Reconfigurable Fault Tolerant Control for nonlinear aircraft based on concurrent SMC-NN adaptor

Abstract

This work focuses on an improved reconfigurable Fault Tolerant Flight Control (FTFC) strategy based on a traditional model reference Neural Network (NN) adaptive flight control architecture. An expanded control scheme is developed by using a concurrent learning NN strategy combined with the Sliding Mode Control (SMC) theory. The improved NN using concurrent update information to compensate for model inversion error is described for the full dynamic characteristics of the aircraft system. The SMC is implemented to treat the NN as a controlled system and allows a stable, dynamic calculation of the learning rates. The proposed reconfigurable FTFC system based on concurrent SMC-NN adaptor is tested on a nonlinear Unmanned Aerial Vehicle (UAV), the Machan UAV, in the presence of fault and disturbance scenarios. The results show that the designed controller achieves better adaptive performance by using the SMC in on-line concurrent NN learning law.