Decision-Making in Structural Health Monitoring and Predictive Maintenance of Wind Turbines

The fourth stage of the life cycle of a wind farm refers to operation and maintenance activities. This stage includes routine maintenance and repairs that are necessary to achieve the design life of the wind turbine. Structural health monitoring for wind turbines is focused on the condition monitoring of the foundation, tower, and rotor blades for damage detection at an early stage, life cycle prognosis, and the optimization of wind farm operations. Regardless of location, a sustainable reduction of operating costs with a simultaneous increase in yields is gaining more and more relevance. Therefore, it is more important than ever to detect structural damage and icing at an early stage in order to avoid severe damage. Structural health monitoring of the foundation, tower, and rotor blade and conventional condition monitoring on the drive train are becoming increasingly important in this context. Based on a detailed system condition analysis, it is possible to plan ahead, optimize the operation of wind turbines, and extend their lifetime; thus, the operation of wind farms becomes more efficient and economical. Once the wind farm is ready for operation, the next stage involves regular health monitoring and predictive maintenance. Due to the construction of wind turbine blades and many blade-breaking accidents caused by blade vibration, proper models for monitoring predictive maintenance could be helpful (Zhou et al., 2023; Liu et al., 2023; Rokicki et al., 2023). Predictive maintenance helps to determine the condition of in-service equipment in order to predict when proper maintenance should be performed. Implementation of condition monitoring and fault detection system entails initial investment, but these costs are being offset by the benefits of continuous production, minimum downtimes, and early planning for the replacement of defective parts. Therefore, in this chapter, various combinatorial models could be used for monitoring and predictive maintenance of wind turbines/farms is presented. A strategy for predictive maintenance of the machine as a whole and of its individual components is presented, which is based on optimization models determining whether repair or replacement is necessary. A concept for an intelligent decision-making system for e-support that integrates different stratagems capable of expressing different uncertainties when forecasting the deterioration of the systems is proposed. A group decision-making approach for the choice of specialized software considering different strategies of uncertainty based on cost–benefit analysis is described too.