作者：肖圣光

作者单位：重庆大学测试中心, 重庆 400044

关键词：轴心轨迹; 故障诊断; 几何特征; 模式识别; 细化分类

摘要：

提出了一种识别轴心轨迹的新方法。采集方向相互垂直的两路振动位移信号,经消噪处理后拟合为轴心轨迹,提取轴心轨迹的方向变化特征,利用模式识别理论中的函数判别法进行分类识别。并对每种类别的轴心轨迹,用一个特征参量来进行细化描述,不仅可以判断机械的运行状态,在发生故障的时候还能对故障严重程度进行评估。通过对仿真分析,取得了良好效果。

Research of identification of shaft orbit for rotating machine

XIAO Sheng-guang

Test Center of Chongqing University, Chongqing 400044, China

Abstract: A novel approach for the identification of shaft orbit is presented. The vibration displacement signals acquired in two mutually vertical directions were treated through noise suppression and fitted to form a shaft orbit. Then the direction changing character was extracted and all shaft orbits were classified and identified with the function discriminated method according to the pattern recognition theory. Each type of shaft orbit was described in detail with one character, which can help to judge the operation status of the mechanical and the extent of the failure. The analysis and simulation got good results.

Keywords: Shaft orbits; Fault diagnosis; Geometric features; Pattern recognition; Thinning classification

2009, 35(2): 7-10  收稿日期: 2008-8-29;收到修改稿日期: 2008-11-15

基金项目: 国家863高新技术发展计划项目(2005AA420350)

作者简介: 肖圣光(1985-),男,湖北仙桃人,硕士研究生,专业方向为虚拟仪器与故障诊断的理论及其应用。

参考文献

[1] 万书亭,李永刚,李和明.基于不变矩特征和新型关联度的轴心轨迹形状自动识别[J].热能动力工程,2005, 20(3):239-241.
[2] 倪传坤,周建中,付波.基于改进不变矩的发电机组轴心轨迹识别[J].电力科学与工程,2004,16(3):16-19.
[3] 陈豫.轴心轨迹提纯与自动识别的研究[J].武汉理工大学学报:交通科学与工程版,2003,27(6):878-881.
[4] 杨淑莹.图像模式识别[M].北京:清华大学出版社,2005.
[5] 张宏林.Visual C++数字图像模式识别技术及工程实践[M].北京:人民邮电出版社,2003.
[6] 江志农,李艳妮.旋转机械轴心轨迹特征提取技术研究[J].振动、测试与诊断,2007,27(2):98-102.
[7] 张新峰,沈兰荪.模式识别及其在图像处理中的应用[J].测控技术,2004,23(5):28-32.