Study on Fault Diagnosis of Rolling Mill Main Transmission System Based on EMD-AR Model and Correlation Dimension

  • Guiping Dai
  • Manhua Wu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5755)


In order to improve the fault diagnosis accuracy of rolling mill main transmission system, a fault feature extraction method based on EMD (Empirical Mode Decomposition)-AR model and Correlation Dimension is proposed. In the proposed method, EMD is used to decompose the vibration signal of complex machine into several intrinsic mode functions (IMFs), then the AR models of some IMF components which contain main fault information are constructed respectively. Finally, the correlation dimensions of auto-regressive parameters in AR models are calculated. Analysis of the experimental results shows that this method not only can reflect the state changes of dynamic system profoundly and detailedly, but also can realize the separation of state features, thus it may judge the fault conditions of rolling mill main transmission system effectively.


Empirical mode decomposition AR model Correlation dimension Rolling mill main transmission system Fault diagnosis 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Yu, W.K., Liu, B.: Processing’s method of non-stationary transient impact torsional vibration signal for Rolling mill. Chinese Journal of Scientific Instrument 26(8), 504–505 (2005)Google Scholar
  2. 2.
    Zong, M., Dai, G.P.: Characteristics study on time-frequency analysis method based on empirical mode decomposition. Chinese Journal of Sensors and Actuators 19(4), 1029–1032 (2006)MathSciNetGoogle Scholar
  3. 3.
    Zhao, H.: Application research of correlation dimension in the machinery equipment fault diagnosis. China Safety Science Journal 16(3), 129–134 (2006)Google Scholar
  4. 4.
    Liu, T.X., Hua, H.X.: Application research of state monitoring method based on fractal geometry. Chinese Journal of Mechanical Engineering 37(5), 100–104 (2001)CrossRefGoogle Scholar
  5. 5.
    Dai, G.P., Liu, B.: Instantaneous parameters extraction based on wavelet denoising and EMD. Acta Metrologica Sinica 28(2), 158–161 (2007)Google Scholar
  6. 6.
    Liu, B., Dai, G.P.: Adaptive wavelet thresholding denoising algorithm based on white noise detection and 3σ rule. Chinese Journal of Sensors and Actuators 18(3), 473–477 (2005)Google Scholar
  7. 7.
    Huang, N.E., et al.: The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. In: Proc.R Soc.Lond.A (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Guiping Dai
    • 1
    • 2
  • Manhua Wu
    • 3
  1. 1.JiangSu Province Support Software Engineering R&D Center for Modern Information Technology Application in Enterprise 
  2. 2.Department of Electronic & Information EngineeringSuzhou Vocational UniversitySuzhouChina
  3. 3.Department of Foreign Languages and International ExchangeSuzhou Vocational UniversitySuzhouChina

Personalised recommendations