Adaptive neural pseudo-inverse control for time-delay nonlinear hysteretic systems considering output constraint and...

Hysteresis nonlinearities, time delays and output constraints are widely present in the practical physical systems such as motion platforms driven by smart material actuators, bionic robots and ultra-high precision machining systems, however, these factors will degrade the control performance and may even induce oscillations in the control system. To overcome the aforementioned problems, in this paper, an adaptive neural pseudo-inverse control scheme is proposed for a class of time-delay nonlinear hysteresis systems considering output constraints with the following contributions: 1) a novel butterfly-like Krasnoselskii-Pokrovskii (BKP) hysteresis model with double loops is constructed to describe the double-loop hysteresis by performing the weighted superposition of the new proposed butterfly-like KP kernel; 2) a novel adaptive pseudo-inverse control algorithm is developed to avoid the difficulty of constructing the direct double-loop inverse model; 3) a new motion control platform actuated by the flexible dielectric elastomer actuators is established to verify the effectiveness of the proposed control scheme and demonstrate its feasibility for drive control systems in soft bionic robots.