利用增量式非线性流形学习的状态监测方法

张熠卓 1; 徐光华 1; 梁霖 1; 张锋 1; 2; 李淑智 1

您当前的位置：

首页 >

文章列表页 >

利用增量式非线性流形学习的状态监测方法

更新时间：2025-07-09

- 利用增量式非线性流形学习的状态监测方法
- Condition Monitoring Method for Mechanical Equipments Based on Incremental Nonlinear Manifold Learning
- 西安交通大学学报 2011年45卷第1期页码：64-68+136
- 作者机构：
  
  1. 西安交通大学机械工程学院,西安,710049
  2. 西安交通大学机械制造系统工程国家重点实验室,西安,710049
- 作者简介：
- 基金信息：
  
  : 2010-05-06. 作者简介: 张熠卓(1982-),男,博士生;徐光华(联系人),男,教授,博士生导师. 基金项目: 国家自然科学基金资助项目(51075323);北京交通大学轨道车辆结构可靠性与运用检测技术教育部工程研究中心资助项目(SROM RGV(BJTU)2010-002);中央高校基本科研业务费专项资金资助项目
- DOI：
  中图分类号： TP206
- 网络首发：2011-01-10，
  
  纸质出版：2011
- 稿件说明：
移动端阅览
张熠卓 1, 徐光华 1, 梁霖 1, 等. 利用增量式非线性流形学习的状态监测方法[J]. 西安交通大学学报, 2011,45(1):64-68+136.

Condition Monitoring Method for Mechanical Equipments Based on Incremental Nonlinear Manifold Learning[J]. 2011, 45(1): 64-68+136.
张熠卓 1, 徐光华 1, 梁霖 1, 等. 利用增量式非线性流形学习的状态监测方法[J]. 西安交通大学学报, 2011,45(1):64-68+136. DOI：

Condition Monitoring Method for Mechanical Equipments Based on Incremental Nonlinear Manifold Learning[J]. 2011, 45(1): 64-68+136. DOI：

摘要

针对传统流形学习方法难以处理大批量设备运行数据的特点

提出了一种采用增量式流形学习方法的机械设备状态监测方法.该方法首先利用局部切空间排列算法对训练样本集进行非线性维数约简

得到初始的低维流形结构

然后通过增量式学习机制对新增的时序样本点进行动态聚类.通过对压缩机喘振试验数据及滚动轴承故障数据的分析表明

该方法的计算复杂度低

可以有效地识别出隐藏在高维特征集中的非线性故障特征

因此具有良好的工程应用前景.

Abstract

Most nonlinear manifold learning methods can not be efficiently operated in a ‘batch’ mode when data are collected sequentially. An incremental learning scheme is proposed for condition monitoring of mechanical equipments. A nonlinear dimensionality reduction algorithm called local tangent space alignment(LTSA)is first utilized to train the low-dimensional manifold structure from the original feature space. To process the long term recordings

an unsupervised learning scheme based on incremental local tangent space alignment(ILTSA)is chosen to cluster the new coming samples dynamically. The proposed method is evaluated by vibration signals measured on defective bearings with different fault types and pressure signals collected from compressor with surge fault

respectively. The results show that the scheme enables to achieve a high accuracy for condition classification with potential in identifying novel patterns from high dimensional feature space.

关键词

Keywords

references

孙涛,徐光华,张春梅. 基于喘振频域特性的失稳预警技术研究 [J].西安交通大学学报,2007,41(11):1321-1325.

SUN Tao, XU Guanghua, ZHANG Chunmei. Instability early warning based on frequency-domain characteristic of surge [J].Journal of Xi'an Jiaotong University,2007,41(11):1321-1325.

黎敏,徐金梧,阳建宏,等.一种基于流形拓扑结构的轴承故障分类方法 [J].控制工程,2009,16(3):358-362.

LI Min,XU Jinwu,YANG Jianhong,et al.Classification method of bearing faults based on topological structure of manifold [J].Control Engineering of China,2009,16(3):358-362.

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 Jianhong, XU Jinwu, YANG Debin, 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.

蒋全胜,贾民平,胡建中,等.基于拉普拉斯特征映射的故障模式识别方法 [J].系统仿真学报,2008,20(20):5710-5713.

JIANG Quansheng, JIA Minping, HU Jianzhong, et al.Method of fault pattern recognition based on Laplacian eigenmaps[J].Journal of System Simulation,2008,20(20):5710-5713.

梁霖,徐光华,栗茂林,等. 基于非线性流形学习的冲击故障特征提取方法 [J].西安交通大学报,2009, 43(11):95-99.

LIANG Lin, XU Guanghua, LI Maolin, et al. Nonlinear manifold learning method of mechanical impact faults extraction [J]. Journal of Xi'an Jiaotong University, 2009,43(11):95-99.

ZHANG Zhenyue,ZHA Hongyuan. Principal manifolds and nonlinear dimension reduction via local tangent space alignment [J]. SIAM Journal on Scientific Computing, 2004, 26(1):313-338.

HE Qingbo, KONG Fanrang, YAN Ruqiang. Subspace-based gearbox condition monitoring by kernel principal component analysis [J]. Mechanical Systems and Signal Processing, 2007,21(4):1755-1772.

LIU Xiaoming, YIN Jianwei, FENG Zhilin, et al. Incremental manifold learning via tangent space alignment [J]. Artificial Neural Networks in Pattern Recognition,2006,4087:107-121.

KOUROPTEVA O. Unsupervised learning with locally linear embedding algorithm: an experimental study [D]. Finland: University of Joensuu. Department of Computer Science and Statistics, 2001.

LOPARO K A. Bearings vibration data set, case western reserve university [DB/OL].[2008-12-05]. http:∥www.eecs.cwru.edu/laboratory/bearing/down-load.html.

LAW H C, JAIN K. Incremental nonlinear dimensionality reduction by manifold learning [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006,28(3):377-391.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于非线性流形学习的喘振监测技术研究

冲击故障特征提取的非线性流形学习方法

利用非线性流形学习的轴承早期故障特征提取方法

独立分量分析和流形学习在VSC-HVDC系统故障诊断中的应用

利用局部线性嵌入的模态识别