An Effective Induction Motor Fault Diagnosis Approach Using Graph-Based Semi-Supervised Learning

Abstract

Machine learning has paved its way into induction motors fault diagnosis area, where supervised learning and deep learning have been employed. However, both learning methods require a large amount of labeled data to train the model, which pose significant challenges in real life applications. To overcome this issue, in this paper, the graph-based semi-supervised learning (GSSL) is adopted to develop a fault diagnosis method for direct online induction motors due to GSSL's superior feature that only a small amount of labeled data is needed in training datasets. To evaluate its suitability, the greedy-gradient max cut (GGMC) algorithm in the GSSL family is chosen in this study, and an effective fault diagnosis approach is developed using experimental stator currents recorded in the lab for two induction motors. The developed approach can conduct binary and multiclass classifications for faults on direct online induction motors. As a critical step, curve fitting equations are developed to calculate features for untested motor loadings by using experimental data for tested motor loadings, which enables the proposed approach to remain effective under all potential motor loading conditions.