Interpretable Spectra PCA for Condition Monitoring of Rotating Machinery: Theoretical and Experimental Investigations

Condition monitoring (CM) of rotating machinery is crucial for condition-based maintenance (CBM), ensuring safety and timely fault detection. Principal component analysis (PCA), an unsupervised learning algorithm for data dimensionality reduction, is widely employed for feature extraction in CM. In contrast to typical applications where PCA serves as a data preprocessing tool, this article proposes a novel approach that links principal components (PCs) obtained through PCA dimensionality reduction of degraded data spectra with a data fusion level health indicator (HI). The approach elucidates the physical significance and changing patterns of these PCs in the frequency domain. Notably, the second PC-based Fourier spectrum (PCBFS-2) effectively discriminates between normal and fault frequencies, enabling automated fault feature recognition. The effectiveness of this method in CM and fault feature recognition is validated through simulations and experiments. Importantly, this approach is interpretable, offering a new perspective for combining data-driven modeling with machine learning techniques.