MeltpoolNet: Melt pool characteristic prediction in Metal Additive Manufacturing using machine learning

Parand Akbari, Francis Ogoke, Ning-Yu Kao, Kazem Meidani, Chun-Yu Yeh, William Lee, Amir Barati Farimani

Abstract

MeltpoolNet is a benchmarking framework and open-source dataset for predicting melt pool behavior in metal additive manufacturing (MAM). By aggregating data from over 80 research papers and employing physics-aware feature engineering, the framework enables high-accuracy prediction of melt pool geometry and defect classification, significantly outperforming traditional analytical models like the Rosenthal equation.

Introduction

In Metal Additive Manufacturing (MAM), a high-energy beam melts metal powder layer by layer. The size, shape, and stability of the resulting melt pool are considered the "DNA" of the final part. Deviations in the melt pool lead to critical defects: if the pool is too deep, "keyhole" pores form; if too shallow, layers fail to adhere (lack of fusion); and if too elongated, the metal beads up (balling).

Engineers traditionally rely on the Rosenthal equation to estimate these characteristics. However, this simplified physics model ignores complex fluid dynamics and material-specific laser absorption, often leading to poor real-world predictions. While machine learning (ML) offers a faster alternative, most existing studies are limited to small, single-machine datasets. MeltpoolNet addresses this by providing a universal, large-scale benchmark for melt pool prediction.

Methods

The MeltpoolNet framework treats melt pool characterization as two distinct tasks: Regression for physical dimensions (depth, width, and length) and Classification for identifying the melt pool mode (Desirable, Keyhole, Lack of Fusion, or Balling).

The MeltpoolNet framework: mapping processing parameters and material properties to melt pool geometry and classification using various machine learning models.

A key innovation is physics-aware featurization. Instead of using only raw parameters like laser power and speed, the authors calculated "Absorptivity Coefficients"—mathematical proxies for energy absorption based on melt pool shape. The framework benchmarks several architectures, including ensemble methods (Random Forest, XGBoost), Gaussian Process Regression (GPR), and deep learning (Neural Networks).

Datasets

The authors compiled a comprehensive dataset by extracting and cleaning data from over 80 MAM research articles. This "data salvage" resulted in approximately 2,200 experimental data points covering 29 different metal alloys and four major MAM processes: Laser Powder Bed Fusion (L-PBF), Electron Beam Powder Bed Fusion (E-PBF), Laser Engineered Net Shaping (LENS), and Electron Beam Additive Manufacturing (EBAM).

Overview of the MeltpoolNet dataset, showing distributions of MAM processes, materials, and melt pool classifications.

Key Insights and Results

Benchmarking results demonstrate that ML models significantly outperform traditional analytical methods:

  • Geometry Prediction: Neural Networks and Gradient Boosting models achieved $R^2$ values between 0.95 and 0.99 for predicting melt pool dimensions. In contrast, the traditional Rosenthal estimation for melt pool length yielded an $R^2$ of -0.15, failing to capture the trend.
  • Defect Classification: The Random Forest model achieved 88.4% accuracy (AUC-ROC of 0.98) in identifying defect-free "desirable" prints versus failure modes like balling.
  • Feature Engineering: Incorporating hatch spacing and absorptivity coefficients improved model accuracy more significantly than increasing model complexity.
  • Interpretability: The authors used constrained optimization to "discover" new physical equations that mimic the Rosenthal form but fit experimental data 20% better, offering a balance between ML accuracy and physical intuition.

Limitations and Future Work

Despite its success, the framework faces challenges with data scarcity for certain features like hatch spacing, which were infrequently reported in source literature. Furthermore, current models predict "steady-state" melt pools, whereas real-world pools fluctuate dynamically. Future work aims to integrate these models into real-time closed-loop control systems to adjust processing parameters on the fly, ensuring part quality throughout the build process.

Summary updated

Abstract

Characterizing melt pool shape and geometry is essential in Metal Additive Manufacturing (MAM) to control the printing process, and avoid defects. Predicting melt pool flaws based on process parameters and powder material is difficult due to the complex nature of MAM processes. Machine learning (ML) techniques can be useful in connecting process parameters to the type of flaws in the melt pool. In this work, we introduced a comprehensive framework for benchmarking ML for melt pool characterization. An extensive experimental dataset has been collected from more than 80 MAM articles containing MAM processing conditions, materials, melt pool dimensions, melt pool modes and flaw types. We introduced physics-aware MAM featurization, versatile ML models, and evaluation metrics to create a comprehensive learning framework for melt pool defect and geometry prediction. This benchmark can serve as a basis for melt pool control and process optimization. In addition, data-driven explicit models have been identified to estimate melt pool geometry from process parameters and material properties. These models have been shown to outperform Rosenthal estimation for melt pool geometry while maintaining interpretability.
BibTeX
@inproceedings{akbari2022meltpoolnet,
  author = {Parand Akbari and Francis Ogoke and Ning-Yu Kao and Kazem Meidani and Chun-Yu Yeh and William Lee and Amir Barati Farimani},
  title = {{MeltpoolNet: Melt pool characteristic prediction in Metal Additive Manufacturing using machine learning}},
  booktitle = {Additive},
  year = {2022},
  doi = {10.1016/j.addma.2022.102817},
}
Figure