About the project
This PhD project advances deep learning for turbulence modeling in combustion. Using CNNs and GANs, it tackles challenges in data demands and generalization. The goal is to develop predictive models for hydrogen-based and carbon-neutral fuels, guiding sustainable energy design. Key tasks include model optimization, integration, and Exascale scalability.
This project explores the cutting edge of artificial intelligence for turbulence modelling in reacting flows. Using advanced deep convolutional neural networks (CNNs) and generative adversarial networks (GANs), the research aims to create predictive models that reliably simulate turbulent combustion processes. While CNNs and GANs have shown promise in capturing complex flow structures, they also come with challenges, including the need for extensive, high-resolution training data and limitations in generalizing to new conditions.
This project will push the boundaries of current methods, developing models that address specific limitations: CNNs’ difficulty with high-frequency flow features and GANs’ computational demands and lesser-understood components. Additionally, the research will pioneer the use of physics-informed loss functions, enhancing model accuracy and applicability. The ultimate goal is to contribute models that can guide the development of hydrogen and carbon-neutral fuels by predicting multi-regime combustion and multi-scale phenomena, critical to advancing sustainable energy technologies.
Key project tasks include creating specialized training datasets, optimizing network architectures for efficiency, integrating physical constraints, and validating models in realistic settings. This work will also focus on scaling solutions to Exascale computing, bringing new possibilities to the field of combustion simulation.
