Monitoring a structure’s health is important to avoid catastrophic failures and reduce operating costs by applying the Condition Based Maintenance (CBM) strategy. CBM can reduce the inspections, but cannot replace them because of the probability of failure or error of CBM.

Reinforcement learning (RL) is an artificial intelligence technique for optimizing decisions based on unrelated factors as it connects the decision to a final goal without understanding the problem details. Also, it allows for automatic policy updates without any user intervention.

Petri nets (PN) are mathematical tools suitable for maintenance modelling since they can model heterogeneous information, parallel operations, and synchronization, and provide a graphical interpretation. In this study, the Petri net model (PN) is combined with the Monte Carlo Reinforcement Learning (MCRL) method to find the optimal maintenance strategy and the optimal inspec- tion intervals for wind turbine blades as a function of the quality of the condition monitoring system (CMS), the health of the blade, and the remaining useful life of the wind turbine.