转子系统三维轴心轨迹和流形学习的故障诊断方法

邵杰; 庞新宇; 杨兆建; 李峰

doi:10.13433/j.cnki.1003-8728.2018.0609

转子系统三维轴心轨迹和流形学习的故障诊断方法

doi: 10.13433/j.cnki.1003-8728.2018.0609

邵杰^1,2,
庞新宇^1,2, ,,
杨兆建^1,2,
李峰^1,2

1.
太原理工大学机械工程学院, 太原 030024;
2.
煤矿综采装备山西省重点实验室, 太原 030024

基金项目:

国家自然科学基金项目（51475318）资助

详细信息

作者简介:
邵杰(1993-),硕士研究生,研究方向为机械故障诊断,shao-jie@foxmail.com

通讯作者:
庞新宇,副教授,硕士生导师,typangxy@163.com

计量
- 文章访问数: 216
- HTML全文浏览量: 35
- PDF下载量: 9
- 被引次数: 0
出版历程
- 收稿日期: 2017-06-29
- 刊出日期: 2018-06-05

Fault Diagnosis Method of 3D Axis Orbit and Manifold Learning for Rotor System

Shao Jie^1,2,
Pang Xinyu^{1,2
, ,},
Yang Zhaojian^1,2,
Li Feng^1,2

1.
College of Mechanical Engineering, Taiyuan University of Technology, Taiyuan 030024, China;
2.
Shanxi Key Laboratory of Fully Mechanized Coal Mining Equipment, Taiyuan 030024, China

摘要

摘要: 提出一种基于三维轴心轨迹和流形学习的故障诊断方法。提取转子系统水平、竖直和轴向的位移信号，采用EEMD分解对原始信号进行降噪，将降噪后的信号合成三维轴心轨迹，采用LTSA流形学习算法对三维轴心轨迹进行降维得到其二维流形图。相较于三维轴心轨迹，降维后的二维流形图更方便分析与识别，并且保留了三维轴心轨迹各数据点的空间拓扑关系。应用该方法进行试验，获取转子系统的正常、不对中、油膜涡动、油膜振荡的三维轴心轨迹及其降维后的二维流形图。利用LTSA算法得到的二维流形图相比于三维轴心轨迹具有简单直观的特征区分。
- 故障诊断 /
- 转子 /
- 轴心轨迹 /
- 流形学习
Abstract: A fault diagnosis method based on 3D axis orbit and manifold learning is proposed. The horizontal, vertical and axial displacement signals of rotor system are extracted and the ensemble empirical mode decomposition (EEMD) is used to denoise the original signal. The denoised signals are combined into 3D axis orbit. Locally tangent space arrangement (LTSA) manifold learning algorithm is used to reduce the dimension of the 3D axis orbit, thus to obtain its 2D manifold diagram. Compared with the 3D axis orbit, the 2D manifold diagram is more convenient for analysis and recognition, and the spatial topological relation of the data points of the 3D axis orbit is retained. The method is applied to the test, 3D axis orbit and 2D manifold diagram of the normal, misalignment, oil whirl and oil whip in the rotor system are obtained. Compared with the 3D axis orbit, the 2D manifold diagram has simple and intuitive feature differentiation.
- fault diagnosis /
- rotor /
- axis orbit /
- manifold learning

HTML全文

参考文献(15)

[1]	王常青.数字图像处理与分析及其在故障诊断中的应用研究[D].武汉:华中科技大学,2012 Wang C Y. Research and application of digital image processing and analysis in fault diagnosis[D]. Wuhan:Huazhong University of Science and Technology, 2012(in Chinese)
[2]	刘刚,李明,乔宝明,等.故障转子系统轴心轨迹的自动识别研究[J].中国测试,2014,40(1):110-114 Liu G, Li M, Qiao B M, et al. Automatic identification of orbits of rotor system with faults[J]. China Measurement & Testing, 2014,40(1):110-114(in Chinese)
[3]	宋高峰,杨兆建,张文静,等.线性扭矩在多支承转子系统中传递特性研究[J].机械科学与技术,2014,33(7):992-995 Song G F, Yang Z J, Zhang W J, et al. Transfer characteristics of linear torque in multi-support rotor system[J]. Mechanical Science and Technology for Aerospace Engineering, 2014,33(7):992-995(in Chinese)
[4]	Ding J, Krodkiewski J M. Inclusion of static indetermination in the mathematical model for non-linear dynamic analyses of multi-bearing rotor system[J]. Journal of Sound and Vibration, 1993,164(2):267-280
[5]	丁进成,孙梦琦,徐光华.大机组转子三维轴心轨迹运行状态研究[J].机床与液压,2010,38(11):140-143 Ding J C, Sun M Q, Xu G H. Research on operation condition of 3-dimensional axis orbit of rotor of large rotating machinery[J]. Machine Tool & Hydraulics, 2010,38(11):140-143(in Chinese)
[6]	杨扬,孙军,赵小勇,等.多缸内燃机曲轴轴承三维轴心轨迹的试验研究[J].机械工程学报,2012,48(3):174-179 Yang Y, Sun J, Zhao X Y, et al. Experimental study of 3D trajectory of journal center of crankshaft bearings in multi-cylinder internal combustion engine[J]. Journal of Mechanical Engineering, 2012,48(3):174-179(in Chinese)
[7]	王红军,徐小力,万鹏.基于轴心轨迹流形拓扑空间的转子系统故障诊断[J].机械工程学报,2014,50(5):95-101 Wang H J, Xu X L, Wan P. Rotor system fault diagnosis based on orbit manifold topological[J]. Journal of Mechanical Engineering, 2014,50(5):95-101(in Chinese)
[8]	万鹏,王红军,徐小力.于局部切空间排列和支持向量机的故障诊断模型[J].仪器仪表学报,2012,33(12):2789-2795 Wan P, Wang H J, Xu X L. Fault diagnosis model based on local tangent space alignment and support vector machine[J]. Chinese Journal of Scientific Instrument, 2012, 33(12):2789-2795(in Chinese)
[9]	Seung H S, Lee D D. The manifold ways of perception[J]. Science, 2000,290(5500):2268-2269
[10]	杨庆,陈桂明,何庆飞,等.局部切空间排列算法用于轴承早期故障诊断[J].振动、测试与诊断,2012,32(5):831-835 Yang Q, Chen G M, He Q F, et al. Inchoate fault diagnosis of rolling bearings based on local tangent space alignment algorithm[J]. Journal of Vibration, Measurement & Diagnosis, 2012,32(5):831-835(in Chinese)
[11]	Xu X L, Jiang Z L, Chen P. Fault trend feature extraction method of variable condition wind power rotating machinery[J]. Advanced Science Letters, 2013,19(4):1185-1188.
[12]	Zhang Z Y, Zha H Y. Principal manifolds and nonlinear dimensionality reduction via tangent space alignment[J]. SIAM Journal on Scientific Computing, 2004,26(1):313-338
[13]	阳建宏,徐金梧,杨德斌,等.基于主流形识别的非线性时间序列降噪方法及其在故障诊断中的应用[J].机械工程学报,2006,42(8):154-158 Yang J H, Xu J W, Yang D B, et al. Noise reduction method for nonlinear time series based on principal manifold learning and ITS application to fault diagnosis[J]. Chinese Journal of Mechanical Engineering, 2006,42(8):154-158(in Chinese)
[14]	李锋,汤宝平,陈法法.基于线性局部切空间排列维数化简的故障诊断[J].振动与冲击,2012,31(13):36-40,61 Li F, Tang B P, Chen F F. Fault diagnosis model based on dimension reduction using linear local tangent space alignment[J]. Journal of Vibration and Shock, 2012,31(13):36-40,61(in Chinese)
[15]	黎敏,阳建宏,徐金梧,等.基于高维空间流形变化的设备状态趋势分析方法[J].机械工程学报,2009,45(2):213-218 Li M, Yang J H, Xu J W, et al. Trend analysis method via manifold evolution in high dimensional space for state of machinery equipment[J]. Journal of Mechanical Engineering, 2009,45(2):213-218(in Chinese)