Machine learning control for drag reduction of a car model in experiment

International audienceWe investigate experimentally a novel model-free in-time control strategy, calledMachine Learning Control (MLC), for aerodynamic drag reduction of a car model. Fluidicactuation is applied at the trailing edge of a blunt-edged Ahmed body combined with a curveddeflection surface. The impact of actuation on the flow is monitored with base pressure sensors.Based on the idea of genetic programming, the applied model-free control strategy detects andexploits nonlinear actuation mechanisms in an unsupervised manner with the aim of minimizingthe drag. Key enabler is linear genetic programming as simple and efficient framework formultiple inputs (actuators) and multiple outputs (sensors). The optimized control laws compriseperiodic forcing, multi-frequency forcing and sensor-based feedback control. Approximately 33%base pressure recovery associated with 22% drag reduction is achieved by the optimal controllaw for a turbulent flow at Re H ≈ 3 × 10 5 based on body height