[1]赖际舟,刘建业,盛守照.用于干涉型光纤陀螺温度漂移辨识的RBF神经网络改进算法[J].东南大学学报(自然科学版),2006,36(4):537-541.[doi:10.3969/j.issn.1001-0505.2006.04.009]
 Lai Jizhou,Liu Jianye,Sheng Shouzhao.Improved learning rule of RBFNN for identifying temperature-introduced drift of IFOG[J].Journal of Southeast University (Natural Science Edition),2006,36(4):537-541.[doi:10.3969/j.issn.1001-0505.2006.04.009]
点击复制

用于干涉型光纤陀螺温度漂移辨识的RBF神经网络改进算法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
36
期数:
2006年第4期
页码:
537-541
栏目:
其他
出版日期:
2006-07-20

文章信息/Info

Title:
Improved learning rule of RBFNN for identifying temperature-introduced drift of IFOG
作者:
赖际舟 刘建业 盛守照
南京航空航天大学自动化学院, 南京 210016
Author(s):
Lai Jizhou Liu Jianye Sheng Shouzhao
College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
关键词:
干涉型光纤陀螺 温度漂移 RBF神经网络 辨识
Keywords:
interfere fiber optic gyroscope temperature-introduced drift radial basis function neural network identification
分类号:
V241.59
DOI:
10.3969/j.issn.1001-0505.2006.04.009
摘要:
针对干涉型光纤陀螺(IFOG)温度漂移的辨识,推导了径向基神经网络(RBFNN)中隐含层神经元、网络的抗噪声性能和拟合精度三者之间的关系,并在此基础上提出了一种新的径向基函数神经网络辨识学习规则.该方法具有很强的抗噪声性能,网络输出不会被陀螺噪声所污染,同时能动态地确定神经元数,辨识精度高,有效地避免了传统RBF网络学习算法中事先固定网络结构可能存在的盲目性.实验结果表明,该方法能够快速、准确地辨识IFOG的温度漂移.
Abstract:
To identify the temperature drift of interfere fiber optic gyroscope(IFOG), the relationship among the nerve unit, the anti-noise performance and the fit precision in radial basis function neural network(RBFNN)is deduced, and a new learning rule of RBFNN is proposed. The improved neural network has strong anti-noise performance and cannot be polluted by the noise of IFOG. The method can also determine the number of nerve cells, avoiding the blindness in choosing the parameter with traditional radial basis function(RBF)network learning rules. The experimental results prove that the proposed method can identify the temperature-introduced drift of IFOG exactly.

参考文献/References:

[1] Lefevre Herve C.光纤陀螺仪[M].北京:国防工业出版社,2002.
[2] 延凤平,蓝慧娟,简水生.光纤陀螺温度补偿方案研究[J].光学学报,1999,19(7):968-974.
  Yan Fengping,Lan Huijuan,Jian Shuisheng.Investigation of the temperature compensated method for fiber optic gyros[J]. Acta Optica Sinica,1999,19(7):968-974.(in Chinese)
[3] 朱荣,张炎华,鲍其莲.RBF神经网络用于辨识光纤陀螺温度漂移[J].上海交通大学学报,2000,34(2):222-225.
  Zhu Rong,Zhang Yanhua,Bao Qilian.Identification of temperature drift for FOG using RBF neural networks[J].Journal of Shanghai Jiaotong University,2000,34(2):222-225.(in Chinese)
[4] Bengio Yoshua,Schuurmans Dale.Guest introduction:special issue on new methods for model selection and model combination[J].Machine Learning,2002,48(1):5-7.
[5] Schuurmans D,Southey F.Metric-based methods for adaptive model selection and regularization [J].Machine Learning,2002,48(1):51-84.
[6] Murata N,Yoshizawa S,Amari S.Network information criterion-determining the number of hidden units for an artificial neural network model[J].IEEE Transactions on Neural Networks,1994,1(5):865-872.
[7] Sugiyama M,Ogawa H.Subspace information criterion for model selection [J]. Neural Computation,2001,13(8):1863-1890.
[8] 盛守照,王道波,黄向华.限定记忆的前向神经网络在线学习算法研究[J].控制与决策,2005,20(3):303-307.
  Sheng Shouzhao,Wang Daobo,Huang Xianghua.Online learning algorithm for feedforward neural networks with moving range[J]. Control and Decision,2005,20(3):303-307.(in Chinese)
[9] 戴华.矩阵论[M].北京:科技出版社,2001:240-255.
[10] 国防科学技术工业委员会.GJB 2426—95光纤陀螺仪测试方法[S].北京:中国标准出版社,1995.

相似文献/References:

[1]方秋华,田新启,茅佩.涡流传感器温漂补偿[J].东南大学学报(自然科学版),1995,25(5):47.[doi:10.3969/j.issn.1001-0505.1995.05.008]
 Farig Qiuhua,Tian,Xinqi,et al.Study of Temperature Drift Compensationof Eddy Current Transducers[J].Journal of Southeast University (Natural Science Edition),1995,25(4):47.[doi:10.3969/j.issn.1001-0505.1995.05.008]

备注/Memo

备注/Memo:
作者简介: 赖际舟(1977—),男,博士,讲师,laijz@nuaa.edu.cn.
更新日期/Last Update: 2006-07-20