基于径向基神经网络的声光偏转器控制模型研究  

Control model of acousto-optic deflector based on radial basis function neural network

作　　者：章晓峰[1] 金韬[1] 

机构地区：[1]浙江大学信息与电子工程系,浙江杭州310027

出　　处：《光学仪器》2008年第5期48-52,共5页Optical Instruments

基　　金：国家自然科学基金资助项目(60307005)

摘　　要：声光偏转是一种高速非机械光束方向控制技术,近年来在卫星光通信领域日益受到重视。运用径向基(RBF)神经网络模型实现声光偏转器光束方向控制,通过训练对RBF网络的权值和网络层元数等结构参数进行优化,调整得到理想模型。研究结果验证了该模型的可靠性与准确性。As a high-speed non-mechanical beam steering technology, acousto-optic deflection has attracted more and more attention in the field of satellite optical communication recently. The beam steering control algorithms of acousto-optic deflector are based on a radial basis function （RBF） neural model. The ideal control model is established by optimizing the parameters and structure of the RBF neural network through training. Study results show its reliability and accuracy of the proposed control model.

关 键 词：径向基神经网络 四象限探测器(QD) 声光偏转器 卫星光通信 

分 类 号：TN929.13[电子电信—通信与信息系统]