Abstract
Axle is an important part of high-speed train. The axle is the key component connecting the train wheelset, which has a great impact on the train safety. The health monitoring of axles is very important for the safe and smooth operation of trains. The axle health detection is a complex process of multi-factor coupling, which faces the problems of health model construction. From the perspective of big data visual analysis, this paper helps people find the information behind the big data of high-speed railway axle monitoring, and makes a prediction and analysis of the health status of high-speed railway axle operation. Starting from the present situation of scatter plot presentation of multi-dimensional data visual analysis, this paper proposes a visual analysis and processing method for high-speed train axle health monitoring, aiming at the problems of intensive rendering, visual mutation and trend prediction when drawing large data scatter plot. Firstly, a new method of the axle data fusion model is proposed in this paper, which can effectively clean the axle health monitoring data and construct the data acquisition and expression mode of axle temperature of high-speed train. Then, visualization of axle data and prediction of axle health trend provide a new analysis model for axle health monitoring. In addition, the visual analysis method of scatter density map data can eliminate the dependence of the original complex mechanical model, and can be used to analyze different working conditions and axle types. Compared with the existing axle health monitoring methods, this method has high accuracy and practicability.
Similar content being viewed by others
References
Ahlberg C, Shneiderman B (1994) Visual information seeking: tight coupling of dynamic query filters with starfield displays. In: Beth A, Susan D, Judith O (eds) Proc. of the CHI. ACM Press, New York, pp 313–317. https://doi.org/10.1145/191666.191775]
Barducci A, Guzzi D, Marcoionni P (2007) Assessing noise amplitude in remotely sensed images using bit-plane and scatterplot approaches. In: IEEE Transactions on Geoscience and Remote Sensing 45(8):2665–2675. https://doi.org/10.1109/TGRS.2007.897421
Elmqvist N, Draqicevic P, Fekete JD (2008) Rolling the dice: mulitidimensional visual exploration using scatterplot matrix navigation. IEEE Transactions on Visualization and Computer Graphics 14(6):1539–1548. https://doi.org/10.1109/TVCG.2008.153]
Guangjun L, Lin M, Zhenwen Z (2018) Fault prediction of train bearing based on dynamic threshold of axis temperature [J]. New Technology & New Products of China 13(13):56–57
Ha D-l, Wang Q, Jiang T (2013) Application of new axle temperature monitoring system on high-speed EMUs [J]. Journal of Dalian Jiaotong University 01:89–94
Hao M (2012) Method of treating train hot box alarm and device failure based on TCDS WEB system diagnosis function [J]. Railway Locomotive & Car 02:85–88
Huang C, Chen C, Fan X (2007) Vibration characteristic analysis of train axle crack and its on-line monitoring method [J]. China Railway Science 05:83–88
Johnsson A, Berbyuk V, Enelund M (2010) Vibration dynamics of high speed train with Pareto optimizeddamping of bogie suspension to enhance safety and comfort[J]. J Geol 27(4):276–285
Lampe OD, Hauser H (2011) Interactive visualization of streaming data with kernel density estimation. In: Proc IEEE Pacific Vis Symp, p 171–178
Li C, Baciu G, Han Y (2018) StreamMap: smooth dynamic visualization of high-density streaming points. IEEE Trans Vis Comput Graph 24(3)
Lonsdale C, Stone D (2006) North American axle failure experience[J]. Foreign Rolling Stock:40–43
MacQueen J (1967) Some methods for classification and analysis of multivariate observations. In: Proc. 5th Berkeley Symp. Math. Statist. Probability, p 281–297
Mohapatra S, Weisshaar JC (2018) Modified Pearson correlation coefficient for two-color imaging in spherocylindrical cells. BMC Bioinf 19(1):428. https://doi.org/10.1186/s12859-018-2444-3
Noriega P, Bascle B, Bernier O (2006) Local kernel color histograms for background subtraction. In: Proc Int Conf Comput Vis Theory Appl, p 213–219
Ren L, Du Y, Ma S, Zhang XL, Dai GZ (2014) Visual analytics towards big data. Ruan Jian Xue Bao/Journal of Software 25(9):1909–1936 (in Chinese). http://www.jos.org.cn/1000-9825/4645.htm.
Sarikaya A, Gleicher M (2018) Scatterplots: tasks, data, and designs. IEEE Trans Vis Comput Graph 24(1):402–412. https://doi.org/10.1109/TVCG.2017.2744184
Song H, Lee J, Kim TJ, Lee KH, Kim B, Seo J (2017) GazeDx: interactive visual analytics framework for comparative gaze analysis with volumetric medical images. In: IEEE Trans Vis Comput Graph 23(1):311–320.
Su R, Wen T, Yan W, Zhang K, Shi D, Xu H (2012) A real-time information service platform for high-speed train[J]. J Comput 7(9):2330–2333
Su R, Zhang K, Yan W, Zhao Z, Xu H, Wen T (2012) Research on virtual reality sound effects for high-speed train simulation system[J]. Journal of Software 7(8):1919–1922
Su R, Gu Q, Wen T (2014) Optimization of high-speed train control strategy for traction energy saving using an improved genetic algorithm[J]. J Appl Math 507308
Thirion JP (1998) Image matching as a diffusion process: an analogy with Maxwell’s demons. Med Image Anal 2(3):243–260
Wickham H (2013) Bin-summarise-smooth: a framework for visualising large data. Tech. Rep., had.co.nz
Willems N, van de Wetering H, van Wijk JJ (2009) Visualization of vessel movements. Comput Graph Forum 28(3):959–966
Zhu JY, Hu ZW, Thompson DJ (2013) Analysis of aerodynamic and aeroacoustic behaviour of a simplified high-speed train Bogie[J]. 126:489–496.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhang, K., Xu, J., Xu, H. et al. Visual analytics towards axle health of high-speed train based on large-scale scatter image. Multimed Tools Appl 79, 16663–16681 (2020). https://doi.org/10.1007/s11042-019-08001-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-019-08001-5