Intelligent Texture Feature-Based Defects Classification of Aircraft Engine Blades

This paper proposes an intelligent, automated defect detection system for aircraft engine blades using fuzzy texture features. Common manufacturing defects like cracks, scratches, and coating shedding can pose threats to engine operation. Traditional manual inspection is time-consuming and prone to human error. The proposed method extracts fuzzy texture features using Grey-Level Co-occurrence Matrix (GLCM), Gabor filters, and wavelet transforms. These features are input into a machine learning algorithm to intelligently classify blade images as defective or not. Experimental results demonstrate the effectiveness of the fuzzy texture-based approach for automated defect classification, improving blade quality inspection efficiency in the manufacturing process.