摘要
提出了一种基于粗糙集-神经网络的故障诊断方法。将粗糙集理论同神经网络结合起来可以用于机载设备的故障诊断。采用粗糙集理论对原始故障诊断样本进行处理,并根据条件属性对决策属性的正域的大小来选择条件属性,提取出对诊断故障贡献最大的最小故障特征集,从而确定神经网络的拓扑结构;通过训练神经网络建立故障特征与故障之间的映射关系,实现故障的诊断。通过A320飞机燃油系统的故障诊断仿真实例,表明这种故障诊断方法的有效性。
In this paper we present a new fault diagnosis method based on rough set-neural network. Rough set theory combined with neural networks can be applied to fault diagnosing of airborne equipment. The original fault diagnosis samples are processed by using rough set theory. According to the decision attribute positive region size of condition attribute（s）, the minimum fault feature subset is selected, and thus the neural network topology structure is determined. The networks well trained can establish the mapping relationship between inputs and outputs, which is used to realize the fault diagnosis. The effectiveness of the method is proved by a simulation example.
出处
《航空电子技术》
2008年第1期37-41,共5页
Avionics Technology
关键词
粗糙集
神经网络
故障诊断
正域
rough set
neural networks
faulty diagnosis
positive region
