Advanced fault diagnosis in industrial robots through hierarchical hyper-laplacian priors and singular spectrum analysis

Abstract

In industrial cases, robustness of the robots is mandatory and thus the development of fault diagnosis systems is essential. This study introduces a novel fault diagnosis method that merges two elements: Two methods shared here are the hierarchical hyper-Laplacian prior (HHLP) and singular spectrum analysis (SSA). The SSA technique decomposes the encoder signals into three components; residual, periodic oscillation and trend. In addition, the HHLP algorithm can identify harmonic interference, periodical impulses, and noise, with maximal posterior probabilities compared to the other algorithms. Compared to traditional Laplacian prior models, this approach provides higher accuracy, which verify the HHLP algorithm can effectively extract fault feature. Real-world applications and some computational studies provide additional light on the practicability of SSA-HHLP method. The research also compares the results with kurtosis-based weighted sparse prototypes, spectral kurtosis, and minimax concave regularization, and indicates that the proposed SSA-HHLP method outperforms other methods in both low outlier and high outlier contamination.