Modelling of 3D Dynamic Stall Using CFD and Neural Networks

Numerical simulation of 3D dynamic stall has been undertaken using Computational Fluid Dynamics based on the Navier-Stokes Equations. The CFD method has been carefully validated against experimental data before being used to study the topology of the 3D dynamic stall vortex and the effects of yaw and rotation on its shape and trajectory. The 3D unsteady viscous computations were found to give a wealth of results at the expense of significant amounts of CPU time. To alleviate this problem and to develop a faster model for 3D dynamic stall aerodynamic loads a neural network was put forward. The neural network was trained using both CFD and experimental data and was subsequently used as a method for interpolating dynamic stall loads between known states for which CFD or experimental data were available. The neural network was found to work well for such interpolations but its capability to extrapolate outside its training envelope was somehow limited. Nevertheless, the neural network was found to be a very efficient technique for reconstructing 3D dynamic stall and has demonstrated great potential as a method for reducing non-linear aerodynamics to a simple computational model.