基于一种新型神经网络的姿态控制故障诊断方法  

Fault Diagnosis of Missile Attitude Control Based on a Neural Network

作　　者：刘曙光[1] 赵振洋[1] 

机构地区：[1]中国空空导弹研究院,河南洛阳471009

出　　处：《航空兵器》2008年第1期57-59,共3页Aero Weaponry

摘　　要：在导弹姿态控制系统的故障检测和诊断中,针对BP神经网络自身存在的收敛速度慢等缺点,介绍了一种新型神经网络——带偏差单元的递归神经网络的结构及算法。将它和一改进算法的BP(称为FBP)网络分别用来对同一导弹姿态控制系统进行故障诊断,结果表明,这种算法提高了故障诊断的快速性,增加了诊断的准确性,故障诊断的正确率优于FBP神经网络。In the research of fault detection and diagnosis for the missile attitude control system, the BP neural network has the disadvantages such as slow convergence. The structure and algorithm of a new type neural network, the recursion neural network with offset units, is introduced in this paper. Applying this method and another an improved BP algorithm（FBP） network to diagnose faults in the same missile attitude control system, the results show that this algorithm improves the speed and veracity of fault diagnosis and its accuracy is higher than FBP.

关 键 词：神经网络 故障诊断 BP网络 导弹姿态控制系统 

分 类 号：TJ765.23[兵器科学与技术—武器系统与运用工程]