Research on Framework Load Correlations Based on Automatic Data Extraction Algorithm

  • Meiwen HuEmail author
  • Binjie Wang
  • Shouguang Sun
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1084)


Actual framework loads are critical to the safety of urban rail vehicles, whose operating modes have an important impact on the fatigue of framework. When the vehicle’s running states and line conditions are different, the operating modes also have obviously different characteristics. In this paper, based on the framework load-time history data of large-scale line measurement, an automatic deep learning method in data mining is used to design the program to achieve an accurate and automatic segmentation of operating conditions, thus obtaining the load-time history under different operating conditions. The calculation of the load correlations under different operating conditions is carried out, leading to corresponding correlation degree of different loads. It lays a solid foundation for building an operating mode of complex framework loads, ensuring the operational safety of rail vehicles and conducting effective reliability assessment.


Data mining Automatic extraction Operating mode of loads 



First of all, I would like to thank Professor Binjie Wang and Shouguang Sun for their guidance during the design process. In addition, I am very grateful to Mr. Wang Peng from Fudan University for his expansive explanation of relevant knowledge.


  1. 1.
    Beijing Municipal People’s Government. Beijing Urban Rail Transit Construction Plan 2011–2020Google Scholar
  2. 2.
    Wang, P., Wang, H., Wang, W.: Finding semantics in time series. In: SIGMOD Conference, pp. 385–396 (2011)Google Scholar
  3. 3.
    Mueen, A., Keogh, E.J.: Online discovery and maintenance of time series motifs. In KDD, pp. 1089–1098 (2010)Google Scholar
  4. 4.
    Sakurai, Y., Papadimitriou, S., Faloutsos, C.: Braid: stream mining through group lag correlations. In: SIGMOD, pp. 599–610 (2005)Google Scholar
  5. 5.
    Shaghayegh, G., Ding, Y.F., Michael, Y., Kaveh, K., Liudmila, U.: Matrix Profile VIII: domain agnostic online semantic segmentation at superhuman performance levels. Department of Computer Science and Engineering, pp. 1–10, October 2017Google Scholar
  6. 6.
    Keogh, E.J., Chu, S., Hart, D., Pazzani, M.J.: An online algorithm for segmenting time series. In: ICDM, pp. 289–296 (2001)Google Scholar
  7. 7.
    Matsubara, Y., Sakurai, Y., Faloutsos, C., Iwata, T., Yoshikawa, M.: Fast mining and forecasting of complex time-stamped events. In: KDD, pp. 271–279 (2012)Google Scholar
  8. 8.
    Rakthanmanon, T., Campana, B.J.L., Mueen, A., Batista, G.E.A.P.A., Westover, M.B., Zhu, Q., Zakaria, J., Keogh, E.J.: Searching and mining trillions of time series subsequences under dynamic time warping. In: KDD, pp. 262–270 (2012)Google Scholar
  9. 9.
    Tatti, N., Vreeken, J.: The long and the short of it: summarising event sequences with serial episodes. In: KDD, pp. 462–470 (2012)Google Scholar
  10. 10.
    Toyoda, M., Sakurai, Y., Ishikawa, Y.: Pattern discovery in data streams under the time warping distance. VLDB J. 22(3), 295–318 (2013)CrossRefGoogle Scholar
  11. 11.
    Matteson, D.S., James, N.A.: A nonparametric approach for multiple change point analysis of multivariate data. J. Am. Stat. Assoc. 109(505), 334–345 (2014)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Matsubara, Y., Sakurai, Y., Faloutsos, C.: AutoPlait: automatic mining of co-evolving time sequences. In: Proceedings of the 2014 ACM SIGMOD, pp. 193–204, June 2014Google Scholar
  13. 13.
    Lan, R., Sun, H.: Automated human motion segmentation via motion regularities. Vis. Comput. 31(1), 35–53 (2015)CrossRefGoogle Scholar
  14. 14.
    Ron, D., Singer, Y., Tishby, N.: The power of amnesia: learning probabilistic automata with variable memory length. Mach. Learn. 25, 117–149 (1996)CrossRefGoogle Scholar
  15. 15.
    Matsubara, Y., Sakurai, Y., Prakash, B.A., Li, L., Faloutsos, C.: Rise and fall patterns of information diffusion: model and implications. In: KDD, pp. 6–14 (2012)Google Scholar
  16. 16.
    Papadimitriou, S., Sun, J., Faloutsos, C.: Streaming pattern discovery in multiple time-series. In: Proceedings of VLDB, pp. 697–708, August-September 2005Google Scholar
  17. 17.
    Li, L., Liang, C.-J.M., Liu, J., Nath, S., Terzis, A., Faloutsos, C.: Thermocast: a cyber-physical forecasting model for data centers. In: KDD, pp. 3–8 (2011)Google Scholar
  18. 18.
    Aminikhanghahi, S., Cook, D.J.: A survey of methods for time series change point detection. Knowl. Inf. Syst. 51, 1–29 (2016)Google Scholar
  19. 19.
    Hao, Y., Chen, Y., Zakaria, J., Hu, B., Rakthanmanon, T., Keogh, E.: Towards never-ending learning from time series streams. In: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 874–882, August 2013Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Beijing Jiaotong UniversityBeijingChina

Personalised recommendations