基于RS的变速器故障属性提取  

Attributes extraction in fault diagnosis of gearbox based on the theory of rough sets

作　　者：袁玲[1] 徐进 

机构地区：[1]合肥工业大学理学院,安徽合肥230009 [2]合肥市小汽车修配厂,安徽合肥230011

出　　处：《合肥工业大学学报（自然科学版）》2005年第2期212-215,共4页Journal of Hefei University of Technology：Natural Science

基　　金：安徽省"十五"重大科技资助项目 (0 110 2 0 0 9)

摘　　要：文章根据粗糙集理论 ,利用分明矩阵及分明函数对变速器故障决策表进行属性约简 ,提取故障识别的重要属性 ,降低决策表的内在冗余性 ,为进一步用人工神经网络进行故障诊断创造了有利条件 ,有利于降低网络的复杂性 。Based on the theory of rough sets,the discernibility matrix and the discernibility function are used to the attributes reduction for the fault diagnosis of gearbox. The application results show that the distinct attributes for fault identification are extracted and the inner redundancy of decision table is revealed, which is in favor of faults diagnosis using the artificial neural network(ANN) further.

关 键 词：故障诊断 变速器 粗糙集 属性约简 

分 类 号：TH165.3[机械工程—机械制造及自动化]