光学精密工程2026，Vol.34Issue(2)：231-244,14.DOI:10.37188/OPE.20263402.0231
压电快速反射镜的神经网络滑模控制
Neural network sliding mode control for piezoelectric fast steering mirrors
摘要
Abstract
To meet the demanding requirements of high-precision alignment and tracking in laser communi-cation systems operating under complex environmental conditions,this paper presented a novel control al-gorithm for a piezoelectric-actuated fast steering mirror(FSM).A Hammerstein-structured nonlinear model incorporating a Prandtl-Ishlinskii hysteresis representation was established for the piezoelectric actu-ator,and system linearization was achieved through a geometrically derived inverse model employed as a feedforward compensator.For the linearized system,a hybrid control strategy integrating radial basis func-tion(RBF)neural networks with sliding mode control was designed,where the RBF network approximat-ed unmodeled nonlinear parameters within the nonsingular fast terminal sliding mode control framework to enhance robustness while maintaining tracking precision.Experimental validation on a servo platform con-firms the algorithm's effectiveness in tracking composite-frequency trajectories with a root mean square er-ror below 2.7 μrad.Under 10%model mismatch conditions,the method maintains a root mean square er-ror under 7.3 μrad when tracking 50 Hz sinusoidal signals,representing performance improvements of ap-proximately 40.16%and 75.9%over conventional nonsingular fast terminal sliding mode control and ac-tive disturbance rejection control,respectively,while demonstrating strong robustness against parameter perturbations.关键词
激光通信/压电驱动/快速反射镜/径向基神经网络/滑模控制Key words
laser communication/piezoelectric actuation/fast steering mirror/radial basis function neu-ral network/sliding mode control分类
信息技术与安全科学引用本文复制引用
鹿麟,孙崇尚,李智斌,刘亚洲..压电快速反射镜的神经网络滑模控制[J].光学精密工程,2026,34(2):231-244,14.基金项目
国家自然科学基金项目(No.U23A20336,No.52227811) （No.U23A20336,No.52227811）
山东省自然科学基金项目(No.ZR2024MF133) （No.ZR2024MF133）
山东省重点研发计划(No.2024TSGC0269) （No.2024TSGC0269）
青岛西海岸新区"一事一议"人才项目 （）
