In the current context where fossil resources are diminishing globally, and carbon emissions are increasing daily, the importance of green energy, particularly wind energy, is growing significantly. The increasing of wind turbines will not only reduce the carbon footprint but also decrease dependence on external resources. To increase the installed capacity of wind turbines, it is crucial to reduce not only installation costs but also operational costs. The largest proportion of operational costs is service, and maintenance costs. One of the most critical approaches to reducing service, and maintenance costs is preventive maintenance activities. The objective of preventive maintenance activities is to minimize or ideally eliminate production losses through scheduled turbine shutdowns before failures occur. In this study, artificial neural network-based algorithms that predict potential hydraulic failures during the operational period were utilized. For this purpose, data from the turbine SCADA system over a period of two years, considering the equipment, and sensors connected to hydraulic systems, were compiled. The study was conducted using the WEKA program, comparing Multilayer Perceptron (MLP), Radial Basis Function Classifier (RBF Classifier), SMOreg (Support Vector Machines for Regression) algorithms. Result of the study, the MLP algorithm was applied with a percentage split of 66% for training, and 33% for testing, achieving a prediction accuracy of 96.32%