储油罐液位时序数据模式发现
作者:
中图分类号:

TP391

基金项目:

国家自然科学基金面上资助项目(41574117);国家重大专项资助项目(2016ZX05033-005-004)。


Pattern discovery of liquid level time series data in oil tank
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [25]
  • |
  • 相似文献
  • | | |
  • 文章评论
    摘要:

    储油罐液位时序数据模式发现对油田生产管理、灾害预警有重要意义,由于目前油气田领域的数据体系繁杂,并未对这些数据加以分类和标识。已有方法借助图形化工具进行人工筛选与检查,这样的方法不适用于长时间不间断生产的石油工业。面对上述问题及已有方法的不足,针对储油罐液位时序数据的特点,提出基于层叠分段与层次聚类模式发现的处理方法。将观测序列转换为离散的线性分段序列,并对各线性分段进行基于DTW (距离的无监督层次聚类,可自动发现时序模式并分配标识符标注时序序列。以储油罐液位时序数据进行实验,发现了隐含的变化模式和变化规律。方法对液位时序变化模式有很好的识别及分类能力,无需人工筛选与检查,并可根据需要,查看不同粒度的变化模式,可为时序数据模式识别,异常检测提供参考和途径。

    Abstract:

    The liquid level of oil tank time series data model is of great significance for oilfield production, management and disaster warning. Due to the miscellaneous data system in the field of oil and gas fields, these data are not classified and marked. There are some methods for manual screening and checking with graphical tools, which are not suitable for long time uninterrupted production of petroleum industry. In the face of the above problems and the shortcomings of the existing methods, a processing method which based on cascade piecewise linear representation and hierarchical clustering for the characteristics of reservoir tank level data is proposed. The observation sequence is transformed into discrete linear piecewise sequence, and each linear segment is clustered by unsupervised hierarchical clustering based on DTW distance, which can automatically discover the temporal pattern and assign identifiers to annotate the sequence. Based on the data of oil tank level sequence data, and the implied models and the changing rules were found. The method has a good ability to recognize and classify the time series change patterns of liquid level, without manual screening and inspection, and can view the changing patterns of different granularity according to the need, which can provide a reference and avenues for time series data pattern recognition and abnormality detection.

    参考文献
    [1] Gong X Y, Si Y W, Fong S, et al. Financial time series pattern matching with extended UCR suite and support vector machine[J]. Expert Systems With Applications, 2016, 55:284-296.
    [2] Lu C, Shi Y T, Chen Y Y, et al. Data mining applied to oil well using K-means and DBSCAN[C/OL].2016 7th International Conference on Cloud Computing and Big Data (CCBD). New York, USA:IEEE, 2016[2019-09-25]. https://doi.org/10.1109/ccbd.2016.018.
    [3] Shokoohiyekta M. Meaningful rule discovery and adaptive classification of multi-dimensional time series data[J]. Dissertations & Theses-Gradworks, 2015, 13(10):323-327.
    [4] 李斌, 谭立湘, 章劲松, 等. 面向数据挖掘的时间序列符号化方法研究[J]. 电路与系统学报, 2000, 5(2):9-14. LI Bin, TAN Lixiang, ZHANG Jinsong, et al. The study of the data mining oriented method for the symbolization of time series[J]. Journal of Circuits and Systems, 2000, 5(2):9-14. (in Chinese)
    [5] 李爱国, 覃征. 在线分割时间序列数据[J]. 软件学报, 2004, 15(11):1671-1679. LI Aiguo, QIN Zheng. On-line segmentation of time-series data[J]. Journal of Software, 2004, 15(11):1671-1679.(in Chinese)
    [6] Fayyad U, Uthurusamy R. Data mining and knowledge discovery in databases[J]. Communications of the ACM, 1996, 39(11):24-26.
    [7] 蔡智, 岳丽华, 王熙法. 时序模式发现算法研究[J]. 计算机研究与发展, 2000, 37(9):1107-1113. CAI Zhi, YUE Lihua,WANG Xifa. Research on an algorithm for time series patterns discovery[J]. Journal of Computer Research and Development, 2000, 37(9):1107-1113. (in Chinese)
    [8] Berndt D J, Clifford J. Using dynamic time warping to find patterns in time series[J]. Intelligent Information Management, 1994, 359-370.
    [9] 杨雨浓, 修春波. 联想神经网络的风速序列预测分析[J]. 重庆大学学报, 2016, 39(4):139-146. YANG Yunong, XIU Chunbo. Wind speed time series prediction based on associative network[J]. Journal of Chongqing University, 2016, 39(4):139-146. (in Chinese)
    [10] 吴文兵, 黄荣华, 刘日华, 等. 耦合信号微分后对双谱的影响[J]. 重庆大学学报, 2017, 40(7):82-90. WU Wenbing, HUANG Ronghua, LIU Rihua, et al. The affection of differentiated coupled signals on bispectrum[J]. Journal of Chongqing University, 2017, 40(7):82-90. (in Chinese)
    [11] Baydogan M G, Runger G. Learning a symbolic representation for multivariate time series classification[J]. Data Mining and Knowledge Discovery, 2015, 29(2):400-422.
    [12] Bondu A, Boullé M, Cornuéjols A. Symbolic representation of time series:A hierarchical coclustering formalization[M]. Cham:Springer International Publishing, 2016:3-16.
    [13] Dai D, Mu D. A fast approach to K-means clustering for time series based on symbolic representation[J]. International Journal of Advancements in Computing Technology, 2012, 4(5):233-239.
    [14] Kate R J. Using dynamic time warping distances as features for improved time series classification[J]. Data Mining and Knowledge Discovery, 2016, 30(2):283-312.
    [15] Lee J, Yoo S, Kim H, et al. The spatial and temporal variation in passenger service rate and its impact on train dwell time:A time-series clustering approach using dynamic time warping[J]. International Journal of Sustainable Transportation, 2018, 12(10):725-736.
    [16] 尹锐, 李雄飞, 李军, 等. 基于线性分段与HMM的时间序列分类算法[J]. 模式识别与人工智能, 2011, 24(4):574-581. YIN Rui, LI Xiongfei, LI Jun, et al. Time series classification algorithm based on linear segmentation and HMM[J]. Pattern Recognition and Artificial Intelligence, 2011, 24(4):574-581. (in Chinese)
    [17] 陈封能,斯坦巴赫,库玛尔.数据挖掘导论(完整版)[M].北京:人民邮电出版社,2011:305,32-327. Fengneng C,Michael Steinbach, Vipin Kumar. Introduction to data mining[M]. BeiJing:the People's Posts and Telecommunications Press,2011:305,32-327.(in Chinese)
    [18] Aljawarneh S, Radhakrishna V, Kumar P V, et al. A similarity measure for temporal pattern discovery in time series data generated by IoT[C/OL]. 2016 International Conference on Engineering & MIS (ICEMIS). New York, USA:IEEE, 2016(2016-11-17)[2019-09-25]. https://ieeexplore.ieee.org/document/7745355/.
    [19] 周东华, 叶银忠. 现代故障诊断与容错控制[M]. 北京:清华大学出版社, 2000:209-214. ZHOU Donghua, YE Yinzhong. Modern Fault Diagnosis and Fault-Tolerant Control[M]. Beijing:Tsinghua University Press, 2000:209-214.(in Chinese)
    [20] Keogh E J, Pazzani M J. Scaling up dynamic time warping for datamining applications[C]//Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining-KDD'00. New York, USA:ACM Press, 2000:285-289.
    [21] Ratanamahatana C A, Keogh E. Multimedia retrieval using time series representation and relevance feedback[M]. Berlin, Heidelberg:Springer Berlin Heidelberg, 2005,3815:400-405.
    [22] 孙吉贵, 刘杰, 赵连宇. 聚类算法研究[J]. 软件学报, 2008, 19(1):48-61. SUN Jigui, LIU Jie, ZHAO Lianyu. Clustering algorithms research[J]. Journal of Software, 2008, 19(1):48-61.(in Chinese)
    [23] Fox W R, Kaufman L, Rousseeuw P J. Finding groups in data:an introduction to cluster analysis[J]. Applied Statistics, 1991, 40(3):486.
    [24] Guo C H, Li H L, Pan D H. An improved piecewise aggregate approximation based on statistical features for time series mining[M].Berlin, Heidelberg:Springer Berlin Heidelberg, 2010,6291:234-244.
    [25] Rousseeuw P J. Silhouettes:A graphical aid to the interpretation and validation of cluster analysis[J]. Journal of Computational and Applied Mathematics, 1987, 20:53-65.
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

文必龙,马强,李菲.储油罐液位时序数据模式发现[J].重庆大学学报,2020,43(3):88-99.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2019-02-13
  • 在线发布日期: 2020-03-31
文章二维码