Robust identification of non-linear dynamic systems using support vector machine

The paper proposes a general framework for modelling non-linear dynamic systems based on a support vector machine (SVM): it first provides a short introduction to regression SVMs, then uses a standard SVM to model a non-linear auto-regressive and moving average (NARMAX) model, and contains a theoretical discussion about its robustness under low and high noise by its properties. The simulation results indicate that the SVM method can reduce the effect of samples and noise for modelling, and its performance is better than that of the neural network modelling method.