Adaptive neural event-triggered sliding mode control with hysteresis for piezoelectric actuator

This paper proposes an adaptive event-triggered sliding mode control framework for piezoelectric actuators (PEAs) to effectively handle strong hysteresis and nonlinear characteristics. The inherent hysteresis of the actuator is described using the Bouc–Wen model, while the remaining unknown nonlinearities are approximated through a radial basis function neural network (RBFNN) with formally bounded approximation errors. A sliding mode control law is designed to guarantee robustness against disturbances and model uncertainties, and an event-triggered mechanism is incorporated to significantly reduce unnecessary controller updates, thereby lowering communication and computation costs. A rigorous Lyapunov-based analysis is developed to ensure closed-loop stability under the proposed adaptive update and triggering conditions. Simulation results demonstrate that the proposed method achieves superior tracking accuracy and a notable reduction in triggering frequency compared with existing event-triggered sliding mode control approaches.