Prediction of melt pool geometry by fusing experimental and simulation data

Abstract

Accurate prediction of the melt pool geometry in laser-directed energy deposition (L-DED) is crucial for ensuring product quality. Although machine learning methods have offered aid in addressing this challenge, existing surrogate models are typically based on either simulation or experimental data. Surrogates trained using numerical simulation data reflect modeling assumptions in their accuracy. Conversely, surrogates developed using experimental data would demand a substantial investment of effort and resources to generate adequate data for training. As a possible solution, in this paper, a multi-fidelity Gaussian process (MFGP) framework is developed to fuse experimental and simulation data. Experimental melt pool dimensions are obtained from single-layer, single-track deposits fabricated via powder-fed L-DED. These constitute the high-fidelity/ground truth data for the MFGP surrogate. An analytical Eagar-Tsai model is calibrated and queried at sampled input points within a predefined process parameter window to yield near-accurate estimates of low-fidelity melt pool data at a significantly lower effort. Thereafter, the MFGP surrogate is designed on the combined sources of data using an appropriate kernel and adequate calibration. An elaborate assessment of the trained surrogate on unseen experimental data is shown to yield results with high accuracy and low uncertainty. The proposed method of blending experimental data with simulation data has the potential to reduce the volume of experimental data required for creating surrogates without compromising accuracy. While the current work focuses on the L-DED of a popular alloy, SS316L, it can be easily extended to other advanced manufacturing processes to design reliable surrogates.