Control Law Design for Helicopter Based on Radial Basis Function Neural Network

In this paper, we present a general methodology for flight control law design. The parameter mapping approach is developed to design flight controller parameters according to the desired performance at certain flight states. Parameters obtained at different flight states are used for training a Radial Basis Function Neural Network (RBFNN). Thus, the RBFNN can generalize the information and offer suitable parameters for the controller, which guarantees a good performance of the helicopter within the whole flight envelope. Simulation results using the actual model indicate that the technique presented in this paper is feasible and effective.