Benchmarking Five Machine Learning Models for Accurate Steel Plate Defect Detection
DOI:
https://doi.org/10.31154/cogito.v11i2.753.382-401Keywords:
flaw detection, steel plate, machine learningAbstract
Early detection of defects in steel plates is essential to ensure structural integrity and product quality in the metal manufacturing industry. This study compares the performance of five machine learning algorithms Support Vector Classifier (SVC), Nu-Support Vector Classifier (NuSVC), Decision Tree (DT), Random Forest (RF), and CatBoost (CB) to classify seven categories of steel plate defects using 26 technical features from a publicly available dataset on Kaggle. The preprocessing pipeline included outlier detection (IQR method), class imbalance correction using SMOTE, and feature normalization via StandardScaler. The models were evaluated using classification metrics such as Accuracy, Precision, Recall, F1-Score, ROC-AUC, and Log Loss. Results revealed that the CatBoost algorithm achieved the most balanced and consistent performance, with an AUC of 0.93, accuracy of 68.3%, and the lowest Log Loss value (0.786). In contrast, the Decision Tree showed severe overfitting with perfect training performance but poor generalization (Log Loss = 15.72). This study highlights the promise of CatBoost as an interpretable and efficient solution for automated defect detection in steel manufacturing, while also offering transparent reproducibility pathways for further research.References
V. Raghavan, Materials science and engineering: a first course. PHI Learning Pvt. Ltd., 2015.
J. Sun, J. Li, Y. Jiang, X. Ma, Z. Tan, and G. Zhufu, “Key Construction Technology and Monitoring of Long-Span Steel Box Tied Arch Bridge,” Int. J. Steel Struct., vol. 23, no. 1, pp. 191–207, 2023, doi: 10.1007/s13296-022-00687-y.
N. F. Arenas and M. Shafique, “Reducing embodied carbon emissions of buildings – a key consideration to meet the net zero target,” Sustain. Futur., vol. 7, p. 100166, 2024, doi: https://doi.org/10.1016/j.sftr.2024.100166.
D. Dieter, G. E., & Bacon, Mechanical metallurgy. New York: McGraw-hill, 1976.
Y.-J. Kim, M. Koçak, R. A. Ainsworth, and U. Zerbst, “SINTAP defect assessment procedure for strength mis-matched structures,” Eng. Fract. Mech., vol. 67, no. 6, pp. 529–546, 2000, doi: https://doi.org/10.1016/S0013-7944(00)00072-2.
A. Dorbane, F. Harrou, and Y. Sun, “Detecting Faulty Steel Plates Using Machine Learning BT - Advances in Computing and Data Sciences,” M. Singh, V. Tyagi, P. K. Gupta, J. Flusser, T. Ören, A. R. Cherif, and R. Tomar, Eds., Cham: Springer Nature Switzerland, 2025, pp. 321–333.
C. Hellier, Handbook of nondestructive evaluation. Mcgraw-hill.
R. Yulianto et al., “Innovative UNET-Based Steel Defect Detection Using 5 Pretrained Models,” Evergreen, vol. 10, no. 4, pp. 2365–2378, 2023, doi: 10.5109/7160923.
L. A. O. Martins, F. L. C. Pádua, and P. E. M. Almeida, “Automatic detection of surface defects on rolled steel using Computer Vision and Artificial Neural Networks,” in IECON 2010 - 36th Annual Conference on IEEE Industrial Electronics Society, 2010, pp. 1081–1086. doi: 10.1109/IECON.2010.5675519.
W.-H. Wu, J.-C. Lee, and Y.-M. Wang, “A Study of Defect Detection Techniques for Metallographic Images,” Sensors, vol. 20, no. 19, 2020, doi: 10.3390/s20195593.
F. P. Dharma and M. L. Singgih, “Surface Defect Detection Using Deep Learning: A Comprehensive Investigation and Emerging Trends BT - AI Technologies and Virtual Reality,” K. Nakamatsu, S. Patnaik, and R. Kountchev, Eds., Singapore: Springer Nature Singapore, 2024, pp. 247–260.
A. Saberironaghi, J. Ren, and M. El-Gindy, “Defect Detection Methods for Industrial Products Using Deep Learning Techniques: A Review,” 2023. doi: 10.3390/a16020095.
I. D. Kordatos and P. Benardos, “Comparative analysis of machine learning algorithms for steel plate defect classification,” Int. J. Mechatronics Manuf. Syst., vol. 15, no. 4, pp. 246–263, Jan. 2022, doi: 10.1504/IJMMS.2022.127211.
R. Zaghdoudi, “Detection and classification of steel defects using machine vision and SVM classifier,” no. April 2020, 1945.
P. Damacharla, A. R. M. V., J. Ringenberg, and A. Y. Javaid, “TLU-Net: A Deep Learning Approach for Automatic Steel Surface Defect Detection,” in 2021 International Conference on Applied Artificial Intelligence (ICAPAI), 2021, pp. 1–6. doi: 10.1109/ICAPAI49758.2021.9462060.
Z. Dong, X. Li, F. Luan, and D. Zhang, “Prediction and analysis of key parameters of head deformation of hot-rolled plates based on artificial neural networks,” J. Manuf. Process., vol. 77, pp. 282–300, 2022, doi: https://doi.org/10.1016/j.jmapro.2022.03.022.
P. Hosseinpour, M. Hosseinpour, and Y. Sharifi, “Artificial neural networks for predicting ultimate strength of steel plates with a single circular opening under axial compression,” Ships Offshore Struct., vol. 17, no. 11, pp. 2454–2469, Nov. 2022, doi: 10.1080/17445302.2021.2000265.
T. Trzepieciński and S. M. Najm, “Application of Artificial Neural Networks to the Analysis of Friction Behaviour in a Drawbead Profile in Sheet Metal Forming,” Materials (Basel)., vol. 15, no. 24, 2022, doi: 10.3390/ma15249022.
D. M. Sekban, E. U. Yaylacı, M. E. Özdemir, M. Yaylacı, and A. Tounsi, “Investigating Formability Behavior of Friction Stir-Welded High-Strength Shipbuilding Steel using Experimental, Finite Element, and Artificial Neural Network Methods,” J. Mater. Eng. Perform., vol. 34, no. 6, pp. 4942–4950, 2025, doi: 10.1007/s11665-024-09501-8.
M. Mohammed Sahib and G. Kovács, “Multi-objective optimization of composite sandwich structures using Artificial Neural Networks and Genetic Algorithm,” Results Eng., vol. 21, p. 101937, 2024, doi: https://doi.org/10.1016/j.rineng.2024.101937.
A. I. Kusuma and Y.-M. Huang, “Product quality prediction in pulsed laser cutting of silicon steel sheet using vibration signals and deep neural network,” J. Intell. Manuf., vol. 34, no. 4, pp. 1683–1699, 2023, doi: 10.1007/s10845-021-01881-1.
E. C. Özkat, “A Method to Classify Steel Plate Faults Based on Ensemble Learning TT - Toplu Öğrenmeye Dayalı Çelik Levha Arızalarını Sınıflandırması İçin Bİr Yöntem,” J. Mater. Mechatronics A, vol. 3, no. 2, pp. 240–256, 2022, doi: 10.55546/jmm.1161542.
J.-W. Yun, S.-W. Choi, and E.-B. Lee, “Study on Energy Efficiency and Maintenance Optimization of Run-Out Table in Hot Rolling Mills Using Long Short-Term Memory-Autoencoders,” 2025. doi: 10.3390/en18092295.
A. Dorbane, F. Harrou, and Y. Sun, “Enhancing Defect Detection in Steel Plate Manufacturing with Explainable Machine Learning and SMOTE for Imbalanced Data,” J. Mater. Eng. Perform., vol. 34, no. 10, pp. 9212–9233, 2025, doi: 10.1007/s11665-025-11136-2.
M. Gao, Y. Wei, Z. Li, B. Huang, C. Zheng, and A. Mulati, “A Survey of Machine Learning Algorithms for Defective Steel Plates Classification,” in 8th International Conference on Computing, Control and Industrial Engineering (CCIE2024), Y. S. Shmaliy, Ed., Singapore: Springer Nature Singapore, 2024, pp. 467–476.
C. Zhang, J. Cui, and W. Liu, “Multilayer Feature Extraction of AGCN on Surface Defect Detection of Steel Plates,” Comput. Intell. Neurosci., vol. 2022, no. 1, p. 2549683, Jan. 2022, doi: https://doi.org/10.1155/2022/2549683.
J. Hernavs, T. Peršak, M. Brezočnik, and S. Klančnik, “Hardened workpiece shape prediction using acoustic responses and deep neural network,” Int. J. Adv. Manuf. Technol., vol. 139, no. 9, pp. 5153–5161, 2025, doi: 10.1007/s00170-025-16198-z.
B. Tang, L. Chen, W. Sun, and Z. Lin, “Review of surface defect detection of steel products based on machine vision,” IET Image Process., vol. 17, no. 2, pp. 303–322, Feb. 2023, doi: https://doi.org/10.1049/ipr2.12647.
R. Yulianto et al., “Innovative UNET-Based Steel Defect Detection Using 5 Pretrained Models,” vol. 10, no. 04, pp. 2365–2378, 2023.
A. C. Walter Reade, “Steel Plate Defect Prediction. Kaggle,” kaggle.com. [Online]. Available: https://kaggle.com/competitions/playground-series-s4e3
W. Hastomo, A. S. Bayangkari Karno, N. Kalbuana, A. Meiriki, and Sutarno, “Characteristic Parameters of Epoch Deep Learning to Predict Covid-19 Data in Indonesia,” in Journal of Physics: Conference Series, 2021. doi: 10.1088/1742-6596/1933/1/012050.
A. S. Bayangkari Karno et al., “Classification of cervical spine fractures using 8 variants EfficientNet with transfer learning,” Int. J. Electr. Comput. Eng. (IJECE); Vol 13, No 6 December 2023DO - 10.11591/ijece.v13i6.pp7065-7077 , Dec. 2023, [Online]. Available: https://ijece.iaescore.com/index.php/IJECE/article/view/30669/17032
K. Singh and S. Upadhyaya, “Outlier Detection: Applications And Techniques.,” Int. J. Comput. …, vol. 9, no. 1, pp. 307–323, 2012, [Online]. Available: http://search.ebscohost.com/login.aspxdirect=true&profile=ehost&scope=site&authtype=crawler&jrnl=16940784&AN=73150560&h=i4TJm6g8nLsTJhcyMBIvsybVnJ9dDMRPUQ7ZLZ8lBk76dVDDRAgMCc258zyyjrF/zu+MvvsObGzF2pYu0H1DPg==&crl=c
D. C. Hoaglin, B. Iglewicz, and J. W. Tukey, “Performance of Some Resistant Rules for Outlier Labeling,” J. Am. Stat. Assoc., vol. 81, no. 396, pp. 991–999, Dec. 1986, doi: 10.1080/01621459.1986.10478363.
M. Kuhn, Applied predictive modeling. 2013.
A. Géron, Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow. O’Reilly Media, Inc, 2022.
C. M. Bishop, Pattern recognition and machine learning. Springer google scholar, 2006.
J. Brownlee, “Feature selection for machine learning in Python.,” MachineLearningMastery. com.
“Scikit-learn documentation.” [Online]. Available: https://scikitlearn.org/stable/modules/generated/sklearn.preprocessing. StandardScaler.html
V. Sharma, “A Study on Data Scaling Methods for Machine Learning,” Int. J. Glob. Acad. Sci. Res., vol. 1, no. 1, 2022, doi: 10.55938/ijgasr.v1i1.4.
Y. KATEB, H. MEGLOULI, and A. KHEBLI, “Steel Surface Defect Detection Using Convolutional Neural Network,” Alger. J. Signals Syst., vol. 5, no. 4, pp. 203–208, 2020, doi: 10.51485/ajss.v5i4.122.
L. D. Avendaño-Valencia and S. D. Fassois, “Support Vector Networks,” J. Phys. Conf. Ser., vol. 628, no. 1, pp. 273–297, 2015, doi: 10.1088/1742-6596/628/1/012073.
S. B. Kotsiantis, I. D. Zaharakis, and P. E. Pintelas, “Machine learning: a review of classification and combining techniques,” Artif. Intell. Rev., vol. 26, no. 3, pp. 159–190, 2006, doi: 10.1007/s10462-007-9052-3.
C. W. Hsu, “A Practical Guide to Support Vector Classificatio,” Dep. Comput. Sci. Natl. Taiwan Univ., vol. 17, no. 5, pp. 819–832, 2010, [Online]. Available: http://www.csie.ntu.edu.tw/~cjlin
N. Hütten, M. Alves Gomes, F. Hölken, K. Andricevic, R. Meyes, and T. Meisen, “Deep Learning for Automated Visual Inspection in Manufacturing and Maintenance: A Survey of Open- Access Papers,” Appl. Syst. Innov., vol. 7, no. 1, 2024, doi: 10.3390/asi7010011.
H. Zhang et al., “Surface defect detection of hot rolled steel based on multi-scale feature fusion and attention mechanism residual block,” Sci. Rep., vol. 14, no. 1, p. 7671, 2024, doi: 10.1038/s41598-024-57990-3.
B. Scholkopf, New support vector algorithms, vol. 12. 2000, pp. 1083–1121.
O. Rokach, L., & Maimon, Data mining and knowledge discovery handbook. Springer New York, 2010.
J. R. Quinlan, “J. R. Quinlan,” vol. 5, no. Quinlan 1993, 2006.
L. Breiman, Random forests. Machine learning. 2001.
Tin Kam Ho, “Random Decision Forests,” Proc. 3rd Int. Conf. Doc. Anal. Recognit., pp. 8–12, 1995, [Online]. Available: http://ieeexplore.ieee.org/document/598994/
Y. Yan, “Improve robustness of machine learning via efficient optimization and conformal prediction,” AI Mag., vol. 45, no. 2, pp. 270–279, Jun. 2024, doi: https://doi.org/10.1002/aaai.12173.
L. Prokhorenkova, G. Gusev, A. Vorobev, A. V. Dorogush, and A. Gulin, “CatBoost: unbiased boosting with categorical features,” in Advances in Neural Information Processing Systems, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett, Eds., Curran Associates, Inc., 2018. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2018/file/14491b756b3a51daac41c24863285549-Paper.pdf
A. V. Dorogush, “Tutorials CatBoost,” 2019, [Online]. Available: https://catboost.ai/en/docs/concepts/tutorials
T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, “Optuna: A Next-generation Hyperparameter Optimization Framework,” in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, in KDD ’19. New York, NY, USA: Association for Computing Machinery, 2019, pp. 2623–2631. doi: 10.1145/3292500.3330701.
G. Ke et al., “LightGBM: A Highly Efficient Gradient Boosting Decision Tree,” in Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, Eds., Curran Associates, Inc., 2017. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2017/file/6449f44a102fde848669bdd9eb6b76fa-Paper.pdf
L. Wu, “A meta-learning network method for few-shot multi-class classification problems with numerical data,” Complex Intell. Syst., vol. 10, no. 2, pp. 2639–2652, 2024, doi: 10.1007/s40747-023-01281-3.
D. J. Hand and R. J. Till, “A Simple Generalisation of the Area Under the ROC Curve for Multiple Class Classification Problems,” Mach. Learn., vol. 45, no. 2, pp. 171–186, 2001, doi: 10.1023/A:1010920819831.
R. M. Everson and J. E. Fieldsend, “Multi-class ROC analysis from a multi-objective optimisation perspective,” Pattern Recognit. Lett., vol. 27, no. 8, pp. 918–927, 2006, doi: https://doi.org/10.1016/j.patrec.2005.10.016.
J. Davis and M. Goadrich, “The relationship between Precision-Recall and ROC curves,” in Proceedings of the 23rd International Conference on Machine Learning, in ICML ’06. New York, NY, USA: Association for Computing Machinery, 2006, pp. 233–240. doi: 10.1145/1143844.1143874.
H. Han, J., Pei, J., & Tong, Data mining: concepts and techniques. Morgan kaufmann., 2022.
M. Sokolova and G. Lapalme, “A systematic analysis of performance measures for classification tasks,” Inf. Process. Manag., vol. 45, no. 4, pp. 427–437, 2009, doi: https://doi.org/10.1016/j.ipm.2009.03.002.
D. M. Powers, “Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation,” arXiv Prepr., 2020.
G. Fouché and L. Langit, “Introduction to Data Mining,” G. Fouché and L. Langit, Eds., Berkeley, CA: Apress, 2011, pp. 369–402. doi: 10.1007/978-1-4302-3325-1_14.
C. Goutte and E. Gaussier, “A Probabilistic Interpretation of Precision, Recall and F-Score, with Implication for Evaluation BT - Advances in Information Retrieval,” D. E. Losada and J. M. Fernández-Luna, Eds., Berlin, Heidelberg: Springer Berlin Heidelberg, 2005, pp. 345–359.
R. Huang et al., “A Review on Evaluation Metrics for Data Classification Evaluations,” Med. Image Anal., vol. 80, no. 2, p. 102478, 2022.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 CogITo Smart Journal
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
