Decoupling design of rolling aircraft using adaptive neuro-fuzzy inference systems

In order to solve the coupling problem of the rolling aircraft which is adverse to the control performance during flight, a dynamic decoupling method based on the feedforward compensation decoupling method is proposed. First, the adaptive neuro-fuzzy inference system based on Takagi-Sugeno model is adopted to establish the approximate model of original coupling system. Then, the dynamic decoupling compensator is obtainded according to the decoupling compensation principle which is deduced under the feedforward decoupling framework. Although this method originate from the linear model-based method, it is applicable to both linear and nonlinear problems because the adaptive neuro-fuzzy inference system is used to establish input-output model. A decoupling design example of rolling aircraft is employed to verify the validity of this method and the simulation results show that this method can obtain good decoupling performance in both dynamic and steady responses Even without a accurate system model.