Backward-Facing Step flows are a very common benchmark problem to assess the reliability of a software for industrial applications. Neural Concept explored such an application: the generalisation to volumetric fields predictions.
An engineer wants to improve the design of an existing fixed-wing UAV by increasing lift by 1.5 times in order to let it carry heavier loads. He wants to leverage on drag measurements for 10 previous prototypes which were tested in a wind tunnel, on a past simulation results database produced by its department over the years with 500 simulated shapes. He can also use new simulations, but each call to a simulation costs 100$ and takes one day on a cluster of machines.
Hydrofoils make everything from water skis to sailboats to giant ferries faster (much faster). Using Neural Concept Shape, these hydrofoils were optimized to reach better performances, allowing to fly faster, longer and safer.
Cycling up to 136.7 km/h, with the only power of your legs? This is the incredible achievement of the IUT Annecy team, using our favorite aero-bike, optimized using Neural Concept Shape.
Satellites: A smarter design regarding the thermal constraints
Satellites are subject to very strong thermal exchanges and which are often very complex to model. As opposed to previous methods, Neural Concept Shape is able to take into account thermal properties to optimise any given shape, to minimize its weight while ensuring the mechanical stability.
Formula 1: Multiple connected components and long-range aerodynamic correlations
Formula 1 requires a very high degree of accuracy, where even the slightest improvement can be a game-changer. Neural Concept Shape is able to match these requirements, and brings real-time design interaction to the engineer.