다양한 이유에서 오는 알 수 없는 오차들의 추정 보상을 위한 오차 기반 RBF 신경망 적응 백스테핑 제어기 설계

Abstract

The servomechanism of the dual axis pan tilt system is used across a wide range of fields. Hence, it requires a robust controller that can control it under any circumstance. In this paper, a dynamic modeling of the dual axis pan tilt system is presented in a strict feedback form, and a backstepping controller is designed. Moreover, an adaptive backstepping controller is designed in a strict feedback form using error state-based radial basis function (RBF) neural networks (NN). The proposed controller prevent any unknown errors due to modeling errors, disturbances, uncertain parameters, or input saturation from undermining control performance. The activation function of the hidden layer was changed. As a result, minimum inputs decrease learning time, thereby allowing the fast estimation and compensation of unknown errors, improving the control performance by change activation function.