| 基于神经元的多传感器数据级融合研究 |
| |
| 引用本文： | 谷立臣,张优云. 基于神经元的多传感器数据级融合研究[J]. 机械工程学报, 2003, 39(7): 89-93 |
| |
| 作者姓名： | 谷立臣 张优云 |
| |
| 作者单位： | 1. 西安建筑科技大学机电工程学院,西安,710055
2. 西安交通大学 |
| |
| 基金项目： | 国家自然科学基金(59990472)，国家“九五”攀登B(PD9521908z1)资助项目 |
| |
| 摘 要： | 在不知道先验知识的条件下,从含有观测噪声的多传感器测量数据中估计出方均误差最小的数据融合值,并作为神经元融合系统训练样本,因而解决了多传感器测量系统数据级融合的标定问题。研究结果表明,融合数据在精度、容错性以及动态响应方面均优于单传感器测量。
|
| 关 键 词： | 多传感器数据 数据级融合 神经元 方均误差 融合标定 |
| 修稿时间： | 2002-02-28 |
RESEARCH ON MULTI-SENSOR DATA LEVEL FUSION BASED ON ARTIFICIAL NEURON |
| |
| Gu Lichen. RESEARCH ON MULTI-SENSOR DATA LEVEL FUSION BASED ON ARTIFICIAL NEURON[J]. Chinese Journal of Mechanical Engineering, 2003, 39(7): 89-93 |
| |
| Authors: | Gu Lichen |
| |
| Affiliation: | Gu Lichen (Xi'an University of Architecture & Technology)Zhang Youyun (Xi'an Jiaotong University) |
| |
| Abstract: | The main goal of this thesis is to obtain reliable outputs, which requires robustness relative to the noise included in input data and to the sensor deterioration or even the missing of the sensor. Without of any pre-defined knowledge concerning sensors, the multi-sensor data level fusion model based on artifical neuron can be used for the estimation of fused data with minimum mean square errors through observed data so as to calibrate the fusion neuron. Simulation results show that the fused data are much more sensitive, accurate, reliable than that of single sensor data . |
| |
| Keywords: | Multi-sensor data Data level fusion Artifical neuron Mean square error Fusion calibration |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
