基于相空间重构的事件性时间序列片段的提取

摘要
图/表
参考文献(23)
相关文章 (15)

全文: PDF (3128 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要时间序列中的相似性片段包含着一些潜在有用的信息。在状态监测系统中，从信号采集系统得到的时间序列中找出相似性片段，是进一步特征提取及状态分析等数据处理的基础。现有的相似性片段寻找算法通常是用滑动长度固定的窗提取等长的子序列进行相似性匹配计算，但在实际应用中，具有相似特征的子序列长度未必一定相等，致使找到的相似性片段可能不具有事件性。针对这一问题研究了一种基于相空间重构的相似性片段寻找方法。首先，将一维时间序列以时延方式嵌入到二维相空间中，计算得到与时间序列相对应的峰值特征序列；其次，根据已有的经验知识通过峰值特征序列确定子序列分割的位置，划分出不等长的事件性片段；最后，对得到的事件性片段进行聚类，从而找出其中的相似性片段。心电信号和故障轴承振动信号的实验结果表明，使用本方法找到的相似性片段长度不等，并具有事件性特征。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	吴旭1
	董永贵2
	侯中杰2
	程卫东1

关键词 ：时间序列, 相似性片段, 事件性片段, 相空间

Abstract：In a condition monitoring system, extracting similarity segments containing some potentially useful imformation from a time series obtained with a signal acquisition system is the basis for further data processing, such as, feature extraction and state analysis. The existing similarity subsequences searching algorithm usually uses a fixed sliding length window to extract equal length subsequences for similarity matching calculation. However, in practical applications, subsequences with similar characteristics are not inevitably equal in length to make the extracted similarity segments not have eventuality. Here, aiming at this problem, a similarity subsequence extraction method was studied based on phase space reconstruction. Firstly, a 1-D time series was embedded in a 2-D phase space according to the time delay method, and a peak feature sequence corresponding to the time series was calculated. Then, the existing empirical knowledge was used to determine the position of subsequence segmentation with the peak feature sequence, and divide eventuality subsequences with unequal lengths. Finally, the acquired eventuality subsequences were clustered to extract similarity subsequences. Test results of ECG signals and faulty bearing vibration signals indicated that the similarity segments extracted using the proposed method are unequal in length and have eventuality characteristics.

Key words： time series similarity subsequence eventuality subsequence phase space

收稿日期: 2019-05-30 出版日期: 2020-09-28

引用本文:

吴旭1，董永贵2，侯中杰2，程卫东1. 基于相空间重构的事件性时间序列片段的提取[J]. 振动与冲击, 2020, 39(19): 39-47.
WU Xu1, DONG Yonggui2, HOU Zhongjie2, CHENG Weidong1. Eventuality segments extraction from a time series based on phase space reconstruction. JOURNAL OF VIBRATION AND SHOCK, 2020, 39(19): 39-47.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2020/V39/I19/39

[1] Aghabozorgi S, Shirkhorshidi A S, Wah T Y. Time-series clustering–A decade review[J]. Information Systems, 2015, 53: 16-38.
[2] Tan P N. Introduction to data mining[M]. Pearson Education India, 2018.
[3] 孔运，王天杨，褚福磊. 自适应TQWT滤波器算法及其在冲击特征提取中的应用[J]. 振动与冲击, 2019, 38(11): 9-16.
KONG Yun, WANG Tianyang, CHU Fulei. Adaptive TQWT filter algorithm and its application in impact feature extraction. JOURNAL OF VIBRATION AND SHOCK, 2019, 38(11): 9-16.
[4] Mueen A, Keogh E, Zhu Q, et al. Exact discovery of time series motifs[C]//Proceedings of the 2009 SIAM international conference on data mining. Philadelphia, PA:Society for Industrial and Applied Mathematics, 2009: 473-484.
[5] He Q, Yan R, Kong F, et al. Machine condition monitoring using principal component representations[J]. Mechanical Systems and Signal Processing, 2009, 23(2): 446-466.
[6] Keogh E, Lin J. Clustering of time-series subsequences is meaningless: implications for previous and future research[J]. Knowledge and information systems, 2005, 8(2): 154-177.
[7] Torkamani S, Lohweg V. Survey on time series motif discovery[J]. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2017, 7(2): e1199.
[8] Yeh C C M, Zhu Y, Ulanova L, et al. Matrix profile I: all pairs similarity joins for time series: a unifying view that includes motifs, discords and shapelets[C]//2016 IEEE 16th international conference on data mining (ICDM).Piscataway,NJ:IEEE, 2016: 1317-1322.
[9] The UCR Matrix Profile Page[EB/OL]. [2019-05-10].http: //www.cs.ucr.edu/~eamonn/MatrixProfile.html
[10] 肖涵，李友荣，吕勇. 基于递归定量分析与高斯混合模型的齿轮故障识别[J]. 振动工程学报, 2011, 24(1): 84-88.
XIAO Han, LI YouRong, LU Yong. Gear fault recognition based on recurrence quantification analysis and Gaussian mixture model[J]. Journal of Vibration Engineering, 2011, 24(1): 84-88.
[11] Hou Z, Dong Y, Xiang J, et al. A Real-Time QRS Detection Method Based on Phase Portraits and Box-scoring Calculation[J]. IEEE Sensors Journal, 2018, 18(9): 3694-3702.
[12] Han L, Romero C E, Yao Z. Wind power forecasting based on principle component phase space reconstruction[J]. Renewable Energy, 2015, 81: 737-744.
[13] Lekscha J, Donner R V. Phase space reconstruction for non-uniformly sampled noisy time series[J]. Chaos: An Interdisciplinary Journal of Nonlinear Science, 2018, 28(8): 085702.
[14] 刘尚坤，唐贵基，庞彬 . 基于相空间重构与平稳子空间分析的滚动轴承故障诊断[J]. 振动与冲击, 2015, 34(22): 187-191.
LIU Shang-kun, TANG Gui-ji, PANG Bin. Fault Diagnosis for Rolling Bearing Based on Phase Space reconstruction and Stationary Subspace Analysis. JOURNAL OF VIBRATION AND SHOCK, 2015, 34(22): 187-191.
[15] Lee J W, Kim K S, Lee B, et al. A real time QRS detection using delay-coordinate mapping for the microcontroller implementation[J]. Annals of biomedical Engineering, 2002, 30(9): 1140-1151.
[16] Liebert W, Pawelzik K, Schuster H G. Optimal embeddings of chaotic attractors from topological considerations[J]. EPL (Europhysics Letters), 1991, 14(6): 521.
[17] Keogh E, Lin J, Fu A. HOT SAX: Finding the most unusual time series subsequence: Algorithms and applications[C]//Proc. of the 5th IEEE Int'l. Conf. on Data Mining. 2004: 440-449.
[18] Mueen A, Keogh E. Extracting optimal performance from dynamic time warping[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2016: 2129-2130.
[19] Mazzoleni P, Matta F, Zappa E, et al. Gaussian pre-filtering for uncertainty minimization in digital image correlation using numerically-designed speckle patterns[J]. Optics and Lasers in Engineering, 2015, 66: 19-33.
[20] Clauset A, Newman M E J, Moore C. Finding community structure in very large networks[J]. Physical review E, 2004, 70(6): 066111.
[21] Blondel V D, Guillaume J L, Lambiotte R, et al. Fast unfolding of communities in large networks[J]. Journal of statistical mechanics: theory and experiment, 2008, 2008(10): P10008.
[22] Goldberger A L, Amaral L A N, Glass L, et al. Components of a new research resource for complex physiologic signals[J]. PhysioBank, PhysioToolkit, and Physionet.
[23] Bearing Data Center. Case western reserve university[EB/OL]. [2014-04-10]. http：//csegroups. case. edu/bearingdatacenter/pages/download-data-file.