Automatic Recognition and Positioning of Wheel Defects in Ultrasonic B-Scan Image Using Artificial Neural Network and Image Processing

摘要

Wheels are one of the most important testing components in rail transport that play a significantrole in the safety of train, and thence, research on wheel defect detection is of greatsignificance. In this article, a method using image processing techniques and artificial neuralnetwork techniques is proposed for the purpose of recognizing defects in ultrasound B-scanimage. A noise reduction and filtering algorithm and a feature extraction algorithm are proposedto simplify identification steps and improve the accuracy of the later recognition. Then,two back propagation neural networks with two hidden layers are built respectively for twoclassification steps. One is to identify noise, while the other is to identify the echo of realdefects. Finally, a 93 % recognition rate is achieved by using the algorithm proposed in thisarticle. The result shows that appropriate feature extraction algorithms and artificial neuralnetwork techniques are efficient and reliable in defects recognition of ultrasound B-scanimages.