Physics-based model for crystallographic texture prediction
Physics-based prediction, uncertainty quantification and decision-making for IN718 crystallographic texture intensity across LPBF defocus regimes
This research provides a more reliable method for predicting material properties in additive manufacturing, which is important for industries that rely on precision metal 3D printing.
This study develops a two-stage physics-based model for predicting crystallographic texture in Inconel 718 under laser powder bed fusion conditions.
Stage 1 maps process variables to melting mode and melt pool geometry, while Stage 2 combines an empirical physics model with a random-forest residual model.
The model uses k-nearest-neighbor weighting to attenuate corrections for poorly supported queries and a study-specific beam-power-density criterion to withhold predictions outside the conduction envelope.
Under leave-one-defocus-out evaluation, the physics anchor achieved an R² of 0.778, outperforming black-box and hybrid models.
The framework can separate data applicability, physics validity, and predictive uncertainty into distinct decisions, allowing it to transfer where unconstrained models fail.
Physics-based prediction, uncertainty quantification and decision-making for IN718 crystallographic texture intensity across LPBF defocus regimes
Reliable prediction of crystallographic texture in laser powder bed fusion is critical for linking process conditions with anisotropic response and for qualification. However, black-box models may fail under shift and cannot distinguish weak data support from loss of physical validity. This study develops a two-stage physics-based model for <001> || BD (build direction) texture in Inconel 718. Stage 1 maps process variables to melting mode and melt pool geometry. Stage 2 predicts texture by combining an empirical physics model with a random-forest residual model. A k-nearest-neighbor weight attenuates residual corrections for poorly supported queries, while a study-specific areal beam-power-density criterion withholds predictions outside the adopted conduction envelope. Conformal intervals are evaluated on the retained physics-valid set, and SHAP and Sobol analyses assess residual sensitivity. Under a controlled leave-one-defocus-out evaluation, the physics anchor achieved R^2 = 0.778, against -0.001 for the black-box model and 0.750 for the gated hybrid. Under leave-one-group-out cross-validation, the gated hybrid reached R^2 = 0.592 against 0.538 for the black-box model. Retained-set coverage was 92.9% at a mean full width of 3.65 multiples of a uniform distribution (MUD) under grouped cross-validation and 100% at a width of 3.21 MUD under transfer to a withheld +80 mm defocus regime. An illustrative mapping produced a retained BD elastic-modulus span of 127-187 GPa. On nine conditions from a separately built sample set, the framework withheld three, attenuated three, and matched the measured ordering for the rest. Separating data applicability, physics validity, and predictive uncertainty into distinct decisions lets the framework transfer where an unconstrained model does not, and withhold predictions where no model class performs adequately.
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include inconel 718, predictive models.
Source attribution: curated from arXiv cs.LG (@Yisheng Lu, John Riris, Jie Song, Yao Fu, Jie Chen).
