几种基于神经网络的导弹惯性器件故障预报方法及其性能比较  

The Performance Analysis of Missile Inertia Device Fault Prediction Based on Neural Networks

作　　者：吕瑛洁[1] 胡昌华[1] 

机构地区：[1]第二炮兵工程学院,西安710025

出　　处：《战术导弹技术》2005年第2期52-55,共4页Tactical Missile Technology

摘　　要：研究了标准BP网络、改进的BP网络(带动量的自适应BP网络)、L-M网络和RBF网络及其学习算法,探讨了基于这四种神经网络的导弹惯性器件故障预报方法,并通过仿真实验对四种网络的预测预报性能进行了分析比较.结果表明,L-M网络和RBF网络对惯性器件的故障预报比两种BP网络更准确,收敛速度更快.BP, fast BP, L-M and RBF neural network (NN) as well as their learn algorithms are studied. The prediction performances of these networks are analyzed and compared by studying on simulation experiment of missile inertia device fault prediction based on the networks. It is demonstrated that L-M NN and RBF NN have the quicker convergence speed, higher efficiency and better precision.

关 键 词：故障预报 BP网络 L-M算法 RBF网络 

分 类 号：TJ765.239[兵器科学与技术—武器系统与运用工程]