journal article·2026-07-24

Comparative machine learning for multi-response quality prediction in CO 2 laser cutting of polypropylene

Oguzhan Der, Gokhan Basar, İlker Mert, Emre Yıldırım

Materials Testing· Volume 68· Issue 7
Publisher page

Abstract

Abstract This research study presents a comprehensive comparative analysis using machine learning techniques to predict multiple quality characteristics in CO 2 laser cutting of polypropylene. A full factorial experimental design was employed with three process parameters: focal length (6.5–8.5 mm), laser power (85–100 W), and cutting speed (4–12 mm s −1 ). The effects of these parameters on surface roughness Ra, top and bottom kerf widths KW, and kerf angle KA were systematically investigated. Experimental results show that cutting speed has the strongest influence on Ra, while kerf geometry is mainly governed by focal length. Moreover, KA is significantly affected by the interaction between cutting speed and focal length. The machine learning models that were created using standardized data sets are Extreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), Gradient Boosting Regressor (GBR), H2O Gradient Boosting Machine (H2O_GBM), and Gaussian Process Regression (GPR). Model performance was evaluated using the coefficient of determination, root mean squared error, mean absolute error, and Pearson correlation coefficient. Ensemble-based models, particularly XGBoost and CatBoost, achieved the highest prediction accuracy for most responses, whereas GPR performed best for Ra. The results indicate optimal cutting quality is achieved at high cutting speeds, large focal lengths, and elevated laser power under controlled processing conditions.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Laser Material Processing Techniques · Laser Applications in Dentistry and Medicine · Erosion and Abrasive Machining

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Marine Engineering Department , Bandirma Onyedi Eylul University , Balikesir , 10200 , Türkiye

Department of Industrial Engineering , Faculty of Engineering and Natural Sciences , Osmaniye Korkut Ata University , Osmaniye , 80010 , Türkiye

Electric & Energy Department, Osmaniye Vocational School , Osmaniye Korkut Ata University , Osmaniye , 80010 , Türkiye

Computer Technology Department, Osmaniye Vocational School , Osmaniye Korkut Ata University , Osmaniye , 80010 , Türkiye

References (37)

Show source-provided references
1. L. Gerdes, S. Mrzljak, J. Keuntje, V. Wippo, P. Jaeschke, and F. Walther, “Fatigue performance of laser cut carbon fiber-reinforced epoxy and polyamide 6 considering specimen width,” Mater. Test., vol. 65, no. 11, pp. 1645–1656, 2023, https://doi.org/10.1515/mt-2023-0170.10.1515/mt-2023-0170 ↗
2. A. Mateo, G. Fargas, J. Calvo, and J. J. Roa, “Influence of laser cutting on the fatigue limit of two high strength steels,” Mater. Test., vol. 57, no. 2, pp. 136–140, 2015, https://doi.org/10.3139/120.110686.10.3139/120.110686 ↗
3. U. Y. Uzunali, H. Çuvalcı, and Ü. Kartal, “Comparative analysis of cutting methods and their impact on fatigue properties of armor steel,” Mater. Test., vol. 67, no. 3, pp. 503–519, 2025, https://doi.org/10.1515/mt-2024-0268.10.1515/mt-2024-0268 ↗
4. A. A. Shamsuri, S. N. A. Md. Jamil, M. Abu Zarin, and M. Z. Mohamed Yusoff, “Effects of co-fillers on the tensile and hardness properties of polymer composites,” Mater. Test., vol. 67, no. 8, pp. 1409–1422, 2025, https://doi.org/10.1515/mt-2024-0557.10.1515/mt-2024-0557 ↗
5. O. Der, A. A. Alqahtani, M. Marengo, and V. Bertola, “Characterization of polypropylene pulsating heat stripes: Effects of orientation, heat transfer fluid, and loop geometry,” Appl. Therm. Eng., vol. 184, no. Feb, 2021, Art. no. 116304, https://doi.org/10.1016/j.applthermaleng.2020.116304.10.1016/j.applthermaleng.2020.116304 ↗
6. O. Der and V. Bertola, “An experimental investigation of oil-water flow in a serpentine channel,” Int. J. Multiphase Flow, vol. 129, 2020, Art. no. 103327, https://doi.org/10.1016/j.ijmultiphaseflow.2020.103327.10.1016/j.ijmultiphaseflow.2020.103327 ↗
7. J. D. Kechagias, K. Ninikas, M. Petousis, N. Vidakis, and N. Vaxevanidis, “An investigation of surface quality characteristics of 3D printed PLA plates cut by CO2 laser using experimental design,” Mater. Manuf. Processes, vol. 36, no. 13, pp. 1544–1553, 2021, https://doi.org/10.1080/10426914.2021.1906892.10.1080/10426914.2021.1906892 ↗
8. O. Der, G. Başar, and M. Ordu, “Statistical investigation of the effect of CO2 laser cutting parameters on kerf width and heat affected zone in thermoplastic materials,” J. Mater. Mechatronics: A, vol. 4, no. 2, pp. 459–474, 2023, https://doi.org/10.55546/jmm.1359453.10.55546/jmm.1359453 ↗
9. G. Basar, “Experimental evaluation and machine learning-based prediction of laser cutting quality in FFF-printed ABS thermoplastics,” Polymers, vol. 17, no. 13, 2025, Art. no. 1728, https://doi.org/10.3390/polym17131728.10.3390/polym17131728 ↗
10. K. Aydın and L. Uğur, “Prediction of kerf and groove widths in CO2 laser cutting process of PMMA using experimental and machine learning methods,” Exp. Tech., vol. 49, no. 5, pp. 873–886, 2025, https://doi.org/10.1007/s40799-025-00786-5.10.1007/s40799-025-00786-5 ↗
11. X. Zhang, L. Zhou, G. Feng, K. Xi, H. Algadi, and M. Dong, “Laser technologies in manufacturing functional materials and applications of machine learning-assisted design and fabrication,” Adv. Compos. Hybrid Mater., vol. 8, no. 1, 2025, Art. no. 76, https://doi.org/10.1007/s42114-024-01154-4.10.1007/s42114-024-01154-4 ↗
12. J. D. Kechagias, K. Ninikas, S. Zaoutsos, L. Tzounis, and P. Stavropoulos, “On optimizing CO2 laser cutting of 3D-printed PA12/CNTs composite sheet kerf characteristics,” Int. J. Adv. Manuf. Technol., vol. 138, nos. 3–4, pp. 1307–1322, 2025, https://doi.org/10.1007/s00170-025-15640-6.10.1007/s00170-025-15640-6 ↗
13. S. Prakash and S. Suman, “Neural network-based prediction for surface characteristics in CO2 laser micro-milling of glass fiber reinforced plastic composite,” Neural Comput. Appl., vol. 33, no. 18, pp. 11517–11529, 2021, https://doi.org/10.1007/s00521-021-05818-w.10.1007/s00521-021-05818-w ↗
14. O. Der, “Multi-output prediction and optimization of CO2 laser cutting quality in FFF-printed ASA thermoplastics using machine learning approaches,” Polymers, vol. 17, no. 14, 2025, Art. no. 1910, https://doi.org/10.3390/polym17141910.10.3390/polym17141910 ↗
15. Ö. Kanbir, K. Ayas, and K. Çavdar, “Effect of atmospheric pressure plasma treatment on the wettability and aging behavior of metal surfaces,” Mater. Test., vol. 67, no. 5, pp. 875–883, 2025, https://doi.org/10.1515/mt-2024-0480.10.1515/mt-2024-0480 ↗
16. O. Der, M. Ordu, and G. Basar, “Optimization of cutting parameters in manufacturing of polymeric materials for flexible two-phase thermal management systems,” Mater. Test., vol. 66, no. 10, pp. 1700–1719, 2024, https://doi.org/10.1515/mt-2024-0127.10.1515/mt-2024-0127 ↗
17. J. A. Pascoe, R. C. Alderliesten, and R. Benedictus, “Methods for the prediction of fatigue delamination growth in composites and adhesive bonds – A critical review,” Eng. Fract. Mech., vols. 112–113, pp. 72–96, 2013, https://doi.org/10.1016/j.engfracmech.2013.10.003.10.1016/j.engfracmech.2013.10.003 ↗
18. O. Der, S. Edwardson, M. Marengo, and V. Bertola, “Engineered composite polymer sheets with enhanced thermal conductivity,” IOP Conf. Ser. Mater. Sci. Eng., vol. 613, no. 1, 2019, Art. no. 012008, https://doi.org/10.1088/1757-899X/613/1/012008.10.1088/1757-899X/613/1/012008 ↗
19. G. Basar, O. Der, and M. A. Guvenc, “AI-powered hybrid metaheuristic optimization for predicting surface roughness and kerf width in CO2 laser cutting of 3D-printed PLA-CF composites,” J. Thermoplast. Compos. Mater., vol. 38, no. 7, pp. 2688–2717, 2025, https://doi.org/10.1177/08927057251344183.10.1177/08927057251344183 ↗
20. O. Der, M. Tasci, G. Basar, and A. Ercetin, “Intelligent modeling and prediction of CO2 laser cutting performance in FFF-printed thermoplastics using machine learning algorithms,” Proc. Inst. Mech. Eng., Part E: J. Process Mech. Eng., 2025, https://doi.org/10.1177/09544089251366429.10.1177/09544089251366429 ↗
21. M. C. Tezel, N. Erdoğan, and E. Acar, “Design optimization of a multi-layer aircraft canopy transparency plate against bird strike,” Mater. Test., vol. 67, no. 9, pp. 1507–1519, 2025, https://doi.org/10.1515/mt-2025-0240.10.1515/mt-2025-0240 ↗
22. I. Bozkurt, “Mechanical behavior of composite pipe structures under compressive force and its prediction using different machine learning algorithms,” Mater. Test., vol. 67, no. 1, pp. 160–182, 2025, https://doi.org/10.1515/mt-2024-0192.10.1515/mt-2024-0192 ↗
23. T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in 2016 Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA, ACM, pp. 785–794.10.1145/2939672.2939785 ↗
24. R. P. Zeilmann and J. L. N. Subtil, “LightGBM and CatBoost for tool wear prediction in milling with drag-finished cutting edges,” Int. J. Adv. Manuf. Technol., vol. 137, nos. 9–10, pp. 4631–4643, 2025, https://doi.org/10.1007/s00170-025-15419-9.10.1007/s00170-025-15419-9 ↗
25. J. H. Friedman, “Greedy function approximation: A gradient boosting machine,” Ann. Stat., vol. 29, no. 5, pp. 1189–1232, 2001, https://doi.org/10.1214/aos/1013203451.10.1214/aos/1013203451 ↗
26. I. Omar, M. Khan, A. Starr, and K. Abou Rok Ba, “Automated prediction of crack propagation using H2O AutoML,” Sensors, vol. 23, no. 20, 2023, Art. no. 8419, https://doi.org/10.3390/s23208419.10.3390/s23208419 ↗
27. M. Hashemitaheri, S. M. R. Mekarthy, and H. Cherukuri, “Prediction of specific cutting forces and maximum tool temperatures in orthogonal machining by support vector and gaussian process regression methods,” Procedia Manuf, vol. 48, pp. 1000–1008, 2020, https://doi.org/10.1016/j.promfg.2020.05.139.10.1016/j.promfg.2020.05.139 ↗
28. İ. Mert, C. Karakuş, and F. Üneş, “Estimating the energy production of the wind turbine using artificial neural network,” Neural Comput. Appl., vol. 27, no. 5, pp. 1231–1244, 2016, https://doi.org/10.1007/s00521-015-1921-0.10.1007/s00521-015-1921-0 ↗
29. O. Mehrabi, Z. Malekshahi Beiranvand, F. A. Rasoul, and M. Moradi, “Enhancing the quality and sustainability of laser cutting processes in laser-assisted manufacturing using a box–behnken design,” Processes, vol. 13, no. 5, 2025, Art. no. 1279, https://doi.org/10.3390/pr13051279.10.3390/pr13051279 ↗
30. A. Hossain et al.., “A fuzzy logic-based prediction model for kerf width in laser beam machining,” Mater. Manuf. Processes, vol. 31, no. 5, pp. 679–684, 2016, https://doi.org/10.1080/10426914.2015.1037901.10.1080/10426914.2015.1037901 ↗
31. A. I. Kusuma and Y.-M. Huang, “Performance comparison of machine learning models for kerf width prediction in pulsed laser cutting,” Int. J. Adv. Manuf. Technol., vol. 123, nos. 7–8, pp. 2703–2718, 2022, https://doi.org/10.1007/s00170-022-10348-3.10.1007/s00170-022-10348-3 ↗
32. A. B. Khoshaim, A. H. Elsheikh, E. B. Moustafa, M. Basha, and E. A. Showaib, “Experimental investigation on laser cutting of PMMA sheets: Effects of process factors on kerf characteristics,” J. Mater. Res. Technol., vol. 11, pp. 235–246, 2021, https://doi.org/10.1016/j.jmrt.2021.01.012.10.1016/j.jmrt.2021.01.012 ↗
33. S. Huang, Z. Fu, C. Liu, and J. Li, “Multi-objective optimization of fiber laser cutting quality characteristics of glass fiber reinforced plastic (GFRP) materials,” Opt. Laser Technol., vol. 167, 2023, Art. no. 109720, https://doi.org/10.1016/j.optlastec.2023.109720.10.1016/j.optlastec.2023.109720 ↗
34. S. Ürgün, H. Yiğit, S. Fidan, and T. Sınmazçelik, “Optimization of laser cutting parameters for PMMA using metaheuristic algorithms,” Arab. J. Sci. Eng., vol. 49, no. 9, pp. 12333–12355, 2024, https://doi.org/10.1007/s13369-023-08627-6.10.1007/s13369-023-08627-6 ↗
35. A. R. Rejani and M. Hashemzadeh, “CO2 laser-air cutting of glass-fibre-reinforced unsaturated polyester (GFRUP): An experimental investigation,” Int. J. Adv. Manuf. Technol., vol. 117, nos. 9–10, pp. 2627–2638, 2021, https://doi.org/10.1007/s00170-021-07180-6.10.1007/s00170-021-07180-6 ↗
36. D. Rodić, M. Sekulić, B. Savković, M. Madić, and M. Trifunović, “Integration of RSM and machine learning for accurate prediction of surface roughness in laser processing,” Appl. Sci., vol. 15, no. 13, p. 7064, 2025, https://doi.org/10.3390/app15137064.10.3390/app15137064 ↗
37. M. S. Raza, S. Datta, B. Bule, and P. Saha, “Parametric study of laser cutting of carbon fibre reinforced polymer (CFRP) and the effect of fibre orientation on cutting quality,” Adv. Mater. Process. Technol., vol. 5, no. 2, pp. 202–212, 2019, https://doi.org/10.1080/2374068X.2018.1564865.10.1080/2374068X.2018.1564865 ↗