| 基于BP神经网络的GFSINS角速度预测 |
| |
| 引用本文： | 韩庆楠,郝燕玲,刘志平,王瑞. 基于BP神经网络的GFSINS角速度预测[J]. 华中科技大学学报(自然科学版), 2011, 0(3): 115-119 |
| |
| 作者姓名： | 韩庆楠 郝燕玲 刘志平 王瑞 |
| |
| 作者单位： | 哈尔滨工程大学自动化学院;海军飞行学院教研部; |
| |
| 基金项目： | 国家自然科学基金资助项目(60604019) |
| |
| 摘 要： | 针对无陀螺捷联惯导系统(GFSINS)中传统角速度算法解算精度不高的问题,提出一种可避免复杂代数运算的反向传播(BP)神经网络算法来求解角速度.基于一种十加速度计构型方案,选择10个加速度计输出、采样周期和臂杆距离等12个已知量作为网络输入,以对数法得到的角速度值作为期望输出,针对5 000个样本在不同的隐含层层数、单层神经元个数以及学习步数等情况下进行网络训练,构建了一个含有30个隐含层神经元的3层BP网络模型.采用此模型对角速度进行实时预测,结果表明:网络具有很好的适应能力和实时性,角速度实时预测时间与对数法相当,且其预测精度比对数法提高大约3倍.
|
| 关 键 词： | 无陀螺捷联惯导系统 角速度预测 反向传播神经网络 对数法 十加速度计 |
Prediction of the angular velocity of GFSINS by BP neural network |
| |
| Han Qingnan Hao Yanling Liu Zhiping Wang Rui. Prediction of the angular velocity of GFSINS by BP neural network[J]. JOURNAL OF HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY.NATURE SCIENCE, 2011, 0(3): 115-119 |
| |
| Authors: | Han Qingnan Hao Yanling Liu Zhiping Wang Rui |
| |
| Affiliation: | Han Qingnan1 Hao Yanling1 Liu Zhiping1 Wang Rui2(1 College of Automation,Harbin Engineering University,Harbin 150001,China,2 Department of Teaching and Research,Navy Fly Academy,Huludao 125001,Liaoning China) |
| |
| Abstract: | Aimed at low precision for traditional angular velocity algorithms in gyro-free strapdown inertial navigation system(GFSINS),a BP(back-propagation)neural network algorithm without complex mathematic computation was put forward to calculate angular velocity.Based on a ten-accelerometer configuration scheme,the accelerometer output,sample interval and fixed position were chosen as input,angular velocity got by lognormal algorithm was chosen as output,and 5 000 samples were trained in several conditions with d... |
| |
| Keywords: | gyro-free strapdown inertial navigation system(GFSINS) angular velocity prediction BP(back-propagation) neural network lognormal algorithm ten-accelerometer |
| 本文献已被 CNKI 等数据库收录！ |
|
