非完备先验知识下的滑动轴承摩擦状态识别

张峻宁; 张培林; 李兵; 吴定海; 杨玉栋

doi:10.13224/j.cnki.jasp.2017.07.022

非完备先验知识下的滑动轴承摩擦状态识别

doi: 10.13224/j.cnki.jasp.2017.07.022

1.
军械工程学院七系,石家庄 050003
2.
军械工程学院四系,石家庄 050003
3.
武汉军械士官学校四系,武汉 430075

基金项目: 国家自然科学基金（51205405,51305454）

计量
- 文章访问数: 717
- HTML浏览量: 3
- PDF量: 499
- 被引次数: 0
出版历程
- 收稿日期: 2016-06-01
- 刊出日期: 2017-07-28

Plain bearing friction state recognition without complete prior knowledge

摘要

摘要: 针对监测系统通常无法全部获取轴承摩擦退化状态的先验知识,无法建立全摩擦状态的识别模型,从状态间的相似性出发,提出一种无先验知识下的基于灰色B型绝对关联度（AGRDB）和稀疏编码的滑动轴承状态识别方法。针对稀疏表示不具有监督性的缺陷,在稀疏编码的目标函数中引入AGRDB算法,训练类间距离最大、类内距离最小的正常润滑和严重摩擦的编码；在相同字典下建立具有一致判别性的稀疏表示模型,通过比较当前状态与正常润滑、严重摩擦的稀疏编码与重构误差,进一步识别当前轴承的状态,仿真信号和柴油机轴承实验的结果表明:所提方法能够在较少先验知识下识别出滑动轴承的早期摩擦状态（100~216min）和严重摩擦状态（216~384min）,且算法简单,适合较少样本下的滑动轴承摩擦故障在线监测。
- 非完备先验知识 /
- 滑动轴承 /
- 状态识别 /
- 灰色B型绝对关联度（AGRDB） /
- 稀疏编码
Abstract: Given that the prior knowledge of all kinds of bearing friction degradation model cannot be attained usually, starting from the similarities of different states, a bearing friction faults state recognition algorithm without prior knowledge was proposed based on sparse representation and absolute grey relational degree of B-mode (AGRDB). First, for the defects of sparse representation without supervision, the AGRDB was involved in the sparse representation, to get normal and severe friction codes under the largest distance between classes and smallest distance within the classes. Second, sparse representation model with discriminant sex was established under the same dictionary. And current state of the bearing was identified by comparing sparse coding and reconstruction error of normal lubrication and serious friction. Finally, the results of simulation signal and diesel engine bearing experiment show that the proposed method can better identify the sliding bearing early friction state (100-216min) and serious friction state (216-384min) under the less prior knowledge. And this algorithm is suitable for plain bearing fault monitoring under less samples.
- without complete prior knowledge /
- plain bearing /
- condition recognition /
- absolute grey relational degree of B-mode（AGRDB） /
- sparse coding

HTML

参考文献(18)

[1]	秦萍,阎兵,谭达明.利用声发射诊断滑动轴承接触摩擦故障的研究［J］.西南交通大学学报,2001,36(3):272-275.QIN Ping,YAN Bing,TAN Daming.Study on fault diagnosis of sliding bearings using ae signals［J］.Journal of Southwest Jiaotong University,2001,36(3):272-275.(in Chinese）
[2]	俞啸,丁恩杰,陈春旭,等.基于HHT和有监督稀疏编码的滚动轴承故障状态识别方法［J］.煤炭学报,2015,40(11):2587-2595.YU Xiao,DING Enjie,CHEN Chunxu,et al.Rolling bearing fault state recognition method based on HHT and supervised sparse coding［J］.Journal of China Coal Society,2015,40(11):2587-2595.(in Chinese）
[3]	孙丹,张楚,郭瑞,等.基于两相流理论滑动轴承动力特性求解［J］.航空动力学报,2012,27(12):2822-2828.SUN Dan,ZHANG Chu,GUO Rui,et al.Solution of dynamic characteristics of journal bearing based on two phase flow theory［J］.Journal of Aerospace Power,2012,27(12):2822-2828.(in Chinese）
[4]	OLSHAUSEN B A.Emergence of simple-cell receptive field properties by learning a sparse code for natural images［J］.Nature,1996,381(6583):607-609.
[5]	WRIGHT J,YANG A Y,GANESH A,et al.Robust face rec-ognition via sparse representation［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(2):210-227.
[6]	朱启兵,杨宝,黄敏.基于核映射稀疏表示分类的轴承故障诊断［J］.振动与冲击,2013,32(11):30-35.ZHU Qibing,YANG Bao,HUANG Min.Bearing fault diagnosis based on a kernel-mapping sparse representation classification［J］.Journal of Vibration and Shock,2013,32(11):30-35.(in Chinese）
[7]	王海涛,谢寿生,武卫,等.基于稀疏最小二乘支持向量机的航空发动机动态过程辨识［J］.航空动力学报,2010,25(9):2140-2146.WANG Haitao,XIE Shousheng,WU Wei,et al.Dynamic process identification of aircraft engine based on a novel sparse least square support vector machines［J］.Journal of Aerospace Power,2010,25(9):2140-2146.(in Chinese）
[8]	郭业才,张铃华.统一化的LGBP特征及稀疏表示的人脸识别算法［J］.计算机辅助设计与图形学学报,2015,27(3):400-406.GUO Yecai,ZHANG Linghua.Face recognition algorithm based on uniform LGBP and SRC［J］.Journal of Computer-Asided Design and Computer Graphics,2015,27(3):400-406.(in Chinese）
[9]	CHEN Y,NASRABADI N M,TRAN T D.Sparse representation for target detection in hyperspectral imagery［J］.Journal of Selected Topics in Signal Processing,2011,5(3):629-640.
[10]	邵晓刚.基于矩阵灰色B型绝对关联度的人脸检测算法研究［D］.长春:东北师范大学,2012.SHAO Xiaogang.The research of the face detection algorithm taking matrix absolute grey relational degree of B-mode as core［D］.Changchun:Northeast Normal University,2012.(in Chinese）
[11]	ELAD M,ABARON M.Image denoising via sparse and redundant representations over learned dictionaries［J］.IEEE Transactions on Image Processing,2006,15(12):3736-3745.
[12]	AHARON M,ELAD M,BRUCKSTEIN A,et al.KSVD:an algorithm for designing of overcomplete dictionaries for sparse representa-tion［J］.IEEE Transactions on Signal Processing,2006,54(11):4315-4320.
[13]	傅和品,秦萍.滑动轴承故障诊断方法的实用性分析研究［J］.轻工机械,2006,24(4):97-98.FU Hepin,QIN Ping.The study of fault diagnosis method on slide bearing［J］.Light Industry Machinery,2006,24(4):97-98.(in Chinese）
[14]	荆双喜,吴鑫涛,华伟.基于小波包频带能量特征提取的低速重载滑动轴承诊断研究［J］.煤矿机械,2007,28(9):191-193.JING Shuangxi,WU Xintao,HUA Wei.Plain bearing fault diagnose based on detecting technology of wavelet packet frequency band energy［J］.Coal Mine Machinery,2007,28(9):191-193.(in Chinese）
[15]	胡瑾秋,张来斌,胡春艳,等.基于一数据自组织挖掘的机械设备状态退化预警方法［J］.中国石油大学学报,2014,38(3):142-150.HU Jinqiu,ZHANG Laibin,HU Chunyan,et al.An early warning method of degradation for mechanical facilities based on data self-organizationmining technology［J］.Journal of China University of Petroleum,2014,38(3):142-150.(in Chinese）
[16]	CHAN T,VESE L.Active contours without edges［J］.IEEE Transactions on Image Processing,2001,10(2):266-277.
[17]	张峻宁,张培林,陈彦龙,等.基于摩擦信号的滑动轴承接触摩擦故障的状态监测［J］.振动与冲击,2016,35(3):68-73.ZHANG Junning,ZHANG Peilin,CHEN Yanlong,et al.Condition monitoring of contacting fault of plain bearings based on friction signals［J］.Journal of Vibration and Shock,2016,35(3):68-73.(in Chinese）
[18]	向丹,岑健.基于EMD熵特征融合的滚动轴承故障诊断方法［J］.航空动力学报,2015,35(5):1149-1156.XIANG Dan,CEN Jian.Method of roller bearing fault diagnosis based on feature fusion of EMD entropy［J］.Journal of Aerospace Power,2015,35(5):1149-1156.(in Chinese）