Start date: Between 1st August 2027 and 1st July 2028
Application deadline: 23:59, 4th January 2027 (UK time)
Introduction: The development of sustainable propulsion systems, based on hydrogen or sustainable aviation fuels (SAFs), is increasing the risk of extreme events occurring in these. These are rare events where the flow in the combustor suddenly takes extreme states far, potentially with grave consequences. Examples are flashback in hydrogen or thermoacoustic instabilities triggered by the varying SAFs properties. The safe and reliable operation of these future sustainable propulsion systems thus requires the ability to anticipate their occurrence through measurable precursors and the deployment of real-time mitigation based on those precursors.
Traditional methods have generally been unable to tackle this due to the turbulent nature of the underlying flows and the complex multiscale/multiphysics nonlinear interactions at the origin of such extreme events. Recent advances in differentiable solver and machine learning offer a pathway to enable such their mitigation and control.
In this project, you will develop a framework for the control of reacting flow extreme events that combines a differentiable reacting flow solver and a machine learning-based controller. The differentiable solver will provide short-term state dependency used by machine learning-based controller to obtain an optimal mitigation control preventing the reacting flow extreme event. This will be applied across various reacting flow applications, leveraging novel reacting flow actuators such spray water injection or electrically-driven fuel droplet control.
Research Group: You will join a research group on the European project CONTEXT, at the intersection of scientific machine learning and fluid dynamics, under the supervision of Dr. Anh Khoa Doan. You will also have the opportunity to interact with experts in turbulence and machine learning across the department, such as Prof. Luca Magri. Dr. George Rigas or Dr. Andrea Novoa.
Learning opportunities: You will develop expertise in reacting flow physics, machine learning for fluids and control, and high-fidelity simulations. You will have the opportunity of using cutting-edge facilities such as Imperial College HPC facilities.
Professional Development: You will have access to engaging professional development workshops in areas such as research communication, computing and data science, and professional progression through our Early Career Researcher Institute, and will have the opportunity to participate to international conferences.
Supervisors: Dr. Nguyen Anh Khoa Doan
Duration: 3.5 years.
Funding: Full tuition fees and an annual tax-free stipend of £23,805 for Home, EU and International students. Find out more about fee status
Eligibility: Candidates will be expected to achieve/have achieved a First class honours MEng/MSci or higher degree (or international equivalent) in: Aeronautical/Mechanical Engineering, Applied Mathematics, Computer/Data Science, or Applied or Computational Physics
We are looking for students with experience in: Fluid Mechanics, Turbulence, CFD, Machine Learning, Reacting Flows
How to apply: Visit Machine learning-based control of reacting flow extreme events for important instructions on how to apply.
Contact: For project information, email: Dr. Nguyen Anh Khoa Doan
For admissions questions, please read our Frequently Asked Questions. If your question isn’t answered, email the PhD Administrator (Admissions)
Equality, Diversity and Inclusion: Imperial is committed to equality and valuing diversity. We are an Athena SWAN Silver Award winner, a Stonewall Diversity Champion, a Disability Confident Employer and are working in partnership with GIRES to promote respect for trans people.
