检索结果-南通市图书馆

Multi-layer perceptron-based data-driven multiscale modelling of granular materials with a novel Frobenius norm-based internal variable

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Rock Mechanics and Geotechnical Engineering 2024年第6期16卷 2198-2218页

作者： Mengqi Wang Y.T.Feng Shaoheng Guan tongming qu Zienkiewicz Centre for Computational Engineering Faculty of Science and EngineeringSwansea UniversitySwanseaWalesSA18EPUK Institute of Theoretical and Computational Physics Graz University of TechnologyGraz8010Austria Department of Civil and Environmental Engineering Hong Kong University of Science and TechnologyClearwater BayKowloonHong KongChina

One objective of developing machine learning(ML)-based material models is to integrate them with well-established numerical methods to solve boundary value problems(BVPs).In the family of ML models,recurrent neural networks(RNNs)have been extensively applied to capture history-dependent constitutive responses of granular materials,but these multiple-step-based neural networks are neither sufficiently efficient nor aligned with the standard finite element method(FEM).Single-step-based neural networks like the multi-layer perceptron(MLP)are an alternative to bypass the above issues but have to introduce some internal variables to encode complex loading histories.In this work,one novel Frobenius norm-based internal variable,together with the Fourier layer and residual architectureenhanced MLP model,is crafted to replicate the history-dependent constitutive features of representative volume element(RVE)for granular materials.The obtained ML models are then seamlessly embedded into the FEM to solve the BVP of a biaxial compression case and a rigid strip footing case.The obtained solutions are comparable to results from the FEM-DEM multiscale modelling but achieve significantly improved efficiency.The results demonstrate the applicability of the proposed internal variable in enabling MLP to capture highly nonlinear constitutive responses of granular materials.

关键词： Granular materials History-dependence Multi-layer perceptron(MLP) Discrete element method FEM-DEM Machine learning

An MPI parallel DEM-IMB-LBM framework for simulating fluid-solid interaction problems

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Rock Mechanics and Geotechnical Engineering 2024年第6期16卷 2219-2231页

作者： Ming Xia Liuhong Deng Fengqiang Gong tongming qu Y.T.Feng Jin Yu Hunan Key Laboratory of Geomechanics and Engineering Safety Xiangtan UniversityXiangtan411105China School of Civil Engineering Southeast UniversityNanjing211189China Department of Civil and Environmental Engineering Hong Kong University of Science and TechnologyHong KongChina Zienkiewicz Centre for Computational Engineering Swansea UniversitySwanseaSA18ENUK Fujian Research Center for Tunneling and Urban Underground Space Engineering Huaqiao UniversityXiamen361021China

The high-resolution DEM-IMB-LBM model can accurately describe pore-scale fluid-solid interactions,but its potential for use in geotechnical engineering analysis has not been fully unleashed due to its prohibitive computational costs.To overcome this limitation,a message passing interface(MPI)parallel DEM-IMB-LBM framework is proposed aimed at enhancing computation efficiency.This framework utilises a static domain decomposition scheme,with the entire computation domain being decomposed into multiple subdomains according to predefined processors.A detailed parallel strategy is employed for both contact detection and hydrodynamic force calculation.In particular,a particle ID re-numbering scheme is proposed to handle particle transitions across sub-domain interfaces.Two benchmarks are conducted to validate the accuracy and overall performance of the proposed framework.Subsequently,the framework is applied to simulate scenarios involving multi-particle sedimentation and submarine landslides.The numerical examples effectively demonstrate the robustness and applicability of the MPI parallel DEM-IMB-LBM framework.

关键词： Discrete element method(DEM) Lattice Boltzmann method(LBM) Immersed moving boundary(IMB) Multi-cores parallelization Message passing interface(MPI) CPU Submarine landslides

Applicability of discrete element method with spherical and clumped particles for constitutive study of granular materials

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Rock Mechanics and Geotechnical Engineering 2022年第1期14卷 240-251页

作者： tongming qu Min Wang Yuntian Feng Zienkiewicz Centre for Computational Engineering College of EngineeringSwansea UniversitySwanseaWales SA18EPUK T-3 Fluid Dynamics and Solid Mechanics Group Theoretical DivisionLos Alamos National LaboratoryLos AlamosNM87545USA

Discrete element method(DEM)has been intensively used to study the constitutive behaviour of granular materials.However,to what extent a real granular material can be reproduced by virtual DEM simulations remains unclear.This study attempts to answer this question by comparing DEM simulations with typical features of experimental granular materials.Three groups of models with spherical and clumped particles are investigated from four perspectives:(i)deviatoric stress and volumetric behaviour;(ii)critical state behaviour;(iii)stress-dilatancy relationship;and(iv)the evolution of principal stress ratio against axial strain.The results demonstrate that DEM with spherical or clumped particles is capable of qualitatively describing macroscopic deviatoric stress responses,volumetric behaviour,and critical state behaviour observed in experiments for granular materials.On the other hand,some qualitative deviations between experiments and the investigated DEM simulations are also observed,in terms of the stress-dilatancy behaviour and principal stress ratio against axial strain,which are proven to be critical for constitutive modelling.The results demonstrate that DEM with spherical or clumped particles may not necessarily fully capture experimental features of granular materials even from a qualitative perspective.It is thus encouraged to thoroughly validate DEM with experiments when developing constitutive models based on DEM observations.

关键词： Discrete element method(DEM) Granular materials Constitutive behaviour Deviatoric hardening model Rolling resistance model Irregular particles

Undrained vane shear strength of sand-foam mixtures subjected to different shear rates

在线全文

学校读者我要写书评

暂无评论

Journal of Rock Mechanics and Geotechnical Engineering 2023年第6期15卷 1591-1602页

作者： Jiazheng Zhong Shuying Wang tongming qu School of Civil Engineering Central South UniversityChangsha410075China Tunnel and Underground Engineering Research Center Central South UniversityChangsha410075China Department of Civil and Environmental Engineering The Hong Kong University of Science and TechnologyClearwater BayHong KongChina

The shear strength of sand-foam mixtures plays a crucial role in ensuring successful earth pressure balance(EPB)shield tunneling.Since the sand-foam mixtures are constantly sheared by the cutterhead and the screw conveyor with varied rotation speeds during tunneling,it is non-trivial to investigate the effect of shear rates on the undrained shear strength of sand-foam mixtures under chamber pressures to extend the understanding on the tunneling process.This study conducted a series of pressurized vane shear tests to investigate the role of shear rates on the peak and residual strengths of sand-foam mixtures at different pore states.Different from the shear-rate characteristics of natural sands or clay,the results showed that the peak strength of sand-foam mixtures under high vertical total stress(σ_(v)≥200 kPa)and low foam injection ratio(FIR30%)decreased with the increase in shear rate.Otherwise,the peak strength was not measurably affected by shear rates.The sand-foam mixtures in the residual state resembled low-viscous fluid with yield stress and the residual strength increased slightly with shear rates.In addition,the peak and residual strengths were approximately linear with vertical effective stress regardless of the total stress and FIR.The peak effective internal friction angle remained almost invariant in a low shear rate(γ′<0.25 s1)but decreased when the shear rate continued increasing.The residual effective internal friction angle was lower than the peak counterpart and insensitive to shear rates.This study unveiled the role of shear rates in the undrained shear strength of sand-foam mixtures with various FIRs and vertical total stresses.The findings can extend the understanding of the rate-dependent shear characteristics of conditioned soils and guide the decision-making of soil conditioning schemes in the EPB shield tunneling practice.

关键词： Sand-foam mixture Shear rate Peak and residual strengths Effective stress Effective internal friction angle

Influence factors and calculation model of the adhesion strength of clayey soil for EPB shield tunnelling

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Transportation Safety and Environment 2022年第3期4卷 55-64页

作者： Shuying Wang Pengfei Liu Jiazheng Zhong Zhunlin Ni tongming qu School of Civil Engineering Central South UniversityChangsha 410075HunanChina CCCC Second Harbor Engineering Company Ltd. Wuhan 430012HubeiChina Institute of Rock and Soil Mechanics Chinese Academy of ScienceWuhan 430061HubeiChina Zienkiewicz Centre for Computational Engineering College of EngineeringSwansea UniversitySwansea SA18EPWalesUK.

When earth pressure balance (EPB) shield tunnels are constructed through clayey ground, the soil adheres to the cutter, cutterheadand chamber bulkhead due to the high adhesion strength between the steel and the clay, thus clogging the shield. To investigatethe influence of different factors on the adhesion strength, this study used montmorillonite, kaolin and mixtures of the two as testsoils. The adhesion strength between the steel and clay is determined with a customized rotary shear apparatus. The results showthat when the consistency index of the soil specimen is less than 1, the adhesion strength between the steel and clay increaseswith the consistency index. As the consistency index decreases, the effect of the normal pressure on the adhesion strength graduallyweakened. As the contact angle of the shear plate increases, thus reducing the hydrophilicity, the adhesion strength decreases. Whenthe soil specimens with different plasticity index values have the same consistency index value, the adhesion strengths are similar.The adhesion strength increases gradually with increasing surface roughness. Based on grey incidence analysis, the order of thefactors affecting the adhesion strength is as follows: normal pressure > consistency index > contact angle > plasticity index ≈ surfaceroughness. The normal pressure, consistency index and contact angle all have important effects on the adhesion strength betweensteel and clay. However, because there are no large differences in the contact angle among the metal materials, the approximateadhesion strength can be calculated by considering the effects of only the normal pressure and consistency index. Themeasures thatare effective for preventing EPB shield clogging are increasing the soil softness and decreasing the hydrophilicity of the cutterheadby applying new materials for the cutters and cutterhead.

关键词： Earth pressure balance(EPB)shield clayey soil adhesion strength grey theory

Deep Learning Predicts Stress–Strain Relations of Granular Materials Based on Triaxial Testing Data

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2021年第7期128卷 129-144页

作者： tongming qu Shaocheng Di Y.T.Feng Min Wang Tingting Zhao Mengqi Wang Zienkiewicz Centre for Computational Engineering College of EngineeringSwansea UniversitySwanseaWalesSA18EPUK College of Shipbuilding Engineering Harbin Engineering UniversityHarbin150001China Institute of Applied Mechanics and Biomedical Engineering Taiyuan University of TechnologyTaiyuan030024China Fluid Dynamics and Solid Mechanics Group Theoretical DivisionLos Alamos National LaboratoryLos AlamosNM 87545USA

This study presents an AI-based constitutive modelling framework wherein the prediction model directly learns from triaxial testing data by combining discrete element modelling(DEM)and deep learning.A constitutive learning strategy is proposed based on the generally accepted frame-indifference assumption in constructing material constitutive models.The low-dimensional principal stress-strain sequence pairs,measured from discrete element modelling of triaxial testing,are used to train recurrent neural networks,and then the predicted principal stress sequence is augmented to other high-dimensional or general stress tensor via coordinate transformation.Through detailed hyperparameter investigations,it is found that long short-term memory(LSTM)and gated recurrent unit(GRU)networks have similar prediction performance in constitutive modelling problems,and both satisfactorily predict the stress responses of granular materials subjected to a given unseen strain path.Furthermore,the unique merits and ongoing challenges of data-driven constitutive models for granular materials are discussed.

关键词： Deep learning granular materials constitutive modelling discrete element modelling coordinate transformation LSTM GRU

基于激光扫描技术的盾构渣土改良状态自动识别方法

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

中南大学学报(自然科学版) 2023年第10期54卷 3975-3986页

作者：周子豪王树英钟嘉政倪准林瞿同明中南大学土木工程学院湖南长沙410075 中南大学隧地工程研究中心湖南长沙410075 重载铁路工程结构教育部重点实验室中南大学湖南长沙410075 香港科技大学土木与环境工程系中国香港999077

为促进渣土改良状态评价方法向着规范化、自动化的方向发展,提出一种基于激光扫描技术的盾构渣土改良状态快速自动识别方法。针对不同含水率和泡沫注入比的粗粒土试样开展坍落度试验,采用激光扫描仪获得坍落体中心位置竖向截面轮廓点云... 详细信息

为促进渣土改良状态评价方法向着规范化、自动化的方向发展,提出一种基于激光扫描技术的盾构渣土改良状态快速自动识别方法。针对不同含水率和泡沫注入比的粗粒土试样开展坍落度试验,采用激光扫描仪获得坍落体中心位置竖向截面轮廓点云数据,并通过计算机提取截面轮廓几何特征点,获得试样的坍落度和割线角,建立以坍落度和割线角的合适范围作为合适改良状态评价指标的自动识别方法。研究结果表明:采用坍落度和坍落体割线角可以准确识别改良粗粒土的改良状态;相对于传统坍落度试验,该方法的突出优点是可自动扫描并快速识别渣土的改良状态;室内坍落度试验结果验证了该方法对粗粒土试样改良状态识别的有效性,可为研究盾构水平传送带上渣土截面轮廓几何特征和渣土改良状态识别提供参考。

关键词：渣土改良坍落度割线角自动识别激光扫描技术

在线全文

学校读者我要写书评

暂无评论

泡沫混合土中颗粒间黏结强度理论计算方法

中南大学学报（自然科学版） 2022年第4期53卷 1320-1330页

作者：刘正日王树英王海波钟嘉政瞿同明中南大学土木工程学院湖南长沙410075 重载铁路工程结构教育部重点实验室中南大学湖南长沙410075 斯旺西大学辛克维奇工程计算中心英国斯旺西SA18EP

盾构掘进往往需要注入泡沫来提高砂土颗粒间黏结力、改善砂性渣土塑流性。为了了解这种泡沫混合土的细观力学特征,对泡沫混合土中颗粒间黏结强度这一关键参数的理论计算方法进行研究。基于能量守恒原理,首先推导泡沫−泡沫与砂土−泡沫颗... 详细信息

盾构掘进往往需要注入泡沫来提高砂土颗粒间黏结力、改善砂性渣土塑流性。为了了解这种泡沫混合土的细观力学特征,对泡沫混合土中颗粒间黏结强度这一关键参数的理论计算方法进行研究。基于能量守恒原理,首先推导泡沫−泡沫与砂土−泡沫颗粒间的抗拉强度计算解析式,揭示颗粒间抗拉强度与泡沫颗粒粒径、表面张力的关系。然后,通过试验测定颗粒间的抗拉强度。研究结果表明:颗粒间抗拉强度随泡沫颗粒粒径及溶液质量分数增加而减小,其中泡沫颗粒粒径的影响更加明显;颗粒间抗拉强度理论计算结果和试验结果相对误差不超过10%,证明解析式能较好地计算泡沫−泡沫、泡沫−砂土颗粒间的抗拉强度,可为离散元数值模拟中颗粒平行黏结模型中黏结强度参数的确定提供理论依据。

关键词：砂性土泡沫颗粒接触黏结强度

基于深度强化学习算法的颗粒材料应力-应变关系数据驱动模拟研究

在线全文

学校读者我要写书评

暂无评论

力学学报 2021年第10期53卷 2712-2723页

作者：狄少丞冯云田瞿同明于海龙哈尔滨工程大学船舶工程学院哈尔滨150001 斯旺西大学辛克维奇工程计算中心英国斯旺西SA18EP

颗粒材料的宏观力学行为受颗粒组分等材料参数,孔隙率、配位数等状态参数的影响,同时又具备复杂的加载路径和加载历史相关性,建立包含多个内变量以及各变量间相互关联的颗粒材料本构模型是一个重要的科学难题.不同于传统的基于屈服面、... 详细信息

颗粒材料的宏观力学行为受颗粒组分等材料参数,孔隙率、配位数等状态参数的影响,同时又具备复杂的加载路径和加载历史相关性,建立包含多个内变量以及各变量间相互关联的颗粒材料本构模型是一个重要的科学难题.不同于传统的基于屈服面、流动法则和硬化函数框架下的唯象本构模型,本文基于颗粒物质力学的研究基础,以颗粒材料平均孔隙率、细观组构参数和弹性刚度参数作为内变量,结合深度学习方法建立以有向图表征的数据本构模型.有向图中以不同的链接网络表示不同的内变量信息流动方向,各个内变量间的映射关系采用循环神经网络来建立,将各个神经网络相互组合,形成包含不同内变量且具有不同预测能力的本构模型.该本构模型的建立过程等价于在众多可能的内变量链接关系空间中寻找最能描述实际材料宏观应力应变行为的优化问题.因此,可将有向图本构模型的建立过程看作"马尔可夫决策过程",采用深度强化学习算法构建有向图的内变量链接组合优化过程,具体采用AlphaGo Zero算法自动寻找最优的颗粒材料数据驱动本构模型建模路径.研究结果表明,采用有向图和深度强化学习算法可建立起完全依靠"数据驱动"的颗粒材料应力-应变关系.此外,本方法提供了一种将不同理论模型从数据角度统一起来,且基于人工智能算法发展更优模型的研究思路,可为相似问题的研究提供借鉴.

关键词：颗粒材料应力-应变关系离散元法深度强化学习有向图