Data-driven farm-wide fatigue estimation on jacket foundation OWTs for multiple SHM setups

The sustained development over the past decades of the offshore wind industry has seen older wind farms beginning to reach their design lifetime. This has led to a greater interest in wind turbine fatigue, the remaining useful lifetime and lifetime extensions. In an attempt to quantify the progression of fatigue life for offshore wind turbines, also referred to as a fatigue assessment, structural health monitoring (SHM) appears as a valuable contribution. Accurate information from a SHM system, can enable informed decisions regarding lifetime extensions. Unfortunately direct measurement of fatigue loads typically revolves around the use of strain gauges and the installation of strain gauges on all turbines of a given farm is generally not considered economically feasible. However, when we consider that great amounts of data, such as Supervisory Control And Data Acquisition (SCADA) and accelerometer data (of cheaper installation than strain gauges), is already being captured, this data might be used to circumvent the lack of direct measurements. It is then highly relevant to know what is the minimal sensor instrumentation required for a proper fatigue assessment. In order to determine this minimal instrumentation, a data-driven methodology is developed for real-world jacket-foundation Offshore Wind Turbines (OWT). Firstly, high-frequent 1s SCADA data is used to train an Artificial Neural Network (ANN) that seeks to estimate the quasi-static thrust load, and able to accurately estimate the thrust load with a Mean Absolute Error (MAE) below 2 %. The thrust load is then, along with 1s SCADA and acceleration data, processed into 10-minute metrics and undergoes a comparative analysis of feature selection algorithms with the goal of performing the most efficient dimensionality reduction possible. The features selected by each method are compared and related to the sensors. The variables chosen by the best-performing feature selection algorithm then serve as the input for a second ANN which estimates the tower fore-aft (FA) bending moment Damage Equivalent Loads (DEL), a valuable metric closely related to fatigue. This approach can then be understood as a two-tier model: the first tier concerns itself with engineering and processing 10 minute features, which will serve as an input for the second tier. It is this two-tier methodology that is used to assess the performance of 8 realistic instrumentation setups (ranging from 10 minute SCADA to 1s SCADA, thrust load and dedicated tower SHM accelerometers). Amongst other findings, it was seen that accelerations are essential for the model's generalization. The best performing instrumentation setup is looked in greater depth, with validation results of the tower FA DEL ANN model show an accuracy of around 1 % (MAE) for the training turbine and below 3 % for other turbines, with a slight underprediction of fatigue rates. Finally, the ANN DEL estimation model – based on a intermediate instrumentation setup (1s SCADA, thrust load, low quality accelerations) – is employed in a farm-wide setting, and the probable causes for outlier behaviour investigated.