Hydrofoils are airfoil-like devices that are used by watercraft to provide lift or stability to a vehicle moving through the water. Computational fluid dynamics (CFD) is a numerical simulation tool that is used to simulate fluid flow around objects like these. Within CFD, turbulence models are used to predict the behavior of a fluid when the flow exhibits very small scales of energetic motion and/or chaos. At best, turbulence models offer an approximation of the complex flow characteristics when flow becomes highly turbulent. Accurate CFD results rely on a fine mesh comprised of smaller elements that form the main object. In this study, an automatic controller is coupled with a turbulence model to control the flow around a hydrofoil based on simple machine learning strategies. The automatic controller was tuned based on a hydrofoil model containing a fine mesh and other complexities that required a long run time to calculate a solution. The tuned controller is then applied to a simpler version of the hydrofoil model in terms of mesh size and turbulence model. The controlled model is evaluated to determine if it can produce the same resulting accuracy based on prior learning from the complex model. Creating a controlled turbulence model to study a hydrofoil will reduce the time and cost for high performance computing resources required in running CFD.