Combining Synchrotron X-ray Diffraction, Mechanistic Modeling, and Machine Learning for In Situ Subsurface Temperature Quantification during Laser Melting

TL;DR

This paper introduces a novel method combining synchrotron X-ray diffraction, mechanistic modeling, and machine learning to quantify subsurface temperature during laser melting in additive manufacturing, enabling better process understanding.

Contribution

It develops a supervised machine learning surrogate model trained with mechanistic simulations and diffraction data to extract temperature metrics with quantified uncertainty during laser melting.

Findings

Maximum temperatures reach the solidus during melting.

Temperature metrics near melting are more accurate.

Uncertainty in temperature estimates ranges from 5% to 15%.

Abstract

Laser melting, such as that encountered during additive manufacturing (AM), produces extreme gradients of temperature in both space and time, which in turn influence microstructural development in the material. Qualification and model validation of the process itself and resulting material produced necessitates the ability to characterize these temperature fields. However, well-established means to directly probe material temperature below the surface of an alloy while it is being processed are limited. To address this gap in characterization capabilities, we present a novel means to extract subsurface temperature distribution metrics, with uncertainty, from in situ synchrotron X-ray diffraction measurements to provide quantitative temperature evolution during laser melting. Temperature distribution metrics are determined using Gaussian Process Regression supervised machine learning surrogate models trained with a combination of mechanistic modeling (heat transfer and fluid flow) and X-ray diffraction simulation. Trained surrogate model uncertainties are found to range from 5% to 15% depending on the metric and current temperature. The surrogate models are then applied to experimental data to extract temperature metrics from an Inconel 625 nickel superalloy wall specimen during laser melting. Maximum temperatures of the solid phase in the diffraction volume through melting and cooling are found to reach the solidus temperature as expected, with mean and minimum temperatures found to be several hundred degrees less. The extracted temperature metrics near melting are determined to be more accurate due to the lower relative levels of mechanical elastic strains. However, uncertainties for temperature metrics during cooling are increased due to the effects of thermomechanical stress.