基于粗糙集理论的数控机床智能故障诊断研究  

Intelligent fault diagnosis of CNC machine tools based on rough set theory

作　　者：姚鑫骅[1] 徐月同[1] 傅建中[1] 陈子辰[1] 

机构地区：[1]浙江大学机械工程学系,浙江杭州310027

出　　处：《浙江大学学报（工学版）》2008年第10期1719-1724,共6页Journal of Zhejiang University：Engineering Science

基　　金：国家自然科学基金资助项目(50675199);浙江省科技计划资助项目(2005E10049)

摘　　要：面向数控机床智能化发展需求,提出了基于数据挖掘技术的智能故障诊断方法.建立机床智能诊断单元的系统框架,框架由状态监控及特征信号采集、历史故障数据分析及诊断规则获取、故障推理机制3个功能模块组成.重点研究诊断规则的获取技术,提出了基于粗糙集理论的故障诊断决策规则生成算法.算法充分利用信息决策系统的特性,通过简化对不必要属性和核心属性的分析,并引入回溯思想计算约简集,有效降低了属性集约简的计算复杂度,提高规则求取效率.在建立规则库的基础上,引入基于证据理论的信息融合技术,解决多传感器故障监测数据与诊断规则准确匹配的问题,建立故障推理机制.实例研究证明该方法可行.An intelligent fault diagnostic method based on data mining was presented to satisfy the development requirements of computer numerical control （CNC） machine tools＇ intelligence. The framework of intelligent fault diagnosis unit was established consisting of characteristic signal acquisition, diagnosis rule extraction and fault reasoning mechanism. The approach of diagnosis rule extraction was studied and an algorithm for acquisition of decision rules was proposed. The algorithm simplified the analysis procedure of core properties and unnecessary properties by using the characteristics of decision-making system and calculated reduction set by backward tracking approach. The algorithm reduced the complexity in reduction set calculation and improved the efficiency of rule extraction. A fault identification mechanism using evidence theory was presented to process fault data collected by various sensors and exactly match them with diagnosis rules. Case study justified the validity of the method.

关 键 词：数控机床 智能故障诊断 粗糙集 证据理论 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]