[논문]머신러닝 기반 금속외관 결함 검출 비교 분석

이세훈; 강성환; 신요섭; 최오규; 김시종; 강재모

doi:10.6109/jkiice.2022.26.6.834

머신러닝 기반 금속외관 결함 검출 비교 분석
Comparative analysis of Machine-Learning Based Models for Metal Surface Defect Detection 원문보기

한국정보통신학회논문지 = Journal of the Korea Institute of Information and Communication Engineering, v.26 no.6, 2022년, pp.834 - 841

이세훈 (Department of Artificial Intelligence, Kyungpook National University) , 강성환 (Department of Artificial Intelligence, Kyungpook National University) , 신요섭 (Department of Artificial Intelligence, Kyungpook National University) , 최오규 (Artificial Intelligence Research Center, Industry Applications Research Division, Korea Electrotechnology Research Institute (KERI)) , 김시종 (Artificial Intelligence Research Center, Industry Applications Research Division, Korea Electrotechnology Research Institute (KERI)) , 강재모 (Department of Artificial Intelligence, Kyungpook National University)

초록
AI-Helper

최근 스마트팩토리와 인공지능 기술의 수요 증가로 인해 다양한 분야에서 인공지능 기술을 적용하는 연구가 진행되고 있다. 결함 검사 분야에서도 인공지능 알고리즘을 도입하기 위한 노력을 기울이고 있다. 특히, 금속 외관의 결함을 검출하는 연구는 다른 소재(목재, 플라스틱, 섬유 등)의 결함을 검출하는 연구에 비해 많은 연구가 이루어지고 있다. 본 논문에서는 머신러닝 기법(서포터 벡터 머신(SVM: Support Vector Machine), 소프트맥스 회귀(Softmax Regression), 결정 트리(Decesion Tree))과 차원 축소 알고리즘(주성분 분석(PCA: Principal Component Analysis), 오토인코더(AutoEncoder))의 9가지 조합과 2가지 합성곱신경망(CNN: Convolutional Neural Network) 기법(자체 알고리즘, ResNet)의 금속 외관의 결함 분류 성능 및 속도를 비교하고 분석하는 연구를 수행하고자 한다. 두 종류의 학습 데이터셋((i) 공용 데이터셋(Public Dataset), (ii) 실측 데이터셋(Actual Dataset))에 대한 실험을 통해 각 데이터셋에 대한 성능 및 속도를 비교 분석하고, 가장 효율적인 알고리즘을 찾아낸다.

Abstract ▼ AI-Helper

Recently, applying artificial intelligence technologies in various fields of production has drawn an upsurge of research interest due to the increase for smart factory and artificial intelligence technologies. A great deal of effort is being made to introduce artificial intelligence algorithms into the defect detection task. Particularly, detection of defects on the surface of metal has a higher level of research interest compared to other materials (wood, plastics, fibers, etc.). In this paper, we compare and analyze the speed and performance of defect classification by combining machine learning techniques (Support Vector Machine, Softmax Regression, Decision Tree) with dimensionality reduction algorithms (Principal Component Analysis, AutoEncoders) and two convolutional neural networks (proposed method, ResNet). To validate and compare the performance and speed of the algorithms, we have adopted two datasets ((i) public dataset, (ii) actual dataset), and on the basis of the results, the most efficient algorithm is determined.

주제어

표/그림 (10)

그림 Fig. 2 Self-Algorithm
그림 Fig. 1 Residual Learning[13]
그림 Fig. 4 Actual Dataset
그림 Fig. 3 Public Dataset[15]
표 Table. 1 Data's count of each class of Public Dataset
표 Table. 2 Data's count of each class of Actual Dataset
표 Table. 3 Performance Comparison of different methods on the Public Dataset
표 Table. 4 ROC Curves of different Machine Learning methods on the Public Dataset
표 Table. 5 Performance Comparison of different methods on the Actual Dataset
표 Table. 6 ROC Curves of different Machine learning methods on the Actual Dataset

참고문헌 (15)

F. C. Campbell, Inspection of metals: understanding the basics, ASM International, OH: USA, 2013.
X. Li, Y. Zhu, Y. Yi, Y. Ding, and K. Zhu, "Application of vision technology in metal surface defect detection," in 2021 IEEE 2nd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA), Chongqing, China, vol. 2, pp. 50-54, 2021.
F. Jia, Y. Lei, N. Lu, and S. Xing, "Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization," Mechanical Systems and Signal Processing, vol. 110, pp. 349-367, Sep. 2018.

상세보기
H. Lin and F. S. Wibowo, "Image data assessment approach for deep learning-based metal surface defect-detection systems," IEEE Access, vol. 9, pp. 47621-47638, Mar. 2021.

상세보기
J. Zhang, S. Li, Y. Yan, Z. Ni, and H. Ni, "Surface Defect Classification of Steel Strip with Few Samples Based on Dual-Stream Neural Network," steel research international, vol. 93, no. 5, 2100554, May. 2021.
W. Zhang, J. Du, X. Li, and W. Wang, "Application of Weighted Object Variance Algorithm in Metal Surface Defect Detection," in IOP Conference Series: Materials Science and Engineering, Yunnan, China, vol. 612. no. 3, Oct. 2019.
M. A. Hearst, S. T. Dumais, E. Osuna, J. Platt, and B. Scholkopf, "Support vector machines," IEEE Intelligent Systems and their Applications, vol. 13, no. 4, pp. 18-28, Jul-Aug. 1998.

상세보기
P. Caleb and M. Steuer, "Classification of surface defects on hot rolled steel using adaptive learning methods," in KES'2000. Fourth International Conference on Knowledge-Based Intelligent Engineering Systems and Allied Technologies. Proceedings(Cat. No. 00TH8516), Brighton, UK, vol. 1, pp. 103-108, 2000.
Md. F. Islam and Md. M. Rahman, "Metal surface defect inspection through deep neural network," in 2018 International Conference on Mechanical, Industrial and Energy Engineering, Khulna, Bangladesh, p. 258, 2018.
Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied todocumentrecognition," in Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998.

상세보기
J. S. Bridle, "Training stochastic model recognition algorithms as networks can lead to maximum mutual information estimation of parameters," Advances in neural information processing systems 2, pp. 211-217, Jun. 1990.
J. R. Quinlan, "Induction of decision trees," Machine learning 1.1, vol. 1, pp. 81-106, Mar. 1986.

상세보기
K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas: NV, USA, pp. 770-778, 2016.
K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556, Sep. 2014.
Northeastern University Kechen Song's Personal Hompage NEU Surface Defect Database [Internet]. Avaliable: http://faculty.neu.edu.cn/songkc/en/zhym/263264/list/index.htm.

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증