Nonlinear System Control Using Neural Networks

The paper is focused especially on presenting possibilities of applying off-line trained artificial neural networks at creating the system inverse models that are used at designing control algorithm for non-linear dynamic system. The ability of cascade feedforward neural networks to model arbitrary non-linear functions and their inverses is exploited. This paper presents a quasi-inverse neural model, which works as a speed controller of an induction motor. The neural speed controller consists of two cascade feedforward neural networks subsystems. The first subsystem provides desired stator current components for control algorithm and the second subsystem provides corresponding voltage components for PWM converter. The availability of the proposed controller is verified through the MATLAB simulation. The effectiveness of the controller is demonstrated for different operating conditions of the drive system.