Physics-Informed Mixture Models and Surrogate Models for Precision Additive Manufacturing

TL;DR

This paper introduces physics-informed mixture and surrogate models to detect defects in laser-based additive manufacturing, demonstrating their effectiveness across real-world and public datasets with different alloys and parameters.

Contribution

It presents a novel physics-guided mixture modeling framework for defect detection in additive manufacturing, integrating physical principles for improved sensitivity and analysis.

Findings

Effective defect detection in real-world AM data

Model sensitivity to physical parameter variations

Successful application across multiple AM processes and datasets

Abstract

In this study, we leverage a mixture model learning approach to identify defects in laser-based Additive Manufacturing (AM) processes. By incorporating physics based principles, we also ensure that the model is sensitive to meaningful physical parameter variations. The empirical evaluation was conducted by analyzing real-world data from two AM processes: Directed Energy Deposition and Laser Powder Bed Fusion. In addition, we also studied the performance of the developed framework over public datasets with different alloy type and experimental parameter information. The results show the potential of physics-guided mixture models to examine the underlying physical behavior of an AM system.