Operational Variables for Improving Industrial Wind Turbine Yaw Misalignment Early Fault Detection Capabilities Using Data-Driven Techniques

Offshore wind turbines are complex pieces of engineering and are, generally, exposed to harsh environmental conditions that making them susceptible unexpected potentially catastrophic damage. This results in significant downtime high maintenance costs. Therefore, early detection major failures is important improve availability, boost power production, reduce article proposes a supervisory control data acquisition (SCADA) data-based Gaussian process (GP) (a data-driven, machine learning approach) fault algorithm where additional model inputs called operational variables (pitch angle rotor speed) used. First, comparative studies these carried out establish whether the parameter leads improved capability; it then used construct an GP algorithm. The developed validated against existing methods terms capability detect advance (and by how much) signs failure with low false positive rate. Failure due yaw misalignment reduction production was found be useful case study demonstrate effectiveness proposed algorithms. Historical SCADA 10-min obtained from pitch-regulated were for models training validation purposes. Results show that: 1) able accuracy curve speed responsible improvement performance 2) inclusion enhanced without any positives, contrast other investigated.