检索结果-南通市图书馆

Surrogate modeling for unsaturated infiltration via the physics and equality-constrained artificial neural networks

Journal of Rock Mechanics and Geotechnical engineering 2024年第6期16卷 2282-2295页

作者： Peng Lan Jingjing Su Sheng Zhang School of civil engineering Central South UniversityChangsha410075China discipline of civil Surveying and Environmental EngineeringPriority Research Centre for Geotechnical Science and EngineeringThe University of NewcastleCallaghanNSW2308Australia Qinghai University Qinghai810016China

Machine learning(ML)provides a new surrogate method for investigating groundwater flow dynamics in unsaturated *** pure data-driven methods(*** neural network,DNN)can provide rapid predictions,but they do require sufficient on-site data for accurate training,and lack interpretability to the physical processes within the *** this paper,we provide a physics and equalityconstrained artificial neural network(PECANN),to derive unsaturated infiltration solutions with a small amount of initial and boundary *** takes the physics-informed neural network(PINN)as a foundation,encodes the unsaturated infiltration physical laws(*** equation,RE)into the loss function,and uses the augmented Lagrangian method to constrain the learning process of the solutions of RE by adding stronger penalty for the initial and boundary *** unsaturated infiltration cases are designed to test the training performance of PECANN,***-dimensional(1D)steady-state unsaturated infiltration,1D transient-state infiltration,two-dimensional(2D)transient-state infiltration,and 1D coupled unsaturated infiltration and *** predicted results of PECANN are compared with the finite difference solutions or analytical *** results indicate that PECANN can accurately capture the variations of pressure head during the unsaturated infiltration,and present higher precision and robustness than DNN and *** is also revealed that PECANN can achieve the same accuracy as the finite difference method with fewer initial and boundary training ***,we investigate the effect of the hyperparameters of PECANN on solving RE *** provides an effective tool for simulating unsaturated infiltration.

关键词： Richards equation(RE) Unsaturated infiltration Data-driven solutions Numerical modeling Machine learning(ML)

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Application of multi-algorithm ensemble methods in high-dimensional and small-sample data of geotechnical engineering:A case study of swelling pressure of expansive soils

引用

Journal of Rock Mechanics and Geotechnical engineering 2024年第5期16卷 1896-1917页

作者： Chao Li Lei Wang Jie Li Yang Chen School of Urban Railway Transportation Shanghai University of Engineering ScienceShanghai201620China discipline of civil and Infrastructure engineering RMIT UniversityMelbourne3001Australia School of Naval Architecture and civil engineering Shanghai Jiao Tong UniversityShanghai200240China

Geotechnical engineering data are usually small-sample and high-dimensional,which brings a lot of challenges in predictive *** paper uses a typical high-dimensional and small-sample swell pressure(P_(s))dataset to explore the possibility of using multi-algorithm hybrid ensemble and dimensionality reduction methods to mitigate the uncertainty of soil parameter *** on six machine learning(ML)algorithms,the base learner pool is constructed,and four ensemble methods,Stacking(SG),Blending(BG),Voting regression(VR),and Feature weight linear stacking(FWL),are used for the multi-algorithm ***,the importance of permutation is used for feature dimensionality reduction to mitigate the impact of weakly correlated variables on predictive *** results show that the proposed methods are superior to traditional prediction models and base ML models,where FWL is more suitable for modeling with small-sample datasets,and dimensionality reduction can simplify the data structure and reduce the adverse impact of the small-sample effect,which points the way to feature selection for predictive *** on the ensemble methods,the feature importance of the five primary factors affecting P_(s) is the maximum dry density(31.145%),clay fraction(15.876%),swell percent(15.289%),plasticity index(14%),and optimum moisture content(13.69%),the influence of input parameters on P_(s) is also investigated,in line with the findings of the existing literature.

关键词： Expansive soils Swelling pressure Machine learning(ML) Multi-algorithm ensemble Sensitivity analysis

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Probabilistic back-analysis of rainfall-induced landslides for slope reliability prediction with multi-source information

引用

Journal of Rock Mechanics and Geotechnical engineering 2024年第9期16卷 3575-3594页

作者： Shui-Hua Jiang Hong-Hu Jie Jiawei Xie Jinsong Huang Chuang-Bing Zhou School of Infrastructure engineering Nanchang UniversityXuefu Road 999Nanchang330031China discipline of civil Surveying and Environmental EngineeringFaculty of Engineering and Built EnvironmentThe University of NewcastleCallaghanNSW2308Australia

Probabilistic back-analysis is an important means to infer the statistics of uncertain soil parameters,making the slope reliability assessment closer to the engineering ***,multi-source information(including test data,monitored data,field observation and slope survival records)is rarely used in current probabilistic *** the probabilistic back-analysis of spatially varying soil parameters and slope reliability prediction under rainfalls by integrating multi-source information is a challenging task since thousands of random variables and high-dimensional likelihood function are usually *** this paper,a framework by integrating a modified Bayesian Updating with Subset simulation(mBUS)method with adaptive Conditional Sampling(aCS)algorithm is established for the probabilistic back-analysis of spatially varying soil parameters and slope reliability *** this framework,the high-dimensional probabilistic back-analysis problem can be easily tackled,and the multi-source information(*** pressure heads and slope survival records)can be fully used in the back-analysis.A real Taoyuan landslide case in Taiwan,China is investigated to illustrate the effectiveness and performance of the established *** findings show that the posterior knowledge of soil parameters obtained from the established framework is in good agreement with the field ***,the updated knowledge of soil parameters can be utilized to reliably predict the occurrence probability of a landslide caused by the heavy rainfall event on September 12,2004 or forecast the potential landslides under future rainfalls in the Fuhsing District of Taoyuan City,Taiwan,China.

关键词： Rainfall-induced landslide Spatial variability Probabilistic back-analysis Slope reliability analysis Bayesian updating

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Probabilistic prediction on three-dimensional roughness of discontinuity based on two-dimensional traces under rock tunnel excavation based on Bayesian theory

引用

Underground Space 2024年第1期14卷 338-356页

作者： Qi Zhang Yuechao Pei Xiaojun Wang Xiaojun Li Yixin Shen School of civil engineering Southeast UniversityNanjing 211189China Department of Geotechnical engineering College of Civil EngineeringTongji UniversityShanghai 200092China

Three-dimensional(3D)roughness of discontinuity affects the quality of the rock mass,but 3D roughness is hard to be measured due to that the discontinuity is invisible in the ***-dimensional(2D)roughness can be calculated from the visible traces,but it is difficult to obtain enough quantity of the traces to directly derive 3D roughness during the tunnel *** this study,a new method using Bayesian theory is proposed to derive 3D roughness from the low quantity of 2D roughness *** more accurately calculating 3D roughness,a new regression formula of 2D roughness is established firstly based on wavelet *** new JRC3D prediction model based on Bayesian theory is then developed,and Markov chain Monte Carlo(MCMC)sampling is adopted to process JRC3D prediction *** discontinuity sample collected from the literature is used to verify the proposed *** groups with the sampling size of 2,3,4,and 5 of each group are randomly sampled from JRC2D values of 170 profiles of the discontinuity,*** research results indicate that 100%,90%,85%,and 60%predicting JRC3D of the sample groups corresponding to the sampling size of 5,4,3,and 2 fall into the tolerance interval[JRC_(true)–1,JRC_(true)+1].It is validated that the sampling size of 5 is enough for predicting *** sensitivities of sampling results are then analyzed on the influencing factors,which are the correlation function,the prior distribution,and the prior *** discontinuity across the excavation face at ZK78+67.5 of Daxiagu tunnel is taken as the tunnel engineering application,and the results further verify that the predicting JRC3D with the sampling size of 5 is generally in good agreement with JRC3D true values.

关键词： Rock discontinuity Joint roughness coefficient Tunnel excavation Bayesian theory Markov chain Monte Carlo sampling

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Application of supervised machine learning to predict the enhanced gas recovery by CO_(2) injection in shale gas reservoirs

引用

Petroleum 2024年第1期10卷 124-134页

作者： Moataz Mansi Mohamed Almobarak Jamiu Ekundayo Christopher Lagat Quan Xie discipline of Petroleum engineering WA School of Mines:MineralsEnergy and Chemical EngineeringCurtin UniversityWestern AustraliaAustralia

The technique of Enhanced Gas Recovery by CO_(2) injection(CO_(2)-EGR)into shale reservoirs has brought increasing attention in the recent ***_(2)-EGR is a complex geophysical process that is controlled by several parameters of shale properties and engineering ***,more challenges arise when simulating and predicting CO_(2)/CH4 displacement within the complex pore systems of ***,the petroleum industry is in need of developing a cost-effective tool/approach to evaluate the potential of applying CO_(2) injection to shale *** recent years,machine learning applications have gained enormous interest due to their high-speed performance in handling complex data and efficiently solving practical ***,this work proposes a solution by developing a supervised machine learning(ML)based model to preliminary evaluate CO_(2)-EGR *** used for this work was drawn across a wide range of simulation sensitivity studies and experimental *** this work,linear regression and artificial neural networks(ANNs)implementations were considered for predicting the incremental enhanced *** on the model performance in training and validation sets,our accuracy comparison showed that(ANNs)algorithms gave 15%higher accuracy in predicting the enhanced CH4 compared to the linear regression *** ensure the model is more generalizable,the size of hidden layers of ANNs was adjusted to improve the generalization ability of ANNs *** ANNs models presented,ANNs of 100 hidden layer size gave the best predictive performance with the coefficient of determination(R2)of 0.78 compared to the linear regression model with R2 of *** developed MLbased model presents a powerful,reliable and cost-effective tool which can accurately predict the incremental enhanced CH4 by CO_(2) injection in shale gas reservoirs.

关键词： Artificial intelligence Supervised Machine Learning Shale Gas Enhanced Shale Gas Recovery CO_(2)Injection CO_(2)sequestration

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Experimental and numerical study on dynamic mechanical behaviors of shale under true triaxial compression at high strain rate

引用

International Journal of Mining Science and Technology 2024年第2期34卷 149-165页

作者： Xiaoping Zhou Linyuan Han Jing Bi Yundong Shou School of civil engineering Wuhan UniversityWuhan 430072China College of civil engineering Guizhou UniversityGuiyang 550025China

High-energy gas fracturing of shale is a novel,high efficacy and eco-friendly mining technique,which is a typical dynamic perturbing *** effectively extract shale gas,it is important to understand the dynamic mechanical properties of *** experiments on shale subjected to true triaxial compression at different strain rates are first conducted in this *** dynamic stress-strain curves,peak strain,peak stress and failure modes of shale are *** results of the study indicate that the intermediate principal stress and the minor principal stress have the significant influence on the dynamic mechanical behaviors,although this effect decreases as the strain rate *** characteristics of compression-shear failure primarily occur in shale subjected to triaxial compression at high strain rates,which distinguishes it from the fragmentation characteristics observed in shale under dynamic uniaxial ***,a numerical three-dimensional Split Hopkinson Pressure Bar(3D-SHPB),which is established by coupling PFC3D and FLAC3D methods,is validated to replicate the laboratory characteristics of *** dynamic mechanical characteristics of shale subjected to different confining stresses are systematically investigated by the coupling PFC3D and FLAC3D *** numerical results are in good agreement with the experimental data.

关键词： Dynamic behaviors True triaxial compression High strain rates Dynamic failure mechanism PFC3D-FLAC3D coupled method

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Prediction of bearing capacity of pile foundation using deep learning approaches

引用

Frontiers of Structural and civil engineering 2024年第6期18卷 870-886页

作者： Manish KUMAR Divesh Ranjan KUMAR Jitendra KHATTI Pijush SAMUI Kamaldeep Singh GROVER Department of civil engineering SRM Institute of Science and Technology Tiruchirappalli CampusTrichy 621105India Department of civil engineering National Institute of Technology PatnaBihar 800005India Department of civil engineering Faculty of EngineeringThammasat School of EngineeringThammasat UniversityBangkok10200Thailand Department of civil engineering Rajasthan Technical UniversityKota 324010India

The accurate prediction of bearing capacity is crucial in ensuring the structural integrity and safety of pile *** research compares the Deep Neural Networks(DNN),Convolutional Neural Networks(CNN),Recurrent Neural Networks(RNN),Long Short-Term Memory(LSTM),and Bidirectional LSTM(BiLSTM)algorithms utilizing a data set of 257 dynamic pile load tests for the first ***,this research illustrates the multicollinearity effect on DNN,CNN,RNN,LSTM,and BiLSTM models’performance and accuracy for the first time.A comprehensive comparative analysis is conducted,employing various statistical performance parameters,rank analysis,and error matrix to evaluate the performance of these *** performance is further validated using external validation,and visual interpretation is provided using the regression error characteristics(REC)curve and Taylor *** from the comparative analysis reveal that the DNN(Coefficient of determination(R^(2))_(training(TR))=0.97,root mean squared error(RMSE)_(TR)=0.0413;R^(2)_(testing(TS))=0.9,RMSE_(TS)=0.08)followed by BiLSTM(R^(2)_(TR)=0.91,RMSE_(TR)=0.782;R^(2)_(TS)=0.89,RMSE_(TS)=0.0862)model demonstrates the highest performance *** is noted that the BiLSTM model is better than LSTM because the BiLSTM model,which increases the amount of information for the network,is a sequence processing model made up of two LSTMs,one of which takes the input in a forward manner,and the other in a backward *** prediction of pile-bearing capacity is strongly influenced by ram weight(having a considerable multicollinearity level),and the effect of the considerable multicollinearity level has been determined for the model based on the recurrent neural network *** this study,the recurrent neural network model has the least performance and accuracy in predicting the pile-bearing capacity.

关键词： deep learning algorithms high-strain dynamic pile test bearing capacity of the pile

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

An ultra-thin bolt tension sensor and online monitoring system:For application in hydropower plant unit

引用

Frontiers of Structural and civil engineering 2024年第9期18卷 1388-1400页

作者： Shaoquan ZHANG Yanke TAN Hanbin GE Qilin ZHANG Department of civil engineering Meijo UniversityNagoya 4688502Japan College of civil engineering Tongji UniversityShanghai 200092China

The condition of bolted connections significantly affects the structural ***,conventional bolt tension sensors fail to provide precise measurements due to their bulky size or inadequate *** study employs the piezoresistive effect of crystalline silicon material to fabricate an ultrathin *** sensor exhibits a linear relationship between pressure and voltage,an exceptional stability at varying temperatures,and a superior resistance to corrosion,making it adaptable and user-friendly for applications of high-strength bolt tension monitoring.A monitoring system,incorporating the proposed sensor,has also been *** system provides real-time display of bolt tension and enables the assessment of sensor and structural conditions,including bolt loosening or component *** efficacy of the proposed sensor and monitoring system was validated through a project carried out at the Xiluodu Hydropower *** to the results,the sensor and online monitoring system effectively gauged and proficiently conveyed and stored bolt tension *** addition,correlations were created between bolt tensions and essential unit parameters,such as water head,active power,and pressures at vital points,facilitating anomaly detection and early warning.

关键词： ultra-thin sensor high-strength bolt tension online monitoring system anomaly alarm hydro-generator units

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Dynamic Response of A Group of Cylindrical Storage Tanks with Baffles Considering the Effect of Soil Foundation

引用

China Ocean engineering 2024年第1期38卷 129-143页

作者： SUN Ying WANG Jia-dong HUO Rui-li ZHOU Ding GU Zhen-yuan QIAN Wang-ping School of Transportation and civil engineering Nantong UniversityNantong 226019China Faculty of civil engineering and Mechanics Jiangsu UniversityZhenjiang 212013China College of civil engineering Nanjing Tech UniversityNanjing 211816China

The sloshing in a group of rigid cylindrical tanks with baffles and on soil foundation under horizontal excitation is studied *** solutions for the velocity potential are derived out by the liquid subdomain *** models with mass-spring oscillators are established to replace continuous *** with the least square technique,Chebyshev polynomials are employed to fit horizontal,rocking and horizontal-rocking coupling impedances of soil,respectively.A lumped parameter model for impedance is presented to describe the effects of soil on tank structures.A mechanical model for the soil-foundation-tank-liquid-baffle system with small amount of calculation and high accuracy is proposed using the substructure *** analytical solutions are in comparison with data from reported literature and numerical codes to validate the effectiveness and correctness of the *** dynamic properties and seismic responses of the soil-tank system are given for the baffle number,size and location as well as soil parameter.

关键词： cylindrical tanks multiple annular baffles equivalent analytical model soil−structure interaction subdomain method dynamic response

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Dynamic prediction of over-excavation gap due to posture adjustment of shield machine in soft soil

引用

Underground Space 2024年第3期16卷 44-58页

作者： Wenyu Yang Junjie Zheng Rongjun Zhang Sijie Liu Wengang Zhang School of civil and Hydraulic engineering Huazhong University of Science and TechnologyWuhan 430074China School of civil engineering Wuhan UniversityWuhan 430072China School of civil engineering Chongqing UniversityChongqing 400045China

The probability analysis of ground deformation is becoming a trend to estimate and control the risk brought by shield *** gap parameter is regarded as an effective tool to estimate the ground loss of tunnelling in soft *** specifically,x,which is a gap parameter component defined as the over(or insufficient)excavation due to the change in the posture of the shield machine,may contribute more to the uncertainty of the ground ***,the existing uncertainty characterization methods for x have several limitations and cannot explain the uncertain correlations between the relevant *** these lines,to better characterize the uncertainty of x,the multivariate probability distribution was developed in this work and a dynamic prediction was proposed for *** attain this goal,1523 rings of the field data coming from the shield tunnel between Longqing Road and Baiyun Road in Kunming Metro Line 5 were utilized and 44 parameters including the construction,stratigraphic,and posture parameters were collected to form the *** to the variance filter method,the mutual information method,and the value of the correlation coefficients,the original 44 parameters were reduced to 10 main parameters,which were unit weight,the stoke of the jacks(A,B,C,and D groups),the pressure of the pushing jacks(A,C groups),the chamber pressure,the rotation speed,and the total *** multivariate probability distribution was constructed based on the Johnson system of ***,the distribution was satisfactorily verified in explaining the pairwise correlation between x and other parameters through 2 million simulation *** last,the distribution was used as a prior distribution to update the marginal distribution of x with any group of the relevant parameters *** performance of the dynamic prediction was further validated by the field data of 3 shield tunnel cases.

关键词： Shield tunnel Ground loss Gap parameter Multivariate probability distribution Bayesian updating Dynamic prediction

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：