Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.06849 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915282751062016 |
|---|---|
| author | Subramani, Tamilselvan Bartscher, Sebastian |
| author_facet | Subramani, Tamilselvan Bartscher, Sebastian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_06849 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Predictive Digital Twins for Thermal Management Using Machine Learning and Reduced-Order Models Subramani, Tamilselvan Bartscher, Sebastian Machine Learning 68T07, 65M99, 80A23 I.2.6; G.1.8; J.2 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. |
| title | Predictive Digital Twins for Thermal Management Using Machine Learning and Reduced-Order Models |
| topic | Machine Learning 68T07, 65M99, 80A23 I.2.6; G.1.8; J.2 |
| url | https://arxiv.org/abs/2505.06849 |