Advanced Predictive Modelling of Drilling Forces: A Comparative Analysis of Machine Learning Approaches
REST Journal on Emerging trends in Modelling and Manufacturing · 15.08.2026 · 1
DOI: 10.46632/jemm/12/3/1 ↗Kurz gefasst
Fachartikel in der Zeitschrift REST Journal on Emerging trends in Modelling and Manufacturing, online erschienen am 15.08.2026. Verfasst von Naga Sivamma N. Die Arbeit nennt 21 Literaturangaben.
Abstract (Originalsprache)
This paper explores methods for predicting drilling forces in manufacturing processes without relying on expensive experimental tests. Three main approaches are explored: phenomenological modelling from experimental data, numerical drilling models, and analytical techniques based on plasticity theory. The study highlights challenges in drilling operations, including delamination in composite materials, issues in high-speed machining, and optimizing drilling parameters for metal matrix composites. We review the applications of artificial intelligence tools, especially fuzzy logic and neural networks, enhanced with genetic algorithms, to model thrust forces and torque during drilling operations. Research demonstrates that the drill diameter significantly affects the torque, while the drill tip angle has the largest impact on the force of thrust. When drilling aluminium alloy, factors including feed rate, cutting speed, and cutter type directly affect drilling time and costs. For composite materials, we analyse methods to reduce delamination by optimizing drilling conditions and tool geometry. Support vector regression, random forest regression, and linear regression are examples of machine learning techniques are evaluated for their effectiveness in predicting drilling performance metrics. These findings provide valuable insights for industries seeking to optimize drilling operations, reduce production waste, and improve machine efficiency without relying on prototype testing.
Zitieren
APA
N, N. S. (2026). Advanced Predictive Modelling of Drilling Forces: A Comparative Analysis of Machine Learning Approaches. REST Journal on Emerging trends in Modelling and Manufacturing, 1. https://doi.org/10.46632/jemm/12/3/1
Vancouver
N NS. Advanced Predictive Modelling of Drilling Forces: A Comparative Analysis of Machine Learning Approaches. REST Journal on Emerging trends in Modelling and Manufacturing. 2026:1. doi:10.46632/jemm/12/3/1
BibTeX
@article{N2026,
author = {N, Naga Sivamma},
title = {Advanced Predictive Modelling of Drilling Forces: A Comparative Analysis of Machine Learning Approaches},
journal = {REST Journal on Emerging trends in Modelling and Manufacturing},
year = {2026},
pages = {1},
doi = {10.46632/jemm/12/3/1}
}
EUVIMED