Adaptive Neural Backstepping Approximated Inverse Control for a Class of Fractional-Order Hysteretic Nonlinear Time-Delay Systems with Unknown Control Direction

The wide application of motion control system based on intelligent material actuator in soft robot, this paper proposes a neural adaptive fractional-order backstepping approximated inverse control (NAFBAIC) strategy for a class of fractional-order time-delay systems with unknown control direction, and hysteretic nonlinearities as input. The main innovations are as follows: 1)Without establishing an exact inverse model of hysteresis, efficient control is achieved for the first time in a fractional-order system; 2)By applying the frequency distribution model, the finite fractional-order state-space representation is transformed into infinite dimension, and the Lyapunov functions is constructed on the basis; 3)The Nussbaum function is introduced into the fractional-order system to solve the problem of unknown control direction; 4)The finite covering lemma is combined with the neural network to approximate the unknown nonlinear function with time-delay in the systems, which reduces the tracking error and improves the control accuracy. Simulation results show the effectiveness of the proposed control strategy.