基于粗糙集神经网络和信息融合的故障诊断

神经网络是智能故障诊断系统的一种重要的方法。粗糙集理论则是处理不完备信息的一种技术。文中以复杂的人工智能诊断问题为研究对象,系统地论述了基于神经网络、粗糙集、信息融合的智能诊断的理论、方法与实践。其主要方法如下:在故障诊断的神经网络模型的基础上,以粗糙集理论中的信息系统属性值表为主要工具,将复杂的组合神经网络约简并删除其中不必要的属性,克服了网络规模过于庞大和分类速度慢的缺点,并给出了基于粗糙集理论的组合神经网络的模型结构,最后再利用数据融合技术,得出更加精确的结果。一个故障诊断实例证明了该方法的有效性。

Fault Diagnosis Based on Rough Set Neural Networks and Data Fusion

The neural network is a kind of important method that break down the intelligent diagnosis problem of complex system.The rough set theory to them handles a kind of technique of the not complete information. In this paper the intelligent diagnosis problem of complex system is the research object. The theory,method, system and practice of intelligent diagnosis problem based on neural networks, rough set theory and date fusion are systematically discussed.In this paper the key idea is as follows: On the basis of fault diagnosis network model,knowledge representation system of rough set theory is taken as a major tool to simplify the complex combine neural network and in which unecessary properties are eliminated .The method overcomes some shortcomings,such as network scale is too large and the rate of classification is slow.Based on rough set combine neural network model is presented. Then, a satisfying result is described by using data fusion. Finally an example of fault diagnosis shows validity of this method.