Optimizing Process Parameters in Laser Transmission Welding Solid PC/Porous-PET Using Prediction Models: Experimental Validation and Morphology Analysis
Materials · 24.07.2026 · 19 (15) · 3177
DOI: 10.3390/ma19153177 ↗Kurz gefasst
Fachartikel in der Zeitschrift Materials, online erschienen am 24.07.2026. Verfasst von Jinqiang Li und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical and Electrical Engineering, Soochow University, Suzhou 215000, China. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of the Jiangsu Higher Education Institutions of China, China Postdoctoral Science Foundation.
Abstract (Originalsprache)
Determining optimal process parameters for laser transmission welding (LTW) of solid/porous materials remains challenging due to the complexity of influencing factors. In this study, the welding of solid polycarbonate (PC) and porous polyethylene terephthalate (porous-PET) was chosen as an exemplary case and the relationship between parameters and welding quality was established using a Gaussian process regression (GPR) model. First, the experimental dataset, comprising welding power, welding speed, PC thickness, and porous-PET density, is established based on a flexible factor-level design. Then, the optimized GPR model trained based on the full experimental dataset achieved high predictive performance, significantly outperforming that trained with the averaged experimental dataset. Next, using the optimal prediction model as the objective function, three different optimization methods, genetic algorithm (GA), Bayesian optimization (BO), and covariance matrix adaptation evolution strategy (CMA-ES), are employed to optimize the process parameters, and the performance of the different optimization algorithms shows that CMA-ES has demonstrated the fastest convergence and the shortest runtime, while still converging to the same recommended parameters as GA and BO. Experimental validation confirms the accuracy of the recommended parameters, with a low relative error. Morphological analysis confirms that the weld seam is uniformly formed at recommended parameters. The proposed strategy provides an efficient route for achieving high-performance LTW joints and shows strong potential for improving process efficiency and reducing manufacturing cost in solid/porous materials joining.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Mechanical and Electrical Engineering, Soochow University, Suzhou 215000, China.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of the Jiangsu Higher Education Institutions of China
- China Postdoctoral Science Foundation
- Natural Science Foundation of Jiangsu Province
- Undergraduate Training Program for Innovation and Entrepreneurship, Soochow University
Zitieren
APA
Li, J., Wu, Y., Luo, X., Zhou, S., Wang, Z., Zhang, H., Zhong, B., & Qiao, H. (2026). Optimizing Process Parameters in Laser Transmission Welding Solid PC/Porous-PET Using Prediction Models: Experimental Validation and Morphology Analysis. Materials, 19(15), 3177. https://doi.org/10.3390/ma19153177
Vancouver
Li J, Wu Y, Luo X, Zhou S, Wang Z, Zhang H, et al. Optimizing Process Parameters in Laser Transmission Welding Solid PC/Porous-PET Using Prediction Models: Experimental Validation and Morphology Analysis. Materials. 2026;19(15):3177. doi:10.3390/ma19153177
BibTeX
@article{Li2026,
author = {Li, Jinqiang and Wu, Yitao and Luo, Xiangsheng and Zhou, Siyu and Wang, Zijian and Zhang, Huang and Zhong, Bowen and Qiao, Haiyu},
title = {Optimizing Process Parameters in Laser Transmission Welding Solid PC/Porous-PET Using Prediction Models: Experimental Validation and Morphology Analysis},
journal = {Materials},
year = {2026},
volume = {19},
number = {15},
pages = {3177},
doi = {10.3390/ma19153177}
}
EUVIMED