[1]吴波,钟和发,刘聪.基于BP神经网络的深部隧道蠕变模型多参数智能反演分析*[J].中国安全生产科学技术,2023,19(7):113-119.[doi:10.11731/j.issn.1673-193x.2023.07.017]
WU Bo,ZHONG Hefa,LIU Cong.Multi-parameter intelligent inversion analysis of deep tunnel creep model based on BP neural network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2023,19(7):113-119.[doi:10.11731/j.issn.1673-193x.2023.07.017]
点击复制
基于BP神经网络的深部隧道蠕变模型多参数智能反演分析*
WU Bo,ZHONG Hefa,LIU Cong.Multi-parameter intelligent inversion analysis of deep tunnel creep model based on BP neural network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2023,19(7):113-119.[doi:10.11731/j.issn.1673-193x.2023.07.017]
《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]
- 卷:
- 19
- 期数:
- 2023年7期
- 页码:
- 113-119
- 栏目:
- 职业安全卫生管理与技术
- 出版日期:
- 2023-07-31
文章信息/Info
- Title:
- Multi-parameter intelligent inversion analysis of deep tunnel creep model based on BP neural network
- 文章编号:
- 1673-193X(2023)-07-0113-07
- 分类号:
- U455.7；X935
- 文献标志码:
- A
- 摘要:
- 为研究某高速公路深部隧道施工开挖后蠕变现象，需获取准确的蠕变本构参数并进一步推演未来围岩蠕变对隧道的影响。基于隧道某断面施工36 d实测位移数据，将BP神经网络多参数智能算法与FLAC3D有限差分软件相结合，反演构建与实际沉降值相符合的4个参数Burgers蠕变本构模型并预测隧道后续100 d拱顶沉降。研究结果表明：拱顶沉降预测与实测值较为吻合，该隧道断面位移均经过快速、缓慢和稳定变形阶段，建议在快速变形、缓慢变形阶段内加强支护措施及监控频率。研究结果可为蠕变参数确定和隧道拱顶沉降预测提供相关理论参考。
- Abstract:
- In order to study the creep phenomenon after the excavation of deep tunnel of an expressway,it is necessary to obtain accurate creep constitutive parameters and further deduce the impact of surrounding rock creep on the tunnel in the future.Based on the measured displacement data in a section of the tunnel after 36 days construction,the BP neural network multi-parameter intelligent algorithm was combined with FLAC3D finite difference software to invert and construct a four-parameter Burgers creep constitutive model which is consistent with the actual settlement value,and the vault settlement of the tunnel for the next 100 days was predicted.The results show that the predicted vault settlement is in good agreement with the measured value.The displacement of the tunnel section passes through the rapid,slow and stable deformation stages,and it is suggested that the support measures and monitoring frequency should be strengthened in the rapid and slow deformation stages.The research results can provide relevant theoretical reference for the determination of creep parameters and the prediction of tunnel vault settlement.
参考文献/References:
［1］高焱,朱永全,张智勇,等.全风化花岗岩力学性能试验及蠕变参数反演［J］.施工技术,2016,45(S2):112-116.
GAO Yan,ZHU Yongquan,ZHANG Zhiyong,et al.Mechanical properties test and creep parameter inversionof the fully weathered granite［J］.Construction Technology,2016,45(S2):112-116.
［2］张素敏,朱永全,高炎,等.全风化花岗岩流变特性试验研究［J］.地下空间与工程学报,2016,12(4):904-911.
ZHANG Sumin,ZHU Yongquan,GAO Yan,et al.Experimental investigation on rheological properties of completely weathered granite［J］.Chinese Journal of Underground Space and Engineering,2016,12(4):904-911.
［3］周瑞鹤,程桦,蔡海兵,等.三轴压缩分级卸荷条件下粉砂岩蠕变特性及蠕变模型［J］.岩石力学与工程学报,2022,41(6):1136-1147.
ZHOU Ruihe,CHENG Hua,CAI Haibing,et al.Creep characteristics and creep model of siltstone under triaxial compression and graded unloading ［J］.Chinese Journal of Rock Mechanics and Engineering,2022,41(6):1136-1147.
［4］张阳茁,杨杰,程琳,等.基于极限学习机的隧洞岩体蠕变参数反分析方法［J］.水资源与水工程学报,2017,28(3):205-210.
ZHANG Yangzhuo,YANG Jie,CHENG Lin,et al.Back analysis of rock creep parameter based on extreme learning machine ［J］.Journal of Water Resources and Water Engineering,2017,28(3):205-210.
［5］冯研,袁胜洋,徐鹏,等.成绵乐高速铁路成都黏土地基蠕变参数反演及沉降预测［J］.四川建筑科学研究,2014,40(5):148-150，159.
FENG Yan,YUAN Shengyang,XU Peng,et al.The creep parameters inversing and settlement prediction of Chengdu clay foundation in Cheng-Mian-Le high-speed railway ［J］.Sichuan Building Science,2014,40(5):148-150，159.
［6］王述红,董福瑞,朱宝强,等.山岭隧道围岩参数智能反演及稳定性分析［J］.应用基础与工程科学学报,2021,29(5):1171-1185.
WANG Shuhong,DONG Furui,ZHU Baoqiang,et al.Intelligent inversion and stability analysis of surrounding rock parameters in mountain tunnel ［J］.Journal of Basic Science and Engineering,2021,29(5):1171-1185.
［7］CHEN C,LI T,MA C,et al.Hoek-Brown failure criterion-based creep constitutive model and BP neural network parameter inversion for soft surrounding rock mass of tunnels［J］.Applied Sciences,2021,11(21):10033.
［8］WANG J,SUN J,KOU H,et al.Multiparameter inversion early warning system of tunnel stress-seepage coupling based on IA-BP algorithm［J］.Advances in Civil Engineering,2021,2021：e1566693.
［9］LI C,HOU S,LIU Y,et al.Analysis on the crown convergence deformation of surrounding rock for double-shield TBM tunnel based on advance borehole monitoring and inversion analysis［J］.Tunnelling and Underground Space Technology,2020,103:103513.
［10］ZHOU X,SUN X,LI Y,et al.Creep parameter inversion for high CFRDs based on improved BP neural network response surface method［J］.Soft Computing,2022:1-15.
［11］SONG Z P,YANG T T,JIANG A N,et al.Experimental investigation and numerical simulation of surrounding rock creep for deep mining tunnels［J］.Journal of the Southern African Institute of Mining and Metallurgy,2016,116(12):1181-1188.
［12］中华人民共和国交通运输部.公路隧道设计规范 第一册 土建工程：JTG 3370.1—2018［S］.北京:人民交通出版社,2019.
［13］中华人民共和国交通运输部.公路工程地质勘察规范：JTG C20—2011［S］.北京:人民交通出版社,2011.
［14］王睿,漆泰岳,冯剑,等.基于遗传算法的BP神经网络隧道施工参数正反演分析与应用［J］.铁道学报,2016,38(4):98-104.
WANG Rui,QI Taiyue,FENG Jian,et al.Genetic algorithm based BP neural network for forward and backward analysis of tunnel construction parameters and its application ［J］.Journal of the China Railway Society,2016,38(4):98-104.
［15］王志亮,李筱艳,殷宗泽.遗传算法和改进的BP网络杂交法在岩土工程中应用［J］.地下空间,2001(3):178-182，238.
WANG Zhiliang,LI Xiaoyan,YIN Zongze.Application of Genetic-Algorithm and improved BP network hybrid method in geotechnical engineering ［J］.Chinese Journal of Underground Space and Engineering,2001(3):178-182，238.
［16］王文玉,王希良,张骞.基于关联分析和遗传算法优化BP的隧道围岩变形预测［J］.铁道标准设计,2020,64(5):126-132.
WANG Wenyu,WANG Xiliang,ZHANG Qian.Deformation prediction of tunnel surrounding rock based on correlation analysis and Genetic-Algorithm optimized BP ［J］.Railway Standard Design,2020,64(5):126-132.
［17］杨文东,张强勇,陈芳,等.基于压缩蠕变试验的流变参数理论解析反演［J］.力学学报,2012,44(3):638-642.
YANG Wendong,ZHANG Qiangyong,CHEN Fang,et al.Theoretical analysis and inversion of rheological parameters based on compression creep test ［J］.Chinese Journal of Theoretical and Applied Mechanics,2012,44(3):638-642.
［18］陈静,江权,冯夏庭,等.基于位移增量的高地应力下硐室群围岩蠕变参数的智能反分析［J］.煤炭学报,2019,44(5):1446-1455.
CHEN Jing,JIANG Quan,FENG Xiating,et al.Intelligent back analysis of rock mass creep parameters for large underground caverns under high in-situ stress based on incremental displacement ［J］.Journal of China Coal Society,2019,44(5):1446-1455.
［19］张锦,陈林,赖祖龙.改进遗传算法优化灰色神经网络隧道变形预测［J］.测绘科学,2021,46(2):55-61，77.
ZHANG Jin，CHEN Lin，LAI Zulong.Tunnel deformation prediction based on grey neural network with improved genetic algorithm ［J］.Science of Surveying and Mapping,2021,46(2):55-61，77.
［20］高亚辉,徐嘉辰,胡福祥,等.大浞河铁矿软岩巷道围岩蠕变的黏弹性参数反演［J］.金属矿山,2017(7):51-54.
Gao Yahui,Xu Jiachen,HU Fuxiang,et al.Viscoelastic parameters inversion of surrounding rock creep of soft rock roadway in Dazhuohe Iron Mine［J］.Metal Mine,2017(7):51-54.
［21］吕志涛,吴庚林,靳晓光,等.隧道膨胀性围岩蠕变特性分析及参数反演［J］.地下空间与工程学报,2016,12(6):1504-1510.
LYU Zhitao,WU Genglin,JIN Xiaoguang,et al.Analysis of creep characteristics and parameter inversion of expansive surrounding rock in tunnels［J］.Chinese Journal of Underground Space and Engineering,2016,12(6):1504-1510.
［22］唐雄俊.考虑围岩应变软化与剪胀效应的深埋隧道合理支护时机分析［J］.隧道建设(中英文),2021,41(S2):190-198.
TANG Xiongjun.Reasonable support time for deep-buried tunnel considering strain softening and shear dilation effect of surrounding rock［J］.Tunnel Construction,2021,41(S2):190-198.
［23］杨军义.围岩蠕变、温度应力和水共同作用下水工隧洞衬砌防裂分析［D］.武汉：武汉大学,2017.
相似文献/References:
备注/Memo
- 备注/Memo:
-
收稿日期： 2022-09-27
* 基金项目： 国家自然科学基金项目(52168055)；江西省自然科学基金项目（20224BAB204058）;江西省地质环境与地下空间工程研究中心开放基金项目(GEUS JXDHJJ2022-009)；江西省“双千计划”创新领军人才项目（jxsq2020101001）
作者简介： 吴波，博士，教授，主要研究方向为隧道与地下工程。
通信作者： 刘聪，博士，讲师，主要研究方向为隧道与地下工程。
