Skip to Main Content
Summary form only given, as follows. This paper presents a combination of simple adaptive control (SAC) method and neural networks for a multi-input multi-output (MIMO) nonlinear magnetic levitation system. The control input is given by the sum of the output of the simple adaptive controller and the output of the neural network. The neural network is used to compensate the nonlinearity of the plant dynamic of the magnetic levitation plant that is not taken into consideration in the usual SAC. The role of the neural network is to construct a linearized model by minimizing online the output error caused by nonlinearities in the control systems.