Collapsing coal-rock identification based on wavelet packet entropy and manifold learning

被引：0

作者：

Li Y. ^{[1
]}

Fu S. ^{[1
]}

Zhou J. ^{[1
]}

Zong K. ^{[1
]}

Li R. ^{[1
]}

Wu M. ^{[1
]}

机构：

[1] School of Mechanical Electronic & Information Engineering, China University of Mining and Technology (Beijing), Beijing

来源：

| 1600年 / China Coal Society卷 / 42期

关键词：

BP neural network; Collapsing coal-rock identification; Manifold learning; Sample entropy; Wavelet packet energy entropy;

D O I：

10.13225/j.cnki.jccs.2017.0642

中图分类号：

学科分类号：

摘要：

In order to recognize the collapsing coal and rock, a feature extraction method of vibration signals based on Wavelet packet entropy and manifold learning is proposed. The vibration signals are caused by the impact of collapsing coal-rock and hydraulic support tail beam.Firstly, the vibration signals are decomposed by Wavelet packet and the signals at different frequency bands are reconstructed, then the Wavelet packet energy entropy is calculated to determine the complexity of the signal energy distribution, the sample entropy at each frequency band is calculated to determine the complexity of the Wavelet packet coefficient at each frequency band.Wavelet packet energy entropy and sample entropy of each frequency band are used as feature vectors and the input of BP neural network to identify the collapsing coal and rock.Then, the low-dimensional manifold of feature vector is extracted by local linear embedding (LLE). The low-dimensional manifold is input into neural network to compare the recognition effect with the feature vector as the input.And an unknown sample low-dimensional estimation method is proposed to get its low-dimensional embedding.The results show that the feature vector based on Wavelet packet entropy and LLE is both accurate and simple, and the neural network identification rate reaches 92.5% using it as the input.Low-dimensional embedding of unknown sample based on low-dimensional estimation method is also accurate. © 2017, Editorial Office of Journal of China Coal Society. All right reserved.

引用

页码：585 / 593

页数：8

共 18 条

[1] Wang J., Development and prospect on fully mechanized mining in Chinese coal mines, International Journal of Coal Science & Technology, 1, 3, pp. 153-260, (2014)
[2] Ma Y., Study on automatic top coal caving system in fully-mechanized coal caving face, Coal Science and Technology, 41, 11, (2013)
[3] Wang B., Wang Z., Zhang W., Coal-rock interface recognition method based on EMD and neural network, Journal of Vibration, Measurement & Diagnosis, 32, 4, pp. 586-590, (2012)
[4] Xue G., Zhao X., Liu E., Et al., Time-domain characteristic extraction of coal and rock vibration signal in fully-mechanized top coal caving face, Coal Science and Technology, 43, 12, pp. 92-97, (2015)
[5] Zhang S., Zhang Y., Wang Y., Et al., Caved coal and rock spectrum on longwall face, Journal of China Coal Society, 32, 9, pp. 971-974, (2007)
[6] Yang J., Jiang H., Ji X., Et al., Vibration identification method of coal and rock hardness based on wavelet packet features, Coal Science and Technology, 43, 12, (2015)
[7] Li Y., Fu S., Jiao Y., Et al., The collapsing coal-rock identification based on fractal box dimension and wavelet packet energy moment, Journal of China Coal Society, 42, 3, pp. 803-808, (2017)
[8] Li Y., Fu S., Li R., Et al., Research onidentification of caving coal and rock traits, Industry and Mine Automation, 43, 2, pp. 24-28, (2017)
[9] Zhao S., Coal-rock interface recognition based on multiwavelet packet energy, Journal of Xi'an University of Science and Technology, 29, 5, pp. 584-588, (2009)
[10] Liu W., Hua Z., Wang R., Vibrational feature analysis for coal gangue caving based on information entropy of Hilbert spectrum, China Safety Science Journal, 21, 4, pp. 32-37, (2011)

← 1 2 →