Skip to main navigation menu Skip to main content Skip to site footer

August 21, 2026; Liverpool, UK
XI International Scientific and Theoretical Conference «Theoretical and practical scientific achievements: research and results of their implementation»

Papers indexed in Google Scholar

ANALYSIS OF THE USE OF MACHINE LEARNING-BASED SURROGATE MODELS IN THE SELECTION OF OPTIMAL CUTTING CONDITIONS

Published 21.08.2026

  • Artem Syzonov
    • ,
  • Artur Myhovych
    •

Artem Syzonov
Educational and Research Institute of Mechanical Engineering; National Technical University of Ukraine «Igor Sikorsky Kyiv Polytechnic Institute», Ukraine

Artur Myhovych
Educational and Research Institute of Mechanical Engineering; National Technical University of Ukraine «Igor Sikorsky Kyiv Polytechnic Institute», Ukraine

PDF

Abstract

In machining, machine learning (ML) is used to predict surface quality, cutting forces, tool condition, and the dynamic stability of the process. In the optimization of cutting conditions, such predictive models can be used as surrogates, replacing repeated experimental or detailed computational evaluation of candidate conditions. Hybrid approaches combine ML with mechanistic models and experimental, sensor or simulation data. The aim of this work is to review ML surrogates for predicting machining responses and to analyze their use in the optimization of cutting conditions. Data and predicted responses. The composition of the input data in the studies considered depends on the task at hand. To predict machining responses under specified conditions, the inputs typically include spindle speed, feed rate, axial depth of cut, radial width of cut, and tool and material characteristics.

Author Biography

Artem Syzonov

Student

Artur Myhovych

PhD, Assistant

References

  1. Survey on machine learning applied to CNC milling processes / M. Pasandidehpoor et al. Advances in Manufacturing. 2025. Vol. 13. P. 847–885. DOI: 10.1007/s40436-025-00564-x.
  2. On-line chatter detection in milling with hybrid machine learning and physics-based model / M. H. Rahimi, H. N. Huynh, Y. Altintas. CIRP Journal of Manufacturing Science and Technology. 2021. Vol. 35. P. 25–40. DOI: 10.1016/j.cirpj.2021.05.006.
  3. Tool wear prediction in milling process using physics-informed machine learning and thermo-mechanical force model with monitoring applications / F. Pashmforoush, A. Ebrahimi Araghizad, E. Budak. Journal of Manufacturing Systems. 2025. Vol. 82. P. 1192–1212. DOI: 10.1016/j.jmsy.2025.08.014.
  4. Machine learning-based optimization to achieve stable milling conditions with maximum productivity / F. Pashmforoush et al. The International Journal of Advanced Manufacturing Technology. 2025. Vol. 141. P. 5873–5886. DOI: 10.1007/s00170-025-16798-9.
  5. Multiobjective Optimization of Surface Roughness and Tool Wear in High-Speed Milling of AA6061 by Machine Learning and NSGA-II / A. -T. Nguyen et al. Advances in Materials Science and Engineering. 2022. Article 5406570. DOI: 10.1155/2022/5406570.
  6. An ensemble neural network for optimising a CNC milling process / P. G. Mongan et al. Journal of Manufacturing Systems. 2023. Vol. 71. P. 377–389. DOI: 10.1016/j.jmsy.2023.09.012.
  7. Improving milling force predictions: a hybrid approach integrating physics-based simulation and machine learning for remarkable accuracy across diverse unseen materials and tool types / A. Ebrahimi Araghizad et al. Journal of Manufacturing Processes. 2024. Vol. 114. P. 92–107. DOI: 10.1016/j.jmapro.2024.02.001.
  8. A physics-guided data driven method for sensorless measurement of cutting forces using CNC servo drive signals / C.-Y. Tai, Y. Altintas. CIRP Annals. 2026. Vol. 75, No. 1. P. 461–465. DOI: 10.1016/j.cirp.2026.04.015.

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.