?
Learning to hear broken motors: Signature-guided data augmentation for induction motor diagnostics
The application of machine learning algorithms in the intelligent diagnosis of three-phase engine has the potential to significantly enhance diagnostic performance and accuracy. Traditional methods largely rely on signature analysis, which, despite being a standard practice, can benefit from the integration of advanced machine learning techniques. In our study, we innovate by combining machine learning algorithms with a novel unsupervised anomaly generation methodology that takes into account the engine physics model. We propose Signature-Guided Data Augmentation, an unsupervised framework that synthesizes physically plausible faults directly in the frequency domain of healthy current signals. Guided by Motor Current Signature Analysis, our approach creates diverse and realistic anomalies without resorting to computationally intensive simulations. The proposed method is a novel training and data-augmentation framework. Our approach achieved 99% accuracy and 0.97 macro-F score for binary fault detection and 86% accuracy and 0.88 macro-F score for multiclass classification across varying loads and phases. This hybrid approach leverages the strengths of both supervised machine learning and unsupervised signature analysis, achieving superior diagnostic accuracy and reliability along with wide industrial application. The findings highlight the potential of our approach to contribute significantly to the field of engine diagnostics, offering a robust and efficient solution for real-world applications.