Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Wenkang, Xu, Ran, Feng, Jingsen, Zhang, Qingfu, Chu, Xu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2504.02888
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915504292102144
author Wang, Wenkang
Xu, Ran
Feng, Jingsen
Zhang, Qingfu
Chu, Xu
author_facet Wang, Wenkang
Xu, Ran
Feng, Jingsen
Zhang, Qingfu
Chu, Xu
contents We evaluated the performance of OpenFOAMGPT incorporating multiple large-language models. Some of the present models efficiently manage different CFD tasks such as adjusting boundary conditions, turbulence models, and solver configurations, although their token cost and stability vary. Locally deployed smaller models like QwQ-32B struggled with generating valid solver files for complex processes. Zero-shot prompting commonly failed in simulations with intricate settings, even for large models. Challenges with boundary conditions and solver keywords stress the requirement for expert supervision, indicating that further development is needed to fully automate specialized CFD simulations.
format Preprint
id arxiv_https___arxiv_org_abs_2504_02888
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Status Quo Investigation of Large Language Models towards Cost-Effective CFD Automation with OpenFOAMGPT: ChatGPT vs. Qwen vs. Deepseek
Wang, Wenkang
Xu, Ran
Feng, Jingsen
Zhang, Qingfu
Chu, Xu
Computation and Language
We evaluated the performance of OpenFOAMGPT incorporating multiple large-language models. Some of the present models efficiently manage different CFD tasks such as adjusting boundary conditions, turbulence models, and solver configurations, although their token cost and stability vary. Locally deployed smaller models like QwQ-32B struggled with generating valid solver files for complex processes. Zero-shot prompting commonly failed in simulations with intricate settings, even for large models. Challenges with boundary conditions and solver keywords stress the requirement for expert supervision, indicating that further development is needed to fully automate specialized CFD simulations.
title A Status Quo Investigation of Large Language Models towards Cost-Effective CFD Automation with OpenFOAMGPT: ChatGPT vs. Qwen vs. Deepseek
topic Computation and Language
url https://arxiv.org/abs/2504.02888