Surface Roughness Optimization in Hard Turning of AISI D2 Steel Using RSM and Machine Learning
Keywords:
Ultra-precision machining, Hard turning, Surface roughness prediction, Machine learning, Optimization, AISI D2 SteelAbstract
Ultra-precision hard turning of hardened steels offers a promising alternative to grinding for achieving high surface quality; however, predicting surface roughness remains challenging due to complex parameter interactions. This study investigates the prediction and optimization of surface roughness (Ra) in hard turning of AISI D2 steel (62 HRC) using a cubic boron nitride (CBN) tool. Experiments were conducted by varying cutting speed, feed rate, and depth of cut under controlled conditions. Response Surface Methodology (RSM) was used to model and optimize the process, while machine learning models including Support Vector Machine (SVM), Artificial Neural Network (ANN), Gaussian Process Regression (GPR), and Adaptive Neuro-Fuzzy Inference System (ANFIS) were developed for prediction. Model performance was evaluated using R, RMSE, and MAPE. Results indicate that feed rate is the most significant factor affecting surface roughness, followed by cutting speed, while depth of cut has minimal influence. Among the models, ANFIS achieved the highest accuracy (R = 0.81, RMSE = 0.17). Optimal conditions (Vc = 100 m/min, f = 0.025 mm/rev, ap = 0.09 mm) yielded a minimum surface roughness of 0.207 µm. The integration of RSM and machine learning provides an effective and reliable framework for accurate prediction and optimization in ultra-precision hard turning.
Downloads
References
[1] Gao R.X., Wang L., Helu M., Teti R. (2020) Big data analytics for smart factories of the future. CIRP Annals, 69(2): 668–692.
https://doi.org/10.1016/j.cirp.2020.05.002
[2] Serin G., Sener B., Ozbayoglu A.M., Unver H.O. (2020) Review of tool condition monitoring in machining and opportunities for deep learning. International Journal of Advanced Manufacturing Technology, 109(3–4): 953–974.
https://doi.org/10.1007/s00170-020-05449-w
[3] Takacs M., Farkas B.Z. (2014) Hard cutting of AISI D2 steel. Proceedings of the 3rd International Conference on Mechanical Engineering and Mechatronics, pp. 1–7.
[4] Das S.R., Kumar A., Dhupal D. (2016) Experimental investigation on cutting force and surface roughness in machining of hardened AISI 52100 steel using CBN tool. International Journal of Machining and Machinability of Materials.
https://doi.org/10.1504/IJMMM.2016.078997
[5] Hatefi S., Abou-El-Hossein K. (2020) Review of non-conventional technologies for assisting ultra-precision single-point diamond turning. International Journal of Advanced Manufacturing Technology, 111(9): 2667–2685.
https://doi.org/10.1007/s00170-020-06240-7
[6] Srithar A., Palanikumar K., Durgaprasad B. (2015) Hard turning of AISI D2 steel by polycrystalline cubic boron nitride tools. Applied Mechanics and Materials, 766–767: 649–654. https://doi.org/10.4028/www.scientific.net/AMM.766-767.649
[7] Sirtuli L.J., Boing D., Schroeter R.B. (2019) Evaluation of adhered layer on PCBN tools during turning of AISI D2 steel. International Journal of Refractory Metals and Hard Materials, 84: 104977.
https://doi.org/10.1016/j.ijrmhm.2019.104977
[8] Mia M., Dhar N.R. (2016) Prediction of surface roughness in hard turning using ANN. Measurement, 92: 464–474.
[9] Zhou Z., Chen X., Li E., Zeng L., Luo K., Zhang J. (2022) Edge intelligence: Paving the last mile of artificial intelligence with edge computing. Proceedings of the IEEE, 107(8): 1738–1762.
https://doi.org/10.1109/JPROC.2019.2918951
[10] Patel V.D., Gandhi A.H. (2019) Analysis and modeling of surface roughness based on cutting parameters and tool nose radius in turning of AISI D2 steel using CBN tool. Measurement, 138: 34–38.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Mauli S. Sudake, Aditya A. Pujari, Dr. Avinash Somatkar, Vishal V. Chahare (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles published in the International Research Journal of Innovation in Science and Technology (IRJIST) are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Authors retain the copyright of their work and grant the journal the right of first publication. Proper attribution to the authors and the journal is required for any reuse of the published content.
