基于非线性流形学习的喘振监测技术研究

张熠卓 1; 徐光华 2; 梁 霖 2

您当前的位置：

首页 >

文章列表页 >

基于非线性流形学习的喘振监测技术研究

更新时间：2025-07-09

- 基于非线性流形学习的喘振监测技术研究
- Surge Monitoring Method Based on Nonlinear Manifold Learning
- 西安交通大学学报 2009年43卷第7期页码：44-48
- 作者机构：
  
  西安交通大学机械工程学院,西安,710049
- 作者简介：
- 基金信息：
  
  : 2008-10-28. 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“863计划”资助项目(2007AA04Z432)
- DOI：
  中图分类号： TP206.3
- 网络首发：2009-07-10，
  
  纸质出版：2009
- 稿件说明：
移动端阅览
张熠卓 1, 徐光华 2, 梁霖 2. 基于非线性流形学习的喘振监测技术研究[J]. 西安交通大学学报, 2009,43(7):44-48.

Surge Monitoring Method Based on Nonlinear Manifold Learning[J]. 2009, 43(7): 44-48.
张熠卓 1, 徐光华 2, 梁霖 2. 基于非线性流形学习的喘振监测技术研究[J]. 西安交通大学学报, 2009,43(7):44-48. DOI：

Surge Monitoring Method Based on Nonlinear Manifold Learning[J]. 2009, 43(7): 44-48. DOI：

摘要

为了提取压缩机喘振发作时表现出的非线性特性

引入了一种新的喘振特征提取方法.首先对原始信号进行多元统计分析

构造高维特征空间

然后利用局部切空间排列的流形学习方法提取出一维主流形

进而通过主流形几何结构的变化来反映系统的非线性变化.分析结果表明

与相关积分方法相比

该方法可以提前1 s识别出喘振特征

并且能够降低误报率

因此在喘振监测中具有良好的应用前景.

Abstract

To extract the nonlinear characteristic of compressor surge

a new monitoring method based on manifold learning is proposed. High dimension space of raw pressure signals is constructed by multivariate statistical analysis

then the local target space alignment(LTSA)algorithm is employed for extracting one dimension principal manifold

to reflect the non-linear dynamic characteristics of compressor system. Experimental results and industrial measurements show that this approach

compared with the correlation integral method

forecasts surge about 1s in advance with lower false prediction rate.

关键词

Keywords

references

李美林,张春梅,王尚锦,等. 用小波和分维数方法处理喘振实验数据 [J].工程热物理学报,2002,23(2): 175-178.

LI Meilin, ZHANG Chunmei, WANG Shangjin, et al. Surge data processing based on wavelet analysis and fractal methods [J]. Journal of Engineering Thermophysics,2002,23(2):175-178.

蒋峻.离心风机喘振在线预报和自适应调节的实验研究 [D].北京:中科院工程热物理所,2001.

BRIGHT M M,QAMMER H K,WEIG H J,et al. Stall precursor identification in high-speed compressor stages using chaotic time series analysis methods [J]. ASME Journal of Turbomachinery,1997,119(3): 491-499.

BRIGHT M M, HELEN K Q, WANG Leizhen. Investigation of pre-stall mode and pip inception in high speed compression through the use of correlation integral [J].AEME Journal of Turbomachinary,1999, 121(4):743-750.

吴云,李应红,张朴. 某涡喷发动机压气机气动失稳过程的非线性分析 [J].航空动力学报,2005,20(5): 890-894.

WU Yun, LI Yinghong, ZHANG Pu. Nonlinear analysis of the process of loosing compressor aerodynamic stability in a turbojet engine [J]. Journal of Aerospace Power, 2005,20(5):890-894.

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.

孙涛,徐光华,张四聪,等.经验模式分解法结合相关积分法的离心风机喘振先兆辨识 [J].动力工程,2006,26(6):849-853.

SUN Tao, XU Guanghua, ZHANG Sicong, et al. Surge symptom identification of centrifugal blowers by EMD in connection with correlation integrals[J]. Journal of Power Engineering, 2006,26(6):849-853.

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.

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.

阳建宏,徐金梧,杨德斌,等. 邻域自适应选取的局部投影非线性降噪方法 [J]. 振动与冲击,2006,25(4): 64-67.

YANG Jianhong, XU Jinwu, YANG Debin, et al. Nonlinear noise reduction method by local projection with adaptive neighborhood selection[J]. Journal of Vibration and Shock, 2006,25(4): 64-67.

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

利用增量式非线性流形学习的状态监测方法

基于喘振频域特性的失稳预警技术研究

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

压缩机系统高阶Moore-Greitzer模型的动态行为分析