采用BP神经网络的四频激光陀螺零偏的光强补偿方法  

Light intensity compensation of four-frequency laser gyro′s bias based on BP neural network

作　　者：赵洪常[1] 肖光宗[1] 汪之国[1] 张斌[1] 

机构地区：[1]国防科学技术大学光电科学与工程学院光电工程系,湖南长沙410073

出　　处：《红外与激光工程》2013年第2期355-360,共6页Infrared and Laser Engineering

基　　金：国防科技大学优秀研究生创新资助项目(B090703);湖南省研究生科研创新资助项目(CX2010B036)

摘　　要：总结了环境因素对四频激光陀螺光强和零偏影响的3种常见方式,指出光强变化和零偏变化都是陀螺经环境因素作用后的外在表现,光强更能全面细致地反映环境因素对陀螺零偏的影响,提出了以光强为基准采用BP神经网络对零偏进行补偿的方法。建立了陀螺零偏的BP神经网络,采用该神经网络针对开机零漂、跳模和高低温冲击等3种不同的零漂产生机理分别进行了补偿实验,实验表明:该方法能够有效辨识产生零漂的不同机理并进行补偿,对提高复杂环境下陀螺的零漂性能有一定的参考意义。Three different manners of environmental factors′ effects on the light intensity and bias of four-frequency laser gyro were summarized.Since both light variation and null drift were the laser gyro′s response to environmental factors′ effects,light intensity can reflect the environmental factors′ effects on laser gyro′ s bias well.As a result,a novel approach of light intensity compensation of four-frequency laser gyro′ s bias based on BP neural network was presented.A BP neural network of laser gyro′ s bias was set up.Then the light intensity compensation experiments for three different mechanisms of generating null drift,including startup null drift,mode hopping,and high-low temperature process,were carried out.It can be concluded that the approach can distinguish above three different mechanisms and compensate for their effects.The approach is meaningful to enhancing the laser gyro′s performance under the complex environment.

关 键 词：四频激光陀螺 零偏 BP神经网络 光强 

分 类 号：TN241[电子电信—物理电子学]