基于递归神经网络的C^3I系统故障预报系统  

On C^3I System Fault Predication System based on Neureal Network Model

作　　者：朱英贵[1] 李海航[1] 王永红[1] 

机构地区：[1]蚌埠坦克学院,安徽蚌埠233013

出　　处：《火力与指挥控制》2005年第3期87-89,共3页Fire Control & Command Control

摘　　要：阐述了C3I系统故障预测系统的设计要求,分析了带有偏差单元的递归神经网络的相关原理,建立了C3I系统故障的神经网络预测模型并提出了相应的训练算法。提出了把神经网络、预测理论和专家系统有机地结合起来建立故障预报系统的初步设想。并以防空C3I系统的典型故障为例,实现了故障的预测。预测结果证明,给出的神经网络预测模型和训练算法是可行的,且具有较高的精度。Design requirement of fault prediction system and the advantage of recursive neural network technique are studied.Recursive neural network technique of C^3I fault diagnostic system is presented,and the algorithm based on the neural network model in the prediction processes is given.The neural network and the fault prediction technique with experts are combined to form a fault prediction system.Finally,the air defense C^3I system as an example is used to realize fault prediction.And the result proves that the forecast model and algorithm based on the neural network are feasible.

关 键 词：C^3I系统 递归神经网络 故障预报 设想 

分 类 号：TJ768.4[兵器科学与技术—武器系统与运用工程]