采用神经网络补偿压电陀螺的零位温漂  

Bias temperature compensation for piezoelectricity gyro using neural network

作　　者：潘英俊[1] 邱建勋[1] 刘宇[1] 黎蕾蕾[1] 

机构地区：[1]重庆大学光电技术及系统教育部重点实验室,重庆400044

出　　处：《自动化与仪器仪表》2006年第4期14-17,共4页Automation & Instrumentation

摘　　要：针对中低精度的压电陀螺静态零位输出随温度漂移严重的问题,分析了产生的原因,做了相应的实验,提出了用BP神经网络进行补偿的方法。该方法具有很强的非线性映射能力,减少压电陀螺的零位输出误差,并且将实验结果与传统的方法的结果进行比较,实验证明,在不改变陀螺结构的情况下,该方法能有效地将陀螺的静态零位温漂误差减小一个数量级以上,从而使该类型陀螺能够应用于中高精度系统中。In the view of serial temperature excursion of piezoelectricity gyro, we analysis the reason for temperature excursion, do the experiment, and propose the way of BP neural network to compensate the temperature excursiorL This method is very functional in non-linear mapping and it could reduce the output error of piezoelectricity gyro, we compare the result with the result of traditional method, it is proved by the experiment that this method could reduce the gyro＇s static bias temperature output error at least 1 order even we do not change the gyro＇s structure, so it could apply this type of gyro to media-high accuracy system.

关 键 词：压电陀螺 温度补偿 BP神经网络 建模 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]