Adaptive Neural Network Based Approach for Active Flow Control

摘要

This paper presents an intelligent control system architecture for micro-adaptive flow control applications. The proposed adaptive non-model based control approach is motivated by the difficulty in constructing an accurate physical model of the micro-adaptive flow control system. The control architecture employs a Neural Network based adaptive control process, and a novel method for protecting the adaptive system from poorly modeled actuator nonlinearities, such as saturation and hyteresis. We give a simple illustration of these features by considering a ducted rotor model.