Abstract: Considering the wake effect and the uncertainty of the marine atmospheric environment,a maintenance routing stochastic programming model of the offshore wind farm is constructed,and the corresponding solution strategy is formulated. Firstly,the scene sets are applied to describe the correlation and uncertainty of wind and waves in the marine environment. Then,an objective function of minimizing maintenance costs is established. And the correlation constraints are built with the consideration of the influence of wind and waves on the vessels’ voyage time and the sea access window. Simultaneously,taking into account the relationship of maintenance status with the wake distribution among wind turbines,the wake model is combined with the maintenance status to characterize the change of the input wind speed of each turbine. Based on this,a refined shutdown loss model is constructed. Besides,in order to improve the efficiency of the solution,a pre-evaluation strategy for the maximum number of maintainable turbines by per vessel in per day is presented during the solution process,which reduces the size of the calculation. Finally,the simulation results show that comparing with traditional approach,the proposed maintenance routing decision method can deal with the random marine environment better,and the decision result considering the wake effect is more economical.