Abstract
Accurate prediction of labyrinth seal flows is important for the design and optimisation of turbomachinery. However, the prediction of such flows with RANS turbulence models is still lacking. The identification of modelling deficits and the development of improved turbulence models requires detailed experimental data. Consequently, a new test rig for straight labyrinth seals was built at the Institute for Turbomachinery and Fluid Dynamics which allows for non-intrusive measurements of the three dimensional velocity field in the cavities.
Two linear eddy viscosity models and one algebraic Reynolds stress turbulence model have been tested and validated against global parameters, local pressure measurements, and non-intrusive measurements of the velocity field. While some models accurately predict the discharge coefficient, large local errors occurred in the prediction of the wall static pressure in the seal. Although improved predictions were possible by using model extensions, significant errors in the prediction of vortex systems remained in the solution. These were identified with the help of PIV results. All turbulence models struggled to accurately predict the size of separations and the swirl imposed by viscous effects at the rotor surface. Additionally, the expansion of the leakage jet in the outlet cavity is not modelled correctly by the numerical models. This is caused by a wrong prediction of turbulent kinetic energy and, presumably, its rate of dissipation.
