Leveraging AI modelling for FDS with Simvue: monitor and optimise for more sustainable simulations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909816661737472 |
|---|---|
| author | Panayis, James Field, Matt Gopakumar, Vignesh Lahiff, Andrew Zarebski, Kristian Abraham, Aby Hodges, Jonathan L. |
| author_facet | Panayis, James Field, Matt Gopakumar, Vignesh Lahiff, Andrew Zarebski, Kristian Abraham, Aby Hodges, Jonathan L. |
| contents | There is high demand on fire simulations, in both scale and quantity. We present a multi-pronged approach to improving the time and energy required to meet these demands. We show the ability of a custom machine learning surrogate model to predict the dynamics of heat propagation orders of magnitude faster than state-of-the-art CFD software for this application. We also demonstrate how a guided optimisation procedure can decrease the number of simulations required to meet an objective; using lightweight models to decide which simulations to run, we see a tenfold reduction when locating the most dangerous location for a fire to occur within a building based on the impact of smoke on visibility. Finally we present a framework and product, Simvue, through which we access these tools along with a host of automatic organisational and tracking features which enables future reuse of data and more savings through better management of simulations and combating redundancy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_26139 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging AI modelling for FDS with Simvue: monitor and optimise for more sustainable simulations Panayis, James Field, Matt Gopakumar, Vignesh Lahiff, Andrew Zarebski, Kristian Abraham, Aby Hodges, Jonathan L. Machine Learning Artificial Intelligence Computational Physics There is high demand on fire simulations, in both scale and quantity. We present a multi-pronged approach to improving the time and energy required to meet these demands. We show the ability of a custom machine learning surrogate model to predict the dynamics of heat propagation orders of magnitude faster than state-of-the-art CFD software for this application. We also demonstrate how a guided optimisation procedure can decrease the number of simulations required to meet an objective; using lightweight models to decide which simulations to run, we see a tenfold reduction when locating the most dangerous location for a fire to occur within a building based on the impact of smoke on visibility. Finally we present a framework and product, Simvue, through which we access these tools along with a host of automatic organisational and tracking features which enables future reuse of data and more savings through better management of simulations and combating redundancy. |
| title | Leveraging AI modelling for FDS with Simvue: monitor and optimise for more sustainable simulations |
| topic | Machine Learning Artificial Intelligence Computational Physics |
| url | https://arxiv.org/abs/2509.26139 |