Pioneering ML-driven framework for in-situ vertical surface roughness prediction in LPBF

Real-time prediction of vertical surface roughness in laser powder bed fusion (LPBF) is essential for process control and quality assurance, yet it remains largely unexplored due to view-blocking by loose powder in the machine bed. This study introduces the first integrated framework that combines in-situ photodiode monitoring with machine learning (ML) to predict sidewall roughness during fabrication. A high-speed photodiode sensor captures melt pool intensity signals near vertical surfaces, which are processed into time- and frequency-domain features. These features, together with process parameters, serve as inputs to ML models, while post-process surface roughness measurements (Sa), obtained via laser scanning confocal microscopy, are used as outputs during training. Once trained, the model can then be applied in real-time to predict roughness directly from photodiode signals acquired during printing, enabling side-specific monitoring without additional measurement steps. Among the five models evaluated, Random Forest (RF) and eXtreme Gradient Boosting (XGB) achieved the highest predictive accuracy, with RF improving from R2 = 0.35 (parameters only) to R2 = 0.78 when in-situ features were included. This framework demonstrates that photodiode-based monitoring, coupled with ML, enables reliable, side-specific, real-time prediction of vertical surface roughness in LPBF, offering a pathway towards adaptive quality control and reduced post-processing.