|本期目录/Table of Contents|

[1]吕俊超,潘建平,俞社鑫.基于循环神经网络的缓坡场地液化侧移预测*[J].中国安全生产科学技术,2021,17(8):18-23.[doi:10.11731/j.issn.1673-193x.2021.08.003]
　LYU Junchao,PAN Jianping,YU Shexin.Prediction of liquefaction-induced lateral displacement in gentle slope field based on recurrent neural network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(8):18-23.[doi:10.11731/j.issn.1673-193x.2021.08.003]
点击复制

基于循环神经网络的缓坡场地液化侧移预测*
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
17
期数:
2021年8期
页码:
18-23
栏目:
学术论著
出版日期:
2021-08-31

文章信息/Info

Title:
Prediction of liquefaction-induced lateral displacement in gentle slope field based on recurrent neural network
文章编号:
1673-193X(2021)-08-0018-06
作者:
吕俊超; 潘建平; 俞社鑫
(1.江西理工大学 土木与测绘工程学院，江西 赣州 341000；
2.江西省环境岩土与工程灾害控制重点实验室，江西 赣州 341000)
Author(s):
LYU Junchao; PAN Jianping; YU Shexin
(1.School of Architectural and Surveying & Mapping Engineering,Jiangxi University of Science and Technology,Ganzhou Jiangxi 341000,China;
2.Key Laboratory of Environmental Geotechnical and Engineering Disaster Control of Jiangxi Province,Ganzhou Jiangxi 341000,China)
关键词:
灾害学; 循环神经网络; 侧移预测; 缓坡场地; Rectified Adam算法
Keywords:
science of disaster;  recurrent neural network;  prediction of lateral displacement;  gentle slope field;  Rectified Adam algorithm
分类号:
X915.5；X43
DOI:
10.11731/j.issn.1673-193x.2021.08.003
文献标志码:
A
摘要:
为预测缓坡场地地震液化侧向位移，基于改进自适应算法（Rectified Adam）和循环神经网络模型（RNN）,提出液化侧移预测模型RA-RNN,通过对侧移数据进行样本学习，并利用改进自适应算法优化循环神经网络结构,验证RA-RNN模型可靠性，并与多元线性回归法（MLR）计算结果进行对比。结果表明:RA-RNN模型计算得到侧移一般为实测位移的0.7~1.3倍，训练结果R2,RMSE,MAE分别为0.977，0.375，0.141；土耳其科喀艾里RA-RNN模型预测结果RMSE和MAE为MLR模型的1/26，1/830;中国台湾集集镇RA-RNN模型预测结果RMSE和MAE为MLR模型的1/18,1/350,RA-RNN模型预测结果较优，预测精度及泛化能力得到很大提升。
Abstract:
In order to predict the seismic liquefaction-induced lateral displacement of gentle slope field,a prediction model of liquefaction-induced lateral displacement (RA-RNN model) based on the improved adaptive algorithm (Rectified Adam) and the recurrent neural network (RNN) model was proposed.Through the sample learning of the lateral displacement data,and using the improved adaptive algorithm to optimize the structure of RNN,the seismic liquefaction-induced lateral displacement data from Kokaeli,Turkey and Chichi,Taiwan were used to verify the reliability of RA-RNN model,and the results were compared with those of the multiple linear regression (MLR) method.It showed that the lateral displacement calculated by the RA-RNN model was mostly between 0.7 and 1.3 times of the measured displacement,and the R2,RMSE and MAE of the training results were 0.977,0.375 and 0.141,respectively.RMSE and MAE of RA-RNN model in Kocaeli,Turkey are 1/26,1/830 of MLR model,RMSE and MAE of RA-RNN model in Market town,Taiwan,China are 1/18,1/350 of MLR model.The prediction effect was good,and the prediction accuracy and generalization ability were greatly improved.

参考文献/References:

［1］NEWMARK N M.Effects of earthquakes on dams and embankments ［J］.Geology Technique,1965,15(2):139-160.
［2］林大富.缓倾斜场地液化侧移简化计算及影响因素研究［D］.成都：西南交通大学,2019.
［3］GU W H,MORGENSTERN N R,ROBERTSON P K.Progressive failure of lower San Fernando dam ［J］.Journal of Geotechnical Engineering,1993,119(2):333-349.
［4］YUAN H,YANG S H,ANDRUS R D,et al.Lique faction-induced ground failure:a study of the Chi-earthquake cases ［J］.Engineering Geology,2004,71(1-2):141-155.
［5］BARTLETT S F,YOUD T L.Empirical analysis of horizontal ground displacement generated by liql1efaction-induced lateral spread ［R］. National Center for Earthquake Engineer Research Technical Report NCEER-92-0021,1992,114.
［6］YOUD T L,HANSEN C M,BARTLETT S F.Revised multilinear regression equations for prediction of lateral spread displacement ［J］.Journal of Geotechnical and Geo-environmental Engineering,2002,128(12):1007-1017.
［7］李程程,李兆焱,袁晓铭.基于多元自回归样条的液化侧移灾害评估模型［J］.地震工程学报,2019,41(5):1355-1360. LI Chengcheng,LI Zhaoyan,YUAN Xiaoming.An estimation of liquefaction-induced lateral spread based on a multivariate adaptive regression spline ［J］.China Earthquake Engineering Journal,2019,41(5):1355-1360.
［8］AVVAL Y J,DERAKHSHANI A.New formulas for predicting liquefaction-induced lateral spreading:model tree approach ［J］.Bulletin of Engineering Geology and the Environment,2019,78(5):3649-3661.
［9］张政,胡记磊,刘华北.基于贝叶斯网络的缓坡场地震液化侧移评估-以台湾集集地震为例［J］.自然灾害学报,2018,27(6):127-132. ZHANG Zheng,HU Jilei,LIU Huabei.Assessment of seismic liquefaction-induced lateral spreading in gentle slope field based on Bayesian network:a case of the chi-earthquake,Taiwan.［J］.Journal of Natural Disasters,2018,27(6):127-132.
［10］JAVADI A A,REZANIA M,NEZHAD M M.Evaluation of liquefaction induced lateral displacements using genetic programming ［J］.Computers and Geotechnics,2006,33(4-5):222-233.
［11］KAYA Z.Predicting liquefaction-induced lateral spreading by using neural network and neuro-fuzzy techniques ［J］.International Journal of Geomechanics,2016,16(4):04015095.
［12］FARROKHI F,FIROOZFAR A,MAGHSOUDI M S.Evaluation of liquefaction-induced lateral displacement using a GMDH-type neural network optimized by genetic algorithm ［J］.Arabian Journal of Geosciences,2020,13(1):4.
［13］LIU L,JIANG H,HE P,et al.On the variance of the adaptive learning rate and beyond ［J］.Arxivcs Machine Learning,2019,8（11）：21-24.
［14］BI C,FU B,CHEN J,et al.Machine learning based fast multi-layer liquefaction disaster assessment ［J］.World Wide Web,2019,22(5):1935-1950.
［15］MOSALLANEZHAD M,MOAYEDI H.Developing hybrid artificial neural network model for predicting uplift resistance of screw piles ［J］.Arabian Journal of Geosciences,2017,10(22):479.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期： 2021-03-05
* 基金项目： 江西省科技支撑计划项目(20133BBG70103)
作者简介： 吕俊超，硕士研究生，主要研究方向为岩土动力学。
通信作者： 潘建平，博士，教授，主要研究方向为岩土工程风险评估与灾害防治。
更新日期/Last Update: 2021-09-08