基于动态多主元模型故障诊断研究  

Research on Fault Diagnosis Based on Dynamic Multi-Principal Component Model

作　　者：王丽君[1] 周月娥 孙敦艳[1] WANG Li-jun;ZHOU Yue-e;SUN Dun-yan(Zijin College,Nanjing University of Science and Technology,Nanjing 210046,China)

机构地区：[1]南京理工大学紫金学院,南京210046

出　　处：《自动化与仪表》2018年第9期44-48,共5页Automation & Instrumentation

摘　　要：随着分散控制系统和企业信息系统在火电机组上的广泛应用,监测系统采集了海量的现场数据,为从这些数据中提前发现系统的故障信息,采用了一种适用于变工况过程的动态多主元模型的故障诊断方法。以电厂锅炉的实际运行数据为基础,以炉膛压力控制为研究对象,使用主元分析PCA方法进行故障检测,使用PCA贡献图的方法进行故障分离和识别,利用计算机编写程序进行仿真试验,找出影响炉膛压力波动大的主要影响因素。试验结果表明,动态多主元模型的故障检测方法具有较好的故障诊断能力,弥补了常规主元分析方法的不足。With DCS and EIS in thermal boiler process on a wide range of applications,lots of spot monitoring data was gathered by the monitoring system.In order to discover the tiny fault information of system in advance for fault detection.A fault diagnosis method based on dynamic multi-principal comment models is being proposed for this purpose.Take the actual movement data of the power station boiler as foundation in the research process,Take the furnace pressure as an object of study,The PCA method is mainly used to research on fault detection while PCA contribution plans to fault isolationand identification.Using computer program for simulation experiment,and find out main influencing factor of the furnace pressure fluctuation influences,reflects the dynamic multiple principal component model of fault detection method has a good ability of fault diagnosis,make up for the deficiency of the traditional principal component analysis method.

关 键 词：故障诊断 炉膛压力 主元分析 动态多主元 

分 类 号：TM621[电气工程—电力系统及自动化]