Sensitivity analysis of large body of control parameters in machine learning control of a square-back Ahmed body

Abstract

Active drag reduction (DR) of a square-back Ahmed body is experimentally studied based on machine learning or artificial intelligence (AI) control. The control system consists of four independently operated arrays of pulsed microjets, 25 pressure taps and an explorative downhill simplex method controller. Two strategies, i.e. asymmetric and symmetric actuations, are investigated, with 12 and 9 control parameters, respectively. Both achieve a DR by 13%, though with distinct flow physics and control mechanisms behind. A model linking the control parameters with the cost is developed based on Taylor expansion around the K-nearest neighbours of the smallest cost obtained from the AI control, resulting in a substantially reduced deviation between measured and predicted costs, especially when involving a large number of control parameters, compared with that based on Taylor expansion around the optimum cost. Sensitivity analysis, conducted based on the model, indicates that the control efficiency, i.e. the ratio of the power saving from DR to the total power consumption, may reach 55 and 78 for the symmetric and asymmetric strategies, respectively, given a 1–2% sacrifice on DR. This efficiency greatly exceeds that (26.5) obtained by Fan et al. (Fan et al. 2020 Phys. Fluids 32 , 125117. ( doi:10.1063/5.0033156 )), whose independent control parameters are only three.