A Status Quo Investigation of Large Language Models towards Cost-Effective CFD Automation with OpenFOAMGPT: ChatGPT vs. Qwen vs. Deepseek
arXiv:2504.02888 · doi:10.1016/j.taml.2025.100623
Abstract
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.
References in corpus (13)
- Machine Learning for Fluid Mechanics
- PaLM: Scaling Language Modeling with Pathways
- Turbulence Modeling in the Age of Data
- Enhancing Computational Fluid Dynamics with Machine Learning
- A Comprehensive Physics-Informed Machine Learning Framework for Predictive Turbulence Modeling
- Physics-Informed Machine Learning Approach for Augmenting Turbulence Models: A Comprehensive Framework
- Deep Neural Networks for Data-Driven Turbulence Models
- OpenFOAMGPT: a RAG-Augmented LLM Agent for OpenFOAM-Based Computational Fluid Dynamics
- Information transfer between turbulent boundary layer and porous media
- Fine-tuning a Large Language Model for Automating Computational Fluid Dynamics Simulations
- Toward Discretization-Consistent Closure Schemes for Large Eddy Simulation Using Reinforcement Learning
- Simulation and analytical modeling of high-speed droplet impact onto a surface
- Optimized Flow Control based on Automatic Differentiation in Compressible Turbulent Channel Flows