http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Deep Learning Algorithms for Defect Detection using Phased Array Ultrasonic Testing Data
Barashok Kseniia,박준필,이재선 한국비파괴검사학회 2023 한국비파괴검사학회지 Vol.43 No.1
Currently, artificial intelligence is increasingly being applied in various fields. Artificial intelligence facilitates the automation of many processes and speed up work. Determining the existence of a defect, its location, size and type are the main tasks solved by nondestructive testing, particularly phased array ultrasonic testing. In this study, deep learning methods were used to determine the existence of defects, and their sizes. Unfortunately, because of the small amount of data, it is impossible to train the neural network to recognize the type of defect. Three neural networks were developed and pretrained to determine the existence of defects. The results of the developed neural networks were compared with those of the TensorFlow library models pretrained using the ImageNet dataset. The developed neural networks show similar performance as the pretrained TensorFlow neural networks.