分步动态自回归核主元分析及其在故障诊断中应用

doi:10.11772/j.issn.1001-9081.2016.05.1464

计算机应用 ›› 2016, Vol. 36 ›› Issue (5): 1464-1468.DOI: 10.11772/j.issn.1001-9081.2016.05.1464

分步动态自回归核主元分析及其在故障诊断中应用

张敏龙, 王涛, 王旭平, 常红伟, 王放

第二炮兵工程大学机电工程系, 西安 710025

收稿日期:2015-07-20 修回日期:2015-09-21 出版日期:2016-05-10 发布日期:2016-05-09
通讯作者: 王涛
作者简介:张敏龙(1991-),男,福建漳州人,硕士研究生,主要研究方向:机电设备状态监测、故障诊断;王涛(1977-),男,陕西宝鸡人,副教授,博士,主要研究方向:故障诊断、统计模式识别;王旭平(1978-),男,浙江金华人,讲师,博士,主要研究方向:信号处理、机械设备状态监测、故障诊断;常红伟(1992-),男,安徽亳州人,硕士研究生,主要研究方向:模式识别、图像处理;王放(1975-),男,陕西西安人,副教授,博士,主要研究方向:汽车理论和虚拟维修。
基金资助:
国家自然科学基金资助项目(61201449,51405498)。

Step dynamic auto-regression kernel principal component analysis and its application in fault diagnosis

ZHANG Minlong, WANG Tao, WANG Xuping, CHANG Hongwei, WANG Fang

Department of Mechanical and Electrical Engineering, The Second Artillery Engineering University, Xi'an Shaanxi 710025, China

Received:2015-07-20 Revised:2015-09-21 Online:2016-05-10 Published:2016-05-09
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61201449, 51405498).

摘要/Abstract

摘要： 针对滑动窗自适应核主元分析法(KPCA)在处理参数敏感和缓慢劣化问题时存在的"过适应"现象,容易产生漏报的问题,提出了一种分步动态自回归KPCA算法。首先,借鉴动态数据矩阵思想,分步建立初始模型;然后,在滑动窗自适应KPCA的基础上,引入指数加权法则处理实时数据、更新模型;最后,分析算法复杂度,并给出具体实现步骤。利用模拟数据分析分解系数和加权因子对算法的影响,结果表明,与滑动窗自适应KPCA相比,所提方法在参数选择恰当的情况下,模型效率提高了近90%,误报次数几乎降为0,还能通过调整加权因子取值来控制算法的适应能力,以解决多样化的动态问题。将算法应用于压缩机喘振和轴承故障实验数据分析,验证了所提算法处理参数敏感和缓慢劣化问题的能力。

关键词: 核主元分析, 滑动窗, 分步动态策略, 指数加权, 故障诊断

Abstract: There are over-fitting phenomenon and prone omissions when moving window adaptive Kernel Principal Component Analysis (KPCA) is utilized to deal with sensitive parameters or slow degradation problem. In order to solve the problem, a step dynamic auto-regression KPCA was proposed. Firstly, the initial model was established step by step drawing on dynamic data matrix. Then, the exponentially weighting rule was introduced to process real-time data and update the model based on the moving window adaptive KPCA. Finally, the algorithm complexity was analyzed and specific steps were given. The simulation data was utilized to analyze the impact of decomposition coefficient and weighting factor. The results show that, compared with the moving window adaptive KPCA, the proposed algorithm efficiency was improved by nearly 90% and the number of false positives was almost 0 in the case of appropriate parameter selection; and it could also control the adaptive ability to solve a variety of dynamic problems by adjusting the value of weighting factor. The algorithm was applied to the experimental data analysis of compressor surge and bearing fault, the result verified its ability to deal with the problem of sensitive parameter and slow degradation.

Key words: Kernel Principal Component Analysis (KPCA), moving window, step dynamic strategy, exponentially weighting, fault diagnosis

中图分类号:

TP277

张敏龙, 王涛, 王旭平, 常红伟, 王放. 分步动态自回归核主元分析及其在故障诊断中应用[J]. 计算机应用, 2016, 36(5): 1464-1468.

ZHANG Minlong, WANG Tao, WANG Xuping, CHANG Hongwei, WANG Fang. Step dynamic auto-regression kernel principal component analysis and its application in fault diagnosis[J]. Journal of Computer Applications, 2016, 36(5): 1464-1468.

参考文献

[1] SCHÖLKOPF B, SMOLA A, MVLLER K R. Nonlinear component analysis as a kernel eigenvalue problem[J]. Neural Computation, 1998, 10(5):1299-1319.
[2] 余文利, 余建军, 方建文.一种新的基于KPCA和改进ε-SVM的入侵检测模型[J].计算机工程与应用, 2015, 51(11):93-98. (YU W L, YU J J, FANG J W. Novel intrusion detection model based on KPCA and improved ε-SVM[J]. Computer Engineering and Applications, 2015, 51(11):93-98.)
[3] LIN C, PENG F, WANG B-H, et al. Research on PCA and KPCA self-fusion based MSTARSAR automatic target recognition algorithm[J]. Journal of Electronic Science and Technology, 2012, 10(4):352-357.
[4] JIANG Q C, YAN X F. Statistical monitoring of chemical processes based on sensitive kernel principal components[J]. Chinese Journal of Chemical Engineering, 2013, 21(6):633-643.
[5] 张恒, 赵荣珍.故障特征选择与特征信息融合的加权KPCA方法研究[J].振动与冲击, 2014, 33(9):89-93, 121. (ZHANG H, ZHAO R Z. Weighted KPCA based on fault feature selection and feature information fusion[J]. Journal of Vibration and Shock, 2014, 33(9):89-93, 121.)
[6] 胡金海, 李应红, 杨帆, 等.一种基于自适应核主元分析的故障检测方法[J].控制工程, 2007, 14(S1):80-83. (HU J H, LI Y H, YANG F, et al. A fault detection method based on kernel principal component analysis[J].Control Engineering of China, 2007, 14(S1):80-83.)
[7] CHOI S W, LEE I B. Nonlinear dynamic process monitoring based on dynamic kernel PCA[J]. Chemical Engineering Science, 2004, 59(24):5897-5908.
[8] WOLD S. Exponentially weighted moving principal component analysis and projection to latent structures[J]. Chemometrics and Intelligent Laboratory Systems, 1994, 23(1):149-161.
[9] 姜万录, 吴胜强, 刘思远.指数加权动态核主元分析法及其在故障诊断中应用[J].机械工程学报, 2011, 47(3):63-68. (JIANG W L, WU S Q, LIU S Y. Exponentially weighted dynamic kernel principal component analysis algorithm and its application in fault diagnosis[J].Journal of Mechanical Engineering, 2011, 47(3):63-68.)
[10] 张庆. 基于核方法的机械设备动态监测诊断模型与关键技术研究[D]. 西安:西安交通大学, 2007. (ZHANG Q. Research on the dynamical model and its key techniques for condition monitoring and fault diagnosis of mechanical equipments based on kernel methods[D]. Xi'an:Xi'an Jiaotong University, 2007.)
[11] LEE J, QIU H, YU G, et al. 'Bearing Data Set', IMS, University of Cincinnati. NASA Ames Prognostics Data Repository, NASA Ames, Moffett Field, CA[EB/OL].[2015-07-20]. http://ti.arc.nasa.gov/projects/data_prognostics/.
[12] QIU H, LEE J, LIN J, et al. Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics[J]. Journal of Sound and Vibration, 2006, 289(4/5):1066-1090.

[1]	景兴红, 孙国栋, 何世彪, 廖勇. 基于滑窗滤波和多项式拟合的时变信道估计方法[J]. 计算机应用, 2021, 41(9): 2699-2704.
[2]	孙淑光, 周琪. 基于残差决策的自动飞行控制系统远程实时故障诊断[J]. 计算机应用, 2020, 40(5): 1522-1528.
[3]	仇媛, 常相茂, 仇倩, 彭程, 苏善婷. 基于长短期记忆网络和滑动窗口的流数据异常检测方法[J]. 计算机应用, 2020, 40(5): 1335-1339.
[4]	杨世强, 罗晓宇, 乔丹, 柳培蕾, 李德信. 基于滑动窗口和动态规划的连续动作分割与识别[J]. 计算机应用, 2019, 39(2): 348-353.
[5]	王日俊, 白越, 曾志强, 段能全, 党长营, 杜文华, 王俊元. 基于自适应观测器的四旋翼无人飞行器多传感器故障诊断方法[J]. 计算机应用, 2018, 38(9): 2735-2741.
[6]	马梦莹, 曾雅丽, 魏甜甜, 陈志德. 基于邻居节点预状态的无线传感器网络故障诊断算法[J]. 计算机应用, 2018, 38(8): 2348-2352.
[7]	王岩, 罗倩, 邓辉. 基于Gibbs抽样的轴承故障诊断方法[J]. 计算机应用, 2018, 38(7): 2136-2140.
[8]	刘张虎, 程春玲. 面向大规模数据主题建模的方差减小的随机变分推理算法[J]. 计算机应用, 2018, 38(6): 1675-1681.
[9]	何春, 李琦, 吴让好, 刘邦欣. 基于故障传播的模块化BP神经网络电路故障诊断[J]. 计算机应用, 2018, 38(2): 602-609.
[10]	徐冰珂, 周宇喆, 杨茂林, 谢远航, 李晓瑜, 雷航. 面向电信行业网络告警系统的告警过滤算法[J]. 计算机应用, 2018, 38(10): 2881-2885.
[11]	杨洪柏, 张宏利, 刘树林. 基于可视化异类特征优选融合的滚动轴承故障诊断[J]. 计算机应用, 2017, 37(4): 1207-1211.
[12]	王鑫, 刘方爱. 改进的多数据流协同频繁项集挖掘算法[J]. 计算机应用, 2016, 36(7): 1988-1992.
[13]	刘秋玥, 程勇, 王军, 钟水明, 徐利亚. 基于累积和控制图的分布式传感网络故障诊断[J]. 计算机应用, 2016, 36(11): 3016-3020.
[14]	叶卫东, 杨涛. 融合极点对称模态分解与时频分析的单通道振动信号盲分离方法[J]. 计算机应用, 2016, 36(10): 2933-2939.
[15]	段峰峰, 王永滨, 杨丽芳, 潘淑静. 基于主成分分析方向深度梯度直方图的立体视觉深度图特征提取[J]. 计算机应用, 2016, 36(1): 222-226.

分步动态自回归核主元分析及其在故障诊断中应用

Step dynamic auto-regression kernel principal component analysis and its application in fault diagnosis

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics