A Hybrid Hierarchical Health Monitoring Solution for Autonomous Detection, Localization and Quantification of Damage Sources in Composite Wind Turbine Blades

Glass fiber reinforced polymer (GFRP) composites are widely used in windturbine blades due to their excellent strength-to-weight ratio and construction flexibilities.However, wind turbines often operate in harsh environmental conditionsthat can lead to various types of damage, including abrasion, corrosion, fractures,cracks, and delamination. Early detection through structural health monitoring(SHM) is essential for maintaining the efficient and reliable operation ofwind turbines, minimizing downtime and maintenance costs, and optimizing energyoutput. This paper presents a hybrid machine-learning model that leveragesacoustic emission (AE) data to identify and classify different types of damage inlaboratory-based composite wind turbine blades. The AE data is collected using asingle sensor, with damage simulated by artificial AE sources (Pencil lead break)and low-velocity impacts. Additionally, simulated abrasion on the blade’s leading edge resembles environmental wear. A deep learning-based hybrid hierarchicalframework is developed for damage classification, localization, and site assessment.This hybrid model offers superior accuracy and robustness compared to theconventional Convolutional Neural Network (CNN) models. The developed SHMsolution provides a more effective and practical solution for in-service monitoringof wind turbine blades, particularly in wind farm settings, with the potential forfuture wireless sensor applications.