Nonlinear reduced-order modeling of unsteady aerodynamic loads based on dynamic local linear neuro-fuzzy models

In the present paper, a reduced-order modeling (ROM) approach based on dynamic local linear neuro-fuzzy models is presented in order to calculate generalized aerodynamic forces in the time-domain. The unsteady aerodynamic forces are modeled as a function of structural eigenmode-based disturbances. In contrast to former aerodynamic input/output model approaches trained by high-fidelity flow simulations, the Mach number is considered as an additional model input to account for varying free-stream conditions. In order to train the relationship between the input parameters and the respective flow-induced loads, the local linear model tree (LOLIMOT) algorithm is used. The ROM method is applied to the AGARD 445.6 configuration in the subsonic and transonic flight regime. It is shown that good agreement is obtained between the ROM results and the respective full-order computational-fluid-dynamics solution.