Opening the Black Box: An Explainable, Few-shot AI4E Framework Informed by Physics and Expert Knowledge for Materials Engineering

TL;DR

This paper introduces an explainable, physics-informed few-shot AI framework for materials engineering that constructs interpretable models from limited data, enhancing understanding and reliability in safety-critical industrial applications.

Contribution

It develops a systematic approach combining synthetic data augmentation and symbolic regression to discover interpretable constitutive equations from scarce data, integrating physics and expert knowledge.

Findings

Achieved 88% accuracy in predicting hot-cracking tendency.

Produced explicit physical insights into cracking mechanisms.

Enabled process optimization and virtual data generation.

Abstract

The industrial adoption of Artificial Intelligence for Engineering (AI4E) faces two fundamental bottlenecks: scarce high-quality data and the lack of interpretability in black-box models-particularly critical in safety-sensitive sectors like aerospace. We present an explainable, few-shot AI4E framework that is systematically informed by physics and expert knowledge throughout its architecture. Starting from only 32 experimental samples in an aerial K439B superalloy castings repair welding case, we first augment physically plausible synthetic data through a three-stage protocol: differentiated noise injection calibrated to process variabilities, enforcement of hard physical constraints, and preservation of inter-parameter relationships. We then employ a nested optimization strategy for constitutive model discovery, where symbolic regression explores equation structures while differential evolution optimizes parameters, followed by intensive parameter refinement using hybrid global-local optimization. The resulting interpretable constitutive equation achieves 88% accuracy in predicting hot-cracking tendency. This equation not only provides quantitative predictions but also delivers explicit physical insight, revealing how thermal, geometric, and metallurgical mechanisms couple to drive cracking-thereby advancing engineers' cognitive understanding of the process. Furthermore, the constitutive equation serves as a multi-functional tool for process optimization and high-fidelity virtual data generation, enabling accuracy improvements in other data-driven models. Our approach provides a general blueprint for developing trustworthy AI systems that embed engineering domain knowledge directly into their architecture, enabling reliable adoption in high-stakes industrial applications where data is limited but physical understanding is available.