| 基于主成分分析与BP神经网络的TBM围岩可掘性分级实时识别方法研究 |
| |
| 引用本文： | 段志伟,杜立杰,吕海明,王家海,刘海东,富勇明. 基于主成分分析与BP神经网络的TBM围岩可掘性分级实时识别方法研究[J]. 隧道建设, 2020, 40(3): 379-388. DOI: 10.3973/j.issn.2096-4498.2020.03.010 |
| |
| 作者姓名： | 段志伟 杜立杰 吕海明 王家海 刘海东 富勇明 |
| |
| 作者单位： | (1. 石家庄铁道大学, 河北 石家庄 050043; 2. 中铁十九局集团第一工程有限公司, 辽宁 辽阳 111000) |
| |
| 基金项目： | 新疆EH工程科研计划(2019EH-TBM-3); 中国铁路总公司科研计划(2016G004-A) |
| |
| 摘 要： | TBM 围岩可掘性等级实时在线识别和预警对TBM 安全高效以及智能化掘进意义重大,基于新疆EH 隧洞工程直径为7. 0 m的敞开式TBM 实际掘进数据与地质数据, 通过TBM 掘进性能与施工风险的特征参数指标对围岩进行可掘性分级。在对不同围岩下区分度较好的掘进参数进行主成分分析之后,获得表征围岩可掘性等级的2 个主成分指标,并在此基础上构建BP 神经网络对围岩可掘性等级进行识别。同时,为提高模型响应速度,设计了一个MATLAB 程序,从而获得了实用性较强的围岩可掘性等级实时识别方法。
|
| 关 键 词： | TBM 围岩可掘性分级 主成分分析 BP 神经网路 实时识别模型 |
| 收稿时间： | 2019-09-29 |
Real-time Identification Method of TBM Surrounding Rock ExcavatabilityGrade Based on Principal Component Analysis and BP Neural Network |
| |
| DUAN Zhiwei,DU Lijie,LYU Haiming,WANG Jiahai,LIU Haidong,FU Yongming. Real-time Identification Method of TBM Surrounding Rock ExcavatabilityGrade Based on Principal Component Analysis and BP Neural Network[J]. Tunnel Construction, 2020, 40(3): 379-388. DOI: 10.3973/j.issn.2096-4498.2020.03.010 |
| |
| Authors: | DUAN Zhiwei DU Lijie LYU Haiming WANG Jiahai LIU Haidong FU Yongming |
| |
| Affiliation: | (1. Shijiazhuang Tiedao University, Shijiazhuang 050043, Hebei, China;2. China Railway 19th Bureau Group First Engineering Co., Ltd., Liaoyang 111000, Liaoning, China) |
| |
| Abstract: | The on-line real-time identification and early warning of TBM surrounding rock excavatability grade issignificant for safe, high-efficient and intelligent TBM tunneling. An open-type TBM with a diameter of 7. 0 m is appliedto EH tunnel in Xinjiang, and the practical boring data and geological data are analyzed. The surrounding rockexcavatability is classified according to the characteristic parameter indicators reflecting the TBM tunneling performanceand construction risk. Further, after analyzing the excavation parameters of better discrimination quality under differentsurrounding rocks with principal component analysis method, two principal component indicators for characterizing theexcavatability grade of surrounding rock are obtained; and based on which, the BP neural network is constructed toidentify the surrounding rock excavatability grade. Meanwhile, in order to increase the response speed of the model, aMATLAB program is designed to obtain real-time identification method of surrounding rock excavatability grade withbetter practicability. |
| |
| Keywords: | TBM rock excavatability grade principal component analysis BP neural network real-time identificationmodel |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《隧道建设》浏览原始摘要信息 |
|
点击此处可从《隧道建设》下载全文 |
|
