To optimally plan maintenance of wind turbine blades, knowledge of the degradation\nprocesses and the remaining useful life is essential. In this paper, a method is proposed for calibration\nof a Markov deterioration model based on past inspection data for a range of blades, and updating\nof the model for a specific wind turbine blade, whenever information is available from inspections\nand/or condition monitoring. Dynamic Bayesian networks are used to obtain probabilities of\ninspection outcomes for a maximum likelihood estimation of the transition probabilities in the\nMarkov model, and are used again when updating the model for a specific blade using observations.\nThe method is illustrated using indicative data from a database containing data from inspections of\nwind turbine blades.
Loading....