Deadzone compensation in nonlinear systems using neural networks

A compensation scheme is presented for general nonlinear actuator deadzones of unknown width in nonlinear systems. The compensator uses two neural networks (NN), one to estimate the unknown deadzone and another to provide adaptive compensation in the feedforward path. The compensator NN has a special augmented form containing extra neurons whose activation functions provide a ´jump function basis set´ for approximating piecewise continuous functions. Closed-loop stability analysis for the deadzone compensator is provided, and yields tuning algorithms for the weights of the two NN. The technique provides a general procedure for using NN to determine the pre-inverse of an unknown right-invertible function.