposed. Two identical 0.25 HP three-phase squirrel-cage induction motors under healthy, single- and multi-fault conditions were tested in the lab. Three-phase stator currents and three-dimensional vibration signals of the two motors were recorded simultaneously in each test, and used as datasets in this study. Features for machine learning are extracted from experimental stator currents and vibration data by the discrete wavelet transform (DWT). To validate the effectiveness of the proposed GGMC-based fault diagnosis method, its classification accuracy using binary classification and multiclass classification for faults of the two motors are compared with other two GSSL algorithms, local and global consistency (LGC) and Gaussian field and harmonic function (GFHF). In this study, the performance of stator currents and vibration as a monitoring signal is evaluated, it is found that stator currents perform much better than vibration signals for multiclass classification, while they both perform well for binary classification.
Highlights
Induction motors are most widely used electric machines in various industrial applications
To fill in this research gap, for the very first time, we propose a greedy-gradient max cut (GGMC)-based direct online induction motors fault diagnosis method in this paper
Experimental stator currents and vibration data recorded in the lab for two identical 0.25 HP induction motors under various healthy and faulty states and motor loadings are used as datasets for GGMC
Summary
Induction motors are most widely used electric machines in various industrial applications. The main contributions of this paper include: 1) propose an effective GGMC-based direct online induction motors fault diagnosis approach using experimental stator current or vibration signals; 2) consider single- and multi-electrical and mechanical faults in the fault profile, and conduct both binary classification and multiclass classification to classify faults of the motors using the proposed approach to evaluate its performance; 3) compare the performance of the proposed GGMC-based approach with other GSSL algorithms, LGC and GFHF; and 4) evaluate the effectiveness of experimental stator currents or vibration as a monitoring signal for the proposed fault diagnosis approach.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
