주조품 분류 정확도 향상을 위한 적대적 생성 네트워크(GAN) 이미지 데이터 확장
Generative Adversarial Network (GAN) Based Image Augmentation for Casting Data Classification Enhancement
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Casting is a method of making metal through molds by changing solid metal into liquid state, which has the advantageof being able to yield a large number of products with complex shapes. Owing to the advantage, it is widely used tomanufacture jewelry, artwork, surgical implants, and impellers in automobiles and ships. However, low quality productscan be produced due to pinholes, sand blows, shrinkage cavities, and cracks that are well-known issues in casting. Especially using a defective impeller, a rotating element of a centrifugal pump that accelerates fluid outside from thecenter and transfers the power of fluid kinetic energy, causes a significant damage to its pump and/or workers nearby dueto its high pressure. Therefore, foundries endeavor to catch any defectives before sending them out to purchasers. However, foundries are usually small or medium-sized enterprises. It is difficult for them to hire additional experiencedworkers to catch more defectives or install photographing and imaging-storing devices to keep track of a large amountof product images for analyses. The foundries usually have a few inspectors to catch defective products and, due to ashortage of manpower and human inaccuracy, defective products are often classified as non-defective products. Thisstudy shows that a combination of classic augmentation and self-attention generative adversarial network improves theaccuracy of classifying non-defective and defective impellers by augmenting a limited amount of image data that can beeven manually photographed. Combining classic augmentation and self-attention generative adversarial networkoutperforms the sole use of classic augmentation in generating quality images for convolutional neural network.
Abstract
Casting is a method of making metal through molds by changing solid metal into liquid state, which has the advantageof being able to yield a large number of products with complex shapes. Owing to the advantage, it is widely used tomanufacture jewelry, artwork, surgical implants, and impellers in automobiles and ships. However, low quality productscan be produced due to pinholes, sand blows, shrinkage cavities, and cracks that are well-known issues in casting. Especially using a defective impeller, a rotating element of a centrifugal pump that accelerates fluid outside from thecenter and transfers the power of fluid kinetic energy, causes a significant damage to its pump and/or workers nearby dueto its high pressure. Therefore, foundries endeavor to catch any defectives before sending them out to purchasers. However, foundries are usually small or medium-sized enterprises. It is difficult for them to hire additional experiencedworkers to catch more defectives or install photographing and imaging-storing devices to keep track of a large amountof product images for analyses. The foundries usually have a few inspectors to catch defective products and, due to ashortage of manpower and human inaccuracy, defective products are often classified as non-defective products. Thisstudy shows that a combination of classic augmentation and self-attention generative adversarial network improves theaccuracy of classifying non-defective and defective impellers by augmenting a limited amount of image data that can beeven manually photographed. Combining classic augmentation and self-attention generative adversarial networkoutperforms the sole use of classic augmentation in generating quality images for convolutional neural network.
참고문헌 (25)
- 김진호, "제조분야 자동 품질 검사를 위한 딥러닝 기반 대형 이미지 분류시스템 개발 및 구축", 한국지능정보시스템학회 학술대회논문집, pp.27~29 (2018)
- 강지훈, "딥 러닝 기반의 이미지학습을 통한 저항 용접품질 검증", 대한조선학회 논문집, 56(6), pp.473~479 (2019), 대한조선학회[DOI]
- 박기화, "물류 스타트업의 디지털 물류 비즈니스 모델 유형 연구", 로지스틱스연구, 27(1), pp.15~33 (2019), 한국로지스틱스학회[DOI]
- 웨이치, "컨테이너 터미널에 적용 가능한 인더스트리 4.0 기반 제품", 서비스의 개념 설계 및 중요성 분석, 2018, pp.26(3), 91~110[DOI]
- 최태은, "스마트 팩토리 도입 및 수용 요인에 관한 실증 연구 -조선기자재 기업 대상으로-", 로지스틱스연구, 28(5), pp.1~10 (2020), 한국로지스틱스학회[DOI]
- "생기원, AI 기반으로 제조공정지능화 선도한다" (2020), 한국생산기술연구원[URL]
- Frid-Adar, M., "Synthetic data augmentation using GAN for improved liver lesion classification", IEEE 15th international symposium on biomedical imaging, pp.289~293 (2018)
- Goodfellow, I. J., "Generative adversarial networks", arXiv preprint, arXiv:1406.2661, ~ (2014)
- Hawkins, D. M., "The problem of overfitting", Journal of chemical information and computer sciences, 44(1), pp.1~12 (2004)
- Hiang, L. I., "Super-resolution and self-attention with generative adversarial network for improving malignancy characterization of hepatocellular carcinoma", IEEE 17th International Symposium on Biomedical Imaging, pp.1556~1560 (2020)
- Iandola, F., "Densenet:Implementing efficient convnet descriptor pyramids", arXiv preprint, arXiv:1404.1869, ~ (2014)
- 정종윤, "FEM 시뮬레이션을 이용한 임펠러의 구조 안전성 평가", 한국산업경영시스템학회지, 43(4), pp.41~47 (2020), 한국산업경영시스템학회[DOI]
- Karras, T., "Progressive growing of gans for improved quality, stability, and variation", arXiv preprint, arXiv:1710.10196, ~ (2017)
- Krizhevsky, A., "ImageNet classification with deep convolutional neural networks", Communications of the ACM, 60(6), pp.84~90 (2017)
- Ledig, C., "Photo-realistic single image super-resolution using a generative adversarial network", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.4681~4690 (2017)
- Lu, C. Y., "Generative adversarial network based image augmentation for insect pest classification enhancement", IFAC-Papers OnLine, 52(30), pp.1~5 (2019)
- Rahman, M. M., "Addressing the class imbalance problem in medical datasets", International Journal of Machine Learning and Computing, 3(2), pp.224~ (2013)
- Simonyan, K., "Very deep convolutional networks for large-scale image recognition", arXiv preprint, arXiv:1409.1556, ~ (2014)
- Szegedy, S., "Inception-v4, inception-resnet and the impact of residual connections on learning", Proceedings of the AAAI Conference on Artificial Intelligence, 31(1) (2017)
- Wu, Q., "DCGAN-based data augmentation for tomato leaf disease identification", IEEE Access, 8, pp.98716~98728 (2020)
- Wu, Y., "Self-attention convolutional neural network for improved MR image reconstruction", Information sciences, 490, pp.317~328 (2019)
- Xu, S., "meprop:Sparsified back propagation for accelerated deep learning with reduced overfitting", Proceedings of International Conference on Machine Learning, pp.3299~3308 (2017)
- Yoon, S. I., "Finite element analysis of casting processes considering molten-metal flow and solidification", Journal of the Korean Society for Precision Engineering, 13(3), pp.110~122 (1996)
- Zhang, H., "Self-attention generative adversarial networks", International conference on machine learning, pp.7354~7363 (2019)
- Zhu, J. Y., "Unpaired image-to-image translation using cycleconsistent adversarial networks", Proceedings of the IEEE international conference on computer vision, pp.2223~2232 (2017)