Predictive Digital Twins for Thermal Management Using Machine Learning and Reduced-Order Models

TL;DR

This paper introduces a scalable digital twin framework for thermal management that combines physics-based reduced-order models with machine learning to enable rapid, accurate predictions in automotive systems.

Contribution

It presents a novel integration of CFD-based reduced-order models with multiple machine learning algorithms for real-time thermal prediction in digital twins.

Findings

Neural Network model achieved lowest MAE of 54.240.

High accuracy demonstrated in predicting thermal dynamics.

Framework supports robust design and predictive maintenance.

Abstract

Digital twins enable real-time simulation and prediction in engineering systems. This paper presents a novel framework for predictive digital twins of a headlamp heatsink, integrating physics-based reduced-order models (ROMs) from computational fluid dynamics (CFD) with supervised machine learning. A component-based ROM library, derived via proper orthogonal decomposition (POD), captures thermal dynamics efficiently. Machine learning models, including Decision Trees, k-Nearest Neighbors, Support Vector Regression (SVR), and Neural Networks, predict optimal ROM configurations, enabling rapid digital twin updates. The Neural Network achieves a mean absolute error (MAE) of 54.240, outperforming other models. Quantitative comparisons of predicted and original values demonstrate high accuracy. This scalable, interpretable framework advances thermal management in automotive systems, supporting robust design and predictive maintenance.