基于磨粒磨损机理的机械磨损状态监测

杨文君; 孙耀宁; 杨延竹; 凡辉; 王国建

doi:10.13224/j.cnki.jasp.2019.06.008

基于磨粒磨损机理的机械磨损状态监测

doi: 10.13224/j.cnki.jasp.2019.06.008

1.
新疆大学机械工程学院,乌鲁木齐 830047
2.
东华大学机械工程学院,上海 201620

基金项目: 国家自然科学基金（51465055）

计量
- 文章访问数: 1186
- HTML浏览量: 5
- PDF量: 1386
- 被引次数: 0
出版历程
- 收稿日期: 2018-11-20
- 刊出日期: 2019-06-28

Mechanical wear condition monitoring method based on abrasive particle wear mechanism

摘要

摘要: 针对机械设备磨损状态监测准确率较低的问题,基于不同磨损机理下磨粒具有不同的形状和纹理特征,提出了一种基于磨粒特征识别的机械磨损状态监测的数学模型。通过形状特征识别球状磨粒和切削磨粒,结合形状、纹理特征识别疲劳磨粒和严重滑动磨粒,基于提取的特征参数建立机械磨损状态监测的特征向量,通过量子粒子群优化(QPSO)的径向基函数神经网络模型,实现对机械磨损状态的监测和判别。实验结果表明:QPSO-RBF神经网络数学模型结构简单,比传统PSO-RBF神经网络模型的识别准确率高5%,可用于常见机械磨损状态的检测。
- 磨粒 /
- 特征分析 /
- 机械磨损 /
- 量子粒子群优化 /
- 状态检测
Abstract: In order to solve the problem of low accuracy in monitoring the wear state of mechanical equipment, a mathematical model of monitoring the wear state based on the recognition of abrasive particle features was proposed based on different wear mechanisms with different shapes and textures. By identifying ball wear particles and cutting wear particles through shape feature, the shape and the texture features were combined to recognize fatigue wear particles and severe sliding wear particles. The feature vector of mechanical wear state monitoring was established based on the extracted feature parameters. Through the radical basis function neural network model by quantum particle swarm optimization (QPSO), the recognition and monitoring of mechanical wear state were realized. The experimental results show that the QPSO-RBF neural network model is simple in structure and 5% higher in recognition accuracy than the traditional PSO-RBF neural network model. It can be used for common mechanical wear condition monitoring
- abrasive particle /
- feature analysis /
- mechanical wear /
- quantum particle swarm optimization /
- condition monitoring

HTML

参考文献(18)

[1]	STACHOWIAKG W,PODSIADLO P.Towards the development of an automated wear particle classification system［J］.Tribology International,2006,39(12):1615-1623.
[2]	范君.磨粒图谱识别系统研究［D］.杭州:浙江大学,2007.FAN Jun.The research of recognition system of wear particle atlas［D］.Hangzhou:Zhejiang University,2007.(in Chinese)
[3]	袁成清.磨损过程中的磨粒表面和磨损表面特征及其相互关系研究［D］.武汉:武汉理工大学,2005.YUAN Chengqing.Study of surface characteristics both of wear particles & wear components and their relationship in wear process［D］.Wuhan:Wuhan University of Technology,2005.(in Chinese)
[4]	吴振锋,左洪福,孙有朝.磨粒分析技术及其在发动机故障诊断中的应用［J］.航空动力学报,2001,16(4):316-322.WU Zhenfeng,ZUO Hongfu,SUN Youzhao.Abrasive particle analysis technology and its application in engine fault diagnosis［J］.Journal of Aerospace Power,2001,16(4):316-322.(in Chinese)
[5]	FENG Ruibin,HAN Zifa,WAN Waiyan,et al.Properties and learning algorithms for faulty RBF networks with coexistence of weight and node failures［J］.Neurocomputing,2017,224(C):166-176.
[6]	王静.基于磨粒分析的磨损模式识别方法研究［D］.杭州:浙江大学,2004.WANG Jing.Research on the method of wear pattern particle recognition based on wear particle analysis［D］.Hangzhou:Zhejiang University,2004.(in Chinese)
[7]	颜欢,韩超,张贤明.铁谱技术智能化应用研究进展［J］.重庆工商大学学报(自然科学版),2016,33(5):85-91.YAN Huan,HAN Chao,ZHANG Xianming.Research progress of intelligent application of ferrography technology［J］.Journal of Chongqing Technology and Business University (Natural Science Edition),2016,33(5):85-91.(in Chinese)
[8]	郝延龙,潘新祥,严志军,等.基于显微图像的在线润滑油中磨粒识别［J］.润滑与密封,2017,42(4):53-59.HAO Yanlong,PAN Xinxiang,YAN Zhijun,et al.Recognition for particles in lubricating oil based on micro-image method［J］.Lubrication Engineering,2017,42(4):53-59.(in Chinese)
[9]	王伟华,殷勇辉,王成焘.基于径向基函数神经网络的磨粒识别系统［J］.摩擦学学报,2003,23(4):340-343.WANG Weihua,YIN Yonghui,WANG Chengtao.Abrasive particle recognition system based on radial basis function neural network［J］.Journal of Tribology,2003,23(4):340-343.(in Chinese)
[10]	肖亮.粒子群径向基函数人工智能网络［D］.黑龙江大庆:东北石油大学,2017.XIAO Liang.The particle swarm optimization-radial basis function neural network of artificial intelligence［D］.Daqing Heilongjiang:Northeast Petroleum University,2017.(in Chinese)
[11]	张顶学,关治洪,刘新芝.基于PSO的RBF神经网络学习算法及其应用［J］.计算机工程与应用,2006,42(20):13-15.ZHANG Dingxue,GUAN Zhihong,LIU Xinzhi.RBF neural network algorithm based on PSO algorithm and its application［J］.Computer Engineering and Applications,2006,42(20):13-15.(in Chinese)
[12]	陈伟,冯斌,孙俊.基于QPSO算法的RBF神经网络参数优化仿真研究［J］.计算机应用,2006,26(8):1928-1931.CHEN Wei,FENG Bin,SUN Jun.Study on optimization of RBF neural network parameters based on QPSO algorithm［J］.Computer Application,2006,26(8):1928-1931.(in Chinese)
[13]	王树文,闫成新,张天序,等.数学形态学在图像处理中的应用［J］.计算机工程与应用,2004,40(32):89-92.WANG Shuwen,YAN Chengxin,ZHANG Tianxu,et al.The application of mathematical morphology in image processing［J］.Computer Engineering and Applications,2004,40(32):89-92.(in Chinese)
[14]	ROYLANCEB J,ALBIRDEWI I A,LAGHARI M S,et al.Computer-aided vision engineering (CAVE):quantification of wear particle morphology［J］.Lubrication Engineering,1994,50(2):111-116.
[15]	王国忠,王静秋,于海武.融合灰色关联分析和主成分分析的磨粒自动识别［J］.计算机技术与发展,2012,22(4):16-20.WANG Guozhong,WANG Jingqiu,YU Haiwu.Automatic recognition of grinding grains by fusion of grey correlation and principal component analysis［J］.Computer Technology and Development,2012,22(4):16-20.(in Chinese)
[16]	王峰,吕植勇,何晓昀,等.铁谱磨粒图像的计算机纹理分析［J］.润滑与密封,2005(2):17-19,74.WANG Feng,L Zhiyong,HE Xiaojun,et al.Computer texture analysis of ferrography wear particles images［J］.Lubrication Engineering,2005(2):17-19,74.(in Chinese)
[17]	常军,刘大山.基于量子粒子群算法的结构模态参数识别［J］.振动与冲击,2014,33(14):72-88. CHANG Jun,LIU Dashan.Structural modal parameter identification based on quantum particle swarm optimization［J］.Journal of Vibration and Shock,2014,33(14):72-88.(in Chinese)
[18]	LI W G,ZHANG H L,FAN W H,et al.A new model about fractional order chaotic time series prediction［J］.Journal of Computational Information Systems,2015,11 (18):6637-6651.