期刊名称：International Journal of Multimedia and Ubiquitous Engineering
印刷版ISSN：1975-0080
出版年度：2015
卷号：10
期号：1
页码：109-118
DOI：10.14257/ijmue.2015.10.1.10
出版社：SERSC
摘要：Acoustic Emission method of nondestructive check is based on exertion wave radiation and their registration during fast local material structure reorganization. It is used as a means of analysis of materials, constructions, productions control and diagnosis during operating time. In the article, it is applied to structural health monitoring of Wind Turbines. Acoustic emission testing is based condition monitoring system uses data already collected at the wind turbine controller. It is an effective way to monitor wind turbines for early warning of failures and performance issues. We used a number of measurements to develop anomaly detection algorithms and investigated classification techniques using clustering algorithms and principal components analysis for capturing fault signatures. When registering signal amplitude it is required to consider its frequency distribution connecting each amplitude rate with the corresponding vibration rate. The correlation and signal to noise ratio were evaluated by the algorithm based on frequency spectrum. Classical method of frequency distortion influence exclusion consists of FRF calculation with subsequent adjustment of received signals spectral characteristics.
