Material-Agnostic Zero-Shot Thermal Inference for Metal Additive Manufacturing via a Parametric PINN Framework

2026-04-16 · Source: Takara TLDR - Daily AI Papers · Field: Manufacturing & Industrial — Artificial Intelligence & Machine Learning, Materials & Production Technology, Smart Manufacturing & Industry 4.0 · Depth: Expert, medium

Summary

A new parametric physics-informed neural network (PINN) framework has been developed for zero-shot thermal inference in metal additive manufacturing (AM), specifically for bare plate laser powder bed fusion (LPBF). This framework addresses the challenge of generalizing thermal modeling across diverse, unseen materials without requiring labeled data, retraining, or pre-training. It features a decoupled architecture that encodes material properties and spatiotemporal coordinates separately, fusing them via conditional modulation. The framework also incorporates physics-guided output scaling, derived from Rosenthal's analytical solution, and a hybrid optimization strategy to improve physical consistency, training stability, and convergence. Experiments demonstrated up to a 64.2% reduction in relative L2 error compared to a non-parametric baseline, achieving superior performance with only 4.4% of the baseline's training epochs across various in-distribution and out-of-distribution metal alloys.

Key takeaway

For AI Scientists and Machine Learning Engineers developing models for additive manufacturing, this parametric PINN framework offers a robust solution for material-agnostic thermal modeling. You should consider adopting its decoupled architecture and physics-guided scaling to achieve zero-shot generalization across new materials, significantly reducing the need for extensive datasets and costly retraining cycles in your projects.

Key insights

A parametric PINN enables zero-shot thermal modeling across diverse materials in metal AM, significantly reducing error and training time.

Principles

• Decouple material properties from spatiotemporal coordinates.
• Align model architecture with governing physical equations.
• Incorporate physics-guided scaling for consistency.

Method

The framework uses a decoupled parametric PINN, conditional modulation for fusion, physics-guided output scaling based on Rosenthal's solution, and a hybrid optimization strategy to achieve zero-shot material generalization.

In practice

• Apply decoupled PINN architectures for material generalization.
• Use conditional modulation to integrate material parameters.
• Implement physics-guided output scaling for stability.

Topics

• Metal Additive Manufacturing
• Physics-Informed Neural Networks
• Zero-Shot Generalization
• Thermal Modeling
• Laser Powder Bed Fusion

Best for: AI Scientist, Machine Learning Engineer, Research Scientist

Related on AIssential

• Material-Agnostic Zero-Shot Thermal Inference for Metal Additive Manufacturing via a Parametric PINN Framework — A parametric PINN framework enables zero-shot thermal modeling across diverse materials in metal AM with high efficiency.
• Robust Parameter and State Estimation in Multiscale Neuronal Systems Using Physics-Informed Neural Networks — PINNs offer robust parameter and state estimation in multiscale neuronal systems, overcoming limitations of traditional methods.
• Data-Efficient Indentation Size Effect Correction in Steels Using Machine Learning and Physics-Guided Augmentation — Physics-guided data augmentation enables accurate ISE correction in steels with small experimental datasets.
• Auxiliary Finite-Difference Residual-Gradient Regularization for PINNs — An auxiliary finite-difference term can effectively regularize PINN residual fields, improving accuracy in specific regions.
• Lightweight Geometric Adaptation for Training Physics-Informed Neural Networks — Curvature-aware optimization using secant information significantly improves PINN training stability and accuracy.
• Physics-Informed Neural Networks: A Didactic Derivation of the Complete Training Cycle — This guide demystifies PINN training by exposing the full algebraic cycle, from forward pass to gradient descent.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Takara TLDR - Daily AI Papers.