
基于ITD与排列熵的往复压缩机故障特征提取方法研究
陈桂娟1,高桐,邹龙庆",付海龙
(1.东北石油大学机械科学与工程学院,黑龙江大庆163318;2.庆阳石化公司,甘肃庆阳745002)
[摘要]:针对往复压缩机振动信号的非平稳、非线性和特征耦合特性,提出了基于ITD与排列端的往复压缩机轴承故障特征提取方法。利用ITD方法将各状态报动信号分解为一系列PR分量,依据相关性系数选择代表故障状态主要信息的 PR分量,计算其排列形成有效的特征向量。以平均样本距离为特征向量可分性标准,对比了ITD与近似端方法所提取特征向量,结果表明此法具有更好的可分性。
[关键词]:ITD;排列城;往复压缩机;特征提取;故障诊断
中图分类号:TH457
文献标志码:A
文章编号:10062971(2014)05-0017-04
设计研究 Desigm&Research
Study on FaultFeature Extraction Method Based on ITD and Permutation Entropy for ReciprocatingCompressor
CHEN Gui-juan',GAO Tong",ZOU Long-qing',FU Hai-long
(1.Mechanical Science and Engineering Institute, Northeast Petroleum University, Daqing163318, China;2.Qingyang Petrochemical Company,Qingyang 745002,China)
Abstract:Based on non stationary,nonlinearity and feature coupling characteristics of reciprocating compressor vibration signal,a feature extraction method of reciprocating compressor fault based on ITD and permutation entropy is proposed.Vibration signals in each state are decomposed into a series of PR components with ITD method,and the PR components which contain the main infor-mation of fault state are chosen according to relative coefficient.Permutation entropy of the selected PR components was calculated as eigenvectors.Average sample distance is used as severability standard of eigenvector, and superiority of this method is proved by com-
paring the average sample distance of eigenvectors extracted by ITD and approximate entropy method. ssouepeuogoxaaneaaossadonugeooadaartdonuauognuadliproma
引言
往复压缩机的结构复杂,激励源繁多,部件运动形式多样,其传动机构往往因为长期摩擦、磨损造成轴承间隙故障。振动信号富含设备状态
收搞日期:2014-03-03
基金项目:国家科技支撑计划项目(2012BAH28F00):黑龙江省教育厅科学技术研究重点项目(125212007);黑龙江省自然基金项目
(E201335);东北石油大学青年科学基金项目(ky120221) 2014年05期(总第247期)
信息,是设备故障特征提取的有效信息源,但往复压缩机振动信号存在非线性、非平稳特性和特征耦合等特点,以傅立叶变换为基础的频域分析和经典的时域统计指标在往复压缩机振动信号分析中存在着定的局限性"。
近些年越来越多的非线性分析方法被用于机械故障诊断,如近似嫡、样本摘和多尺度等。然面,近似摘相对一致性较差,多尺度摘计算较
压摄机技术17 Compre