检索结果-南通市图书馆

Machine learning based models for predicting compressive strength of geopolymer concrete

Frontiers of Structural and Civil Engineering 2024年第7期18卷 1028-1049页

作者： Quang-Huy LE Duy-Hung NGUYEN Thanh SANG-TO Samir KHATIR hoang LE-minh Amir H.GANDOMI Thanh CUONG-LE Center for Engineering Application and Technology Solutions Ho Chi Minh City Open UniversityHo Chi Minh 700000Vietnam institute of Civil Engineering Ho Chi Minh City University of TransportHo Chi Minh 700000Vietnam Faculty of Engineering&Information Technology University of Technology SydneyUltimoNSW 2007Australia

Recently,great attention has been paid to geopolymer concrete due to its advantageous mechanical and environmentally friendly *** effort has been made in experimental studies to advance the understanding of geopolymer concrete,in which compressive strength is one of the most important *** facilitate engineering work on the material,an efficient predicting model is *** this study,three machine learning(ML)-based models,namely deep neural network(DNN),K-nearest neighbors(KNN),and support vector machines(SVM),are developed for forecasting the compressive strength of the geopolymer concrete.A total of 375 experimental samples are collected from the literature to build a database for the development of the predicting models.A careful procedure for data preprocessing is implemented,by which outliers are examined and removed from the database and input variables are standardized before feeding to the fitting *** standard K-fold cross-validation approach is applied for evaluating the performance of the models so that overfitting status is well managed,thus the generalizability of the models is *** effectiveness of the models is assessed via statistical metrics including root mean squared error(RMSE),mean absolute error(MAE),correlation coefficient(R),and the recently proposed performance index(PI).The basic mean square error(MSE)is used as the loss function to be minimized during the model fitting *** three ML-based models are successfully developed for estimating the compressive strength,for which good correlations between the predicted and the true values are obtained for DNN,KNN,and *** numerical results suggest that the DNN model generally outperforms the other two models.

关键词： geopolymer concrete compressive strength prediction machine-learning based model deep neural network K-nearest neighbor support vector machines

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 efficient improved Gradient Boosting for strain prediction in Near-Surface Mounted fiber-reinforced polymer strengthened reinforced concrete beam

引用

Frontiers of Structural and Civil Engineering 2024年第8期18卷 1148-1168页

作者： Abdelwahhab KHATIR Roberto CAPOZUCCA Samir KHATIR Erica MAGAGNINI Brahim BENAISSA Thanh CUONG-LE Structural Section DICEA Polytechnic University of MarcheAncona 60131Italy Centre for Engineering Application&Technology Solutions Ho Chi Minh City Open UniversityHo Chi Minh City 70000Vietnam Design Engineering Laboratory Toyota Technological InstituteNagoya 468-8511Japan

The Near-Surface Mounted(NSM)strengthening technique has emerged as a promising alternative to traditional strengthening methods in recent *** the past two decades,researchers have extensively studied its potential,advantages,and applications,as well as related parameters,aiming at optimization of construction ***,there is still a need to explore further,both from a static perspective,which involves accounting for the nonconservation of the contact section resulting from the bond-slip effect between fiber-reinforced polymer(FRP)rods and resin and is typically neglected by existing analytical models,as well as from a dynamic standpoint,which involves studying the trends of vibration frequencies to understand the effects of various forms of damage and the efficiency of *** address this gap in knowledge,this research involves static and dynamic tests on simply supported reinforced concrete(RC)beams using rods of NSM carbon fiber reinforced polymer(CFRP)and glass fiber reinforced polymer(GFRP).The main objective is to examine the effects of various strengthening *** research conducts bending tests with loading cycles until failure,and it helps to define the behavior of beam specimens under various damage degrees,including concrete *** analysis by free vibration testing enables tracking of the effectiveness of the reinforcement at various damage levels at each stage of the loading *** addition,application of Particle Swarm Optimization(PSO)and Genetic Algorithm(GA)is proposed to optimize Gradient Boosting(GB)training performance for concrete strain prediction in NSM-FRP *** GB using Particle Swarm Optimization(GBPSO)and GB using Genetic Algorithm(GBGA)systems were trained using an experimental data set,where the input data was a static applied load and the output data was the consequent *** models of GBPSO and GBGA have been shown to provide highly accurate results for predicting *** model

关键词： NSM technique fiber-reinforced polymer rods static and dynamic analysis GB PSO GA finite element 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

Relationship between land use and user’s behavior along the street:A case study of Da Nang city,Viet Nam

引用

Frontiers of Architectural Research 2024年第1期13卷 144-163页

作者： Duy Thinh Do Duy Thao Do Faculty of Civil Engineering Ho Chi Minh City University of Technology and Education(HCMUTE)Ho Chi Minh City 71307Viet Nam School of Computing Korea Advanced Institute of Science and TechnologyDaejeon 34141Republic of Korea

Human activities on street spaces are affected by both physical and non-physical settings on *** two aspects are primarily impacted by land use which results in the uneven distribution of different activities on *** research investigates land use patterns and their characteristics in association to user’s *** using mixed qualitative and quantitative research methods,e.g.,place-centered behavioral map,observation,visual encounter surveys,machine learning,the relationship between user’s behavior and land use characteristics along the street is *** user behaviors along both types of streets were classified into six main categories,with 26 *** observation results show that the residential use of land along the street was transformed into the commercial use for various types of shophouses based on the resident’s *** is a great correlation between land use and user’s *** findings give support to authorities to manage urban streets and develop a sustainable policy for improving street ***,this research contributes useful information to urban designers and planners in creating a successful street space that is appropriate for the Vietnam Community.

关键词： Land use pattern User’s behavior Da Nang Street space Data mining

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

A deep neural network based surrogate model for damage identification in full-scale structures with incomplete noisy measurements

引用

Frontiers of Structural and Civil Engineering 2024年第3期18卷 393-410页

作者： Tram BUI-NGOC Duy-Khuong LY Tam T TRUONG Chanachai ThoNGChoM T.NGUYEN-ThoI Laboratory for Computational Mechanics Institute for Computational Science and Artificial IntelligenceVan Lang UniversityHo Chi Minh City 70000Vietnam Faculty of Mechanical-Electrical and Computer Engineering School of TechnologyVan Lang UniversityHo Chi Minh City 70000Vietnam Faculty of Civil Engineering School of TechnologyVan Lang UniversityHo Chi Minh City 70000Vietnam Department of Computer Science Aarhus UniversityAarhus 8000Denmark Thammasat University research unit in structural and foundation engineering Department of Civil EngineeringThammasat UniversityPathumthani 12120Thailand Laboratory for Applied and Industrial Mathematics Institute for Computational Science and Artificial IntelligenceVan Lang UniversityHo Chi Minh City 70000Vietnam Thammasat School of Engineering Thammasat UniversityPathumthani 12120Thailand

The paper introduces a novel approach for detecting structural damage in full-scale structures using surrogate models generated from incomplete modal data and deep neural networks(DNNs).A significant challenge in this field is the limited availability of measurement data for full-scale structures,which is addressed in this paper by generating data sets using a reduced finite element(FE)model constructed by SAP2000 software and the MATLAB programming *** surrogate models are trained using response data obtained from the monitored structure through a limited number of measurement *** proposed approach involves training a single surrogate model that can quickly predict the location and severity of damage for all potential *** achieve the most generalized surrogate model,the study explores different types of layers and hyperparameters of the training algorithm and employs state-of-the-art techniques to avoid overfitting and to accelerate the training *** approach’s effectiveness,efficiency,and applicability are demonstrated by two numerical *** study also verifies the robustness of the proposed approach on data sets with sparse and noisy measured ***,the proposed approach is a promising alternative to traditional approaches that rely on FE model updating and optimization algorithms,which can be computationally *** approach also shows potential for broader applications in structural damage detection.

关键词： vibration-based damage detection deep neural network full-scale structures finite element model updating noisy incomplete modal data

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

Investigation of crack segmentation and fast evaluation of crack propagation, based on deep learning

引用

Frontiers of Structural and Civil Engineering 2024年第4期18卷 516-535页

作者： Than V.TRAN H.NGUYEN-XUAN Xiaoying ZHUANG institute of Photonics Leibniz University HannoverHannover 30167Germany CIRTech institute HUTECH UniversityHo Chi Minh City 700000Vietnam College of Civil Engineering Tongji UniversityShanghai 200092China

Identifying crack and predicting crack propagation are critical processes for the risk assessment of engineering *** traditional approaches to crack modeling are faced with issues of high computational costs and excessive computing *** address this issue,we explore the potential of deep learning(DL)to increase the efficiency of crack detection and forecasting crack ***,there is no single algorithm that can fit all data sets well or can apply in all cases since specific tasks *** the paper,we present DL models for identifying cracks,especially on concrete surface images,and for predicting crack ***,SegNet and U-Net networks are used to identify concrete *** gradient descent(SGD)and adaptive moment estimation(Adam)algorithms are applied to minimize loss function during ***,time series algorithms including gated recurrent unit(GRU)and long short-term memory(LSTM)are used to predict crack *** experimental findings indicate that the U-Net is more robust and efficient than the SegNet for identifying crack segmentation and achieves the most outstanding *** evaluation of crack propagation,GRU and LSTM are used as DL models and results show good agreement with the experimental data.

关键词： deep learning crack segmentation crack propagation encoder−decoder recurrent neural network

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

Traveling wave solutions of the nonlinear Gilson-Pickering equation in crystal lattice theory

引用

Journal of Ocean Engineering and Science 2024年第1期9卷 40-49页

作者： A.T.Nguyen O.Nikan Z.Avazzadeh Division of Applied Mathematics Science and Technology Advanced InstituteVan Lang UniversityHo Chi Minh CityVietnam Faculty of Technology Van Lang UniversityHo Chi Minh CityVietnam School of Mathematics Iran University of Science and TechnologyNarmakTehranIran Department of Applied Mathematics Xi’an Jiaotong-Liverpool UniversitySuzhou 215123China

This paper focuses on obtaining the traveling wave solutions of the nonlinear Gilson-Pickering equa-tion(GPE),which describes the prorogation of waves in crystal lattice theory and plasma *** solution of the GPE is approximated via the finite difference technique and the localized meshless radial basis function generated finite *** association of the technique results in a meshless approach that does not require linearizing the nonlinear *** the first step,the PDE is converted to a system of nonlinear ODEs with the help of the radial *** the second step,a high-order ODE solver is adopted to discretize the nonlinear ODE *** global collocation techniques pose a considerable computationl burden due to the calculation of the dense algebraic *** proposed method approx-imates differential operators over the local support domain,leading to sparse differentiation matrices and decreasing the computational *** results and comparisons are provided to confirm the efficiency and accuracy of the method.

关键词： Nonlinear Gilson–Pickering equation Soliton wave solutions Meshless technique RBF LRBF-FD Optimal shape parameter

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

Advancing Wound Filling Extraction on 3D Faces:An Auto-Segmentation and Wound Face Regeneration Approach

引用

Computer Modeling in Engineering & Sciences 2024年第5期139卷 2197-2214页

作者： Duong Q.Nguyen Thinh D.Le Phuong D.Nguyen Nga T.K.Le H.Nguyen-Xuan Department of Mathematics and Statistics Quy Nhon UniversityQuy Nhon City55100Viet Nam Applied Research institute for Science and Technology Quy Nhon UniversityQuy Nhon City55100Viet Nam CIRTECH institute HUTECH UniversityHo Chi Minh City72308Viet Nam

Facial wound segmentation plays a crucial role in preoperative planning and optimizing patient outcomes in various medical *** this paper,we propose an efficient approach for automating 3D facial wound segmentation using a two-stream graph convolutional *** method leverages the Cir3D-FaIR dataset and addresses the challenge of data imbalance through extensive experimentation with different loss *** achieve accurate segmentation,we conducted thorough experiments and selected a high-performing model from the *** selectedmodel demonstrates exceptional segmentation performance for complex 3D facial ***,based on the segmentation model,we propose an improved approach for extracting 3D facial wound fillers and compare it to the results of the previous *** method achieved a remarkable accuracy of 0.9999993% on the test suite,surpassing the performance of the previous *** this result,we use 3D printing technology to illustrate the shape of the wound *** outcomes of this study have significant implications for physicians involved in preoperative planning and intervention *** automating facial wound segmentation and improving the accuracy ofwound-filling extraction,our approach can assist in carefully assessing and optimizing interventions,leading to enhanced patient ***,it contributes to advancing facial reconstruction techniques by utilizing machine learning and 3D bioprinting for printing skin tissue *** source code is available at https://***/SIMOGroup/WoundFilling3D.

关键词： 3D printing technology face reconstruction 3D segmentation 3D printed model

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

Integrated strategies on cobalt phosphides-based electrocatalysts for efficient hydrogen evolution reaction

引用

Tungsten 2024年第3期6卷 488-503页

作者： Thanh Dam Mai Ha Huu Do Faculty of Mechanical Engineering and Technology Ho Chi Minh City University of Industry and Trade VKTech Research Center NTT Hi-Tech Institute Nguyen Tat Thanh University

The development of cost-effective and durable hydrogen evolution reaction(HER) electrocatalysts plays a vital role in dealing with the issues related to carbon dioxide *** phosphide-based nanomaterials are evaluated as promising advocates for HER due to high catalytic activities,good stability,and rich *** review commences with an exploration of the synthetic pathways of CoP,including solid-phase,solution-phase along with electrochemical ***,the mechanism of hydrogen formation is expressed thoroughly,after which various integrated strategies of morphology engineering with doping,assisted highly conductive materials,and construction of heterostructure were introduced for ***,burdensome tasks and possible guidance for the advancement of CoP-based nanomaterials were discussed for hydrogen production.

关键词： Cobalt phosphides Nanomaterials Electrocatalysts Hydrogen evolution reaction

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

One-loop contributions for h→ℓℓγ and e−e+→hγ in the U(1)_(B−L) extension of the standard model

引用

chinese physics C 2024年第5期48卷 23-49页

作者： Tran Dzung Tri Thanh Huy Nguyen Khiem hong Phan institute of Fundamental and Applied Sciences Duy Tan UniversityHo Chi Minh City 700000Vietnam Faculty of Natural Sciences Duy Tan UniversityDa Nang City 550000Vietnam VNUHCM-University of Science 227 Nguyen Van CuDistrict 5Ho Chi Minh CityVietnam

We present one-loop contributions for h→ℓℓγ with ℓ=νe,μ,τ,e,μ and e−e+→hγ in the U(1)_(B−L) extension of the standard model. In the phenomenological results, the signal strengths for h→ℓℓγ at the Large Hadron Collider and for e−e+→hγ at future lepton colliders are analyzed in the physical parameter space for both the vector and chiral B−L models. We found that the contributions from the neutral gauge boson Z′ to the signal strengths are rather small. Consequently, the effects will be difficult to probe at future colliders. however, the impacts of charged Higgs and CP-odd Higgs in the chiral B−L model on the signal strengths are significant and can be measured with the help of the initial polarization beams at future lepton colliders.

关键词： Higgs phenomenology one-loop Feynman integrals analytic methods for quantum field theory dimensional regularization future lepton colliders

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

Modeling Geometrically Nonlinear FG Plates: A Fast and Accurate Alternative to IGA Method Based on Deep Learning

引用

Computer Modeling in Engineering & Sciences 2024年第3期138卷 2793-2808页

作者： Se Li Tiantang Yu Tinh Quoc Bui College of Mechanics and Materials Hohai UniversityNanjing211100China Duy Tan Research institute for Computational Engineering(DTRICE) Duy Tan UniversityHo Chi Minh CityVietnam

Isogeometric analysis (IGA) is known to showadvanced features compared to traditional finite element *** IGA one may accurately obtain the geometrically nonlinear bending behavior of plates with functionalgrading (FG). however, the procedure is usually complex and often is time-consuming. We thus put forward adeep learning method to model the geometrically nonlinear bending behavior of FG plates, bypassing the complexIGA simulation process. A long bidirectional short-term memory (BLSTM) recurrent neural network is trainedusing the load and gradient index as inputs and the displacement responses as outputs. The nonlinear relationshipbetween the outputs and the inputs is constructed usingmachine learning so that the displacements can be directlyestimated by the deep learning network. To provide enough training data, we use S-FSDT Von-Karman IGA andobtain the displacement responses for different loads and gradient indexes. Results show that the recognition erroris low, and demonstrate the feasibility of deep learning technique as a fast and accurate alternative to IGA formodeling the geometrically nonlinear bending behavior of FG plates.

关键词： FG plates geometric nonlinearity deep learning BLSTM IGA S-FSDT

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：