Adaptive Neuro-Fuzzy System for Detection of Wind Turbine Blade Defects

Wind turbines are the most frequently used objects of renewable energy today. However, issues that arise during their operation can greatly affect their effectiveness. Blade erosion, cracks, and other defects can slash turbine performance while also forcing maintenance costs to soar. Modern defect detection applications have significant computing resources needed for training and insufficient accuracy. The goal of this study is to develop the improved adaptive neuro-fuzzy inference system (ANFIS) for wind turbine defect detection, which will reduce computing resources and increase its accuracy. Unmanned aerial vehicles are deployed to photograph the turbines, and these images are beamed back and processed for early defect detection. The proposed adaptive neuro-fuzzy inference system processes the data vectors with lower complexity and higher accuracy. For this purpose, the authors explored grid partitioning and subtractive clustering methods and selected the last one because it uses three rules only for fault detection, ensuring low computational costs and enabling the discovery of wind turbine defects quickly and efficiently. Moreover, the proposed ANFIS is implemented in a controller, which has an accuracy of 91%, that is 1.4 higher than the accuracy of the existing similar controller.