Method for Automatic Recognition of Defects in Aircraft Riveted Joints Using Wavelet Transform and Neural Network

Abstract

This paper presents the method for automatic recognition of defects in aircraft riveted joints. The proposed method consists of three steps: pre-processing, feature extraction and classification. Feature extraction was then performed using discrete wavelet transform. Classification was performed using deep neural network. An example of solving the problem of detecting and recognizing a defect in rivets is considered.