Sparse representation based on adaptive multiscale features for robust machinery fault diagnosis

Abstract

In machinery fault diagnosis, it is fairly time consuming and expertise-demanded for manually selecting features, so it is profitable to automate this process for rapid and robust fault diagnosis. An automatic and adaptive feature extraction scheme via K-SVD algorithm was proposed in this paper, and without additional classifier, the fault detection was directly implemented by sparse representation. Higher animals apply the integration of global and local information to identify unknown objects for better recognition. Enlightened by this mechanism, the judgments by global and local frequency features were fused for better diagnosis by evidence theory. This fusion not only improved the successful rate, but also presented the reliability of diagnosis, which provided worthwhile recommendations and was essential to final decision. Verified in bearing fault diagnosis, the results demonstrated that the proposed scheme improved accuracy, robustness and efficiency, and this scheme had potential value for engineering application.