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

Abstract

Highlights Square-spot laser reshaping reduced sidewall roughness in laser directed energy deposition (LDED) Ti-6Al-4V thin walls. An 80-sample process dataset linked laser parameters to sidewall roughness. Random forest (RF) outperformed support vector regression (SVR) and eXtreme Gradient Boosting (XGBoost), with R2 = 0.940 and root mean square error (RMSE) = 1.760 μm. Validation reduced Ra from 28.98 μm to 5.76 μm with an 80.1% roughness reduction. Abstract 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.