A statistical estimator of turbulence intermittency in physical and numerical experiments

The velocity increments statistic in various turbulent flows is analysed th rough the hypothesis that different scales are linked by a multiplicative p rocess, of which multiplier is infinitely divisible. This generalisation of the Kolmogorov-Obukhov theory is compatible with the finite Reynolds numbe r value of real flows, thus ensuring safe extrapolation to the infinite Rey nolds limit. It exhibits a beta estimator universally depending on the Reyn olds number of the flow, with the same law either for Direct Numerical Simu lations or experiments, both for transverse and longitudinal increments. As an application of this result, the inverse dependence R-lambda = f(beta) i s used to define an unbiased R-lambda value for a Large Eddy Simulation fro m the resolved scales velocity statistics. However, the exact shape of the multiplicative process, though independent of the Reynolds number for a giv en experimental setup, is found to depend significantly on this setup and o n the nature of the increment, longitudinal or transverse. The asymmetry of longitudinal velocity increments probability density functions exhibits si milarly a dependence with the experimental setup, but also systematically d epends on the Reynolds number.