Vibration-based Health Monitoring of a Wind Turbine Blade: A Machine Learning Approach
1گروه طراحی کاربردی، دانشکده مهندسی مکانیک، دانشکده فنی دانشگاه تهران
2گروه طراحی کاربردی، دانشکده مهندسی
3دانشکده مهندسی مکانیک، دانشکده فنی دانشگاه تهران
Development of structural health monitoring algorithms for wind turbines is an emerging need because the wind farm facilities are aging. In the current article, an algorithm is devel-oped for autonomous health monitoring of a wind turbine blade, which is one of the most expensive parts of the turbine, based on acceleration measurements taken from several points on the blade. A close to reality finite element model of the blade is used for data ac-quisition. Advanced algorithms of system identification are used for extracting damage sen-sitive features. Moreover, a one-class kernel support vector machine (SVM) is trained to find the data associated with a damaged state of the structure. Finally, success of the procedure in detecting the existence and location of damage is depicted.
Structural health monitoring؛ Wind Turbine Blade؛ Finite Element Modelling؛ Feature Extrac-tion؛ system identification؛ One-Class Kernel SVM