A Flow-rate-conserving CNN-based Domain Decomposition Method for Blood Flow Simulations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918144351666176 |
|---|---|
| author | Klaes, Simon Klawonn, Axel Kubicki, Natalie Lanser, Martin Nakajima, Kengo Shimokawabe, Takashi Weber, Janine |
| author_facet | Klaes, Simon Klawonn, Axel Kubicki, Natalie Lanser, Martin Nakajima, Kengo Shimokawabe, Takashi Weber, Janine |
| contents | This work aims to predict blood flow with non-Newtonian viscosity in stenosed arteries using convolutional neural network (CNN) surrogate models. An alternating Schwarz domain decomposition method is proposed which uses CNN-based subdomain solvers. A universal subdomain solver (USDS) is trained on a single, fixed geometry and then applied for each subdomain solve in the Schwarz method. Results for two-dimensional stenotic arteries of varying shape and length for different inflow conditions are presented and statistically evaluated. One key finding, when using a limited amount of training data, is the need to implement a USDS which preserves some of the physics, as, in our case, flow rate conservation. A physics-aware approach outperforms purely data-driven USDS, delivering improved subdomain solutions and preventing overshooting or undershooting of the global solution during the Schwarz iterations, thereby leading to more reliable convergence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_15900 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Flow-rate-conserving CNN-based Domain Decomposition Method for Blood Flow Simulations Klaes, Simon Klawonn, Axel Kubicki, Natalie Lanser, Martin Nakajima, Kengo Shimokawabe, Takashi Weber, Janine Numerical Analysis Machine Learning 68T07, 76M10, 65N55 This work aims to predict blood flow with non-Newtonian viscosity in stenosed arteries using convolutional neural network (CNN) surrogate models. An alternating Schwarz domain decomposition method is proposed which uses CNN-based subdomain solvers. A universal subdomain solver (USDS) is trained on a single, fixed geometry and then applied for each subdomain solve in the Schwarz method. Results for two-dimensional stenotic arteries of varying shape and length for different inflow conditions are presented and statistically evaluated. One key finding, when using a limited amount of training data, is the need to implement a USDS which preserves some of the physics, as, in our case, flow rate conservation. A physics-aware approach outperforms purely data-driven USDS, delivering improved subdomain solutions and preventing overshooting or undershooting of the global solution during the Schwarz iterations, thereby leading to more reliable convergence. |
| title | A Flow-rate-conserving CNN-based Domain Decomposition Method for Blood Flow Simulations |
| topic | Numerical Analysis Machine Learning 68T07, 76M10, 65N55 |
| url | https://arxiv.org/abs/2509.15900 |