Pattern Recognition of the Soft Abrasive Flow Based on Wavelet Packet


Article Preview

A Pattern Recognition method based on wavelet packet and artificial neural is proposed for solid-liquid two-phase flow characteristic parameters and the non-linear relationship between flow pattern. This method firstly established the physical and dynamic model, then set a monitoring point. To get the optimum wavelet tree and its information entropy, six floors of wavelet packet was used to decompose the collected velocity fluctuation signal. Transported the proper vector which is component by information entropy into Back Propagation neural network to train and identify. The recognition results show that this method can effectively overcome the subjectivity of traditional identification methods. It has good recognition effect, thus provide an effective choice for solid-liquid two-phase flow pattern recognition.



Advanced Materials Research (Volumes 588-589)

Edited by:

Lawrence Lim




K. D. Hu et al., "Pattern Recognition of the Soft Abrasive Flow Based on Wavelet Packet", Advanced Materials Research, Vols. 588-589, pp. 756-760, 2012

Online since:

November 2012




[1] S. M. Ji, F. Q. Xiao, D. P. Tan: Science China-Technological Sciences Vol. 53 (2010), p.2867.

[2] M. J. Embrechts, et al: Proceeding of the American Power Conference 1996, p.860.

[3] B. Sun, Q. Wang, Y. L. Zhou: Chinese Journal of Scientific Instrument Vol. 27(2006), p.725.

[4] Z. H. Gui, F. Q. Han: Automation of Electric Power Systems Vol. 28(2004), p.62.

[5] B. Sun, Y. L. Zhou: Chemical Engineering Vol. 34(2006), p.33.

[6] Z. B. Sheng: Journal of Weinan Teachers University Vol. 23(2008), p.65.