Automatic Detection and Intensity Classification of Pitch Misalignment of Wind Turbine Blades: a Learning-based Approach

Abstract

In recent years, monitoring wind turbine operations, especially in offshore and remote installations, has become crucial. System failures, challenging assessments, and costly maintenance operations are notable concerns. Blade pitch misalignment poses one of the most significant threats, being a leading cause of downtime and energy production reduction. Traditional assessments through frequent inspections are resource-intensive and time-consuming; still they are frequently required as turbines lack routine implementation of effective automatic detection systems. To address this, our study introduces a novel machine learning-based method for autonomous pitch misalignment recognition, which relies on signals measured by a limited set of sensors, already integrated into modern wind turbines. From those signals, frequency domain features derived by harmonic analysis are extracted, ensuring robust detection also in turbulent wind conditions. This innovative method lays the groundwork for early and precise wind turbine diagnostics, promoting the shift from time-based to condition-based inspections. This transition aims to reduce maintenance costs and unexpected downtime, ultimately enhancing energy production.