ISNN 2005: Advances in Neural Networks – ISNN 2005 pp 827-832 | Cite as
Modeling and Prediction of Violent Abnormal Vibration of Large Rolling Mills Based on Chaos and Wavelet Neural Networks
Conference paper
Abstract
This paper analyses the chaotic characteristics of violent abnormal vibration signals of a large rolling mill, and studies phase space reconstruction techniques of the signals. On this basis, the vibration model of wavelet neural networks and the model of backpropagation neural networks are set up, respectively, through inversion methods. The properties of these two models are tested and compared with each other. The result shows that the wavelet neural networks have an advantage over the backpropagation neural networks in rapid convergence and high accuracy.
Preview
Unable to display preview. Download preview PDF.
References
- 1.Cheng, Y., Liao, G., Shi, T., et al.: Friction-type Chatter on 4-h Cold Rolling Mills. Journal of Huazhong University of Science & Technology 31, 105–107 (2003)Google Scholar
- 2.Tang, H., Li, X., Zhong, J.: Analysis Torsion Self-excited Vibration in Rolling Mill. Journal of Xiangtan Mine Institute 17, 21–24 (2002)Google Scholar
- 3.Wang, Q., Tan, J.: A Study of the Vertical Vibration of the Plate and Strip Rolling Mill Based on the Gap Dynamics. Mechanical Science and Technology 22, 721–723 (2003)Google Scholar
- 4.Teng, L., Liu, T., Tong, D., et al.: Application of Correlation Dimension to Machinery Condition Monitoring. Journal of Vibration Engineering 15, 399–403 (2002)Google Scholar
- 5.Packard, N.H., Crutchfield, J.P., Farmers, J.D., et al.: Geometry From a Time Series. Phys. Rev. Letter 45, 712–716 (1980)CrossRefGoogle Scholar
- 6.Cao, L.: Practical Method for Determining the Minimum Embedding Dimension of a Scalar Time Series. Physic D 110, 43–50 (1997)MATHCrossRefGoogle Scholar
- 7.Wang, Y., Lin, C.: Runge-Kutta: Neural Network for Identification of Dynamical Systems in High Accuracy. IEEE Trans. on Neural Networks 9, 294–307 (1998)CrossRefGoogle Scholar
- 8.Xiang, X.: Prediction of Chaotic Time Series Based on Chaotic Theory and Radical Basis Function Neural Networks. Journal of Fuzhou University 31, 401–404 (2003)MATHGoogle Scholar
- 9.Zhang, J., Walter, G., Miao, Y.: Wavelet Neural Networks for Function Learning. IEEE Trans. on Signal Processing 43, 1485–1497 (1995)CrossRefGoogle Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 2005