Machine Learning Approaches for Classification of Ultra High Carbon Steel Micrographs

Abstract:

The aim of this investigation is to analyze the performance of several supervised machine learning algorithms for solving the automatic classification problem of steel image microstructures. We conducted an experiment using a public-domain dataset of Ultra High Carbon Steel Micrographs (UHCSM). This image database consists of a collection of scanning electron micrographs (SEM) taken from samples of a commercial roll-mill casting with a nominal carbon of 2%. Heat treatments such as annealing, water quenching, air and furnace cooling were performed on steel samples so primary microconstituents could be found in micrographs. Each of these microconstituents defines each of the categories of classification to be accomplished by machine learning algorithms. The heat treatments brought about 4 usable classes (sets of images) of primary microconstituents: pearlite, spheroidite, proeutectoid cementite network, pearlite containing spheroidite. All labeled images are prepared to improve models' accuracy in a preprocessing stage so that the image dataset is ready for feature extraction. In order to develop classification models, we put to the test distinct machine learning approaches by working with Matlab's classification learner application where we perform automated training to search for the best classification model type, including Decision Trees, Support Vector Machines (SVM), Discriminant Analysis, Nearest Neighbors, Naive Bayes, Ensemble k-NN, and Neural Network classification. For obtaining the features of the images (feature extraction) we choose the method of Bag-of-features with 400 words for the first experiment, and 327 words by removing less important features for a second experiment. The experimented models reached very different accuracy values on training, with SVM as the best classifier which gets 91.6% accuracy. We can conclude that classic machine learning algorithms solve the classification, but an accuracy improvement can be reached by investigating deep learning techniques.

• Periodical: Key Engineering Materials (Volume 959)
• Pages: 119-127
• DOI: https://doi.org/10.4028/p-2SqO8w
• Online since: October 2023
• Authors: Jorge Muñoz-Ródenas, Valentín Miguel*, Francisco García-Sevilla, Juana Coello, Alberto Martínez-Martínez
• Keywords: Bag of Features, High Carbon Steel, Machine Learning, Microstructure

References

[1] Bautista-Monsalve, F.; García-Sevilla, F.; Miguel, V.; Naranjo, J.; Manjabacas, M.C. A novel machine-learning-based procedure to determine the surface finish quality of titanium alloy parts obtained by heat assisted single point incremental forming. Metals (2021), 11, 1287

DOI: 10.3390/met11081287

[2] DeCost, B.L., Hecht, M. D., Francis, T., Webler, B.A., Picard, Y. N., and Holm, E.A. Uhcsdb: UltraHigh carbon steel micrograph DataBase: Tools for exploring large heterogeneous microstructure datasets. Integr. Mat. Manuf. Innov (2017) 6, 197–205

DOI: 10.1007/s40192-017-0097-0

[3] DeCost BL, Hecht MD, Francis T, Webler BA, Picard YN, Holm EA Uhcsdb: ultrahigh carbon steel micrograph database. Integr Mater Manuf Innov (2017) 6(2) 197–205.

DOI: 10.1007/s40192-017-0097-0

[4] D.S. Bulgarevich, S. Tsukamoto, T. Kasuya, M. Demura, and M. Watanabe, Pattern recognition with machine learning on optical microscopy images of typical metallurgical microstructures, Sci Rep, (2018) 8(1). https://www.nature.com/articles/s41598-018-20438-6

DOI: 10.1038/s41598-018-20438-6

[5] D.S. Bulgarevich, S. Tsukamoto, T. Kasuya, M. Demura, and M. Watanabe, Automatic steel labeling on certain microstructural constituents with image processing and machine learning tools, Sci. Technol. Adv. Mater. (2019) 20(1), 532–542. https://dx.doi.org/10.1080/ 14686996.2019.1610668

DOI: 10.1080/14686996.2019.1610668

[6] M.  Müller, D. Britz, T. Staudt, and F. Mücklich, Microstructural classification of bainitic subclasses in low-carbon multiphase steels using machine learning techniques, Metals (2021) 11(11) 1836.

DOI: 10.3390/met11111836

[7] K. Tsutsui, H. Terasaki, T. Maemura, K. Hayashi, K. Moriguchi,and S. Morito, Microstructural diagram for steel based on crystallography with machine learning, Comput. Mater. Sci., (2019) 159 403–11.

DOI: 10.1016/j.commatsci.2018.12.003

[8] Muñoz-Rodenas J, García-Sevilla F, Coello-Sobrino J, Martínez-Martínez A, Miguel-Eguía V. Effectiveness of machine-learning and deep-learning strategies for the classification of heat treatments applied to low-carbon steels based on microstructural analysis. Applied Sciences (2023) 13(6):3479

DOI: 10.3390/app13063479

[9] Han, L., Liu, Y., Chen, G., Li, K., Wang, J. and Zhou, R., Formation of Graphite Phase in Powder Metallurgical Ultrahigh Carbon Steels with High Wear Resistance. Adv. Eng. Mater. (2018) 20: 1800002

DOI: 10.1002/adem.201800002

[10] G. Csurka, C. R. Dance, L. Fan, J. Willamowski, and C. Bray, Visual categorization with bags of keypoints, Workshop on Statistical Learning in Computer Vision (2004), 1–22.

[11] E. Nowak, F. Jurie, and B. Triggs, Sampling strategies for bag-of-features image classification, Computer Vision – ECCV Lecture Notes in Computer Science (2006) 3954 490–503

DOI: 10.1007/11744085_38

[12] H. Jégou, M. Douze, C. Schmid, and P. Pérez, Aggregating local descriptors into a compact image representation, 23rd IEEE Conference on Computer Vision & Pattern Recognition (2010) 3304–3311

DOI: 10.1109/CVPR.2010.5540039

[13] H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool, Speeded-up robust features (surf), Comput. Vis. Image Underst (2008) 110(3) 346–359

DOI: 10.1016/j.cviu.2007.09.014

[14] G. Hinton, S. Roweis, Stochastic neighbor embedding, in: Advances in Neural Information Processing Systems (2003) 15 833–840.

[15] L. van der Maaten, G. Hinton, Visualizing data using t-SNE, J. Mach. Learn.Res. (2008) 9 2579-2605.

[16] Peluffo-Ordóñez, D.H., Lee, J.A., Verleysen, M.: Short review of dimensionality reduction methods based on stochastic neighbour embedding. In: Villmann, T., Schleif, F.-M., Kaden, M., Lange, M. (eds.) Advances in Self-Organizing Maps and Learning Vector Quantization. AISC, 295, 65–74. Springer, Cham (2014)

DOI: 10.1007/978-3-319-07695-9_6

[17] Berrendero JR, Cuevas A, Torrecilla JL The mRMRvariable selection method: a comparative study for functional data.J. Stat. Comput. Simul. (2016) 86(5) 891–907.

DOI: 10.1080/00949655.2015.1042378

[18] Peng H., Long F., Ding C. Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy, IEEE Trans. Pattern Anal. Mach. Intell. (2005) 27 (8) 1226-1238.

DOI: 10.1109/tpami.2005.159

[19] C-L Fan, Evaluation of Classification for Project Features with Machine Learning Algorithms, Symmetry (2022)14(2):372

DOI: 10.3390/sym14020372

[20] Fawcett T. An introduction to ROC analysis. Pattern Recognition Letters (2006) 27(8) 861–874.

DOI: 10.1016/j.patrec.2005.10.010

[21] Xu-hui, W., Ping, S., Li, C., Ye, W. (2009). A ROC curve method for performance evaluation of support vector machine with optimization strategy. In 2009 International Forum on Computer Science-Technology and Applications (IEEE) (2009) 2 117–120.

DOI: 10.1109/ifcsta.2009.356