A Bibliometric Study on the Applications of Neural Networks in Metal Surface Defect Inspection

Sandro Bessa de Lima; Marcos dos Santos; Júlio César Duarte

doi:10.22456/2175-2745.142111

Authors

Sandro Bessa de Lima Instituto Militar de Engenharia (IME) https://orcid.org/0009-0008-8264-1675
Marcos dos Santos Instituto Militar de Engenharia (IME)
Júlio César Duarte Instituto Militar de Engenharia (IME) https://orcid.org/0000-0001-6656-1247

DOI:

https://doi.org/10.22456/2175-2745.142111

Keywords:

Machine Learning, Convolutional Neural Networks, Segmentation, Transfer Learning, Data Augmentation, Bibliometrix, Computer Vision, Metal Surfaces

Abstract

The transformation industries are tasked with the process of converting vast amounts of chemical compounds into metal sheets. By applying artificial intelligence to detect anomalies and enhance the scope of visual inspection on metal surfaces, these industries have significantly advanced their digital transformation. In this research, we explore and highlight extensively used neural network architectures, since, despite the existing literature, recent bibliometric studies on this important topic remain scarce. Keeping this in mind, this work presents an analysis of a quantitative approach based on bibliometric metrics to evaluate the application of neural network architectures aimed at inspecting defects on metal alloy surfaces, using data from the Scopus and Web of Science databases as references. It primarily focuses on identifying aspects related to the research in this field, such as the distribution of scientific publications, the most relevant sources, the interaction dynamics among these sources, the most prominent subjects in recent research (trend topics), and the application of machine learning techniques to the detection of metal surfaces' failures. Finally, our results show a lack of relevant public datasets of adequate size, as well as structured methods to apply the combined neural network architectures and techniques of machine learning in real-world applications within the scope of this research.

Downloads

Download data is not yet available.

References

ZUCHNIAK, K. et al. Corrosion detection on aircraft fuselage with multi-teacher knowledge distillation. In: PASZYNSKI, M. et al. (Ed.). Computational Science – ICCS 2021. Cham: Springer International Publishing, 2021. p. 318–332. ISBN 978-3-030-77980-1. Disponível em: ⟨https://link.springer.com/content/pdf/10.1007/978-3-030-77980-1_25.pdf?pdf=inline%20link⟩.

RAMANI, V.; ZHANG, L.; KUANG, K. S. C. Probabilistic assessment of time to cracking of concrete cover due to corrosion using semantic segmentation of imaging probe sensor data. Automation in Construction, v. 132, p. 103963, 2021. ISSN 0926-5805. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S0926580521004143⟩.

ASARI, V. K. et al. Recent progress in wide-area surveillance: protecting our pipeline infrastructure. In: LIN, Q.; ALLEBACH, J. P.; FAN, Z. (Ed.). Imaging and Multimedia Analytics in a Web and Mobile World 2015. 2015. v. 9408, p. 940802. Disponível em: ⟨https://doi.org/10.1117/12.2086905⟩.

BASTIAN, B. T. et al. Visual inspection and characterization of external corrosion in pipelines using deep neural network. NDT & E International, v. 107, p. 102134, 2019. ISSN 0963-8695. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S096386951930060X⟩.

FARADY, I. et al. Evaluation of data augmentation on surface defect detection. In: 2021 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW). [s.n.], 2021. p. 1–2. Disponível em: ⟨https://ieeexplore.ieee.org/document/9603212/keywords#keywords⟩.

YUN, J. P. et al. Automated defect inspection system for metal surfaces based on deep learning and data augmentation. Journal of Manufacturing Systems, v. 55, p. 317–324, 2020. ISSN 0278-6125. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S027861252030042X⟩.

BOŽIČ, J.; TABERNIK, D.; SKOČAJ, D. Mixed supervision for surface-defect detection: From weakly to fully supervised learning. Computers in Industry, Elsevier BV, v. 129, p. 103459, ago. 2021. ISSN 0166-3615. Disponível em: ⟨http://dx.doi.org/10.1016/j.compind.2021.103459⟩.

IGNACIO; JULIANO. Processamento e análise digital de imagens em estudos da cinética de recristalização de ligas Al-Mg-X. 2013. 1-106 p. Dissertação (Mestrado) — Instituto de Pesquisas Energéticas e Nucleares, Universidade de São Paulo, São Paulo, 2013.

CAIO, J. Segmentação semântica de imagens de sensoriamento remoto em cenário de conjunto aberto. 1–98 p. Dissertação (Mestrado) — Universidade Federal de Minas Gerais (UFMG), 2019. Dissertação de Mestrado.

DUY, L. D. et al. Deep learning in semantic segmentation of rust in images. In: Proceedings of the 2020 9th International Conference on Software and Computer Applications. New York, NY, USA: Association for Computing Machinery, 2020. (ICSCA ’20), p. 129–132. ISBN 9781450376655. Disponível em: ⟨https://doi.org/10.1145/3384544.3384606⟩.

HAZIRBAS, C. Feature Selection and Learning for Semantic Segmentation. 1-80 p. Dissertação (Mestrado) — Technical University Munich, Germany, June 2014.

NASH, W.; DRUMMOND, T.; BIRBILIS, N. Deep Learning AI for Corrosion Detection. In: ONEPETRO (Ed.). Corrosion 2019. [s.n.], 2019. (NACE CORROSION, All Days), p. NACE–2019–13267. Disponível em: ⟨https://onepetro.org/NACECORR/proceedings-abstract/CORR19/All-CORR19/NACE-2019-13267/127373⟩.

ABRAHAM, A. Adaptation of fuzzy inference system using neural learning. In: Fuzzy Systems Engineering: Theory and Practice. Berlin, Heidelberg: Springer Berlin Heidelberg, 2005. p. 53–83. ISBN 978-3-540-32397-6. Disponível em: ⟨https://doi.org/10.1007/11339366_3⟩.

SHORTEN, T. M. K. C. A survey on image data augmentation for deep learning. Journal of Big Data, v. 6, p. 1–48, 2019.

FARADY, I. et al. Evaluation of data augmentation on surface defect detection. In: [S.l.: s.n.], 2021. p. 1–2.

KATSAMENIS, I. et al. Pixel-level corrosion detection on metal constructions by fusion of deep learning semantic and contour segmentation. In: BEBIS, G. et al. (Ed.). Advances in Visual Computing. Cham: Springer International Publishing, 2020. p. 160–169.

CAO, Y. et al. Corrosion detection in transformers based on hierarchical annotation. In: SUN, X. et al. (Ed.). Artificial Intelligence and Security. Cham: Springer International Publishing, 2021. p. 575–584. ISBN 978-3-030-78609-0. Disponível em: ⟨https://link.springer.com/content/pdf/10.1007/978-3-030-78609-0_49.pdf?pdf=inline%20link⟩.

BERRADA, L.; BENGIO, Y.; LAJOIE, G. A meta-analysis of overfitting in machine learning. In: Proceedings of the Conference on Neural Information Processing Systems (NeurIPS). [s.n.], 2022. Disponível em: ⟨https://proceedings.neurips.cc/paper/2022⟩.

THOMÉ, L. F. S. A. M. T.; SCAVARDA, A. J. Conducting systematic literature review in operations management. Production Planning & Control, Taylor & Francis, v. 27, n. 5, p. 408–420, 2016. Disponível em: ⟨https://doi.org/10.1080/09537287.2015.1129464⟩.

MIGUEL, P. A. C. et al. Metodologia de pesquisa em engenharia de produção e gestão de operações. [S.l.], 2018. v. 3rd ed.

MONGEON, P.; PAUL-HUS, A. The journal coverage of web of science and scopus: a comparative analysis. Scientometrics, Springer Science and Business Media LLC, v. 106, n. 1, p. 213–228, out. 2015. ISSN 1588-2861. Disponível em: ⟨http://dx.doi.org/10.1007/s11192-015-1765-5⟩.

ARIA, M.; CUCCURULLO, C. bibliometrix: An r-tool for comprehensive science mapping analysis. Journal of Informetrics, v. 11, n. 4, p. 959–975, 2017. ISSN 1751-1577. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S1751157717300500⟩.

BIBLIOMETRIX.ORG. Biblioshiny: the shiny app for bibliometrix. 2023. ⟨https://www.bibliometrix.org/home/index.php/layout/biblioshiny⟩.

BAI, J. et al. A Comprehensive Survey on Machine Learning Driven Material Defect Detection: Challenges, Solutions, and Future Prospects. 2024. Disponível em: ⟨https://arxiv.org/abs/2406.07880⟩.

AKBAS, C.; ARIN, I. S.; ONAL, S. A PRISMA Driven Systematic Review of Publicly Available Datasets for Benchmark and Model Developments for Industrial Defect Detection. 2024. Disponível em: ⟨https://arxiv.org/abs/2406.07694⟩.

LATIF, S. et al. Deep learning for the industrial internet of things (IIoT): A comprehensive survey of techniques, implementation frameworks, potential applications, and future directions. Sensors, v. 21, n. 22, 2021. ISSN 1424-8220. Disponível em: ⟨https://www.mdpi.com/1424-8220/21/22/7518⟩.

ALONSO, S. et al. h-index: A review focused in its variants, computation and standardization for different scientific fields. Journal of Informetrics, v. 3, n. 4, p. 273–289, 2009. ISSN 1751-1577. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S1751157709000339⟩.

GUO, X.; LI, X.; YU, Y. Publication delay adjusted impact factor: The effect of publication delay of articles on journal impact factor. Journal of Informetrics, v. 15, n. 1, p. 101100, 2021. ISSN 1751-1577. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S1751157720301474⟩.

YANG, J.; LIU, Z. The effect of citation behaviour on knowledge diffusion and intellectual structure. Journal of Informetrics, v. 16, n. 1, p. 101225, 2022. ISSN 1751-1577. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S1751157721000961⟩.

YUN, J. P. et al. Automated defect inspection system for metal surfaces based on deep learning and data augmentation. Journal of Manufacturing Systems, v. 55, p. 317–324, 2020. ISSN 0278-6125. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S027861252030042X⟩.

BASTIAN, B. T. et al. Visual inspection and characterization of external corrosion in pipelines using deep neural network. NDT & E International, v. 107, p. 102134, 2019. ISSN 0963-8695. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S096386951930060X⟩.

BLOCK, S. B. et al. Inspection of imprint defects in stamped metal surfaces using deep learning and tracking. IEEE Transactions on Industrial Electronics, v. 68, n. 5, p. 4498–4507, 2021.

KATSAMENIS, I. et al. Pixel-level corrosion detection on metal constructions by fusion of deep learning semantic and contour segmentation. In: BEBIS, G. et al. (Ed.). Advances in Visual Computing. Cham: Springer International Publishing, 2020. p. 160–169. ISBN 978-3-030-64556-4. Disponível em: ⟨https://link.springer.com/content/pdf/10.1007/978-3-030-64556-4_13.pdf?pdf=inline%20link⟩.

MAO, S.; RAJAN, D.; CHIA, L. T. Deep residual pooling network for texture recognition. Pattern Recognition, v. 112, p. 107817, 2021. ISSN 0031-3203. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S0031320321000042⟩.

ASLAM, Y.; SANTHI, N.; RAMASAMY, N. Localization and segmentation of metal cracks using deep learning. Journal of Ambient Intelligence and Humanized Computing, v. 12, p. 4205–4213, 2021. ISSN 1868-5145. Disponível em: ⟨https://link.springer.com/content/pdf/10.1007/s12652-020-01803-8.pdf⟩.

FORKAN, A. R. M. et al. Corrdetector: A framework for structural corrosion detection from drone images using ensemble deep learning. Expert Systems with Applications, v. 193, p. 116461, 2022. ISSN 0957-4174. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S0957417421017437⟩.

LIU, Z. et al. Visual defect inspection of metal part surface via deformable convolution and concatenate feature pyramid neural networks. IEEE Transactions on Instrumentation and Measurement, v. 69, n. 12, p. 9681–9694, 2020. Disponível em: ⟨https://ieeexplore.ieee.org/document/9115064⟩.

NASH, W.; LIANG, Z.; ZHENG, N. B. Deep learning corrosion detection with confidence. npj Materials Degradation, v. 26, n. 6, p. 2397–2106, 2022. Disponível em: ⟨https://doi.org/10.1038/s41529-022-00232-6⟩.

MUNAWAR, H. S. et al. Civil infrastructure damage and corrosion detection: An application of machine learning. Buildings, v. 12, n. 2, 2022. ISSN 2075-5309. Disponível em: ⟨https://www.mdpi.com/2075-5309/12/2/156⟩.

ATHA, D. J.; JAHANSHAHI, M. R. Evaluation of deep learning approaches based on convolutional neural networks for corrosion detection. Structural Health Monitoring, v. 17, n. 5, p. 1110–1128, 2018. Disponível em: ⟨https://doi.org/10.1177/1475921717737051⟩.

FARADY, I. et al. Evaluation of data augmentation on surface defect detection. In: 2021 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW). [S.l.: s.n.], 2021. p. 1–2.

CHEN, Y. et al. Metal surface corrosion grade estimation from single image. In: YU, H.; DONG, J. (Ed.). Ninth International Conference on Graphic and Image Processing (ICGIP 2017). SPIE, 2018. v. 10615, p. 106154Z. Disponível em: ⟨https://doi.org/10.1117/12.2302776⟩.

JIAN, B.-L. et al. Deep learning model for determining defects of vision inspection machine using only a few samples. Sensors and Materials, v. 32, p. 4217, 12 2020.

XU, X. et al. Intelligent corrosion detection and rating based on faster region-based convolutional neural network. In: 2020 Global Reliability and Prognostics and Health Management (PHM-Shanghai). [S.l.: s.n.], 2020. p. 1–5.

TIAN, Z. et al. Corrosion identification of fittings based on computer vision. In: 2019 International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM). [s.n.], 2019. p. 592–597. Disponível em: ⟨https://ieeexplore.ieee.org/document/8950822⟩.

SHUKLA, M.; RAVULAKOLLU, K. K. Surface corrosion grade classification using convolution neural network. International Journal of Recent Technology and Engineering (IJRTE), v. 8, n. 3, p. 7645–7649, September 2019. ISSN 2277-3878. Disponível em: ⟨https://www.ijrte.org/wp-content/uploads/papers/v8i3/C6196098319.pdf⟩.

DONG, H.; GANG, T.; ZHENGKUN, Z. Surface corrosion detection of quayside crane based on improved mobilenetv2-ssdlite. Laser & Optoelectronics Progress, v. 58, p. 1615006, 2021. Disponível em: ⟨https://www.researching.cn/articles/OJ13de7d125dd5d517⟩.

AHUJA, S. K.; SHUKLA, M. K.; RAVULAKOLLU, K. K. Optimized deep learning framework for detecting pitting corrosion based on image segmentation. International Journal of Performability Engineering, v. 17, n. 7, p. 627, 2021. Disponível em: ⟨http://www.ijpe-online.com/EN/abstract/article_4605.shtml⟩.

CHOUHAD, H. et al. Smart data driven defect detection method for surface quality control in manufacturing. Measurement Science and Technology, IOP Publishing, v. 32, n. 10, p. 105403, jul. 2021. Disponível em: ⟨https://dx.doi.org/10.1088/1361-6501/ac0b6c⟩.

RAHMAN, A.; WU, Z.; KALFARISI, R. Semantic deep learning integrated with RGB feature-based rule optimization for facility surface corrosion detection and evaluation. Journal of Computing in Civil Engineering, v. 35, n. 6, p. 04021018, ago. 2021.

LI, W. et al. Deep learning based online metallic surface defect detection method for wire and arc additive manufacturing. Robotics and Computer-Integrated Manufacturing, v. 80, p. 102470, 2023. ISSN 0736-5845. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S0736584522001521⟩.

JAGER, M.; KNOLL, C.; HAMPRECHT, F. A. Weakly supervised learning of a classifier for unusual event detection. IEEE Transactions on Image Processing, v. 17, n. 9, p. 1700–1708, sep. 2008. ISSN 1057-7149. Disponível em: ⟨https://doi.org/10.1109/TIP.2008.2001043⟩.

HE, Y. et al. An end-to-end steel surface defect detection approach via fusing multiple hierarchical features. IEEE Transactions on Instrumentation and Measurement, v. 69, n. 4, p. 1493–1504, 2020.