ENHANCED PRODUCTION QUALITY PREDICTION IN COLD ROLLING PROCESSES USING TABTRANSFORMER AND MACHINE LEARNING ALGORITHMS

Year 2025, Volume: 26 Issue: 2, 112 - 131, 25.06.2025

Yavuz Selim Balcıoğlu , Semih Göksu , Bülent Sezen

https://doi.org/10.18038/estubtda.1590581

Abstract

In this study, the impact of production parameters on product quality in cold rolling processes was examined, and the qualitative status of products was predicted using machine learning algorithms. While existing literature focuses on production efficiency, this study stands out by systematically comparing eight different machine learning algorithms: Decision Tree, KNN, Naive Bayes, Logistic Regression, Random Forest, XGBoost, Support Vector Machines, and TabTransformer. The results reveal that TabTransformer, a transformer-based model designed for tabular data, outperforms the other algorithms in terms of accuracy and generalization capability, making significant contributions to the automation of quality control in production processes. Additionally, feature importance analysis provides critical insights into parameter optimization, making this study a valuable addition to the literature on industrial quality prediction.

Keywords

Quality prediction , Cold rolling , Tabtransformer , Machine learning

References

• [1] Marchi B, Zanoni S, Jaber MY. Economic production quantity model with learning in production, quality, reliability and energy efficiency. Computers & Industrial Engineering. 2019; 129: 502-511.
• [2] Qorbani D, Grösser S. The impact of Industry 4.0 technologies on production and supply chains. arXiv preprint arXiv:2004.06983. 2020.
• [3] Rüttimann BG, Stöckli MT. From batch & queue to industry 4.0-type manufacturing systems: a taxonomy of alternative production models. Journal of Service Science and Management. 2020; 13(2): 299-316.
• [4] Carneiro F, Azevedo A. A six sigma approach applied to the analysis of variability of an industrial process in the field of the food industry. In: 2017 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM). December 2017: 1672-1679.
• [5] Pulakanam V. Responsibility for product quality problems in sequential manufacturing: a case study from the meat industry. Quality Management Journal. 2011; 18(1): 7-22.
• [6] Niemiec K, Krenczyk D. Selected quality indicators and methods of their measurement. In: IOP Conference Series: Materials Science and Engineering. August 2018; 400(2): 022039.
• [7] Tchigirinsky J, Chigirinskaya N, Evtyunin A. Stability assessment methods of technological processes. In: MATEC Web of Conferences. 2021; 346: 03013.
• [8] Kovac D, Vince T, Molnar J, Kovacova I. Modern Internet Based Production Technology. In: Er MJ, ed. New Trends in Technologies: Devices. Computer, Communication and Industrial Systems. In Tech; 2010. DOI: 10.10438.
• [9] Wuest T, Weimer D, Irgens C, Thoben KD. Machine learning in manufacturing: advantages, challenges, and applications. Production & Manufacturing Research. 2016; 4(1): 23-45.
• [10] Kang Z, Catal C, Tekinerdogan B. Machine learning applications in production lines: A systematic literature review. Computers & Industrial Engineering. 2020; 149: 106773..
• [11] Sankhye S, Hu G. Machine learning methods for quality prediction in production. Logistics. 2020; 4(4): 35.
• [12] Ramezani J, Jassbi J. Quality 4.0 in action: smart hybrid fault diagnosis system in plaster production. Processes. 2020; 8(6): 634.
• [13] Maropoulos G. Advanced Data Collection and Analysis in Data Driven Manufacturing Process. Chinese Journal of Mechanical Engineering. 2020; 33(3): 32-52..
• [14] Huang PX, Zhao Z, Liu C, Liu J, Hu W, Wang X. Implementation of an Automated Learning System for Non-experts. arXiv preprint arXiv:2203.15784. 2022.
• [15] Eppinger SD, Huber CD, Pham VH. A methodology for manufacturing process signature analysis. Journal of Manufacturing Systems. 1995; 14(1): 20-34.
• [16] Roh Y, Heo G, Whang SE. A survey on data collection for machine learning: a big data-ai integration perspective. IEEE Transactions on Knowledge and Data Engineering. 2019; 33(4): 1328-1347.
• [17] Liang H, Sun X, Sun Y, Gao Y. Text feature extraction based on deep learning: a review. EURASIP Journal on Wireless Communications and Networking. 2017; 2017: 1-12.
• [18] Wu H, Meng FJ. Review on evaluation criteria of machine learning based on big data. In: Journal of Physics: Conference Series. April 2020; 1486(5): 052026.
• [19] Duan GJ, Yan X. A real-time quality control system based on manufacturing process data. IEEE Access. 2020; 8: 208506-208517.
• [20] Bai Y, Li C, Sun Z, Chen H. Deep neural network for manufacturing quality prediction. In: 2017 Prognostics and System Health Management Conference (PHM-Harbin). July 2017: 1-5.
• [22] Straat M, Koster K, Goet N, Bunte K. An Industry 4.0 example: Real-time quality control for steel-based mass production using Machine Learning on non-invasive sensor data. In: 2022 International Joint Conference on Neural Networks (IJCNN). July 2022: 01-08.
• [23] Kara A. A hybrid prognostic approach based on deep learning for the degradation prediction of machinery. Sakarya University Journal of Computer and Information Sciences. 2021; 4(2): 216-226.
• [24] Hatipoğlu A, Güneri Y, Yılmaz E. A comparative predictive maintenance application based on machine and deep learning. 2024.