[1]胡圣祥,王世峻.基坑施工引起周边管线沉降的一个深度学习模型[J].华南地震,2023,(02):165-173.[doi:10.13512/j.hndz.2023.02.19]
 HU Shengxiang,WANG Shijun.A Deep Learning Model of Surrounding Pipeline Settlement Caused by Foundation Pit Construction[J].,2023,(02):165-173.[doi:10.13512/j.hndz.2023.02.19]
点击复制

基坑施工引起周边管线沉降的一个深度学习模型()
分享到:

华南地震[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2023年02期
页码:
165-173
栏目:
土木工程防震减灾
出版日期:
2023-06-20

文章信息/Info

Title:
A Deep Learning Model of Surrounding Pipeline Settlement Caused by Foundation Pit Construction
文章编号:
1001-8662(2023)02-0165-09
作者:
胡圣祥王世峻
国网上海市电力公司经济技术研究院,上海 200233
Author(s):
HU ShengxiangWANG Shijun
Institute of Economics and Technology,Shanghai Electric Power Company of State Grid, Shanghai 200233, China
关键词:
基坑施工地下管线沉降预测卷积神经网络长短期记忆神经网络
Keywords:
Foundation pit construction Underground pipeline settlement Prediction Convolutional neural networkLong-short-term memory based neural network
分类号:
U231.3
DOI:
10.13512/j.hndz.2023.02.19
摘要:
基坑施工会引起周围地下管线沉降是一个动态过程,传统地下管线沉降预测方法不能反映这一动态过程、从而难以真正实现信息化施工。根据某基坑施工过程中周边地下管线沉降的监测数据,使用卷积神经网络(CNN)对监测数据进行特征提取,使用基于长短期记忆(LSTM)的神经网络对沉降进行分析,建立了基于深度学习网络的地下管线沉降预测模型,探讨了超参数和建筑物类型对预测准确度的影响。结果表明,利用所建CNN–LSTM联合人工神经网络,预测值与实际监测值比较接近;网络设置时,初始学习率、隐藏单元数、最大回代轮次可分别取为0.006、240、60;网络预测结果好坏与管线是否是刚性无关,预测值与实测值吻合的高低顺序是电力管线(柔性)、上水管线(刚性)、信息管线(柔性)、电信管线(柔性)。研究成果对基坑工程安全施工具有一定的参考价值。
Abstract:
The settlement of surrounding underground pipelines caused by foundation pit construction is a dynamic process. The traditional prediction method of underground pipeline settlement cannot reflect this dynamic process, so it is difficult to truly realize information construction. Based on the monitoring data of the settlement of the surrounding underground pipeline during the foundation pit construction,the convolutional neural network(CNN) is used to extract the feature of the monitoring data , and the neural network based on long-short-term memory (LSTM)is used to analyze the settlement. The prediction model of underground pipeline settlement based on deep learning network is established, and the influence of hyperparameters and building types on the prediction accuracy is discussed. The results show that the predicted value and the monitoring value are relatively coincident by the using the CNN-LSTM combined with artificial neural network. The initial learning rate,number of hidden units, and the maximum number of iterations can be set as 0.006, 240 and 60, respectively in the network design. The prediction results of the network are independent of whether the pipeline is rigid or not,and the order of the agreement between the predicted value and the measured value is power pipeline(flexible), water supply pipeline(rigid), information pipeline(flexible), telecommunication pipeline(flexible) . The results have a certain reference value for the safe construction of foundation pit engineering

参考文献/References:

[1]姜峥.基坑开挖引起邻近管线变形的理论解析[J].地下空间与工程学报,2014,10(2):362-368.[2]刘雪珠,顾蒙娜,吴祥祖,等.地铁深基坑施工对临近地下管线影响的监测分析[J].工程勘察,2014,(S1):462-467.[3]王立峰,陈巧红,冯利坡.地铁车站基坑开挖的管线变形研究[J].科技通报,2019,35(10):166-170.[4]居尚威,李雄威.地铁深基坑施工扰动下邻近管线影响区域划分及迁改保护措施[J].常州工学院学报,2022,35(2):7-14.[5]施有志,华建兵,连宇新,等.地铁深基坑施工扰动下邻近管线安全评价及保护措施[J]. 工程地质学报,2018,26( 4):1043-1053.[6]王云琪,徐鹏举.深基坑开挖对周围地下管线影响研究[J].低温建筑技术,2015(2):79-81.[7]葛照国.长江漫滩地区基坑施工对周边地表沉降及地下管线影响的现场试验研究[J].现代隧道技术,2014,51(5):205-209.[8]杜金龙,杨敏. 深基坑开挖对邻近地埋管线影响分析[J].岩石力学与工程学报,2009,28(S1):3015-3020.[9] Guo P. Numerical model of pipe-soil interaction under oblique loading[J]. Journal of Geotechnical and Geoenviron-mental Engineering,2005,131(2):260-268.[10]王英楠,王江锋.郑州某地铁站基坑开挖对临近管线的影响分析[J].水利与建筑工程学报,2021,19(5):129-133.[11]杨本亮.地铁车站基坑施工对周边管线的影响[J].水科学与工程技术,2022(3):59-63.[12]施有志,葛修润,李秀芳,等.地铁深基坑施工对周边管线影响数值分析[J].中山大学学报(自然科学版),2017, 56(6):83-93.[13]朱琴君,庞志辉,何伟,等.基坑工程对邻近天然气管道的影响及管道防护[J].煤气与热力,2020,40(6):38-42.[14]李洛宾,龚晓南,甘晓露,等.基于循环神经网络的盾构隧道引发地面最大沉降预测[J].土木工程学报,2020,53 (S1):13-20.[15] Zhang P,Wu H N,Chen R P,et al. Prediction of subsidence during TBM operation in mixed-face ground conditions from realtime monitoring data [J]. Applied Sciences-Basel, 2021,11(24):12130.[16] Lee H K,Song M K,Lee S S. Times-series data augmen-tation and deep learning for construction equipment activity recognition [J]. Advanced Engineering Informatics,2019 (42):100944.[17] Cao Y,Zhou X,Yan K. Deep learning neural network model for tunnel ground surface settlement prediction based on sensor data [J]. Mathematical Problems in Engineering, 2021(1):1-14.[18]杨俊超.基于大数据分析与挖掘的铁路沉降灾害预警模型研究[D].成都:电子科技大学,2021.[19]洪宇超,钱建固,叶源新,等.基于时空关联特征的CNN-LSTM模型在基坑工程变形预测中的应用[J].岩土工程学报,2021,43(S2):108-111.[20]赵华菁,张名扬,刘维,等.基于神经网络算法的深基坑地连墙变形动态预测[J].地下空间与工程学报,2021,17 (S1):321-327.[21]谭儒蛟,徐添华,徐文杰,等.基于神经网络的大型深基坑工程土体参数反演[J].水力发电学报,2015,34(7):109-117.

备注/Memo

备注/Memo:
收稿日期:2022-10-15基金项目:国家自然科学基金项目(51678352)作者简介:胡圣祥(1986-),男,高级工程师,主要从事电力工程规划、设计、评审相关工作。E-mail:sxhu2009@163.com
更新日期/Last Update: 2023-06-15