Research on H_∞ adaptive control of aero-engine based on RBF neural network compensation

Abstract

Aero-engine control system is an important mechanism of aircraft, the uncertainty of control gain attenuation and unmodeled dynamics of aero-engine can affect its control performance, therefore, a controller combining H∞ adaptive control and compensation control is designed.Firstly, the H∞ adaptive controller is designed based on the mixed sensitivity theory.And then, based on Lyapunov strict stability theory, the radial basis function (RBF)neural network compensation controller is designed to compensate the uncertainty, and the fitting speed is adjusted by the linear function related to the error.Finally, the normalized aero-engine model is taken as the controlled object to carry out the multi-variable simulation test.The results show that the adaptive controller designed in this paper can effectively compensate the uncertainty and reduce the overshoot and adjusting time compared with the H∞controller.

Keywords

• aero-engine
• multi-variable control
• uncertainty
• mixed sensitivity
• rbf neural network compensation