粗糙集理论在故障诊断规则获取中的应用

本文的目的是给出一种利用粗糙集理论解决故障诊断的规则获取问题的方法 ,该方法的特点是可以处理由于类重叠引起的样本信息不精确、不一致情况下的规则获取 .以规则形式表示的知识接近于人脑推理过程 ,因此基于规则的诊断方法在故障诊断中得到广泛使用 ,但规则获取是其瓶颈之一 .粗糙集 (RS)理论是为开发自动规则生成系统而提出的 ,其主要思想是在保持分类能力不变的前提下 ,通过知识约简 ,导出概念的分类规则 .因此 ,可以把 RS理论用于规则的故障诊断中 .本文给出了基于决策矩阵和决策函数的获取规则方法的流程图 ,以故障诊断实例说明其使用方法 ,并验证了其有效性

THE APPLICATION OF ROUGH SET THEORY IN THE FAULT DIAGNOSIS RULE ACQUISITION

The purpose of this paper is to present a method of fault diagnosis rule acquisition using Rough Set theory. This method can solve the problem of rule acquisition under condition of imprecise and inconsistent information on account of kind overlapping. Knowledge representation in the form of rules closes to man brain reasoning procedure, so diagnosis method based on rules has a wide application in fault diagnosis, but rule acquisition is one of the bottlenecks. Rough Set (RS) theory has been present for developing automation rule generation system, its main idea is to acquire concept's classifying rules through knowledge reduction maintaining classify ability. Therefore, we can use RS theory to fault diagnosis based on rules. This paper presents a flow chart of rule acquisition based on decision matrix and decision function, explains its application method using a fault diagnosis example, and proves its validity.