基于相关向量机的MEMS加速度计零偏温漂补偿

徐哲; 刘云峰; 董景新

基于相关向量机的MEMS加速度计零偏温漂补偿

清华大学精密仪器系, 北京 100084

基金项目: 总装“十二五”预研资助项目（513090203**）

详细信息

中图分类号: U666.1
计量
- 文章访问数: 1505
- HTML全文浏览量: 119
- PDF下载量: 586
- 被引次数: 0
出版历程
- 收稿日期: 2012-12-18
- 网络出版日期: 2013-11-30

Thermal bias drift compensation of MEMS accelerometer based on relevance vector machine

Department of Precision Instrument, Tsinghua University, Beijing 100084, China

摘要

摘要: 应用相关向量机（RVM，Relevance Vector Machine）回归预测方法建立了基于RVM的零偏温漂预测补偿模型，利用温度值和温升速率作为输入可预测不同温变过程下的加速度计零偏温漂，探讨了不同训练样本数量、核函数类型和不同的核函数宽度对预测补偿效果的影响，最后应用环境温度试验数据对模型进行检验和验证.结果表明：基于RVM的零偏温漂预测补偿模型能够有效的预测微机械（MEMS，Micro Electro Mechanical Systems）加速度计零偏温漂，模型预测的均方根误差小于1%，补偿后滞环误差最大由0.06g缩减为0.015g.
- 相关向量机 /
- 加速度计 /
- 零偏温漂
Abstract: Thermal bias drift prognosis and compensation model was built based on the regression algorithm of relevance vector machine. The thermal bias drift of the accelerometer experiencing different temperature load can be classified by using both the temperature and the temperature rate as the model input. The influence of training sample number, the kernel function and the parameter sigma were discussed. Experimentation with the data of the temperature cycling test was conducted. According to the experimental result, the thermal bias drift of the accelerometer can be prognosed accurately by the model, the mean square error is less than 1%, and the size of the thermal hysteresis loop is reduced from 0.06g to 0.015g.
- relevance vector machine /
- accelerometer /
- thermal bias drift

HTML全文

参考文献(12)

[1]	董景新.惯性仪表——微机械加速度计[M].北京:清华大学出版社, 2002:1-5 Dong Jingxin.Micro inertial instrument:micromechanical accelerometer[M].Beijing:Tsinghua University Press, 2002:1-5 (in Chinese)
[2]	张鹏飞, 王宇, 龙兴武, 等.加速度计温度补偿模型的研究[J].传感技术学报, 2007, 20 (5):1012-1016 Zhang Pengfei, Wang Yu, Long Xingwu, et al.Research on temperature compensating model for accelerometer[J].Chinese Journal of Sensors and Actrator, 2007, 20 (5):1012-1016 (in Chinese)
[3]	王立昆, 杨新锋.一种基于RVM回归的分类方法[J].电子科技, 2011, 24 (5):14-16 Wang Likun, Yang Xinfeng.A classification method based on RVM regression[J].Electronic Science and Technology, 2011, 24 (5):14-16 (in Chinese)
[4]	陈佳, 颜学峰, 钟伟民, 等.基于多项式核rvm的非线性模型预测控制[J].控制工程, 2008, 15 (2):158-160 Chen Jia, Yan Xuefeng, Zhong Weimin, et al.Nonlinear model predictive control based on RVM with polynomial kernel[J].Control Engineering of China, 2008, 15 (2):158-160 (in Chinese)
[5]	Tipping M E.Sparse Bayesian learning and the vector machine[J].The Journal of Machine Learning Research, 2001, 1 (3):211-244
[6]	Faul A C, Tipping M E.Analysis of sparse Bayesian learning[C]//Advances in Neural Information Processing Systems (NIPS 14) .Vancouver:NIPS, 2002:383-389
[7]	Wong P K, Xu Q, Vong C M, et al.Rate-dependent hysteresis modeling and control of a piezostage using online support vector machine and relevance vector machine[J].Industrial Electronics, IEEE Transactions on, 2012, 59 (4):1988-2001
[8]	Ding Errui, Zeng Ping, Yao Yong.A novel regressive algorithm based on relevance vector machine[C]//Fourth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2007) .Piscataway, NJ:IEEE, 2007:463-467
[9]	Wong P K, Wong H C, Vong C M.Modelling and prediction of automotive engine airratio using relevance vector machine[C]//2012 12th International Conference on Control Automation Robotics & Vision (ICARCV) .Piscataway, NJ:IEEE, 2012:1710-1715
[10]	Liu F, Song H, Qi Q, et al.Time series regression based on relevance vector learning mechanism[C]//2008 International Conference on Wireless Communications, Networking and Mobile Computing.Piscataway, NJ:IEEE Computer Society, 2008:1-4
[11]	Yang B, Zhang Z, Sun Z.Robust relevance vector regression with trimmed likelihood function[J].Signal Processing Letters, IEEE, 2007, 14 (10):746-749
[12]	Yuan J, Bo L, Wang K, et al.Adaptive spherical Gaussian kernel in sparse Bayesian learning framework for nonlinear regression[J].Expert Systems with Applications, 2009, 36 (2):3982-3989