An attitude control of a helicopter by adaptive PID controller

The effectiveness of neural networks is discussed for nonlinear systems. The radial basis function network (RBFN) is proposed as one of the neural networks. This network has the bases functions, therefore, the large value can be obtained in the neighborhood of the training data. In this paper, the RBFN is utilized for the purpose of nonlinear compensation. That is, the control parameters are tuned by RBFN. First, the suitable values are learned for RBFN by using the input and output data. Finally, the practically and utility of proposed method is discussed through the experimental evaluation of the infrared-controlled model helicopter.