BP-AdaBoost模型在光纤陀螺零偏温度补偿中的应用

刘元元; 杨功流; 李思宜

BP-AdaBoost模型在光纤陀螺零偏温度补偿中的应用

北京航空航天大学仪器科学与光电工程学院, 北京 100191

基金项目: 国家安全重大基础研究资助项目（613186）；中央高校基本科研业务费专项资金资助项目（YWF-10-01-B30）

详细信息

中图分类号: V241.5
计量
- 文章访问数: 1378
- HTML全文浏览量: 178
- PDF下载量: 520
- 被引次数: 0
出版历程
- 收稿日期: 2013-04-19
- 网络出版日期: 2014-02-20

Application of BP-AdaBoost model in temperature compensation for fiber optic gyroscope bias

School of Instrument Science and Opto-electronics Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China

摘要

摘要: 针对光纤陀螺零偏漂移随温度呈复杂的非线性变化，建立了BP-AdaBoost（Back Propagation neural network，Adaptive Boosting）模型对零偏进行补偿，改善了光纤陀螺的零偏稳定性能.同时，研究了模型参数对预测精度的影响，给出了BP神经网络隐含层神经元个数的选择以及AdaBoost模型迭代次数的确定方法.运用AdaBoost算法提升单个BP神经网络的预测能力，提高了集成模型整体的预测精度.对采集的光纤陀螺输出实测数据进行了事后仿真，结果表明，BP-AdaBoost模型相比传统的线性回归模型、混合线性回归模型、单个BP神经网络模型的补偿效果更显著，验证了该模型的有效性，具有重大的工程应用参考价值.
- 光纤陀螺 /
- 温度补偿 /
- AdaBoost算法 /
- BP神经网络
Abstract: Aimed at the complex non-linearity in bias temperature error model of fiber optic gyroscope(FOG), based on back propagation (BP) neural network and adaptive boosting(AdaBoost) learning algorithm, a new BP-AdaBoost temperature compensation method was proposed to effectively enhance the FOG bias stability. The effects of model parameters on the prediction precision were also investigated. A program for determining the number of hidden layer neurons in BP neural network and the number of iterations in AdaBoost model was given. The prediction error by this BP-AdaBoost algorithm is smaller than that by single BP neural network. By large amount of experiments and calculations from FOG, the compensation results show that, the proposed approach has better performance compared with those traditional linear regression model, mixed linear regression model, and single BP neural network. Through the analysis and simulation, this approach improved is validated and has a great value of engineering reference.
- fiber optic gyroscope /
- temperature compensation /
- adaptive boosting (AdaBoost) algorithm /
- back propagation (BP) neural network

HTML全文

参考文献(16)

[1]	韩冰, 林玉荣, 邓正隆．光纤陀螺温度漂移误差的建模与补偿综述[J].中国惯性技术学报, 2009, 17(2):218-224 Han Bing, Lin Yurong, Deng Zhenglong.Overview on modeling and compensation of FOG temperature drift[J].Journal of Chinese Inertial Technology, 2009, 17(2):218-224(in Chinese)
[2]	Xiao Zhi, Ye Shijie, Zhong Bo, et al.BP neural network with rough set for short term load forecasting[J].Expert Systems with Applications, 2009, 36(1):273-279
[3]	韩力群．人工神经网络理论:设计及应用[M].北京:化学工业出版社, 2002 Han Liqun.Theoretics, design and application of artificial neutral network[M].Beijing:Chemical Industry Press, 2002(in Chinese)
[4]	申冲, 陈熙源．基于提升小波与灰色神经网络的光纤陀螺振动误差建模[J].中国惯性技术学报, 2011, 19(5):611-614 Shen Chong, Chen Xiyuan.Vibration error modeling of FOG based on lifting wavelet and grey neural network[J].Journal of Chinese Inertial Technology, 2011, 19(5):611-614(in Chinese)
[5]	周琪, 秦永元, 成研, 等．光纤陀螺热致漂移误差的模糊补偿[J].中国惯性技术学报, 2010, 18(4):471-475 Zhou Qi, Qin Yongyuan, Cheng Yan, et al.Fuzzy compensation of thermally induced bias drift in fiber optical gyro[J].Journal of Chinese Inertial Technology, 2010, 18(4):471-475(in Chinese)
[6]	冯丽爽, 南书志, 金靖．光纤陀螺温度建模及补偿技术研究[J].宇航学报, 2006, 27(5):939-942 Feng Lishuang, Nan Shuzhi, Jin Jing.Research on modeling and compensation technology for temperature errors of FOG[J].Journal of Astronautics, 2006, 27(5):939-942(in Chinese)
[7]	Chen Xiyuan. Modeling temperature drift of FOG by improved BP algorithm and by Gauss-Newton algorithm[M].Berlin:Springer, 2004:805-812
[8]	Schapire R E. The boosting approach to machine learning:an overview[J].Nonlinear Estimation and Classification, 2003: 149- 172
[9]	Green M, Ekelund U, Edenbrandt L, et al.Exploring new possibilities for case-based explanation of artificial neural network ensembles[J].Neural Networks, 2009, 22(1):75-81
[10]	Qiao Changming, Sun Shuli, Hou Ying.Design of strong classifier based on adaboost M2 and back propagation network[J].Journal of Computational and Theoretical Nanoscience, 2013, 10(12): 2836-2840
[11]	Shupe D M.Thermally induced nonreciprocity in the fiber-optic interferometer[J].Applied Optics, 1980, 19(5):654-655
[12]	Hansen L K, Salamon P.Neural network ensembles[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(10):993-1001
[13]	Freund Y, Schapire R E, Abe N.A short introduction to boosting[J].Journal of Japanese Society for Artificial Intelligence, 1999, 14(5):771-780
[14]	Islam M, Yao Xin, Murase K.A constructive algorithm for training cooperative neural network ensembles[J].IEEE Transactions on Neural Networks, 2003, 14(4):820-834
[15]	史峰, 王辉, 郁磊, 等．MATLAB智能算法30个案例分析[M].北京:北京航空航天大学出版社, 2012:237-247 Shi Feng, Wang Hui, Yu Lei, et al.Analysis of MATLAB intelligent algorithm in 30 cases[M].Beijing:Beihang University Press, 2012:237-247(in Chinese)
[16]	陈维娜, 曾庆化, 李荣冰, 等．微机械陀螺温度混合线性回归补偿方法[J].中国惯性技术学报, 2012, 20(1):99-103 Chen Weina, Zeng Qinghua, Li Rongbing, et al.Mixed linear regression temperature compensation method for annular-vibrating MEMS gyroscope[J].Journal of Chinese Inertial Technology, 2012, 20(1):99-103(in Chinese)