Bearing fault diagnosis based on spectrum image sparse representation of vibration signal

Bearings are crucial for industrial production and susceptible to malfunction in rotating machines. Image analysis can give a comprehensive description of vibration signal, thus, it has achieved much more attention recently in fault diagnosis field. However, it brings lots of redundant information from a single spectrum image matrix behind rich fault information, and massive spectrum image samples lead to exacerbation of this situation, which readily results in the accuracy-dropping problem of multiple local defective bearings diagnosis. To solve this issue, a novel feature extraction method based on image sparse representation is proposed. Original spectrum images are acquired through fast Fourier transformation. Sparse coefficient that reveals the underlying structure of spectrum image based on raw signals is extracted as the feature by implementing the orthogonal matching pursuit and K-singular value decomposition algorithm strategically, and then two-dimensional principal component analysis is applied for further processing of these features. Finally, fault types are identified based on a minimum distance strategy. The experimental results are given to demonstrate the effectiveness of the proposed method.