Neural Concept Shape used to Optimize the Aerodynamics Properties of Tomorrow’s Airplanes

Using Neural Concept Shape’s surrogate model, Airbus was able to reduce the average time it takes to predict the pressure field on the external body of airplanes from one hour to 30 ms, i.e. over 3 orders of magnitude speed-up.

A customized application was delivered at the end of this first project.

Sharpness of results : NCS was able to reliably predict non-linear flow such as shock waves and the overall error range was within the range of the full-fledged numerical solver with a R2 accuracy of 0.99.

The process will make it possible to take into account aerodynamics performance during the optimization of the structure of the wing and avoid lengthy iterations between teams. NCS has been tested and approved by Airbus’ engineers and we are now collaborating to accelerate the engineering process and to generate new design solutions across many kinds of design problems in areas such as fluid dynamics, structural engineering, and electromagnetics.

Figure 1: Pressure distribution over an airfoil, comparison between NCS (red) and the simulation (blue). Note that the engineers can also vary the Mach number and the angle of attack
Figure 2: NCS is reaching very high level of accuracy, with a R2 of 0.993
About the author
Thomas von Tschammer
As Neural Concept Director of Operation, he joined the team in 2018 aiming to empower engineers with next a next generation tool dedicated to CAD and CAE.