Physics-Informed Machine Learning of Argon Gas-Driven Melt Pool Dynamics

TL;DR

This paper introduces a physics-informed machine learning approach using neural networks to efficiently predict melt pool dynamics in metal additive manufacturing, reducing computational costs compared to traditional CFD methods.

Contribution

The paper develops a data-efficient PINN model that integrates physical laws to predict melt pool behavior without extensive training data or solving complex Navier-Stokes equations.

Findings

PINN accurately predicts temperature, velocity, and pressure in melt pools.

The approach significantly reduces computational cost compared to CFD.

Model constants can be inferred through data-driven discovery.

Abstract

Melt pool dynamics in metal additive manufacturing (AM) is critical to process stability, microstructure formation, and final properties of the printed materials. Physics-based simulation including computational fluid dynamics (CFD) is the dominant approach to predict melt pool dynamics. However, the physics-based simulation approaches suffer from the inherent issue of very high computational cost. This paper provides a physics-informed machine learning (PIML) method by integrating neural networks with the governing physical laws to predict the melt pool dynamics such as temperature, velocity, and pressure without using any training data on velocity. This approach avoids solving the highly non-linear Navier-Stokes equation numerically, which significantly reduces the computational cost. The difficult-to-determine model constants of the governing equations of the melt pool can also be inferred through data-driven discovery. In addition, the physics-informed neural network (PINN) architecture has been optimized for efficient model training. The data-efficient PINN model is attributed to the soft penalty by incorporating governing partial differential equations (PDEs), initial conditions, and boundary conditions in the PINN model.