SVM方法在某多级离心泵故障诊断中的应用  

APPLICATION OF SVM METHOD IN FAULT DIAGNOSIS OF A MULTI⁃STAGE CENTRIFUGAL PUMP

作　　者：李有根 马文生 李方忠 王庆锋[3] LI YouGen;MA WenSheng;LI FangZhong;WANG QingFeng(College of Mechanical Engineering,Chongqing University of Technology,Chongqing 400054,China;Postgraduate Training Base,Chongqing Pump Industry Co.,Ltd.,Chongqing 400033,China;College of Mechanical and Electrical Engineering,Beijing University of Chemical Technology,Beijing 100029,China)

机构地区：[1]重庆理工大学机械工程学院,重庆400054 [2]重庆水泵厂有限责任公司研究生培养基地,重庆400033 [3]北京化工大学机电工程学院,北京100029

出　　处：《机械强度》2024年第2期272-280,共9页Journal of Mechanical Strength

基　　金：国家重点研发计划子课题(2020YFC1512403);重庆市科技局重点项目(cstc2018jszx-cyzdX0167)资助。

摘　　要：针对实际工程中多级离心泵故障样本难获取的现象,通过多级离心泵故障模拟试验台模拟实际产品的碰摩、不对中、不平衡三种典型故障,基于支持向量机(Support Vector Machine,SVM)建立故障诊断模型的方法实现故障的分类。采用集合经验模态分解(Ensemble Empirical Mode Decomposition,EEMD)算法提取振动信号的时频域特征,结合时、频域和信息熵特征构造高维特征样本后,以主成分分析(Principal Component Analysis,PCA)优化输入样本质量,实现对故障的高效分类。另外,对比分析SVM和反向传播(Back Propagation,BP)神经网络的分类效果,表明SVM模型分类的效果更好,在多级离心泵的故障诊断中具有良好的适用性。In allusion to the difficulty to obtain fault samples of multi⁃stage centrifugal pumps in practical engineering,three typical faults containing rubbing,misalignment and unbalance were simulated through the fault simulation test⁃bed of multi⁃stage centrifugal pumps.And a fault diagnosis model based on support vector machine(SVM)was established to realize the classification of three types of faults.High dimensional feature samples were constructed by extracting time⁃frequency domain characteristics of vibration signal with ensemble empirical mode decomposition(EEMD),combined with characteristics of time domain,frequency domain and information entropy.The efficient fault classification was achieved by optimizing the quality of input samples with principal component analysis(PCA).In addition,by comparing the classification effects of SVM and back propagation(BP)neural network,it shows that the SVM model has better classification effect and high applicability in fault diagnosis of multi⁃stage centrifugal pump.

关 键 词：多级离心泵 支持向量机 BP神经网络 集合经验模态分解 主成分分析 

分 类 号：TH311[机械工程—机械制造及自动化] TP181[自动化与计算机技术—控制理论与控制工程] TP206[自动化与计算机技术—控制科学与工程] TH165.3