A Novel Method and Its Field Tests for Monitoring and Diagnosing Blade Health for Wind Turbines

Abstract

A new diagnostic method is proposed to efficiently monitor the structural health and detect damages in wind turbine blades. A high-resolution real-time blade condition monitoring system that considers the harsh turbine operating environment and uses optical sensors and a wireless network is presented. A hybrid algorithm, which merges probabilistic analysis, design loads, and real-time load estimates, is introduced to enhance operational safety and reliability. Moreover, the alarm limits are updated every 10 min through a learning algorithm to further improve reliability. The proposed algorithm was implemented in a blade monitoring system. The effectiveness of the proposed algorithm was demonstrated for a 3-MW wind turbine in the Yeongheung wind farm.