Analysis of Wire Rolling Processes Using Convolutional Neural Networks

• Autorzy: Capelin Matheus , Martinez Gustavo A.S. , Xin Yutao , Siqueira Adriano F. , Qian Wei-Liang

Identyfikatory

DOI

10.12913/22998624/183699

• Języki publikacji: EN

Abstrakty

EN

This study leverages machine learning to analyze the cross-sectional profiles of materials subjected to wire-rolling processes, focusing on the specific stages of these processes and the characteristics of the resulting microstructural profiles. The convolutional neural network (CNN), a potent tool for visual feature analysis and learning, is utilized to explore the properties and impacts of the cold plastic deformation technique. Specifically, CNNs are constructed and trained using 6400 image segments, each with a resolution of 120x90 pixels. The chosen architecture incorporates convolutional layers intercalated with polling layers and the “relu” activation function. The results, intriguingly, are derived from the observation of only a minuscule cropped fraction of the material’s cross-sectional profile. Following calibration and training of two distinct neural networks, we achieve training and validation accuracies of 97.4%/97% and 79%/75%, respectively. These accuracies correspond to identifying the cropped image’s location and the number of passes applied to the material. Further improvements in accuracy are reported upon integrating the two networks using a multiple-output setup, with the overall training and validation accuracies slightly increasing to 98.9%/79.4% and 94.6%/78.1%, respectively, for the two features. The study emphasizes the pivotal role of specific architectural elements, such as the rescaling parameter of the augmentation process, in attaining a satisfactory prediction rate. Lastly, we delve into the potential implications of our findings, which shed light on the potential of machine learning techniques in refining our understanding of wire-rolling processes and guiding the development of more efficient and sustainable manufacturing practices.

Słowa kluczowe

EN

convolutional neural network; cold plastic deformation; machine learning; wire-rolling process; sustainable manufacturing

• Wydawca: Lublin University of Technology ; Polish Society of Ecological Engineering (PTIE), Branch of PTIE in Lublin
• Czasopismo: Advances in Science and Technology. Research Journal
• Rocznik: 2024
• Tom: Vol. 18, no 2
• Strony: 103--114
• Opis fizyczny: Bibliogr. 26 poz., fig., tab.

Twórcy

autor

Capelin Matheus

• Escola de Engenharia de Lorena, Universidade de São Paulo, 12602-810, Lorena, SP, Brazil

• https://orcid.org/0009-0004-1360-0096

autor

Martinez Gustavo A.S.

• Escola de Engenharia de Lorena, Universidade de São Paulo, 12602-810, Lorena, SP, Brazil

• https://orcid.org/0000-0002-7870-9269

autor

Xin Yutao

• Instituto de Física, Universidade Federal Fluminense, 24210-346, Niterói-RJ, Brazil

autor

Siqueira Adriano F.

• Escola de Engenharia de Lorena, Universidade de São Paulo, 12602-810, Lorena, SP, Brazil

autor

Qian Wei-Liang

• Escola de Engenharia de Lorena, Universidade de São Paulo, 12602-810, Lorena, SP, Brazil
• Faculdade de Engenharia de Guaratinguetá, Universidade Estadual Paulista, 12516-410, Guaratinguetá, SP, Brazil
• Center for Gravitation and Cosmology, College of Physical Science and Technology, Yangzhou University, Yangzhou 225009, China

• https://orcid.org/0000-0002-3450-1984

Bibliografia

• 1. Asakawa M, Shigeta H, Shimizu A, Tirtom I, Yanagimoto J. Experiments on and finite element analyses of the tilting of fine steel wire in roller die drawing. ISIJ international. 2013 Oct 15; 53(10): 1850-7. DOI: 10.2355/isijinternational.53.1850
• 2. Shukur JJ, Khudhir WS, Abbood MQ. Analysis of tool geometry and lubrication conditions effect on the forming load during wire drawing process. Advances in Science and Technology. Research Journal. 2022; 16(4). DOI: 10.12913/22998624/152934
• 3. Kesavulu P, Ravindrareddy G. Analysis and optimization of wire drawing process. Int. J. Eng. Res. Technol. 2014; 3(9).
• 4. El Amine K, Larsson J, Pejryd L. Experimental comparison of roller die and conventional wire drawing. Journal of Materials Processing Technology. 2018 Jul 1; 257: 7-14. DOI: 10.1016/j.jmatprotec.2018.02.012
• 5. Ekkelenkamp JH, Khsrovabadi PB. Design and manufacture of a roller die system for wire drawing. Wire Journal International, December. 1989.
• 6. Zinutti A. Cold rolling of small diameter steel wires. Wire J. Int.. 1996; 29: 78-84.
• 7. Pilarczyk JW, Dyja H, Golis B, Tabuda E. Effect of roller die drawing on structure, texture and other properties of high carbon steel wires. Metals and Materials. 1998 Aug; 4: 727-731.
• 8. Bitkov V. Expediency of roller dies application in fire drawing-Part1. Wire Cable Technol.. 2008; 36(1): 58-60.
• 9. Goodfellow, Y. Bengio, A. Courville, Deep Learning (MIT Press, 2016), http://www.deeplearningbook.org.
• 10. Setio AA, Ciompi F, Litjens G, Gerke P, Jacobs C, Van Riel SJ, Wille MM, Naqibullah M, Sánchez CI, Van Ginneken B. Pulmonary nodule detection in CT images: false positive reduction using multiview convolutional networks. IEEE transactions on medical imaging. 2016 Mar 1; 35(5): 1160-1169. DOI: 10.1109/TMI.2016.2536809
• 11. Kang, K. Liu, B. Hou, N. Zhang, PLoS ONE 2017; 11: e0188290. DOI: 10.1371/journal.pone.0188290
• 12. Lakhani P, Sundaram B. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology. 2017 Aug; 284(2): 574-582. DOI: 10.1148/radiol.2017162326
• 13. Yasaka K, Akai H, Abe O, Kiryu S. Deep learning with convolutional neural network for differentiation of liver masses at dynamic contrast-enhanced CT: a preliminary study. Radiology. 2018 Mar; 286(3): 887-896. DOI: 10.1148/radiol.2017170706
• 14. Yamashita R, Nishio M, Do RK, Togashi K. Convolutional neural networks: an overview and application in radiology. Insights into imaging. 2018 Aug; 9: 611-629. DOI: 10.1007/s13244-018-0639-9
• 15. Browne M, and Ghidary SS. Convolutional neural networks for image processing: an application in robot vision. In: Australasian Joint Conference on Artificial Intelligence. Berlin, Heidelberg: Springer Berlin Heidelberg, 2003 Dec 3, 641-652. DOI: 10.1007/978-3-540-24581-0_55
• 16. Gu J, Wang Z, Kuen J, Ma L, Shahroudy A, Shuai B, Liu T, Wang X, Wang G, Cai J, Chen T. Recent advances in convolutional neural networks. Pattern Recognition. 2018 May 1; 77: 354-77. DOI: 10.1016/j.patcog.2017.10.013
• 17. Hong S, You T, Kwak S, Han B. Online tracking by learning discriminative saliency map with convolutional neural network. In: International Conference on Machine Learning, PMLR, 2015 Jun 1, 597-606. DOI: 10.48550/arXiv.1502.06796
• 18. Li H, Li Y, Porikli F. Deeptrack: Learning discriminative feature representations online for robust visual tracking. IEEE Transactions on Image Processing 2015; 25(4): 1834-1848. DOI: 10.48550/arXiv.1503.00072
• 19. Chen Y, Yang X, Zhong B, Pan S, Chen D, Zhang H. CNN Tracker: Online discriminative object tracking via deep convolutional neural network. Applied Soft Computing. 2016 Jan 1; 38: 1088-98.
• 20. Capelin M, Rodrigues AD, Monteiro GD, Martinez GA, Eleno LT, Qian WL. Clasificación de procesos de deformación plástica de alambre mediante redes neuronales convolucionales. DYNA New Technologies. 2023 Jan 1; 10(1): pp. 12. DOI: 10.6036/NT10918
• 21. Nebbar MC, Zidani M, Djimaoui T, Abid T, Farh H, Ziar T, Helbert AL, Brisset F, Baudin T. Microstructural evolutions and mechanical properties of drawn medium carbon steel wire. International Journal of Engineering Research in Africa. 2019 Mar 25; 41: 1-7. DOI: 10.4028/www.scientific.net/JERA.41.1
• 22. Djimaoui T, Zidani M, Nebbar MC, Abid T, Farh H, Helbert AL, Brisset F, Baudin T. Study of microstructural and mechanical behavior of mild steel wires cold drawn at TREFISOUD. International Journal of Engineering Research in Africa 2018 Aug 1; 36: 53-59. DOI: 10.4028/www.scientific.net/JERA.36.53
• 23. Zhou LC, Zhao YF, Fang F. Effect of reserved texture on mechanical properties of cold drawn pearlitic steel wire. Advanced Materials Research 2014 Jul 9; 936: 1948-1452. DOI: 10.4028/www.scientific.net/AMR.936.1948
• 24. Zhang X, Godfrey A, Hansen N, Huang X. Hierarchical structures in cold-drawn pearlitic steel wire. Acta Materialia 2013 Aug 1; 61(13): 4898-4909. DOI: 10.1016/j.actamat.2013.04.057
• 25. Cao TS, Vachey C, Montmitonnet P, Bouchard PO. Comparison of reduction ability between multistage cold drawing and rolling of stainless steel wire – Experimental and numerical investigations of damage. Journal of Materials Processing Technology 2015 Mar 1; 217: 30-47. DOI: 10.1016/j.jmatprotec.2014.10.020
• 26. Bitkov V. Expediency of roller dies application in wire drawing – Part 2. Wire Cable Technology 2008; 36(3): 112-113.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).