PCA-SDG在TEP多源故障诊断中的应用
首发时间:2011-11-02
摘要:针对传统基于SDG(符号有向图)的故障诊断方法对每个变量节点状态和高低阈值难以确定,且对各个变量单独统计,不考虑变量间相互关系的缺点,提出一种PCA(主元分析)与SDG相结合的故障诊断方法,并将其用于多源故障诊断中。将实测数据与由历史数据建立的主元模型预测值比对,判断过程中出现故障征兆的变量,根据变量状态,在SDG模型上进行反向推理,找到故障源。通过TEP仿真实验验证,表明该方法能够及时有效地检测出单个或多个故障,提高了诊断的准确性与分辨率。
For information in English, please click here
Application of PCA-SDG Based Multiple Fault Diagnosis
Abstract:The fault diagnosis using SDG (signed directed graph) is uncertain about node state and threshold value ,and performs single variable analysis without considering correlation of variables. A method combining PCA(principle component analysis) and SDG was proposed to improve the traditional multiple fault diagnosis. Compared the measured data to prediction created by the PCA model based on historical data ,we can single out process variables with the failure symptom.Based on the states of variables, backward inference on SDG model is used to find the possible fault root(s). The TEP case studies show that this method can find one or more faults fast, improving the accuracy and resolution.
Keywords: multiple fault diagnosis signed directed graph principle component analysis TEP
基金:
论文图表:
引用
No.****
同行评议
共计0人参与
勘误表
PCA-SDG在TEP多源故障诊断中的应用
评论
全部评论0/1000