Fault Diagnosis in Rolling Element Bearings Using Bi-Spectrum-Based EMD and Simplified Fuzzy ARTMAP

Rolling Element Bearings (REBs) are critical components in rotating machinery, and their failure can cause significant operational and financial losses. This study proposes a novel fault diagnosis method combining Bi-Spectrum-Based Empirical Mode Decomposition (BSEMD) and Simplified Fuzzy ARTMAP (SFAM) for accurate and reliable fault detection in REBs. BSEMD uses Empirical Mode Decomposition (EMD) to decompose non-stationary vibration signals into Intrinsic Mode Functions (IMFs), followed by bi-spectrum analysis to extract fault-related features. The bi-spectrum, a higher-order statistical tool, identifies phase coupling and is robust to Gaussian noise, making it ideal for noisy environments. The extracted features are classified using SFAM, known for its incremental learning and high accuracy. Experiments on synthetic and real-world datasets demonstrate the method’s effectiveness in diagnosing bearing faults under various conditions, outperforming traditional approaches in accuracy, noise robustness, and computational efficiency. This makes it a promising tool for condition monitoring and predictive maintenance.