油液在线监测系统中的磨粒识别

李绍成; 左洪福; 张艳彬

doi:null

您当前的位置：

首页 >

文章列表页 >

油液在线监测系统中的磨粒识别

微纳技术与精密机械 | 更新时间：2020-08-12

- 油液在线监测系统中的磨粒识别
- Wear debris recognition for oil on-line monitoring system
- 光学精密工程 2009年17卷第3期页码：589-595
- 作者机构：
  
  1. 南京航空航天大学机电学院,江苏南京,210016
  2. 南京航空航天大学民航学院,江苏南京210016
  3. 南京邮电大学通信与信息工程学院,江苏南京210046
- 作者简介：
- 基金信息：
  
  国家863高技术研究发展计划资助项目(No.2006AA04Z427)();中国民航总局科技资金资助项目(No.MHRD0724)()
- DOI：
  中图分类号： TH87;TP391.4
- 收稿日期：2008-04-24，
  
  修回日期：2008-06-27，
  
  网络出版日期：2009-03-25，
  
  纸质出版日期：2009-03-25
- 稿件说明：
移动端阅览
李绍成, 左洪福, 张艳彬. 油液在线监测系统中的磨粒识别[J]. 光学精密工程, 2009,17(3): 589-595

LI Shao-cheng, ZUO Hong-fu, ZHANG Yan-bin. Wear debris recognition for oil on-line monitoring system[J]. Editorial Office of Optics and Precision Engineering, 2009,17(3): 589-595
李绍成, 左洪福, 张艳彬. 油液在线监测系统中的磨粒识别[J]. 光学精密工程, 2009,17(3): 589-595 DOI：

LI Shao-cheng, ZUO Hong-fu, ZHANG Yan-bin. Wear debris recognition for oil on-line monitoring system[J]. Editorial Office of Optics and Precision Engineering, 2009,17(3): 589-595 DOI：

摘要

针对机械设备磨损状态监测要求

构建了基于显微图像分析的油液在线监测系统。根据系统的光路特点

对磨粒图像进行了基于彩色特征的转换

并通过与背景图像的差值处理来快速提取磨粒目标。基于最小二乘支持向量机设计了两类磨粒分类器

并利用粒子群优化算法对最小二乘支持向量机模型中的参数进行了优化选取。在此基础上

根据磨粒识别体系

设计了磨粒综合分类器。最后

利用铁谱分析技术对系统性能和识别效果进行了检验

结果表明

系统的识别精度达到95％以上

满足磨粒在线监测要求。

Abstract

For the demands of wear on-line monitoring for mechanical equipment

an on-line oil moni toring system based on microscopic imagea nalysis is constructed.According to the characteristic of system light route

the image of wear debris is converted into gray image based on its colorfeature

and the wear debris object is extracted by subtracting the background image from the wear debris image.The classifier for two kinds of wear debris is designed based on the least square support vector machines

and the parameters of this model are optimized by Particle Swarm Optimization（PSO）algo rithm.Based on this classifier

an integrative wear debris classifier is designed according to the wear debris recognition system.The performance and recognition precision of this system are tested by the ferrography technology.The result shows that the recognition precision of this system is as highas 95%

which can meet the demand of wear debris on-line monitoring.

关键词

Keywords

references

夏志新. 液压系统污染控制[M]. 北京:机械工业出版社,1992. XIA ZH X. Pollution Control in Hydraulic System[M]. Beijing: China Machine Press, 1992. (in Chinese)[2] ROYLANCE B J. Ferrography—then and now[J]. Tribology International, 2005,38(10):857-862.[3] XIAO H L. The development of ferrography in China—some personal reflections[J]. Tribology International, 2005,38(10):904-907.[4] MORRIS S, WOOD R J K, HARVEY T J, et al.. Use of electrostatic charge monitoring for early detection of adhesive wear in oil lubricated contacts[J]. Journal of Tribology, 2002,124(2):288-296.[5] 吴振锋,左洪福,杨忠. 磨损微粒显微形态学特征量化描述体系[J]. 交通运输工程学报, 2001,1(1):115-119. WU ZH F, ZUO H F, YANG ZH. The quantification character parameter system of debris micrography[J].Journal of Triffic and Transportation Engineering, 2001,1(1):115-119. (in Chinese)[6] 赵吉文,刘永斌,苏亚辉,等. 新型直线电机支持向量机非线性建模研究[J]. 光学精密工程,2006,14(3):450-455. ZHAO J W,LIU Y B,SU Y H,et al.. Research on SVM model of a novel cylinder linear motor[J]. Opt. Precision Eng., 2006,14(3):450-455. (in Chinese)[7] SUYKENS J A K, VAN G T, DE M B, et al.. Least Squares Support Vector Machines[M]. Singapore: World Scientific Publishing Co. Pte. Ltd., 2002.[8] 赵吉文,刘永斌,孔凡让,等. 基于SVM和遗传算法的新型直线电机结构参数优化[J]. 光学精密工程,2006,14(5):870-875. ZHAO J W,LIU Y B,KONG F R,et al.. Parameter optimization of novel cylinder type motor based on SVM and genetic argorithm[J]. Opt. Precision Eng., 2006,14(5):870-875. (in Chinese)[9] TRELEA I C. The particle swarm optimization algorithm: convergence analysis and parameter selection[J]. Information Processing Letters, 2003,85(6):317-325.[10] 崔长彩,黄富贵,张认成,等. 粒子群优化算法及其在圆柱度误差评定中的应用[J]. 光学精密工程,2006,14(2):256-260. CUI CH C,HUANG F G,ZHANG R CH,et al.. Research on cylindricity evaluation based on the particle swarm optimization[J]. Opt. Precision Eng., 2006,14(2):256-260. (in Chinese)[11] VAN D B. Analysis of particle swarm optimizers . South Africa: Department of Computer Science, University of Pretoria, 2002.

浏览量

636

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

模拟初级视觉皮层增强CNN神经网络结构的稳定性

基于激光入射光斑识别的非接触式波高测量

基于机器学习识别与标记分水岭分割的盲道图像定位

基于稀疏编码空间金字塔匹配和GA-SVM的列车故障自动识别

图像椭圆扁度不变性及其在仿射不变量构造中的应用