Predictive Digital Twins for Thermal Management Using Machine Learning and Reduced-Order Models
This work addresses thermal management challenges in automotive systems, offering a scalable and interpretable solution for robust design and predictive maintenance, though it is incremental as it combines existing methods in a novel application.
The paper tackled the problem of real-time thermal management in automotive headlamp heatsinks by developing a predictive digital twin framework that integrates physics-based reduced-order models with machine learning, achieving a mean absolute error of 54.240 using a neural network for optimal model configuration.
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.