飞机防滑刹车系统的智能故障诊断与重构

来源期刊:中南大学学报(自然科学版)2010年第1期

论文作者:廖力清 段凌飞 熊翔 王颂

文章页码:207 - 212

关键词:BP神经网络;专家系统;故障诊断;加权有向图形;系统重构

Key words:BP neural network; expert system; fault diagnosis; weighted direct graph; system reconstruction

摘    要:针对目前飞机在起飞着陆过程中故障率高的问题,设计一种交叉冗余飞机防滑刹车系统的智能故障诊断与重构系统。该系统基于BP神经网络专家系统,利用专家先验知识、神经网络的数值推理和自学习能力对飞机刹车过程出现的故障进行分析和建模,继而准确推断和定位故障;通过对系统信号流向优先级建立对应加权有向图模型,采用寻找最短路径的算法对系统进行优化重构,从而使飞机刹车系统达到更高的安全水平。研究结果证明:在刹车过程中,给定随机故障后,系统能迅速、准确地判断和定位故障并实时重构系统,达到1次和部分2次故障时能正常工作且保证工作性能的设计目标。

Abstract: Owing to the fact that the latest developed dual anti-skid braking system can easily cause accident after the system has some faults but it cannot reconstruct the system rapidly, an intellectual fault diagnosis and reconstruction crossing dual braking system was designed. This system was based on the BP neural network with expert system, using the expert’s knowledge, numeric capacity and self-learning to analyze the fault and make a model of the system to get the exact position of the fault. After knowing the fault position, a weighted direct graph model of system which depended on the priority circuit was made to optimize and reconstruct the system through seeking the shortest circuit arithmetic, then the braking system could be operated safely after faults occurred. The results show that when some random faults are generated, the system can estimate the fault and reconstruct the system rapidly. It can make the system safe when part faults occur.

基金信息:国家高技术研究发展计划大型客机关键技术攻关项目

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号