A study on defect detection in X-ray image castings based on unsupervised learning

Soo-Hwan Lee; Hong-Il Seo; Ju-Hyeon Seong; Yang-Ick Joo; Dong-Hoan Seo

doi:10.5916/jamet.2020.44.6.487

추천

검색

질문

자료유형: 학술저널

저자정보: Soo-Hwan Lee (Korea Maritime & Ocean University) Hong-Il Seo (Korea Maritime & Ocean University) Ju-Hyeon Seong (Korea Maritime & Ocean University) Yang-Ick Joo (Korea Maritime & Ocean University) Dong-Hoan Seo (Korea Maritime & and Ocean University)

저널정보: 한국마린엔지니어링학회 Journal of Advanced Marine Engineering and Technology (JAMET) 한국마린엔지니어링학회지 제44권 제6호

발행연도: 2020.12

수록면: 487 - 493 (7page)

DOI: 10.5916/jamet.2020.44.6.487

이용수

📌

연구주제

📖

연구배경

🔬

연구방법

🏆

연구결과

초록· 키워드

오류제보하기

In this paper, we propose a deep-learning-based defect detection system for the non-destructive quality inspection of castings based on X-ray images. Our system comprises a defect classification network and a defect search network and achieves high classification performance with limited data by minimizing the overfitting for one type of object. The proposed defect classification network determines whether the acquired X-ray image is Defect by using a convolution neural network and outputs the defect probability through softmax. Compared to binarized defect classification or defect location tracking, this method of outputting the defect probability does not require a separate reworking of the training dataset, because the data labeling is the same as the existing quality evaluation task. In addition, to detect the location of the defect causing the defect classification, our proposed defect search network estimates the region where the defect is likely to exist through a Grad-CAM based on the feature map of the classification network. The proposed network then determines the ROI around each peak of the estimated regions and detects the exact shape and location of the defect through boundary detection. It is, therefore, possible to minimize quality control costs through a precise quality analysis of each casting product by simultaneously detecting small defects that are easy to ignore because large defects are found in the image. To verify the validity of this study, an experiment was conducted by constructing a dataset of actual cast products, and the proposed detection model achieved an accuracy of 90%. In addition, by comparing the fully connected network and the SVM-based model, the model improved by about 20%, demonstrating that it is possible to detect defects without labeling defect locations.

#Defect detection #X-ray image #Castings #Unsupervised #Deep learning

참고문헌 (19)

참고문헌 신청

L. D. Chiffre / 2014 / Industrial applications of computed tomography / CIRP Annals 63(2):655~677

A. D. Plessis / 2018 / X-ray microcomputed tomography in additive manufacturing : A review of the current technology and applications / 3D Printing and Additive Manufacturing 5(3):227~247

A. D. Plessis / 2018 / Standard method for microCT-based additive manufacturing quality control 2 : Density measurement / MethodsX 5:1117~1123

A. Thompson / 2016 / X-ray computed tomography for additive manufacturing : A review / Measurement Science and Technology 27(7):072001

J. P. Kruth / 2011 / Computed tomography for dimensional metrology / CIRP Annals 60(2):821~842

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!