Research on QGA-SVM rock burst orientation classification based on model reliability examination

被引：0
作者：
Qiu, Daohong [1 ,2 ]
Li, Shucai [1 ]
Zhang, Lewen [1 ]
Su, Maoxing [1 ]
Xie, Fudong [1 ]
机构：
[1] Research Center of Geotechnical and Structural Engineering, Shandong University, Jinan
[2] Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu
来源：
Yingyong Jichu yu Gongcheng Kexue Xuebao/Journal of Basic Science and Engineering | 2015年 / 23卷 / 05期
关键词：
Model reliability; Quantum genetic algorithm; Rock burst; Support vector machine; Trend examination method;
D O I：
10.16058/j.issn.1005-0930.2015.05.012
中图分类号：
学科分类号：
摘要：
Rock burst is the main geological disaster that affects the construction of underground engineering in high stress area. And rock burst prediction has become one of the worldwide difficulties in underground projects. In order to improve the precision of support vector machine (SVM) in rock burst classification, a model reliability examination method is presented, which checks the model reliability through the influence trend of evaluation index to evaluation grade. This model reliability examination method is a general method that can be used in any model reliability examination based on foreknowable experience method. When the kernel function parameter values of support vector machine (SVM) are preliminary selected, quantum genetic algorithm (QGA) is utilized for global research in the solution space. Finally, the QGA-SVM rock burst classification model based on model reliability examination is established, and has been applied to practical engineering. The result shows that the improved SVM has higher generalization ability and prediction accuracy in rock burst classification and recognition. © 2015, Editorial Board of Journal of Basic Science and Engineering. All right reserved.
引用
收藏
页码：981 / 991
页数：10
相关论文
共 20 条
  • [1] Feng X., Chen B., Ming H., Et al., Evolution law and mechanism of rockburst in deep tunnels: Immediate rockburst, Chinese Journal of Rock Mechanics and Engineering, 31, 3, pp. 433-444, (2012)
  • [2] Zhang J., Fu B., Rockburst and its criteria and control, Chinese Journal of Rock Mechanics and Engineering, 27, 10, pp. 2034-2042, (2008)
  • [3] Chen B., Feng X., Zeng X., Et al., Real-time microseismic monitoring and its characteristic analysis during TBM tunneling in deep-buried tunnel, Chinese Journal of Rock Mechanics and Engineering, 30, 2, pp. 275-283, (2011)
  • [4] Feng X., Zhao H., Prediction of rockburst using support vector machine, Journal of Northeastern University (Natural Science), 23, 1, pp. 57-59, (2002)
  • [5] Zhao H., Feng X., Yin S., Classification of engineering rock based on support vector machine, Rock and Soil Mechanics, 23, 6, pp. 698-701, (2002)
  • [6] Jia C., Wu H., Gong D., Coal demand prediction based on a support vector machine model, Journal of China University of Mining & Technology, 36, 1, pp. 107-110, (2007)
  • [7] Zhang X., Yao W., Tian F., Structural damage identification based on time-varying ARMA model and support vector machine, Journal of Basic Science and Engineering, 21, 6, pp. 1094-1102, (2013)
  • [8] Luo H., Wang J., Shi X., Et al., Quantum genetic algorithm and its application in geophysical inversion, Chinese Journal of Engineering Geophysics, 5, 6, pp. 635-642, (2008)
  • [9] Zhou M., Research of MIMO-OFDM detection based on neural network optimized by quantum genetic algorithm, Computer Engineering and Applications, 47, 27, pp. 161-163, (2011)
  • [10] Sang H., He D., Zhang D., Soft-Sensing modeling of a support vector machines and fermentation process through genetic algorithms, Journal of Northeastern University (Natural Science), 28, 6, pp. 781-784, (2007)
12