基于神经网络的军用飞机故障预报系统研究  

Military Plane Fault Prediction System Based on Neural Network Model

作　　者：赵海东[1] 缪旭东[1] 吕世聘[1] 

机构地区：[1]海军大连舰艇学院战术软件中心,辽宁大连116018

出　　处：《系统工程与电子技术》2003年第7期894-896,共3页Systems Engineering and Electronics

摘　　要：在军用航空领域 ,及时准确的故障预报对提高飞行器的安全性具有极其重要的意义。针对飞机故障预报系统的设计要求 ,考虑到神经网络用于故障预测的优点 ,在神经网络技术应用于军用飞机的故障预测过程中提出了神经网络模型的训练算法。把神经网络、预测理论、专家系统有机地结合起来建立了一个故障预报系统。并以某型军用飞机冷气系统的典型故障为例 ,实现了故障的预测。实例预测结果证明 。In the military aviation field, exact fault prediction is very important for the security of the aerocraft. According to design requirement of military plane fault prediction system and the advantage of neural network technique, the application of neural network technique in military plane fault prediction is presented, and the algorithm based on the neural network model in the prediction processes is given. The air system of military plane as an example is used to realize fault prediction. The neural network and the fault prediction technique with exert are combined to form a fault prediction system. Finally, the result proves that the forecast model and algorithm based on the neural network are feasible.

关 键 词：军用飞机 神经网络 故障预报 专家系统 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] E917[自动化与计算机技术—控制科学与工程]