Nonlinearity compensation based on identified NARX polynomials models

This paper deals with the compensation of nonlinearities in dynamical systems using Nonlinear polynomial AutoRegressive models eXogenous inputs (NARX) identified from data. The approach is formulated for static and contexts general case also adapted hysteresis. Both simulated experimental results are presented to illustrate method. In case, proposed method compared other approaches was found be competitive. yielded a maximum tracking error $$3.9\%$$ while corresponding value uncompensated system $$21.0\%$$ . Furthermore, technique typically signals lower energy requirements. show that methodology can provide practically linearize simple nonlinear very few terms.