Intelligent Optimization of Drilling Parameters in Polymer Composites using Machine Learning and Metaheuristic Techniques

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2026 | Volume : 14 | 01 | Page :
    By

    V. Priya,

  • V. Balambica,

  • M. Achudhan,

  1. Research Scholar, Department of Mechatronics Engineering, Bharath Institute of Higher Education and Research, Selaiyur, Chennai, Tamil Nadu, India
  2. Professor, Department of Mechanical Engineering, Bharath Institute of Higher Education and Research, Selaiyur, Chennai, Tamil Nadu, India
  3. Associate Professor, Department of Mechanical Engineering, Bharath Institute of Higher Education and Research, Selaiyur, Chennai, Tamil Nadu, India

Abstract

The study tests different ways to use ML and metaheuristic algorithms to determine the best drilling parameters for polymer matrix composites. The research uses a composite matrix made from 55.25% vinyl ester, 44.0% Nickel–Phosphorous coated glass fiber and 0.75% Al₂O₃ nanowires which are tested for tensile strength (64.57 MPa), flexural strength (85.86 MPa) and impact strength (71.79 kJ/m²). By applying a Taguchi orthogonal array, it is observed that a slower spindle, a lower feed rate and a larger drill minimized delamination, thrust force and torque during drilling. Linear regression, ridge regression, Random Forest and Gradient Boosting Regression models were used to estimate the delamination factor. Metaheuristic algorithms, Firefly, PSO, Cuckoo Search, GWO, SALP and Orca, were used to determine the best drilling parameters. The success of the models was judged using MSE and R² and linear and ridge regression gave the best outcomes, both with an MSE of 0.0001 and an R² value of 0.9812. Firefly produced the best delamination result with a DF of 1.3644, whereas PSO and GWO had the best drilling parameters (with a DF of 1.1766). The novelty of this research lies in the integrated use of both machine learning models and metaheuristic optimization techniques to optimize drilling processes in polymer composite materials. This hybrid approach allows for improved prediction accuracy and more efficient parameter tuning. The results demonstrate that PSO and GWO are the most effective algorithms for minimizing delamination in polymer drilling, contributing valuable insights to the field of manufacturing and machining in polymer matrix composites.

Keywords: Ní–P Coated Composites, Delamination Factor (DF), Particle Swarm Optimization (PSO), Grey Wolf Optimization (GWO), Orca Optimization.

How to cite this article:
V. Priya, V. Balambica, M. Achudhan. Intelligent Optimization of Drilling Parameters in Polymer Composites using Machine Learning and Metaheuristic Techniques. Journal of Polymer & Composites. 2026; 14(01):-.
How to cite this URL:
V. Priya, V. Balambica, M. Achudhan. Intelligent Optimization of Drilling Parameters in Polymer Composites using Machine Learning and Metaheuristic Techniques. Journal of Polymer & Composites. 2026; 14(01):-. Available from: https://journals.stmjournals.com/jopc/article=2026/view=239167


References

  1. Bhushi U, Suthar J, Teli SN. Performance analysis of metaheuristics optimization techniques for drilling process on CFRP composites. Mater Today Proc. 2020;28:1106–1114.
  2. Kalita K, Mallick PK, Bhoi AK, Ghadai RK. Optimizing drilling induced delamination in GFRP composites using genetic algorithm and particle swarm optimisation. Adv Compos Lett. 2018;27(1):1–9.
  3. Kumar J, Verma RK, Mondal AK. Taguchi–grey theory-based harmony search algorithm (GR-HSA) for predictive modeling and multi-objective optimization in drilling of polymer composites. Exp Tech. 2021;45:531–548.
  4. Natarajan E, Markandan K, Sekar SM, Varadaraju K, Nesappan S, Albert Selvaraj AD, Lim WH, Franz G. Drilling-induced damages in hybrid carbon and glass fiber-reinforced composite laminate and optimized drilling parameters. J Compos Sci. 2022;6(10):310.
  5. Pendokhare D, Chakraborty S. Parametric optimization of conventional drilling processes using human-based metaheuristic algorithms: A comparative analysis. In: Singh S, Singh I, editors. Advances in Materials and Manufacturing. ICDMT 2024. Lecture Notes in Mechanical Engineering. Singapore: Springer; 2025.
  6. Abd-Elwahed M. Drilling process of GFRP composites: modeling and optimization using hybrid ANN. Sustainability. 2022;14(11):6599.
  7. Soepangkat BOP, Pramujati B, Effendi MK, et al. Multi-objective optimization in drilling Kevlar fiber reinforced polymer using grey fuzzy analysis and backpropagation neural network–genetic algorithm (BPNN–GA) approaches. Int J Precis Eng Manuf. 2019;20:593–607.
  8. Soepangkat BOP, Norcahyo R, Effendi MK, Pramujati B. Multi-response optimization of carbon fiber reinforced polymer (CFRP) drilling using back propagation neural network–particle swarm optimization (BPNN–PSO). Eng Sci Technol Int J. 2020;23(3):700–713.
  9. Taiwo EO, Oke SA, Rajan J, Jose S, Oyetunji EO, Adedeji KA. Optimizing the parameters of carbon fiber reinforced plastic composite drilling process using signal-to-noise ratio-based grey wolf optimization algorithm. Int J Ind Eng Eng Manag. 2024;6(1).
  10. Kayaroganam P, Krishnan V, Natarajan E, Natarajan S, Muthusamy K. Drilling parameters analysis on in-situ Al/B₄C/mica hybrid composite and an integrated optimization approach using fuzzy model and non-dominated sorting genetic algorithm. Metals. 2021;11(12):2060.
  11. Benkhelladi A, Laouissi A, Laouici H, et al. Assessment of hybrid composite drilling and prediction of cutting parameters by ANFIS and deep neural network approach. Int J Adv Manuf Technol. 2024;135:589–606.
  12. Mahmood ZN, Al-Khazraji H, Mahdi SM. Adaptive control and enhanced algorithm for efficient drilling in composite materials. J Eur Syst Autom. 2023;56(3).
  13. Antil P, Singh S, Manna A, Katal N, Pruncu CI. Polym Compos. 2021;42(10):5051–5065.
  14. Kharwar PK, Verma RK. Nature instigated grey wolf algorithm for parametric optimization during machining (milling) of polymer nanocomposites. J Thermoplast Compos Mater. 2023;36(1):118–140.
  15. Gautam GD, Shrivastava Y. Advancements in metaheuristic optimization techniques for laser beam cutting of FRP composites: a review. Proc Inst Mech Eng E J Process Mech Eng. 2024. doi:10.1177/09544089241278097.
  16. Ghasempour-Mouziraji M, Hosseinzadeh M, Hajimiri H, et al. Machine learning-based optimization of geometrical accuracy in wire cut drilling. Int J Adv Manuf Technol. 2022;123:4265–4276.
  17. Sreenivasulu R, Chaitanya G. Self adaptive penalty method coupled with metaheuristic algorithms to optimization of varying geometrical parameters in drilling for multi hole parts. Sigma J Eng Nat Sci. 2022. doi:10.14744/sigma.2022.00101.
  1. Mehmood N, Umer M, Asgher U. Multi-hole drilling tool path planning and cost management through hybrid SFLA–ACO algorithm for composites and hybrid materials. J Compos Sci. 2022;6:364.
  2. Sahoo A, Mishra D. Parametric optimization of response parameter of Nd:YAG laser drilling for basalt-PTFE coated glass fibre using genetic algorithm. J Eng Res. 2023. doi:10.1016/j.jer.2023.07.014.
  3. Saravanakumar S, Sathiyamurthy S, Vinoth V. Enhancing machining accuracy of banana fiber-reinforced composites with ensemble machine learning. Measurement. 2024;235:114912.
Ahead of Print Subscription Original Research
Volume 14
01
Received 21/05/2025
Accepted 24/07/2025
Published 25/03/2026
Publication Time 308 Days
46

Login


My IP

PlumX Metrics