基于db5小波分析的u-blox惯导信息去噪实现  

Implementation of u-blox INS information denoising based on db5 wavelet analysis

作　　者：于露 马红皎[1] 罗近涛 胡永辉[1] YU Lu;MA Hong-jiao;LUO Jin-tao;HU Yong-hui(National Time Service Center,Chinese Academy of Sciences,Xi’an 710600,China;School of Electronic,Electrical and Communication Engineering,University of Chinese Academy of Sciences,Beijing 101400,China)

机构地区：[1]中国科学院国家授时中心,西安710600 [2]中国科学院大学电子电气与通信工程学院,北京101400

出　　处：《时间频率学报》2020年第1期54-65,共12页Journal of Time and Frequency

基　　金：地理信息工程国家重点实验室2017年度开放基金资助课题(SKLGIE2017-Z-1-1)。

摘　　要：使用快速傅里叶变换、功率谱密度法、Allan方差分析法对UBLOX-EVK-M8U的微机械惯导器件进行了频域与时域的分析,获得了其随机噪声的主要来源为量化噪声、角速度随机游走和零偏不稳定性。在对噪声特性分析的基础上,采用小波变换进行滤波处理。简单介绍了db5小波的基本原理,对不同小波变换的去噪效果进行分析比较,并找到了最佳匹配类型。最后设计了一种基于db5小波的处理方法,该方法可以有效去除加速度及角速度的噪声,其仿真结果表明,db5小波5层分解在方差和波形相似度等方面均有明显改善。This study analyzed the UBLOX-EVK-M8U micro-mechanical inertial device in frequency and time domain by the FFT(fast Fourier transform),PSD(power spectral density)and Allan variance methods.And the main source of random noise was obtained,it mainly includes quantization noise,angular velocity random walk and zero offset instability.Based on the analysis of the noise characteristics,the wavelet transform is used for filtering.After introduced the basic principle of db5 wavelet,the denoising effect of different wavelet transforms is analyzed and compared,and the best match type was found.Finally,a processing method based on db5 wavelet is designed.This method can effectively remove the noise of acceleration and angular velocity,the simulation results shown that the db5 wavelet 5-layer decomposition has significant improvements in terms of variance and waveform similarity.

关 键 词：u-blox ALLAN方差 小波分析 惯性导航 

分 类 号：TN967.2[电子电信—信号与信息处理]