Article Sidebar

Download
PDF
Statistic
Read Counter : 0 Download : 0

Main Article Content

Abstract

AI-driven CNC machining optimization requires balancing surface quality and productivity while avoiding unsupported integration of independently collected machining data. This study proposes a leakage-controlled, surrogate-assisted framework using two open datasets: a 27-condition turning surface-quality dataset and a 968-observation milling tool-life dataset comprising 14 tools. The datasets were analyzed independently, with no row-wise fusion or DOC–ADOC mapping. Cutting speed, feed rate, and depth of cut were used as controllable turning variables, while milling sensor and metadata features were used separately for remaining useful life (RUL) prediction. The selected Ridge surface model achieved LOOCV MAE = 0.1077, RMSE = 0.1383, and , while nested validation yielded , indicating limited out-of-sample generalization. The no-cycle RUL model achieved MAE = 23.44 cycles, RMSE = 31.39 cycles, and under leave-one-tool-out validation. NSGA-II significantly outperformed equal-budget random search in normalized hypervolume (0.7711 vs. 0.7421). Because the surrogate surface was statistically limited, continuous optimization was treated as exploratory. Final selection was therefore anchored to measured Pareto-efficient turning conditions. Equal-weight TOPSIS selected , , and , with measured and , as the balanced practical recommendation.

Keywords

CNC machining optimization Surface roughness prediction Tool-health monitoring NSGA-II–TOPSIS

Article Details

How to Cite
Channi, A. S. ., Nalbandh, A. H. ., Madane, A. R. ., Gulati, V. ., Babu, G. R. ., Chandratreya, A. ., & Tripathi, D. (2026). AI-driven multi-objective optimization of CNC machining parameters for enhanced surface finish and tool life. Future Technology, 5(4), 232–245. Retrieved from https://fupubco.com/futech/article/view/1154
Download Citation
Endnote/Zotero/Mendeley (RIS)
BibTeX
Bookmark and Share

References

  1. P. Wu, Y. He, Y. Li, J. He, X. Liu, and Y. Wang, “Multi-objective optimisation of machining process parameters using deep learning-based data-driven genetic algorithm and TOPSIS,” Journal of Manufacturing Systems, vol. 64, pp. 40–52, 2022, doi: 10.1016/j.jmsy.2022.05.016.
  2. G. Serin, B. Sener, A. M. Ozbayoglu, and H. O. Unver, “Review of tool condition monitoring in machining and opportunities for deep learning,” The International Journal of Advanced Manufacturing Technology, vol. 109, no. 3–4, pp. 953–974, 2020, doi: 10.1007/s00170-020-05449-w.
  3. H. Yang, H. Zheng, and T. Zhang, “A review of artificial intelligent methods for machined surface roughness prediction,” Tribology International, vol. 199, Art. no. 109935, 2024, doi: 10.1016/j.triboint.2024.109935.
  4. L. G. P. de Souza, G. A. V. B. Vasconcelos, L. A. R. Costa, M. B. Francisco, A. P. de Paiva, and J. R. Ferreira, “Roughness prediction using machine learning models in hard turning: An approach to avoid rework and scrap,” The International Journal of Advanced Manufacturing Technology, vol. 133, no. 9–10, pp. 4205–4221, 2024, doi: 10.1007/s00170-024-13951-8.
  5. A. T. Nguyen, V. H. Nguyen, T. T. Le, and N. T. Nguyen, “Multiobjective optimization of surface roughness and tool wear in high-speed milling of AA6061 by machine learning and NSGA-II,” Advances in Materials Science and Engineering, vol. 2022, Art. no. 5406570, 2022, doi: 10.1155/2022/5406570.
  6. M. Behzadian, S. K. Otaghsara, M. Yazdani, and J. Ignatius, “A state-of-the-art survey of TOPSIS applications,” Expert Systems with Applications, vol. 39, no. 17, pp. 13051–13069, 2012, doi: 10.1016/j.eswa.2012.05.056.
  7. X. Lu, Y. Zhang, Z. Sun, H. Gu, C. Jiang, and S. Y. Liang, “Multi-objective optimization of cutting parameters for micro-milling nickel-based superalloy thin-walled parts based on improved NSGA-II algorithm,” The International Journal of Advanced Manufacturing Technology, vol. 135, no. 1–2, pp. 775–786, 2024, doi: 10.1007/s00170-024-14478-8.
  8. Z. Zhang, F. Wu, and A. Wu, “Research on multi-objective process parameter optimization method in hard turning based on an improved NSGA-II algorithm,” Processes, vol. 12, no. 5, Art. no. 950, 2024, doi: 10.3390/pr12050950.
  9. A. Gouarir, G. Martínez-Arellano, G. Terrazas, P. Benardos, and S. J. P. C. Ratchev, “In-process tool wear prediction system based on machine learning techniques and force analysis,” Procedia CIRP, vol. 77, pp. 501–504, 2018, doi: 10.1016/j.procir.2018.08.253.
  10. T. Mohanraj, S. Shankar, R. Rajasekar, N. R. Sakthivel, and A. Pramanik, “Tool condition monitoring techniques in milling process—A review,” Journal of Materials Research and Technology, vol. 9, no. 1, pp. 1032–1042, 2020, doi: 10.1016/j.jmrt.2019.10.031.
  11. M. Kuntoğlu, A. Aslan, D. Y. Pimenov, Ü. A. Usca, E. Salur, M. K. Gupta, T. Mikolajczyk, K. Giasin, W. Kapłonek, and S. Sharma, “A review of indirect tool condition monitoring systems and decision-making methods in turning: Critical analysis and trends,” Sensors, vol. 21, no. 1, Art. no. 108, 2021, doi: 10.3390/s21010108.
  12. K. Antosz, E. Kozłowski, J. Sęp, and S. Prucnal, “Application of machine learning to the prediction of surface roughness in the milling process on the basis of sensor signals,” Materials, vol. 18, no. 1, Art. no. 148, 2025, doi: 10.3390/ma18010148.
  13. X. Lu, Y. Zhang, Z. Sun, H. Gu, C. Jiang, and S. Y. Liang, “Multi-objective optimization of cutting parameters for micro-milling nickel-based superalloy thin-walled parts based on improved NSGA-II algorithm,” The International Journal of Advanced Manufacturing Technology, vol. 135, no. 1, pp. 775–786, 2024.
  14. Z. Zhang, F. Wu, and A. Wu, “Research on multi-objective process parameter optimization method in hard turning based on an improved NSGA-II algorithm,” Processes, vol. 12, no. 5, Art. no. 950, 2024.
  15. G. Piecuch and T. Żabinski, “A new open dataset from a milling process—data for classification and estimation of tool life,” figshare, Dataset, 2025, doi: 10.6084/m9.figshare.28589216.v1. The corresponding published data descriptor is also available as Scientific Data, vol. 12, Art. no. 650, 2025, doi: 10.1038/s41597-025-04923-y.
  16. H. Harigovind, B. B. Nair, and N. R. Sakthivel, “A Sensor based turning dataset for data-driven surface roughness estimation,” Mendeley Data, Version 3, 2025, doi: 10.17632/ybyhxv4czd.3.
  17. M. Pasic, D. Marinkovic, D. Lukic, D. Begic-Hajdarevic, A. Zivkovic, M. Milosevic, and K. Muhamedagic, “Prediction and optimization of surface roughness and cutting forces in turning process using ANN, SHAP analysis, and hybrid MCDM method,” Applied Sciences, vol. 14, no. 23, Art. no. 11386, 2024, doi: 10.3390/app142311386.
  18. F. Pashmforoush, A. E. Araghizad, and E. Budak, “Tool wear prediction in milling process using physics-informed machine learning and thermo-mechanical force model with monitoring applications,” Journal of Manufacturing Systems, vol. 82, pp. 1192–1212, 2025, doi: 10.1016/j.jmsy.2025.08.014.
  19. P. Cinat, G. Gnecco, and M. Paggi, “Multi-scale surface roughness optimization through genetic algorithms,” Frontiers in Mechanical Engineering, vol. 6, Art. no. 29, 2020, doi: 10.3389/fmech.2020.00029.
  20. K. Deb and R. B. Agrawal, “Simulated binary crossover for continuous search space,” Complex Systems, vol. 9, no. 2, pp. 115–148, 1995. https://content.wolfram.com/sites/13/2018/02/09-2-2.pdf