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.

Compressive sensing and sparse decomposition in precision machining process monitoring: From theory to applications

“…It did not need feature extraction and dimension reduction, as the fault is classified from its raw sparse space. Zhu et al [69] proposed an adaptive feature extraction scheme via K-SVD algorithm. Both global and local frequency features were fused by evidence theory, and the fault detection could be accomplished by the sparse representation without any additional classification step.…”

Research on fault diagnosis of hydraulic pump using convolutional neural network

“…Deep learning mainly contains three models: stacked autoencoders (SAE), deep belief network (DBN) and CNN. The vibration signal of hydraulic pump is period, so its features are of strong translation, which makes DBN and SAE cannot directly process the vibration signal [13,14]. Among them, CNN is shift invariant to local features and its unique weight sharing mechanism suits the structure of image and sound signal.…”

Feature Mapping Techniques for Improving the Performance of Fault Diagnosis of Synchronous Generator

“…Zhu et al proposed an automatic and adaptive feature extraction technique via K-SVD. Faults are diagnosed using the reconstruction error of the sparse representation (Zhu et al, 2014). Further, fusion sparse coding technique was proposed to extract impulse components from the vibration signals effectively (Deng, Jing, & Zhou, 2014).…”