Feature extraction and classification method of mine microseismic signals based on EWT_Hankel_SVD

被引：0
|
作者：
Cheng T. [1 ]
Wu Y. [1 ]
Luo X. [1 ]
Dai C. [1 ]
Yin B. [1 ]
机构：
[1] Jiangxi University of Science and Technology, Ganzhou
来源：
Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument | 2019年 / 40卷 / 06期
关键词：
Empirical wavelet transform; Feature extraction; Hanke1; matrix; Mine microseismic signal; Pattern recognition; Singular value decomposition;
D O I：
10.19650/j.cnki.cjsi.J1904605
中图分类号：
学科分类号：
摘要：
To solve the difficult problem of automatic identification rock mass microseism and blasting vibration signals, a feature extraction and classification method based on empirical wavelet transform_Hankel matrix_singular value decomposition (EWT_Hnakel_SVD) is proposed. Firstly, EWT spectrum segmentation method is improved to adapt the transient and diversity of microseism signals. Its effectiveness is demonstrated by using simulation signals. Then, the improved EWT is used to decompose the microseismic and blasting vibration signals. Five principal components of f1~f5 are obtained by correlation analysis, which are utilized to formulate the Hankel matrix. The maximum singular value and singular entropy of each Hankel matrix are calculated. Finally, the genetic algorithm-optimized support vector machine (GA-SVM) is adopted to classify the microseism and blasting signals. Experimental results show that the singular entropy of the blasting vibration signal component fl~f4 is too much singular entropy of the rock mass microseismic signal component fl~f4, and the maximum singular value of the blasting vibration signal component fl~f5 is greater than that of the rock mass microseismic signal component fl~f5. The improved EWT recognition is better than traditional EWT and empirical mode decomposition. GA-SVM recognition effect is better than support vector machine, logistic regression and Bayes discriminant method. The method based on EWT_Hankel_SVD and GA-SVM classification can reach accuracy rate 94%. © 2019, Science Press. All right reserved.
引用
收藏
页码：181 / 191
页数：10
相关论文
共 35 条
  • [11] Zhao G.Y., Deng Q.L., Ma J., Analysis and recognition of mine microseismic signals based on FSWT time-frequency analysis, Chinese Journal of Geotechnical Engineering, 37, 2, pp. 306-312, (2015)
  • [12] Shang X.Y., Li X.B., Peng K., Et al., Feature extraction and classification of mine microseism and blast based on EMD-SVD, Chinese Journal of Geotechnical Engineering, 38, 10, pp. 1849-1858, (2016)
  • [13] Li W., Feature extraction and classification method of mine microseismic signals based on LMD and pattern recognition, Journal of China Coal Society, 42, 5, pp. 1156-1164, (2017)
  • [14] Dong L.J., Sun D.Y., Li X.B., Et al., A statistical method to identify blasts and microseismic events and its engineering application, Chinese Journal of Geotechnical Engineering, 35, 7, pp. 1423-1433, (2016)
  • [15] Dong L.J., Wesseloo J., Yves P., Et al., Discriminant models of blasts and seismic events in mine seismology, International Journal of Rock Mechanics and Mining Science, 86, pp. 282-291, (2016)
  • [16] Shang X.Y., Li X.B., Morales-Esteban A., Et al., Improving microseismic event and quarry blast classification using artificial neural networks based on principal component analysis, Soil Dynamics and Earthquake Engineering, 99, pp. 142-149, (2017)
  • [17] Li B.L., Li N., Wang E.Y., Et al., Characteristics of coal mining microseismic and blasting signals at Qianqiu coal mine, Environmental Earth Sciences, 76, 21, pp. 1-15, (2017)
  • [18] Vallejos J.A., Mckinnon S.D., Logistic regression and neural network classification of seismic records, Internation Journal of Rock Mechanics and Mining Science, 62, pp. 86-95, (2013)
  • [19] Zhu W.Y., Feng Z.P., Fault diagnosis of planetary gearbox based on improved experience wavelet transform, Chinese Journal of Science Instrument, 37, 10, pp. 2193-2201, (2016)
  • [20] Gills J., Empirical wavelet transform, IEEE Transactions on Signal Processing, 61, 16, pp. 3999-4010, (2013)
1234