摘要
微机电系统(MEMS)陀螺仪的零位偏移是影响惯性导航定位精度的主要原因之一。针对MEMS陀螺仪零位随温度变化的非线性偏移问题,提出一种基于风驱动优化-最小二乘支持向量机(WDO-LSSVM)的MEMS陀螺仪零偏温度补偿模型。通过小波变换对MEMS陀螺仪三轴输出数据进行滤波预处理,结合最小二乘支持向量机(LSSVM)和风驱动优化(WDO)算法,构建MEMS陀螺仪的零偏温度补偿模型。实验结果表明:与传统的反向传播神经网络(BP)模型、粒子群优化-最小二乘支持向量机(PSO-LSSVM)模型相比,所提模型的陀螺仪零偏均方根误差和平均绝对误差均减小了约50%,实现了具有良好普适性的MEMS陀螺仪零偏温度补偿,进而可以提高惯性导航系统的定位精度。
The microelectromechanical system(MEMS)gyroscope zero bias is one of the key factors that affect the inertial navigation and positioning accuracy.To solve the nonlinear drift of MEMS gyroscope zero bias varying with temperature,a temperature compensation model based on wind driven optimization-least squares support vector machines(WDO-LSSVM)is proposed.The three-axis output data of MEMS gyroscope is filtered and preprocessed by wavelet transform,and the zero bias temperature compensation model is established by combining least square support vector machine(LSSVM)with wind-driven optimization(WDO)algorithms.The experimental results show that both the root mean square error and the mean absolute error of the proposed model are reduced by about 50% compared with traditional back propagation neural network(BP)model and particle swarm optimization least squares support vector machine(PSO-LSSVM)model.The proposed model has good universality in MEMS gyroscope compensation of bias drift with temperature and enables positioning accuracy improving of inertial navigation system.
作者
刘宇
林非凡
陈燕苹
彭慧
韩亮
汪立新
LIU Yu;LIN Feifan;CHEN Yanping;PENG Hui;HAN Liang;WANG Lixin(Chongqing Key Laboratory of Autonomous Navigation and Microsystems,Chongqing University of Posts and Telecommunications,Chongqing 400065,China;Chongqing Engineering Research Center of Intelligent Sensing Technology and Microsystem,Chongqing University of Posts and Telecommunications,Chongqing 400065,China;School of Missile Engineering,Rocket Force University of Engineering,Xi'an 710025,China)
出处
《中国惯性技术学报》
EI
CSCD
北大核心
2023年第7期688-695,共8页
Journal of Chinese Inertial Technology
基金
国家自然科学基金(52175531)
重庆市教育委员会科学技术研究项目(KJZD-M202000602)。
关键词
MEMS陀螺仪
风驱动优化算法
最小二乘支持向量机
温度补偿
MEMS gyroscope
wind driven optimization algorithm
least squares support vector machine
temperature compensation
