Machine Learning-Based Surface Roughness Prediction in Turning of Hardened AISI 4340 Steels: Incorporating Tool Wear via Cutting Length

A.  Ginting; M.S.  Kasim; B.T. Hang Tuah  Baharudin

doi:10.6180/jase.202601_29(1).0003

Machine Learning-Based Surface Roughness Prediction in Turning of Hardened AISI 4340 Steels: Incorporating Tool Wear via Cutting Length

A. Ginting¹This email address is being protected from spambots. You need JavaScript enabled to view it., M.S. Kasim², and B.T. Hang Tuah Baharudin³

¹Laboratory of Machining Processes, Department of Mechanical Engineering, Faculty of Engineering, Universitas Sumatera Utara, Jalan Almamater, J17.01.01, Kampus USU, 20155, Medan, Indonesia

²CADCAM Research Group, Faculty of Innovative Design and Technology, Universiti Sultan Zainal Abidin, Kampus Gong Badak, 23100, Kuala Nerus, Terengganu, Malaysia

³Department of Mechanical and Manufacturing Engineering, Faculty of Engineering, Universiti Putra Malaysia, 43400, UPM Selangor, Selangor Darul Ehsan, Malaysia

Received: July 30, 2024
Accepted: March 3, 2025
Publication Date: April 30, 2025

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202601_29(1).0003

This study explores the predictive modeling of surface roughness in the hard turning of AISI 4340 steel using machine learning techniques, specifically Random Forest (RF) and Gaussian Process Regression (GPR). The uncoated carbide was used and the experimental design considered varying cutting speeds (70, 90, 110 m/min), feeds (0.14, 0.16, 0.22 mm/rev), depths of cut ( 0.25, 0.5 mm), and cutting length (80, 160,240 mm) to account for tool wear as an uncontrollable factor. The RF model achieved an RMSE of 0.1627µ m and an R² value of 0.9718, while the GPR model had an RMSE of 0.1676µ m and an R² value of 0.8333. The novelty of this study lies in considering the influence of tool wear via cutting length, significantly impacting the RMSE of the GPR model. Using K-fold cross-validation (K=7) on a 50% training dataset resulted in the lowest RMSE values for both models. Despite the GPR model’s slightly lower performance, it demonstrated robustness and consistency across different cross-validation splits and random states, making it a reliable option for predicting surface roughness. This research provides insights into the application of machine learning for process optimization in hard turning operations, highlighting the importance of tool wear and training dataset size. Future work could extend these findings to other machining processes and material types to validate the models’ robustness and generalizability.

Keywords: Cutting length; Gaussian Process Regression; Hard turning; Model performance; Random Forest.

[1] W.König, R. Komanduri, H. Toenshoff, and G. Ack ershott, (1984) “Machining of hard materials" CIRP annals 33(2): 417–427. DOI: 10.1016/s0007-8506(16)30164-0.
[2] H. K. Toenshoff, C. Arendt, and R. B. Amor, (2000) “Cutting of hardened steel" Cirp Annals 49(2): 547–566. DOI: 10.1016/S0007-8506(07)63455-6.
[3] R. de Souza Ruzzi, L. R. R. da Silva, R. B. da Silva, W. M.daSilva Junior, and E. C. Bianchi, (2020) “To pographical analysis of machined surfaces after grinding with different cooling-lubrication techniques" Tribology International 141: 105962. DOI: 10.1016/j.triboint.2019.105962.
[4] K. S. S. Lopes, W. F. Sales, and E. S. Palma, (2008) “Influence of machining parameters on fatigue endurance limit of AISI 4140 steel" Journal of the Brazilian So ciety of Mechanical Sciences and Engineering 30: 77–83. DOI: 10.1590/S1678-58782008000100011.
[5] Y. L. Lee, J. Pan, R. B. Hathaway, and M. E. Barkey. Fatigue testing and analysis: Theory and practice. 2004. DOI: 10.1016/B978-0-7506-7719-6.X5000-3.
[6] W.F. Sales, J. Schoop, L. R. da Silva, Á. R. Machado, and I. S. Jawahir. A review of surface integrity in machining of hardened steels. 2020. DOI: 10.1016/j.jmapro.2020.07.040.
[7] S.S.Sarjana, I. Bencheikh, M. Nouari, and A. Ginting, (2020) “Study on cutting performance of cermet tool in turning of hardened alloy steel" International Journal of Refractory Metals and Hard Materials 91: DOI: 10.1016/j.ijrmhm.2020.105255.
[8] M.H.S.Elmunafi, D. Kurniawan, and M. Noordin, (2015) “Use of Castor Oil as Cutting Fluid in Machining of Hardened Stainless Steel with Minimum Quantity of Lubricant" Procedia CIRP 26: 408–411. DOI: 10.1016/j.procir.2015.03.001.
[9] A.E.Diniz, J. R. Ferreira, and F. T. Filho, (2003) “Influence of refrigeration/lubrication condition on SAE 52100 hardened steel turning at several cutting speeds" International Journal of Machine Tools and Manufacture 43: DOI: 10.1016/S0890-6955(02)00186-4.
[10] D. A. Axinte and R. C. Dewes, (2002) “Surface integrity of hot work tool steel after high speed milling experimental data and empirical models" Journal of Materials Processing Technology 127: DOI: 10.1016/ S0924-0136(02)00282-0.
[11] Y. B. Guo, W. Li, and I. S. Jawahir, (2009) “Surface integrity characterization and prediction in machining of hardened and difficult-to-machine alloys: A state-of-art research review and analysis" Machining Science and Technology 13: DOI: 10.1080/10910340903454922.
[12] F. Aggogeri, N. Pellegrini, and F. L. Tagliani. Recent advances on machine learning applications in machining processes. 2021. DOI: 10.3390/app11188764.
[13] T. Segreto and R. Teti, (2019) “Machine learning for in-process end-point detection in robot-assisted polishing using multiple sensor monitoring" International Journal of Advanced Manufacturing Technology 103: DOI: 10.1007/s00170-019-03851-7.
[14] J. V. Abellan-Nebot and F. R. Subirón. A review of machining monitoring systems based on artificial intelligence process models. 2010. DOI: 10.1007/s00170-009-2191-8.
[15] V. Nasir and F. Sassani. A review on deep learning in machining and tool monitoring: methods, opportunities, and challenges. 2021. DOI: 10.1007/s00170-021-07325-7.
[16] B.huLi, B.cunHou, W.taoYu, X.bingLu, and C.wei Yang. Applications of artificial intelligence in intelligent manufacturing: a review. 2017. DOI: 10.1631/FITEE.1601885.
[17] J. F. Arinez, Q. Chang, R. X. Gao, C. Xu, and J. Zhang, (2020) “Artificial Intelligence in Advanced Manufacturing: Current Status and Future Outlook" Journal of Manufacturing Science and Engineering, Transactions of the ASME 142: DOI: 10.1115/1.4047855.
[18] M.P.Motta, C. Pelaingre, A. Delamézière, L. B. Ayed, and C. Barlier. “Machine learning models for surface roughness monitoring in machining operations”. In: Procedia CIRP. 108. 2022. DOI: 10.1016/j.procir.2022.03.110.
[19] R. A. Sidabutar. “Pengembangan sistem dan unit Mini mumQuantity Lubrication (MQL) untuk meningkatkan performa pahat pada pemesinan keras". (mathesis). Uni versitas Sumatera Utara, 2021.
[20] I. 1302:2002. ISO 1302-2002: Geometrical Product Speci f ications (GPS)- Indication of surface texture in technical product documentation. Tech. rep. ISO International Standard, 2002.
[21] I. 4288:1998. Geometrical Product Specifications (GPS) —Surface texture: Profile method — Rules and procedures for the assessment of surface texture. Tech. rep. ISO International Standard, 1998.
[22] L. Breiman, (2001) “Random forests" Machine Learn ing 45: 5–32.
[23] M.Schonlau and R. Y. Zou, (2020) “The random forest algorithm for statistical learning" The Stata Journal: Promoting communications on statistics and Stata 20: 3–29. DOI: 10.1177/1536867X20909688.
[24] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cour napeau, M. Brucher, M. Perrot, and É. Duchesnay, (2011) “Scikit-learn: Machine learning in Python" Journal of Machine Learning Research 12:
[25] A. C. Müller and S. Guido. Introduction to Machine Learning with Python and Scikit-Learn. 2015.
[26] P. Jiang and J. Chen, (2016) “Displacement prediction of landslide based on generalized regression neural networks with K-fold cross-validation" Neurocomputing 198: DOI: 10.1016/j.neucom.2015.08.118.
[27] A. Marrel and B. Iooss, (2024) “Probabilistic surrogate modeling by Gaussian process: A review on recent insights in estimation and validation" Reliability Engineering &System Safety 247: 110094. DOI: 10.1016/j.ress.2024.110094.
[28] T. Hastie, R. Tibshirani, and J. Friedman, (2009) “The Elements of Statistical Learning, Second Edition" Springer New York, NY 27:
[29] B. Anandan and M. Manikandan, (2023) “Machine learning approach with various regression models for predicting the ultimate tensile strength of the friction stir welded AA 2050-T8 joints by the K-Fold cross validation method" Materials Today Communications 34: 105286. DOI: 10.1016/j.mtcomm.2022.105286.
[30] A. Rohani, M. Taki, and M. Abdollahpour, (2018) “A novel soft computing model (Gaussian process regression with K-fold cross validation) for daily and monthly solar radiation forecasting (Part: I)" Renewable Energy 115: 411–422. DOI: 10.1016/j.renene.2017.08.061.
[31] G. Jiang and W. Wang, (2017) “Error estimation based on variance analysis of k-fold cross-validation" Pattern Recognition 69: 94–106. DOI: 10.1016/j.patcog.2017.03.025.
[32] V. Dubey, A. K. Sharma, and D. Y. Pimenov, (2022) “Prediction of Surface Roughness Using Machine Learning Approach in MQL Turning of AISI 304 Steel by Varying Nanoparticle Size in the Cutting Fluid" Lubricants 10: DOI: 10.3390/lubricants10050081.

Latest Articles