Hybrid Physics-Informed Machine Learning Frameworks for Predictive Thermodynamic Modeling
Ariq Ahanaf
Affiliation: Ideal School and College
IJSCAR Vol. 2, Issue 2 (2025) · pp. 16–20
Abstract
Recent advances in machine learning (ML) have opened new frontiers for modeling complex thermodynamic systems. Traditional thermodynamic property predictions often rely on methods limited in accuracy or scope. This research explores the potential of ML methods specifically support vector regression (SVR) and physics-informed neural networks (PINNs) to improve predictive accuracy for thermodynamic properties. We propose a hybrid framework combining these supervised learning algorithms with classical thermodynamic modeling concepts. Accompanying Python code examples using scikit-learn and TensorFlow demonstrate model training cross-validation and the application of basic physics-informed constraints using synthetic datasets. Execution of these examples shows that SVR can achieve high accuracy on synthetic entropy data a physics-informed neural network with non-negativity constraints attains R2 of approximately 0.78 for heat capacity prediction and a hybrid model with learned Shomate-like correction substantially improves performance to R2 of approximately 0.88 all on synthetic data. While the provided code focuses on property prediction the broader conceptual framework discussed herein extends to potential digital twin integration and reinforcement learning for operational optimization in complex energy systems representing avenues for future development.
Keywords: Physics-Informed Machine Learning, Thermodynamic Modeling, Support Vector Regression, Neural Networks, Digital Twins