基于PCA的往复压缩机气阀故障异常监测方法Method of Valve Fault Detection for Reciprocating Compressor based on Principal Component Analysis
徐丰甜,李建,孔祥宇,李村波,江志农,张进杰
XU Feng-tian,LI Jian,KONG Xiang-yu,LI Cun-bo,JIANG Zhi-nong,Zhang Jin-jie
摘要(Abstract)：
针对气阀故障异常自动检测迫切需求,针对气阀故障在温度数据的表现特点,即同类气阀正常工作时温度波动一致,故障时温度波动存在差异,采用主成分分析(PCA)从气阀阀盖温度数据中提取故障特征参数,建立基于径向基函数的故障异常监测模型,实现了故障异常自动检测,并可进一步对故障气阀进行自动定位,为故障早期快速报警奠定了基础。
In order to satisfy the pressing needs of valve fault automatically detection,and according to the characteristic of valves' temperature data,it's found that the suction( or exhaust) valves' temperature is consistent when the valves work,otherwise it's not. From this fact,the authors use the PCA( Principal Component Analysis) to extract features to reflect the performance based on valves' temperature data. Simultaneously,with the establishment of radial basis model,it can achieve valve fault anomaly detection and automatic location of abnormal valve,and lay the foundation of early and quick warning of valve fault.
关键词(KeyWords)：
往复压缩机;气阀故障;PCA;特征提取;异常检测
reciprocating compressor;valve fault;PCA;feature extraction;anomaly detection
基金项目(Foundation): 国家重点基础研究发展计划(“973”计划)项目(2012CB026000);; 国家自然科学基金重点项目(51135001)
作者(Author):
徐丰甜,李建,孔祥宇,李村波,江志农,张进杰
XU Feng-tian,LI Jian,KONG Xiang-yu,LI Cun-bo,JIANG Zhi-nong,Zhang Jin-jie
参考文献(References)：
- [1]高晶波,唐立强,王日新,等.基于神经网络的往复压缩机气阀故障诊断方法[J].压缩机技术,2005,(1):25-27.
- [2]毕文阳,江志农,刘锦南.往复压缩机气阀故障模拟实验与诊断研究[J].流体机械,2013,41(6):6-10.
- [3]张云,江志农,张进杰.往复式压缩机进气阀优化设计方法研究[J].流体机械,2014,42(1):40-42.
- [4]韦晨,王泽军,谭蔚,等.气瓶动态爆破压力预测[J].压力容器,2014,31(4):41-48.
- [5]李宝栋,宿忠娥,柴世文.基于支持向量机的往复压缩机气阀故障诊断[J].自动化与仪器仪表,2013,(1):157-158.
- [6]魏中青,马波,窦远,等.基于MLE阈值规则的小波特征提取技术在气阀故障诊断中的应用[J].振动与冲击,2011,30(1):237-241.
- [7]马晋,江志农,高金吉.基于混沌分形理论的特征提取技术在气阀故障诊断中应用[J].振动与冲击,2012,31(19):26-30.
- [8]董宁娟.基于参数识别的往复压缩机气阀故障诊断方法的研究[D].哈尔滨:哈尔滨工业大学,2006.
- [9]高晶波,王日新,徐敏强.基于示功图修正的往复压缩机气阀故障诊断方法[J].压缩机技术,2009,(3):4-7.
- [10]K Pearson.On Lines and Planes of Closest Fit to Systems of Points in Space[J].Philosophical Magazine,1901,2(11):559-572.
- [11]Abdi H,Williams LJ.Principal component analysis[J].Wiley Interdisciplinary Reviews:Computational Statistics,2010,2(4):433-459.
- [12]Shaw.Multivariate statistics for the Environmental Sciences[J].Chichester:Wiley,2003,9:233.
- [13]Ian Jolliffe.Principal Component Analysis[M].John Wiley&Sons,2005.