Energies, Vol. 19, Pages 202: Stress-Based Fatigue Diagnosis of Wind Turbine Blades Using Physics-Informed AI Reduced-Order Modeling
Energies doi: 10.3390/en19010202
Authors:
Jun-Yeop Lee
Minh-Chau Dinh
Seok-Ju Lee
This paper proposes an integrated, stress-based framework for fatigue diagnosis of wind turbine blades that is tailored to field deployments where detailed structural design information is unavailable. The approach combines a data-driven reduced-order model (ROM) for directional damage equivalent loads (DELs) with a physics-based Soderberg index and a one-class support vector machine (SVM) anomaly detector. The framework is implemented and evaluated using measurements from a 2 MW onshore turbine equipped with blade-root strain gauges and standard SCADA monitoring. Ten-minute operating windows are formed by synchronizing SCADA records with high-frequency strain data, converting strain to stress, and computing DELs via Rainflow counting for flapwise, edgewise, and torsional blade root directions. SCADA inputs are summarized by their 10 min statistics and augmented with yaw misalignment features; these are used to train LightGBM-based ROMs that map operating conditions to directional DELs. On an independent test set, the DEL-ROM achieves coefficients of determination of approximately 0.87, 0.99, and 0.99 for flapwise, edgewise, and torsional directions, respectively, with small absolute errors relative to the measured DELs. The Soderberg index is then used to define conservative Normal/Alert/Alarm classes based on representative material parameters, while a one-class SVM is trained on DEL- and stress-based fatigue features to learn the distribution of normal operation. A simple AND-normal/OR-abnormal rule combines the Soderberg class and SVM label into a hybrid diagnostic decision. Application to the field dataset shows that the proposed framework provides interpretable fatigue-safety margins and reliably highlights operating periods with elevated flapwise fatigue usage, demonstrating its suitability as a scalable building block for digital-twin-enabled condition monitoring and life-extension assessment of wind turbine blades.