Description
The quest for carbon-neutral aviation propels us toward uncharted technological frontiers. In TRANSDIFFUSE, we present an ambitious program to develop an AI-driven model that may revolutionize propulsion technologies. As a synergistic consortium, we unite the numerical modelling prowess of Valero's team, the high-fidelity computational capabilities of Lehmkuhl's group, and Paniagua's experimental ingenuity.
TRANSDIFFUSE aims to develop new tools related to clean propulsion, specifically an AI-driven model called FluidGPT. In doing so, we expect to enable major advancements to the aeronautical and power generation sectors, including, for example, hydrogen pressure gain combustion (PGC) engines, which are compact, lightweight, high-efficiency turbines. In initiating FluidGPT, we aim to overcome challenges like those facing PGC, by exploiting the thing that has made compact turbomachinery so difficult to design: the troublesome transonic flows propelled from the combustor. With our model we aim to control and manipulate those transonic flows.
Our approach to FluidGPT is anchored in characterizing, predicting, and then manipulating the intricate, unsteady, inherently difficult transonic flows thus unlocking the design and development of transonic diffusing passages, a notorious obstacle to designing turbomachinery passages in new, compact, efficient engines. FluidGPT will model the Navier-Stokes equations for such conditions, enabling the prediction and control of previously unmanageable flow behaviours. A complete model of the Navier-Stokes equations in transonic diffusing passages has never been achieved by the scientific community, and our model will be able to reproduce flow configurations never seen before. Embracing innovation and synergy, TRANSDIFFUSE will also unlock new design guidelines and flow control techniques to surmount limitations across the aeronautical and power generation sectors. This program may redefine fluid dynamics modelling and control.
