Cape Horn Engineering has carried out a research project in collaboration with SumToZero, Sail GP Technologies and NAVASTO to build a machine learning model for real time computational fluid dynamics (CFD) predictions.
The project has predicted new sailing conditions in less than a second, an average 1666x faster compared to running a full simulation.
Cape Horn Engineering’s AeroSim Portal was used to run a matrix for the SailGP F50 foiling catamarans, in which they varied many sailing parameters such as ride height, trim and heel, and sail shapes like the sheeting angle, flap angle and flap twist, as well as the jib shape.
The sailing changes were tested in varying boat speed, wind speeds and directions, amounting to 400 simulations.
Great experience
“As we already had the large dataset from our CFD run, these F50 simulations became the perfect foundation to start pushing into the world of machine learning,” said a spokesperson from Cape Horn Engineering. “We had been contacted by NAVASTO who has great experience in the field but was yet to apply it to the marine industry, thus the collaboration began.”
The project is a step forward in to developing the tools necessary to improve of Wind Assisted Ship Propulsion (WASP) technologies, replacing wind tunnel testing.
“Our long-term vision has always been to supersede the wind tunnel once and for all for racing teams, replacing the need to book tunnel sessions to learn sail trim using scaled down sail models,” said the spokesperson.
“The power of the tools used in this project make it possible to trim sails in real time and directly see how the flow is affected.”
The tools can also be extended to virtual reality, as well as providing a more controlled environment for systematic testing.
“We are one step closer to our vision with these latest tools,” said the spokesperson.
