EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning-Assisted Square-Spot Laser Surface Reshaping for Sidewall Roughness Control of LDED Ti-6Al-4V Thin-Walled Structures

Wenjun Yu, Fei Li, Yanze Wang, Pengpeng Xiong, Xiaohu Guan, Feiyue Lyu, Jicheng Chen iD

Materials · 11.08.2026 · 19 (16) · 3406

DOI: 10.3390/ma19163406 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials, online erschienen am 11.08.2026. Verfasst von Wenjun Yu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Chengdu Aircraft Industrial (Group) Co., Ltd., Chengdu 610091, China. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Chengdu Aircraft Industrial (Group) Co., Ltd..

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Laser directed energy deposition (LDED) can fabricate Ti-6Al-4V thin-walled structures efficiently, but the deposited sidewalls usually contain adhered particles, layer steps, and waviness that limit surface quality. This study combined square-spot laser surface reshaping with machine learning-assisted parameter design to control sidewall roughness. Sixteen single-factor experiments were first conducted to clarify the effects of laser power, scanning speed, spot overlap ratio, and scan number. An 80-sample dataset was then established to train and compare random forest (RF), support vector regression (SVR), and eXtreme Gradient Boosting (XGBoost) models, and SHapley Additive exPlanations (SHAP) were used to interpret feature contributions. RF showed the best predictive performance, with R2 = 0.940 and RMSE = 1.760 μm, and was coupled with Bayesian optimization (BO) for inverse parameter design. For a target arithmetic mean roughness (Ra) of 5 μm, the optimized condition was 500 W, 2.57 mm/s, 48.09% overlap, and five scans. The predicted Ra was 5.02 μm, while the validation experiment yielded 5.76 μm, reducing the initial roughness from 28.98 μm by 80.1%. These results demonstrate that interpretable machine learning can support target-driven square-spot laser reshaping for LDED Ti-6Al-4V thin-walled structures.

Schlagwörter

Stichwörter der Autor:innen

laser directed energy depositionmachine learningsquare-spot laser reshapingsurface qualitythin-walled structures

Autor:innen und Institutionen

  • Chengdu Aircraft Industrial (Group) Co., Ltd., Chengdu 610091, China.
  • College of Materials Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China.

ORCID-Profile: Jicheng Chen

Förderung

  • Chengdu Aircraft Industrial (Group) Co., Ltd.

Zitieren

APA

Yu, W., Li, F., Wang, Y., Xiong, P., Guan, X., Lyu, F., & Chen, J. (2026). Machine Learning-Assisted Square-Spot Laser Surface Reshaping for Sidewall Roughness Control of LDED Ti-6Al-4V Thin-Walled Structures. Materials, 19(16), 3406. https://doi.org/10.3390/ma19163406

Vancouver

Yu W, Li F, Wang Y, Xiong P, Guan X, Lyu F, et al. Machine Learning-Assisted Square-Spot Laser Surface Reshaping for Sidewall Roughness Control of LDED Ti-6Al-4V Thin-Walled Structures. Materials. 2026;19(16):3406. doi:10.3390/ma19163406

BibTeX
@article{Yu2026,
  author = {Yu, Wenjun and Li, Fei and Wang, Yanze and Xiong, Pengpeng and Guan, Xiaohu and Lyu, Feiyue and Chen, Jicheng},
  title = {Machine Learning-Assisted Square-Spot Laser Surface Reshaping for Sidewall Roughness Control of LDED Ti-6Al-4V Thin-Walled Structures},
  journal = {Materials},
  year = {2026},
  volume = {19},
  number = {16},
  pages = {3406},
  doi = {10.3390/ma19163406}
}
Kostenlos starten →