Adaptive Trajectory Tracking Control for Dual-Axis Rotary Piezoelectric Micro/Nano Manipulator Based on RBF Neural Network Sliding Mode Control

With the rapid development of micro/nano technology, the application demand for dualaxis rotary piezoelectric micro/nano manipulator in precision instruments such as Scanning Electron Microscopes (SEM) is increasing. To address the nonlinear characteristics and uncertainties inherent in the system, this paper proposes an Adaptive Sliding Mode Control (ASMC) based on Radial Basis Function (RBF) neural networks (RBF-ASMC). By combining the Lagrangian equation and the improved Bouc-Wen hysteresis model, the dynamic model of the system was established. Subsequently, based on the established sliding mode dynamic equation, RBF neural networks were used to approximate the unknown dynamics of the system, and adaptive laws were utilized to optimize control parameters. Simulation results showed that when the RBF-ASMC was applied to a dual-axis rotary system, the mean error (MAE) was $0.009^{\circ}$, the root mean square error (RMSE) was $0.025^{\circ}$, and the convergence time was 0.85 s. Compared with traditional Feedback Linearization Control (FLC) and Nonlinear Disturbance Observer Sliding Mode Control (NDOSMC), RBF-SMC had stronger adaptability and antiinterference ability.