运用神经网络代数算法的陀螺仪非线性误差补偿  

Nonlinear Error Compensation of Gyroscope Using Algebra Algorithm of Neural Networks

作　　者：马斌良[1] 黄玉美[1] 刘蜀阳[1] 陈亮[1] 

机构地区：[1]西安理工大学机械与精密仪器工程学院,陕西西安710048

出　　处：《应用科学学报》2008年第4期436-440,共5页Journal of Applied Sciences

基　　金：国家自然科学基金(No.50075069);陕西省教育厅产业化培育计划(No.03JC17)资助项目

摘　　要：为了提高陀螺仪的测量精度,基于神经网络代数算法提出一种新的非线性误差补偿模型.由于该算法将复杂非线性优化问题转化为线性代数方程组问题,所以该模型具有速度快、实时性好和能实现样本空间精确映射的优点.通过实验对比证明该模型比曲线拟合精度要高.多次重复性实验证明该模型能够将误差限制在0.1(°)/s以内,满足实际控制要求.To improve measurement precision of gyroscope, a novel nonlinear error compensation model is proposed using an algebra algorithm of neural networks. The model has advantages of real-time processing and precision mapping in the sample space because the algorithm transforms the complicated nonlinear optimization problem into linear algebraic equations. Compared to polynomial show that the model can reduce error to 0.1（°）/s fitting, the proposed model has better precision. Experiments and meet practical control needs.

关 键 词：陀螺仪 神经网络 代数算法 非线性误差补偿 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置]