Wind and solar energy are two popular alternative energy sources. However, wind turbines are larger and more complex than solar panels. Accordingly, wind turbines are more exposed to environmental factors and therefore more prone to mechanical failures. Our work improves the reliability and efficiency of wind energy systems by presenting an artificial intelligence (AI)-based system that predicts mechanical gearbox and electrical failures. Historical data are aggregated with real-time sensor data to train the prediction model. Apart from related mechanical and environmental data, sensors provide real-time vibration, internal nacelle temperature, wind speed, noise and smoke levels. The developed system integrates AI and Large Language Model (LLM)-based interfaces for real-time interactive monitoring of turbines. The user interface of the developed system allows users to receive informative responses on performance, detected risks, predicted failures, and energy production levels. The developed model has been validated using 5-fold cross-validation based on <em>Accuracy</em>, <em>Precision</em>, <em>Recall</em>, <em>F1-Score</em>, and <em>ROC-AUC</em>. The model achieves approximately 89.68 % <em>Accuracy</em>, 90.08 % <em>F1- Score</em>, 95.65 % <em>ROC-AUC</em>, and novel metric 65.13 %, <em>Overall Performance</em>. The performance results demonstrate the promising potential of AI- and LLM-integrated systems for wind energy applications. Prototype data, labeled via the XGBoost model trained with SCADA data, was retrained using the LightGBM algorithm, achieving 98.37 % <em>Accuracy</em>, 99.16 % <em>F1-Score</em>, 98.95 % <em>ROC-AUC</em> and 94.65 % <em>Overall Performance</em>; the analysis proved that the newly added gas and sound sensors significantly improved the fault prediction performance of the system.