摘要
借助粗糙集理论中的动态层次聚类的连续属性离散化算法和属性约简算法,对金属矿主通风机各类特征信息在线监测的数据进行融合,去除风机故障诊断决策表中的冗余和不一致信息,分析并推导出导致风机故障各因素的内在联系,找出关键因素和非关键因素,最终提取出故障诊断规则。研究结果表明:该故障故障方法能够对金属矿主通风机故障做出快速准确的诊断,并且在某矿山的实际应用中取得了良好的效果,达到了预期的目标。
By virtue of discretization of continuous features and attribute reduction algorithm,online monitoring data were integrated for various feature information concerning the main ventilator of metal mine,and the redundant and inconsistent information in the ventilator fault decision table was deleted.The internal relationship among various factors leading to ventilator breakdown was analyzed.Key factors and non-key factors were distinguished from each other for the convenience of fault decision rules.The results show that the rules can be applied for quick and proper decision of main ventilator faults in metal mine.The application in a certain metal mine has produced satisfactory result,achieving intended target.
出处
《中南大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2013年第7期2861-2866,共6页
Journal of Central South University:Science and Technology
基金
国家高技术研究发展计划("863"计划)项目(2011AA060407)
国家自然科学基金资助项目(50774092)
湖南省研究生科研创新基金资助项目(CX2011B116)
关键词
风机
监测监控
故障诊断
粗糙集理论
信息融合
fan
control and monitor
fault diagnosis
rough set theory
information fusion
