GPT-Micro: A large language paradigm for accelerated, inexpensive, and thermodynamics-consistent discovery of constitutive models in manufacturing

2026-06-06

AI Summary

This work addresses the limitations of traditional constitutive modeling, which relies heavily on manual expertise, suffers from low efficiency and high data costs, and often yields thermodynamically inconsistent results in existing data-driven approaches. To overcome these challenges, the authors propose the GPT-Micro paradigm, which uniquely integrates large language models with thermodynamic conservation constraints and sparse-data-driven symbolic regression. This framework automatically extracts semantic knowledge from scientific literature to generate physically consistent constitutive hypotheses without requiring predefined functional forms. Validated in the context of printed electronics manufacturing, the method reduces data requirements by over 70% and accelerates model discovery from months to hours, successfully yielding novel, interpretable, and thermodynamically complete analytical models.

Abstract

Constitutive modeling of the relationship between process-imposed material states and fundamental material properties is critical to control of material microstructure in manufacturing processes. The limited accuracy resulting from the typical reliance on fallible human expertise and intuition for postulation and revision of the models functional form results in incremental and time consuming model discovery. Conventional Machine Learning (ML) incurs significant cost and time of data generation. Model discovery using Large Language Models (LLMs) suffers from the above issues and/or ignores the inviolability of fundamental thermodynamics laws. This work creates a novel GPT-Micro paradigm for autonomous, data sparse, and thermodynamics-compliant discovery of de-novo constitutive models. This framework seamlessly integrates semantic knowledge extraction from literature, enforcement of thermodynamics-based conservation laws, and sparse datasets, with LLM-driven generation and refinement of model hypotheses. Validation is performed for a long-intractable constitutive modeling problem in a printed electronics process testbed. This reveals significant and simultaneous advantages over the state-of-the-art including: (a) More than 70 percent reduction in data burden relative to ML-based modeling without loss in accuracy; (b) 400X reduction in discovery time after data generation, from months to hours, relative to human-driven modeling; (c) Discovery of models with novel functional forms without subjective human choice of a starting hypothesis; (d) Enhanced physics-rooted trustworthiness, human interpretability, and mechanistic insight via synthesis of compact, conservation-compliant, and physically complete analytical models. The potential of GPT-Micro to realize rapid, low-cost, physically trustworthy, and interpretable microstructure modeling across the manufacturing landscape is discussed.

Problem

• constitutive modeling
• manufacturing
• thermodynamics consistency
• data sparsity
• material microstructure

Innovation

• GPT-Micro
• constitutive modeling
• thermodynamics-consistent
• large language models
• data-sparse discovery