期刊文献+

公路隧道施工期围岩快速分类极限学习机模型研究 被引量:1

Study on the Extreme Learning Machine Model of Highway Tunnel Rapid Surrounding Rock Classification in Construction Phase
下载PDF
导出
摘要 针对以往智能优化算法学习速度慢、对参数选择敏感等问题,引入极限学习机(ELM)方法用于围岩分类。在分类指标方面,结合快速性与准确性,制定快速分级参数标准,以公路隧道设计规范中的BQ法为基准,从以往及正在施工的隧道中收集对应的样本,从而建立了公路隧道施工期围岩快速分类的极限学习机模型。之后将正在开挖隧道工作面的快速分级参数,提供给模型进行判别,达到快速、精确分级目的。通过抚松隧道实际验证,该模型判断结果与实际施工情况吻合,可用于指导施工阶段的隧道围岩快速分级。 Specific to the problem such as slow learning speed,and sensitivity to parameter selection of the existing intelligent optimization algorithm,Extreme Learning Machine(ELM) is used for classification of surrounding rock. In terms of classification index,the rapid and accuracy classification standard parameters are formulated. Based on the BQ method which is in highway tunnel design specification,the corresponding sample are collected from the tunnel under construction,thus the Extreme Learning Machine model of highway tunnel surrounding rock classification in construction period is established. In the end,the rapid classification index of tunnel's working face is measured,and provided to the model to achieve fast and accurate classification. Fu Song tunnel's practical validation shows that the judgment results of the model are tally with the actual construction situation. It's proved that the model can be used to guide the tunnel surrounding rock classification in construction phase.
出处 《城市勘测》 2016年第1期149-153,共5页 Urban Geotechnical Investigation & Surveying
基金 大连市交通科技项目(2011-10) 吉林省交通厅交通运输科技项目(2012-1-6)
关键词 极限学习机 围岩分级 隧道 extreme learning machine classification of surrounding rock tunnel
  • 相关文献

参考文献11

二级参考文献76

共引文献210

同被引文献14

引证文献1

二级引证文献9

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