摘要
神经网络具有很强的自学习、自适应能力及非线性变换特性,为模型的辨识提供了一条十分有效的途径。本文基于反向传播(Back-Propagation)网络的研究,将神经网络应用于陀螺漂移误差模型辨识,通过陀螺的实际测试数据对神经网络的加权进行训练,得到了较为满意的结果。
Because of having the functions of self - learning adaptiveand nonlinear transformation, neural networks provide an effective way foridentifying model. Based on foe research of Back- Propagation network, aneural network is applied ic identify gyro drift error model and the actual gyro test data are used during network learning in this paper. The result is successful.
出处
《中国惯性技术学报》
EI
CSCD
1998年第3期35-38,共4页
Journal of Chinese Inertial Technology