Machine Learning Model for Real Time CFD Prediction

Following an R&D collaboration between the companies Cape Horn Engineering, SumToZero, SailGP Technologies and Navasto, we are proud to present preliminary results of a Machine Learning Model for Real Time CFD Prediction.

Cape Horn Engineering was commission by SumToZero and SailGP Technologies from New Zealand to generate an aerodynamic force model for the current SailGP F50 foiling catamaran, with the all-purpose wing and jib. The full CFD results thus generated using Cape Horn Engineering's state-of-the-art AeroSim Portal were provided to Navasto in Germany, who are experts in AI and Machine Learning solutions, to train a Reduced Order Model (ROM). This ROM can then be used to predict CFD results in real time for new unseen conditions. Furthermore, the model can be interrogated to optimize input parameters and can include constraints. For example, we could optimize inputs to give the maximum driving force, with a constrain on the maximum side force, that can be produced and for a given wind speed.

The movie shows the ParaView plug-in created by Navasto which is used to interface with the ROM. It is possible to change the input parameters and see the results in real-time. The predictions not only include the force results, but the full flow field, thus you can see the pressures on the hull and sails and the streamline around them which show the flow velocity.

This project is a stepping stone to develop the tools necessary for optimizing many engineering problems, with our initial focus on the improvement of Wind Assisted Ship Propulsion (WASP) technologies.

All simulations were performed with the code STAR-CCM+ from Siemens Digital Industries.