Team building at institute level
Ir. at UCL 2017
Main project: Learning and collective intelligence for optimized operations in wake flows
Funding: ERC Project
Supervisor(s): Philippe Chatelain
Physics dictates that a flow device has to leave a wake or the signature of it producing sustentation forces, and can then impact negatively or favorably another device downstream (e.g. Wake turbulence between aircraft in air traffic, wake losses within wind farms). This project proposes an Artificial Intelligence and bio-inspired paradigm for the control of flow devices subjected to wake effects. To each flow device is associated an intelligent agent that pursues given goals of efficiency or turbulence alleviation. Every one of these flow agents now relies on machine-learning tools to learn how to make the right decision when confronted with wake or turbulent flow structures. At a system level, Multi-Agent System and Distributed Learning paradigms are employed. The goal is to demonstrate that the design of a system that learns how to control the flow, is simpler than the design of the control scheme and will yield a more robust scheme.
Collaborative control of multiple devices constitutes a field of development that will be transformative in many engineering areas. Collaboration is indeed proven to consistently bring increased global efficiency, adaptivity and robustness in the applications of interest. The design of robust collaborative schemes is a topic in its own, which is particularly delicate when the devices interactions are flow-mediated, due to the non-linearity of flows. More crucially, they affect the operation of the impacted devices.
IMMC main research direction(s):
Research group(s): TFL