中国机械工程Issue(24)：3327-3335,9.DOI:10.3969/j.issn.1004-132X.2015.24.011
基于LPP与VPMCD的液压泵故障模式识别
Fault Pattern Identification of Hydraulic Pump Based on VPMCD and LPP Algorithm
摘要
Abstract
Aiming at the problems that vibration signals were complex and the effective features were difficult to extract ,a novel fault feature extraction method for pump was proposed based on LPP algorithm .The vibration signals of pump were decomposed into a number of intrinsic mode function (IMF) with ensemble empirical mode decomposition(EEMD) ,and then sensitive IMFs which con-tained more state informations were selected ,and the high dimensional fault feature sets were extrac-ted from the sensitive IMFs .Then the sensitive feature sets were gained by carrying out fusion and di-mensional reduction to the high dimensional feature sets with LPP processing .On account of the fa-vorable performance of VPMCD ,the VPMCD was proposed to realize the fault pattern identification of pump .A variable predictive model(VPM ) of each sensitive feature was established and the fault pat-tern of pump was diagnosed based on the VPMs .The analysis results of practical pump signals testify the rationality and availability of proposed method .In addition ,comparative analysis results demon-strate the more favorable performance of proposed method .关键词
液压泵/故障模式识别/局部保留投影法/基于变量预测模型的模式识别Key words
hydraulic pump/fault mode identification/locality preserving projection(LPP)/varia-ble predictive model based class discriminate(VPMCD)分类
机械制造引用本文复制引用
王余奎,李洪儒,许葆华..基于LPP与VPMCD的液压泵故障模式识别[J].中国机械工程,2015,(24):3327-3335,9.基金项目
国家自然科学基金资助项目 （）
