HHLP-SSA: Enhanced Fault Diagnosis in Industrial Robots Using Hierarchical Hyper-Laplacian Prior and Singular Spectrum Analysis

Abstract

In industrial applications, the reliability of robots is paramount, necessitating efficient fault diagnosis systems. This research presents a novel fault diagnosis approach combining hierarchical hyper-Laplacian prior (HHLP) with singular spectrum analysis (SSA) for analyzing rotary encoder signals in industrial robots. The SSA method decomposes the encoder signals into residual, periodic oscillations, and trend components. The HHLP algorithm identifies harmonic interference, periodic impulse disturbances, and noise, optimized to maximize posterior probability for accurate detection. The proposed method demonstrates superior performance compared to traditional Laplacian prior models, emphasizing the effectiveness of HHLP in fault feature extraction. Experimental applications validate the SSAHHLP method’s efficacy. The study compares the results with spectral kurtosis and minimax concave regularization, confirming the SSA-HHLP method’s robustness and accuracy.