基于数据挖掘的故障诊断方法分析-电力系统及其自动化专业论文.docxVIP

太原理 太原理 工火学硕个研究生学位论文 太原 太原型二大学硕士研究生学位论文 I III I IV ，‘ STUDY OF FAULT DIAGNOSIS BASED ON DATA MIN卧 G ABSTRACT With the rapid development of science and tcchnology and modemization of large equipments tending to structure complex and multi-functional ，fierce competition have a higher request in equipment accuracy. Once a failure occurs， a chain-reaction wi l1 force the entire production at a standstil J. If the fault doesnt be discovered timely，it would affect the daily work，which causes severely casualties and m句or economic losses，and even catastrophic consequences. So prediction and monitoring of the fault has caused extensive concem in various fields. At the end of the 20th century，data mining as an intelligent data analysis techniques have been widely used in many fields. By data mllllllg，useful or potentially useful knowledge can be found，which contains lots of information ，and can generate rules or laws. Firstly，this paper researches abnormaJ vibration of motor failure in the work of steel fabricating machine. Unusual motor failure of rotor imbalance， rotor misalignment and rotor rubbing are anaJyzed. And with the analysis of frequency can we get training sample set by characteristic signal. Second，the paper especially studied c1assification algorithm of data mining in the application of fault diagnosis. The diagnosis method based on data mining， actually，is a method of have the fault signal classified and induction. According to the spectrum signature of fault signals to extract the characteristic rrequency， and categorize the tàult signals，obtain different fault type. 1n this pape巳 1select decision tree. As a kind of classification method ，decision tree can generative easy to understand rule by leaming a small training sample. Decision tree algorithm of short time is suitable to practical working system. There is morc redundancy in a training sample. Therefore，attribute was reduced by discernible matrix algorithm of rough set theo