In this course, you'll explore how to integrate machine learning techniques with computational fluid dynamics to enhance thermal flow predictions and optimize engineering designs. You'll start with the basics of fluid mechanics, gradually moving into machine learning models that apply to physical systems, synthetic data generation, and the use of physics-informed neural networks. The course also emphasizes real-time integration of these hybrid methods into workflows, comparing them to classical CFD approaches in terms of accuracy and efficiency.
What you'll learn
understand the fundamentals of fluid mechanics relevant to machine learning models
apply machine learning architectures to physics-based systems
validate machine learning models against high-fidelity CFD simulations
generate synthetic data for training machine learning models
integrate ML-CFD methods into engineering design processes
Course objectives
to teach the integration of machine learning with computational fluid dynamics
to provide insights into advanced thermal flow predictions
to compare hybrid ML-CFD methods with classical approaches