Comparative Study on Different CNN Architectures Developed on Microstructural Classification in Al-Si Alloys

• Autorzy: Kalkan Mahmut Furkan , Aladag Mehmet , Kurzydlowski Krzysztof J. , Yilmaz Necip Fazil , Yavuz Abdulcabbar

Identyfikatory

DOI

10.24425/amm.2024.149784

• Języki publikacji: EN

Abstrakty

EN

Recent advances in artificial intelligence have opened up new avenues for microstructure characterization, notably in metallic materials. Physical and mechanical properties generally depend on the microstructure of the metallic material. On the other hand, microstructural characterization takes time and calls for specific techniques that don’t always lead to conclusive results quickly. To address this issue, this research focuses on the application of artificial intelligence approaches to microstructural categorization. We demonstrate the advantages of the AI approach using an example of Al-Si alloy, a material that is widely employed in a variety of industries. To specify a suitable convolutional neural network (CNN) approach for the microstructural classification of the Al-Si alloy, CNN models were trained and compared using DenseNet201, Inception v3, InceptionResNetV2, ResNet152V2, VGG16, and Xception architectures. Resulting from the comparison, it was determined that the developed supervised transfer learning model can execute the microstructural classification of Al-Si alloy microstructural images. This paper is an attempt to advance methods of microstructure recognition/classification/characterization by using Deep Learning approaches. The significance of the established model is demonstrated and its accordance with the literature data. Also, necessity is shown of developing material models and optimization through systematic microstructural investigation, production conditions, and material attributes.

Słowa kluczowe

EN

artificial intelligence; microstructural characterization; Al-Si alloy; convolutional neural network; CNN; material classification

• Wydawca: Institute of Metallurgy and Materials Science of Polish Academy of Sciences ; Committee of Materials Engineering and Metallurgy of Polish Academy of Sciences
• Czasopismo: Archives of Metallurgy and Materials
• Rocznik: 2024
• Tom: Vol. 69, iss. 2
• Strony: 563--570
• Opis fizyczny: Bibliogr. 40 poz., fot., rys.

Twórcy

autor

Kalkan Mahmut Furkan

• Gaziantep University, Faculty of Engineering, Department of Mechanical Engineering, 27310, Sehitkamil, Gaziantep, Turkiye

• https://orcid.org/0000-0002-1903-5583

autor

Aladag Mehmet

• Bialystok University of Technology, Faculty of Mechanical Engineering, Wiejska 45C, 15-351 Bialystok, Poland

• https://orcid.org/0000-0002-2484-7519

autor

Kurzydlowski Krzysztof J.

• Bialystok University of Technology, Faculty of Mechanical Engineering, Wiejska 45C, 15-351 Bialystok, Poland

• https://orcid.org/0000-0003-3875-4820

autor

Yilmaz Necip Fazil

• Gaziantep University, Faculty of Engineering, Department of Mechanical Engineering, 27310, Sehitkamil, Gaziantep, Turkiye
• Hasan Kalyoncu University, Board of Trustees, 27410 Gaziantep, Turkey

• https://orcid.org/0000-0002-0166-9799

autor

Yavuz Abdulcabbar

• Gaziantep University, Faculty of Engineering, Department of Metallurgical and Materials Engineering, 27310, Sehitkamil, Gaziantep, Turkiye

• https://orcid.org/0000-0002-7216-0586

Bibliografia

• [1] M. Yilmaz, H.I. Kurt, N.F. Yilmaz, Manufacturing and Characterization of Al-XMg-XMgO Composites Using Stir Casting Process. Int. J. Met. 17 (3), 2308-2322 (2023). DOI: https://doi.org/10.1007/s40962-022-00946-y
• [2] Z. Qiu, K. Sugio, G. Sasaki, Classification of Microstructures of Al-Si Casting Alloy in Different Cooling Rates with Machine Learning Technique. Mater. Trans. 62 (6), 719-725 (2021). DOI: https://doi.org/10.2320/matertrans.MT-MBW2020002
• [3] K.J. Kurzydlowski, B. Ralph, The Quantitative Description of the Microstructure of Materials, 1995 CRC Press.
• [4] S.P. Mishra, M.R.A. Rahul, Comparative Study and Development of a Novel Deep Learning Architecture for Accelerated Identification of Microstructure in Materials Science. Comput. Mater. Sci. 200, 110815 (2021)
• [5] E.A. Holm, R. Cohn, N. Gao, A.R. Kitahara, T.P. Matson, B. Lei, S.R. Yarasi, Overview: Computer Vision and Machine Learning for Microstructural Characterization and Analysis. Metall. Mater. Trans. A Phys. Metall. Mater. Sci. 51 (12), 5985-5999 (2020). DOI: https://doi.org/10.1007/s11661-020-06008-4
• [6] K. Tsutsui, K. Matsumoto, M. Maeda, T. Takatsu, K. Moriguchi, K. Hayashi, S. Morito, H. Terasaki, Mixing Effects of SEM Imaging Conditions on Convolutional Neural Network-Based Low-Carbon Steel Classification. Mater. Today Commun. 32 (July), 104062 (2022). DOI: https://doi.org/10.1016/j.mtcomm.2022.104062
• [7] A. Cheloee Darabi, S. Rastgordani, M. Khoshbin, V. Guski, S. Schamuder, Hybrid Data-Driven Deep Learning Framework for Material Mechanical Properties Prediction with the Focus on Dual-Phase Steel Microstructures. Mater. 16 (1), 447 (2023). DOI: https://doi.org/10.3390/MA16010447
• [8] Z.L. Wang, Y. Adachi, Property Prediction and Properties-to-Microstructure Inverse Analysis of Steels by a Machine-Learning Approach. Mater. Sci. Eng. A. 744, 661-670 (2019). DOI: https://doi.org/10.1016/j.msea.2018.12.049
• [9] A. Chowdhury, E. Kautz, B. Yener, D. Lewis, Image Driven Machine Learning Methods for Microstructure Recognition. Comput. Mater. Sci. 123, 176-187 (2016). DOI: https://doi.org/10.1016/j.commatsci.2016.05.034
• [10] M. Ji, M. Yang, S. Soghrati, Deep Learning Model to Predict the Failure Response of Steel Pipes under Pitting Corrosion. Comput. Mech. 71 (2), 293-310 (2022). DOI: https://doi.org/10.1007/s00466-022-02238-y
• [11] A. Agrawal, Choudhary, Deep Materials Informatics: Applications of Deep Learning in Materials Science. MRS Commun. 9 (3), 779-792 (2019). DOI: https://doi.org/10.1557/mrc.2019.73
• [12] V.C. Shunmugasamy, E. Khalid, B. Mansoor, Friction Stir Extrusion of Ultra-Thin Wall Biodegradable Magnesium Alloy Tubes - Microstructure and Corrosion Response. Mater. Today Commun. 26, 102129 (2021). DOI: https://doi.org/10.1016/j.mtcomm.2021.102129
• [13] B. Gallagher, M. Rever, D. Loveland, T.N. Mundhenk, B. Beauchamp, E. Robertson, G.G. Jaman, A.M. Hiszpanski, T.Y.J. Han, Predicting Compressive Strength of Consolidated Molecular Solids Using Computer Vision and Deep Learning. Mater. Des. 190, 108541 (2020). DOI: https://doi.org/10.1016/j.matdes.2020.108541
• [14] C. Shen, X. Wei, C. Wang, W. Xu, A Deep Learning Method for Extensible Microstructural Quantification of DP Steel Enhanced by Physical Metallurgy-Guided Data Augmentation. Mater. Charact. 180, 111392 (2021). DOI: https://doi.org/10.1016/j.matchar.2021.111392
• [15] S. Feng, H. Fu, H. Zhou, Y. Wu, Z. Lu, H.A. Dong, A General and Transferable Deep Learning Framework for Predicting Phase Formation in Materials. npj Comput. Mater. 7 (1), 1-10 (2021). DOI: https://doi.org/10.1038/s41524-020-00488-z
• [16] E. Maggiori, Y. Tarabalka, G. Charpiat, P. Alliez, Convolutional Neural Networks for Large-Scale Remote-Sensing Image Classification. IEEE Trans. Geosci. Remote Sens. 55 (2), 645-657 (2017). DOI: https://doi.org/10.1109/TGRS.2016.2612821
• [17] F. Chollet, Xception: Deep Learning with Depthwise Separable Convolutions. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1800-1807 (2017). DOI: https://doi.org/10.1109/cvpr.2017.195
• [18] M. Shafiq, Z. Gu, Deep Residual Learning for Image Recognition: A Survey. Appl. Sci. 12 (18), 8972 (2022). DOI: https://doi.org/10.3390/APP12188972
• [19] C. Szegedy, S. Loffe, V. Vanhoucke, A.A. Alemi, Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. Proc. AAAI Conf. Artif. Intell. 31 (1), 4278-4284 (2017). DOI: https://doi.org/10.1609/AAAI.V31I1.11231
• [20] T. Lu, B. Han, L. Chen, F. Yu, C. Xue, A Generic Intelligent Tomato Classification System for Practical Applications Using DenseNet-201 with Transfer Learning. Sci. Rep. 11 (1), 15824 (2021). DOI: https://doi.org/10.1038/s41598-021-95218-w
• [21] H. Barhoumi, S. Souissi, M.B. Amar, F. Elhalouani, Study on the Effect of Pressure and Cooling Rate on the Solidification Characteristics and Mechanical Properties of Al-11% Si Cast Alloy. J. Mater. Env. Sci. 10 (8), 696-705 (2019).
• [22] T.H. Ludwig, P.L. Schaffer, L. Arnberg, Influence of Some Trace Elements on Solidification Path and Microstructure of Al-Si Foundry Alloys. Metall. Mater. Trans. A. 44, 3783-3796 (2013).
• [23] K. Wang, P. Tang, Y. Huang, Y. Zhao, W. Li, J. Tian, Characterization of Microstructures and Tensile Properties of Recycled Al-Si-Cu-Fe-Mn Alloys with Individual and Combined addition of Titanium and Cerium. Scanning. 2018 (2018).
• [24] Schmitz Metallographie GmbH Microstructure Database; 2023.
• [25] R. Romankiewicz, F. Romankiewicz, Influence of Modification on the Refinement of Primary Silicon Crystals in Hypereutectic Silumin AlSi21CuNi. Prod. Eng. Arch. 19 (19), 30-36 (2018).
• [26] Zambon, Phosphorus Modification in Al-Si Hypereutectic Alloys. NTNU 2016.
• [27] F. Yu, J. Pei, K. He, D. Zhao, L. Zuo, Solidification Microstructure and Temperature Field During Direct Chill Casting of Al-16Si Alloy. Trans. Indian Inst. Met. 62, 347-351 (2009).
• [28] P. Chokermorh, P. Pandee, C. Limmaneevichitr, Role of Scandium additions in Primary Silicon Refinement of Hypereutectic Al-20Si Alloys. Int. J. Cast Met. Res. 31 (5), 269-278 (2018).
• [29] A. Radjai, K. Miwa, T. Nishio, An Investigation of the Effects Caused by Electromagnetic Vibrations in a Hypereutectic Al-Si Alloy Melt. Metall. Mater. Trans. A. 29, 1477-1484 (1998).
• [30] P. Jiandon, S. Talangkun, Microstructural Modification Hardness and Surface Roughness of hypereutectic Al-Si Alloys by a Combination of Bismuth and Phosphorus. Crystals. 12 (8), 1026 (2022).
• [31] J. Abboud, J. Mazumder, Developing of Nano Sized Fibrous Eutectic Silicon in Hypereutectic Al-Si Alloy by Laser Remelting. Sci. Rep. 10 (1), 1-18 (2020).
• [32] R. Pastirčák, J. Ščury, J. Moravec, The Effects of Pressure During the Crystallization on Properties of the AlSi12 Alloy. Arch. Foundry Eng. 17 (3), 103-106 (2017). DOI: https://doi.org/10.1515/afe-2017-0099
• [33] R. Pastirčák, M. Brůna, D. Bolibruchová. The Influence of Different Wall Thicknesses of the Casting in the Direct Squeeze Casting. Arch. Foundry Eng. 19 (1), 19-24 (2019). DOI: https://doi.org/10.24425/afe.2018.125185
• [34] E.M. Elgallad, H.W. Doty, S.A. Alkahtani, F.H. Samuel, Effects of La and Ce addition on the Modification of Al-Si Based Alloys. Adv. Mater. Sci. Eng. (2016). DOI: https://doi.org/10.1155/2016/5027243
• [35] M.G. Day, A. Hellawell, The Microstructure and Crystallography of Aluminium - Silicon Eutectic Alloys. Proc. R. Soc. London. Ser. A. Math. Phys. Sci. 305 (1483), 473-491 (1968).
• [36] J. Lemley, S. Bazrafkan, P. Corcoran, Smart Augmentation Learning an Optimal Data Augmentation Strategy. IEEE Access. 5, 5858-5869 (2017). DOI: https://doi.org/10.1109/ACCESS.2017.2696121
• [37] E.C. Too, L. Yujian, S. Njuki, L.A. Yingchun, A Comparative Study of Fine-Tuning Deep Learning Models for Plant Disease Identification. Comput. Electron. Agric. 161, 272-279 (2019). DOI: https://doi.org/10.1016/j.compag.2018.03.032
• [38] F. Chen, J.U. Thou, Assessing the Effects of Convolutional Neural Network Architectural Factors on Model Performance for Remote Sensing Image Classification: An in-Depth Investigation. Int. J. Appl. Earth Obs. Geoinf. 112 ,102865 (2022). DOI: https://doi.org/10.1016/j.jag.2022.102865
• [39] M. Hossin, M.N. Sulaiman, A Review on Evaluation Metrics for Data Classification Evaluations. Int. J. Data Min. Knowl. Manag. Process. 5 (2), 1-11 (2015). DOI: https://doi.org/10.5121/ijdkp.2015.5201
• [40] D. Krstinić, M. Braović, L. Šerić, D. Božić-Štulić, Multi-Label Classifier Performance Evaluation with Confusion Matrix. Comput. Sci. Inf. Technol. 2020, 1-14 (2020). DOI: https://doi.org/10.5121/csit.2020.100801