Abstract
This article aims to introduce a non-conventional method for extracting, decoding and classifying the information regarding defects that could appear and develop in components of rotating machinery (e.g. in bearings). Such an information is encoded by vibrations and regards the type and the severity degree of possible defects. Though vibration is not as complex as speech or seismic signals, decoding this information is not easy. Unlike many Signal Processing applications, where the noise is attenuated or compensated, one focuses here on the noisy component of vibrations, where defects are encoded. The classification of defects is based upon some statistical and fuzzy concepts described within the article. A succinct comparison between Fuzzy-Statistical and Envelope Analysis Methods is performed as well.
Get full access to this article
View all access options for this article.