Generalized predictive control of time-delay nonlinear systems based on extreme learning machine

For a class of nonlinear controlled objects with time-delay, this paper proposes a generalized predictive self-tuning control method based on extreme learning machine. In the generalized predictive self-tuning control (GPC), the predictive model of the nonlinear controlled object is established by the extreme learning machine (ELM), and constantly revising forecast output data to improve the accuracy of the prediction. The controller adopts a GPC implicit correction algorithm, without to identify the model parameters, the calculated amount is greatly reduced. The simulation shows that the method in this paper is superior and practical, the prediction output track the reference trajectory better than the commonly used PID self-tuning method.