期刊文献+

基于模式识别的煤与瓦斯突出区域预测 被引量:9

Forecast to Coal/Gas Outburst Area Through Pattern Recognition Method
下载PDF
导出
摘要 从潘一矿13 1煤层煤与瓦斯突出特征出发,探讨了突出机理,认为该煤层的突出是构造应力主导的倾出和压出类型的突出·针对该类型的煤与瓦斯突出,从突出的诸控制因素和预测方法的工程可行性等层面讨论了区域预测思想和具体的方法·指出煤和顶底板岩石物理力学性质的异常是构造应力主导的倾出和压出型突出危险区的基本特征和必然共性,并提出了侧重分析煤物理力学性质和瓦斯信息,对勘探资料和测井资料进行充分的数据挖掘,并结合支持向量机先进的分类算法的多因素模式识别区域预测方法,它既有理论基础,又具有工程实用性和可操作性·用这一方法对潘一矿13 1煤层煤与瓦斯突出的区域进行预测,得到的突出危险区与实际发生的突出点分布范围相吻合· Based on the coal/gas outburst characteristics of the 13-1 coal seam in Panyi Coal Mine, the outburst mechanism was explored. The erupted or extruded type of the coal seam is regarded as mainly caused by the tectonic stresses. How to forecast the coal/gas outburst area and its practice are discussed from the point of view of various control factors and engineering feasibility. The abnormality of the physical-mechanical properties of the coal and rock supported by roofs and information on gas are the basic characteristics and inevitably the general character causing the hazardous erupted or extruded outburst areas mainly due to tectonic stresses. The area forecast is proposed the way it should be based on sufficient data mining for the exploration and log information in combination with multi-factor pattern recognition approach by using an advanced classification algorithm of the support vector machine. Such a forecast is not only based on a theoretical foundation but provide engineering practicability and operability. The forecast results obtained are in good conformation with the measured data of the 13-1 coal seam in Panyi Coal Mine.
出处 《东北大学学报(自然科学版)》 EI CAS CSCD 北大核心 2004年第9期903-906,共4页 Journal of Northeastern University(Natural Science)
基金 国家重点基础研究发展规划项目(2002CB412708) 国家'十五'科技攻关项目(2001BA803B0404)
关键词 煤与瓦斯突出 区域预测 模式识别 支持向量机 coal/gas outburst area forecast pattern recognition support vector machine
  • 相关文献

参考文献5

  • 1[2]Zajtsev P P, Malova G V, Panchenko,et al. Electric properties of outburstable bituminous coals and prediction of outbursts of coal and gas[J]. Khimiya Tverdogo Topliva, 1992,5(5):88-92.
  • 2[7]Platt J, Schülkopf B, Burges C, et al. Fast training of support vector machines using sequential minimal optimization[A]. Advances in Kernal MethodsSupport Vector Learning[C]. Cambridge: MIT Press, 1999.185-208.
  • 3[8]Amari S, Wu S. Improving support vector machine classifier by modifying kernel function[J]. Neural Networks, 1999,12(6):783-789.
  • 4[9]Bartlett P L, Shawe-Taylor J. Generalization performance on support vector machines and other pattern classifiers[A]. Advances in Kernel MethodsSupport Vector Learning[C]. Cambridge: MIT Press, 1999.43-54.
  • 5[10]Burges C J C. A tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Discovery, 1998,2(2):121-167.

同被引文献42

引证文献9

二级引证文献36

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部