检索结果-内蒙古大学图书馆

Multigoal-oriented dual-weighted-residual error estimation using PINNs

Machine Learning for computational science and Engineering 2025年第1期1卷 1-18页

作者： Chakraborty, Ayan Wick, Thomas Rabczuk, Timon Zhuang, Xiaoying Chair of Computational Science and Simulation Technology Institute of Photonics Faculty of Mathematics and Physics Leibniz University Hannover Germany Institute of Applied Mathematics Welfengarten 1 AG Wissenschaftliches Rechnen Leibniz University Hannover Germany Cluster of Excellence PhoenixD (Photonics Optics and Engineering - Innovation Across Disciplines) Leibniz University Hannover Hannover Germany Université Paris-Saclay ENS Paris-Saclay LMT - Laboratoire de Mecanique et Technologie Gif-sur-Yvette France Institute of Structural Mechanics Bauhaus University Weimar Weimar Germany Department of Geotechnical Engineering College of Civil Engineering Tongji University Shanghai China

Deep learning has shown successful application in visual recognition and certain artificial intelligence tasks. It is mainly considered as a powerful tool with high flexibility to approximate functions. This paper proposes a generalized NURBS based approach to solve nonlinear partial differential equations (PDEs) on arbitrary complex-geometry domains by using physics-informed neural networks (PINNs). Our approach is based on a posteriori error estimation in which the adjoint problem is solved for the error localization to formulate an error estimator within the framework of neural network. An efficient and easy to implement algorithm is developed to obtain a posteriori error estimate for multiple goal functionals by employing the dual-weighted residual approach, which is followed by the computation of both primal and adjoint solutions using the neural network. The present study shows that such a data-driven model based learning has superior approximation of quantities of interest even with relatively less training data. Moreover, we illustrate the versatility of activation functions in achieving better learning capabilities and improving convergence rates, especially at the early training stage, and also in increasing solutions accuracies. The novel algorithmic developments are substantiated with several numerical test examples. It has been demonstrated that deep neural networks have distinct advantages over shallow neural networks, and the techniques for enhancing convergence have also been reviewed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhance liquid nitrogen fracturing performance on hot dry rock by cyclic injection

引用

Petroleum science 2023年第2期20卷 951-972页

作者： Chun-Yang Hong Rui-Yue Yang Zhong-Wei Huang Xiao-Ying Zhuang Hai-Tao Wen Xiao-Li Hu State Key Laboratory of Petroleum Resources and Prospecting China University of PetroleumBeijing102249China Chair of Computational Science and Simulation Technology Faculty of Mathematics and PhysicsLeibniz Universität HannoverHannover30167Germany

Producing complex fracture networks in a safe way plays a critical role in the hot dry rock (HDR) geothermal energy exploitation. However, conventional hydraulic fracturing (HF) generally produces high breakdown pressure and results only in single main fracture morphology. Furthermore, HF has also other problems such as the increased risk of seismic events and consuption of large amount of water. In this work, a new stimulation method based on cyclic soft stimulation (CSS) and liquid nitrogen (LN2) fracturing, known as cyclic LN2 fracturing is explored, which we believe has the potential to solve the above issues related to HF. The fracturing performances including breakdown pressure and fracture morphology on granites under true-triaxial stresses are investigated and compared with cyclic water fracturing. Cryo-scanning electron microscopy (Cryo-SEM) tests and X-ray computed tomography (CT) scanning tests were used for quantitative characterization of fracture parameters and to evaluate the cyclic LN2 fracturing performances. The results demonstrate that the cyclic LN2 fracturing results in reduced breakdown pressure, with between 21% and 67% lower pressure compared with using cyclic water fracturing. Cyclic LN2 fracturing tends to produce more complex and branched fractures, whereas cyclic water fracturing usually produces a single main fracture under a low number of cycles and pressure levels. Thermally-induced fractures mostly occur around the interfaces of different particles. This study shows the potential benefits of cyclic LN2 fracturing on HDR. It is expected to provide theoretical guidance for the cyclic LN2 fracturing application in HDR reservoirs.

关键词： Hot dry rock Liquid nitrogen fracturing Cyclic injection Thermal stress Fatigue damage

来源：评论

学校读者我要写书评

暂无评论

Surrounding rock classification from onsite images with deep transfer learning based on EfficientNet

引用

Frontiers of Structural and Civil Engineering 2024年第9期18卷 1311-1320页

作者： Xiaoying ZHUANG Wenjie FAN Hongwei GUO Xuefeng CHEN Qimin WANG Department of Geotechnical Engineering College of Civil EngineeringTongji UniversityShanghai 200092China Chair of Computational Science and Simulation Technology Institute of PhotonicsLeibniz University HannoverHannover 30167Germany Key Laboratory of Geotechnical and Underground Engineering of Ministry of Education Tongji UniversityShanghai 200092China Guizhou Xingyi Huancheng Expressway Co. Ltd.Xingyi 562400China

This paper proposes an accurate,efficient and explainable method for the classification of the surrounding rock based on a convolutional neural network(CNN).The state-of-the-art robust CNN model(EfficientNet)is applied to tunnel wall image *** filtering,data augmentation and other data pre-processing techniques are used to improve the data quality and *** with transfer learning,the generality,accuracy and efficiency of the deep learning(DL)model are further improved,and finally we achieve 89.96%*** with other state-of-the-art CNN architectures,such as ResNet and Inception-ResNet-V2(IRV2),the presented deep transfer learning model is more stable,accurate and *** reveal the rock classification mechanism of the proposed model,Gradient-weight Class Activation Map(Grad-CAM)visualizations are integrated into the model to enable its explainability and *** developed deep transfer learning model has been applied to support the tunneling of the Xingyi City Bypass in the high mountain area of Guizhou,China,with great results.

关键词： surrounding rock classification convolutional neural network EfficientNet Gradient-weight Class Activation Map

来源：评论

学校读者我要写书评

暂无评论

Modeling boundary conditions in high-order, nodal, time-domain finite element methods 23

Modeling boundary conditions in high-order, nodal, time-doma...

引用

23rd International Congress on Acoustics: Integrating 4th EAA Euroregio, ICA 2019

作者： Pind, Finnur Jeong, Cheol-Ho Hesthaven, Jan S. Engsig-Karup, Allan P. Strømann-Andersen, Jakob Henning Larsen Denmark Acoustic Technology Dept. of Electrical Engineering Technical University of Denmark Denmark Chair of Computational Mathematics and Simulation Science École polytechnique fédérale de Lausanne Switzerland Scientific Computing Dept. of Applied Mathematics and Computer Science Technical University of Denmark Denmark

ISBN: (纸本)9783939296157

Accurate modeling of boundary conditions is an important aspect in room acoustic simulations. It has been shown that the acoustics of rooms is not only dependent on the frequency characteristic of the complex boundary impedance, but also on the angle dependent properties of the impedance ("extended reaction"). This paper presents a computationally efficient method for modeling local-reaction (LR) and extended-reaction (ER) boundary conditions in high-order, nodal, time-domain finite element methods, such as the spectral element method (SEM) or the discontinuous Galerkin finite element method (DGFEM). The frequency and angle dependent boundary impedance is mapped to a multipole model and formulated in differential form. The solution of the boundary differential equations comes with minimal computational cost. In the ER model, wave splitting is applied at the boundary to separate the incident and reflected parts of the sound field. The directional properties of the incident sound field are determined from the incident particle velocity and the boundary conditions are adjusted continuously according to the wave angle of incidence. The accuracy of the boundary condition model is assessed by comparing simulations against measurements, where a significantly improved match between simulations and measurements is found when the ER model is used. © 2019 Proceedings of the International Congress on Acoustics. All rights reserved.

关键词： *fpin@*** Extended-reaction High-order numerical methods Sound absorption Wave-based room acoustic simulations

来源：评论

学校读者我要写书评

暂无评论

Deep learning to evaluate seismic-induced soil liquefaction and modified transfer learning between various data sources

引用

Underground Space 2025年

作者： Hongwei Guo Chao Zhang Hongyuan Fang Timon Rabczuk Xiaoying Zhuang Department of Geotechnical Engineering College of Civil Engineering Tongji University Shanghai 200092 China Key Laboratory of Urban Security and Disaster Engineering Ministry of Education Beijing University of Technology Beijing 100124 China School of Water Conservancy and Transportation/Yellow River Laboratory/Underground Engineering Research Institute Zhengzhou University Zhengzhou 450001 China National Local Joint Engineering Laboratory of Major Infrastructure Testing and Rehabilitation Technology Zhengzhou 450001 China Collaborative Innovation Center for Disaster Prevention and Control of Underground Engineering Jointly Built by Provinces and Ministries Zhengzhou 450001 China Institute of Structural Mechanics Bauhaus University Weimar Weimar 99425 Germany Chair of Computational Science and Simulation Technology Faculty of Mathematics and Physics Leibniz University Hannover Hannover 30167 Germany

Soil liquefaction assessment remains a crucial and complex challenge in seismic geotechnical engineering due to various liquefaction records and limited information, which entails a more generalized off-the-shelf model that can achieve favourable performance on different data sources. In this work, a deep learning model is built and investigated on the soil liquefaction prediction and a modified transfer learning scheme between different data sources is presented. Various datasets, including shear wave velocity-based, CPT-based, SPT-based, and real cases, are collected and utilized to verify the effectiveness and accuracy of the proposed model. Because different data sources in soil liquefaction generally share several geotechnical and mechanical parameters, we work to combine model prior information, feature mapping and data reconstruction in transfer learning models to tackle multi-source domain adaption, which can be further applied to other predictive analysis and facilitate online learning models in geotechnical engineering. Also, the deep learning model is compared with several classical machine learning and ensemble learning models and the modified transfer learning model is formulated by comparing different feature transformation techniques integrated with various feature-based and instance-based transfer learning methods. The accuracy and effectiveness of the deep learning and modified transfer learning models have been validated in the numerical study.

关键词： Liquefaction Prediction Deep learning Ensemble methods Transfer learning Feature-based Instance-based Source data Target data Deep autoencoder Variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Polytopal composite finite elements for modeling concrete fracture based on nonlocal damage models

arXiv

引用

arXiv 2023年

作者： Huynh, Hai D. Natarajan, S. Nguyen-Xuan, H. Zhuang, Xiaoying Chair of Computational Science and Simulation Technology Department of Mathematics and Physics Leibniz University Hannover Germany Integrated Modelling and Simulation Lab Department of Mechanical Engineering Indian Institute of Technology Madras Chennai600036 India Ho Chi Minh City Viet Nam

The paper presents an assumed strain formulation over polygonal meshes to accurately evaluate the strain fields in nonlocal damage models. An assume strained technique based on the Hu-Washizu variational principle is employed to generate a new strain approximation instead of direct derivation from the basis functions and the displacement fields. The underlying idea embedded in arbitrary finite polygons is named as Polytopal composite finite elements (PCFEM). The PCFEM is accordingly applied within the framework of the nonlocal model of continuum damage mechanics to enhance the description of damage behaviours in which highly localized deformations must be captured accurately. This application is helpful to reduce the mesh-sensitivity and elaborate the process-zone of damage models. Several numerical examples are designed for various cases of fracture to discuss and validate the computational capability of the present method through comparison with published numerical results and experimental data from the literature. © 2023, CC0.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

Boosting Electrical Output of Triboelectric Nanogenerators (TENGs) by Adapting Fringing Effect for Self-powering Devices

Boosting Electrical Output of Triboelectric Nanogenerators (...

引用

IEEE Nanotechnology Materials and Devices Conference (NMDC)

作者： Teresa Cheng Ling Yang Xiaoning Jiang Xiaoying Zhuang Department of Mathematics and Physics Computational Science and Simulation Technology Leibniz University Hannover Hannover Germany Geriatric Department Shanghai Fourth People’s Hospital Affiliated to Tongji University Department of Mechanical and Aerospace Engineering North Carolina State University Raleigh North Carolina USA Department of Mathematics and Physics Chair of Computational Science and Simulation Technology Leibniz University Hannover Hannover Germany

Energy nanogenerators have recently attracted much attention for energy harvesting due to their ability to convert mechanical energy into electricity. Triboelectric nanogenerators (TENGs) remain one of the most promising technologies because they can harvest from small-scale physical changes, e.g., low frequency vibrations [1]. Thus, the harvested energy enables the self-powering of various applications, including wearable devices, wireless sensors, and ultimately implantable electronic devices. However, due to the natural properties of high voltage but low current output, there is a huge space to improve the total power output.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Systematic Molecular Dynamics Investigation on the Graphene Polymer Nanocomposites for Bulletproofing

引用

Computers, Materials & Continua 2020年第12期65卷 2009-2032页

作者： Hamidreza Noori Zi Goangseup Bohayra Mortazavi Alessandro Di Pierro Emad Jomehzadeh Xiaoying Zhuang Kim Sang-Hyun Timon Rabczuk Institute of Structural Mechanics Bauhaus-Universität WeimarWeimarD-99423Germany Chair of Computational Science and Simulation Technology Department of Mathematics and PhysicsLeibniz Universität HannoverHannover30157Germany Cluster of Excellence PhoenixD(Photonics Opticsand Engineering-Innovation Across Disciplines)Gottfried Wilhelm Leibniz Universität HannoverHannoverGermany Dipartimento di ScienzaApplicata e Tecnologia Politecnico di TorinoAlessandria CampusAlessandria15121Italy Faculty of Mechanical and Material Engineering Graduate University of Advanced TechnologyKermanIran School of Civil Environmental and Architectural EngineeringKorea UniversitySeoulKorea Chief Research Engineer Mechanical Engineering R&D LabLIG Nex1Seung NamKorea Division of Computational Mechanics Ton Duc Thang UniversityHo Chi Minh CityVietnam Faculty of Civil Engineering Ton Duc Thang UniversityHo Chi Minh CityVietnam

In modern physics and fabrication technology,simulation of projectile and target collision is vital to improve design in some critical applications,like;bulletproofing and medical ***,the most prominent member of two dimensional materials presents ultrahigh tensile strength and ***,polydimethylsiloxane(PDMS)is one of the most important elastomeric materials with a high extensive application area,ranging from medical,fabric,and interface *** this work we considered graphene/PDMS structures to explore the bullet resistance of resulting *** this aim,extensive molecular dynamic simulations were carried out to identify the penetration of bullet through the graphene and PDMS composite *** this paper,we simulate the impact of a diamond bullet with different velocities on the composites made of single-or bi-layer graphene placed in different positions of PDMS *** underlying mechanism concerning how the PDMS improves the resistance of graphene against impact loading is *** discuss that with the same content of graphene,placing the graphene in between the PDMS result in enhanced bullet *** work comparatively examines the enhancement in design of polymer nanocomposites to improve their bulletproofing response and the obtained results may serve as valuable guide for future experimental and theoretical studies.

关键词： Graphene nanocomposites bulletproofing impact PDMS

来源：评论

学校读者我要写书评

暂无评论

Atomic stick-slip friction as a two-dimensional thermally activated process

引用

Physical Review B 2022年第16期105卷 165429-165429页

作者： Quanzhou Yao Jiawei Sun Xiaoying Zhuang Peter Wriggers Xi-Qiao Feng Qunyang Li Applied Mechanics Laboratory Department of Engineering Mechanics Tsinghua University Beijing 100084 China Chair of Computational Science and Simulation Technology Institute of Photonics Department of Mathematics and Physics Leibniz University Hannover 30167 Hannover Germany Institute for Continuum Mechanics Leibniz University Hannover Garbsen Germany State Key Laboratory of Tribology Tsinghua University Beijing 100084 China

Widely recognized as a thermally activated process, atomic stick-slip friction has been typically explained by Prandtl-Tomlinson model with thermal activation. Despite the limited success, theoretical predictions from the classic model are primarily based on a one-dimensional (1D) assumption, which is generally not compatible with real experiments that are two-dimensional (2D) in nature. In this letter, a theoretical model based on 2D transition state theory has been derived and confirmed to be able to capture the 2D slip kinetics in atomic-scale friction experiments on crystalline surface with a hexagonal energy landscape. Moreover, we propose a reduced scheme that enables extraction of intrinsic interfacial parameters from 2D experiments approximately using the traditional 1D model. The 2D model provides a theoretical tool for understanding the rich kinetics of atomic-scale friction or other phenomena involving higher dimensional transitions.

关键词： Friction Atomic force microscopy Thermal & statistical models

来源：评论

学校读者我要写书评

暂无评论

Laser exfoliation of graphene from graphite

arXiv

引用

arXiv 2020年

作者： Javvaji, Brahmanandam Vasireddi, Ramakrishna Zhuang, Xiaoying Mahapatra, D. Roy Rabczuk, Timon Department of Aerospace Engineering Indian Institute of Science Bangalore560012 India Chair of Computational Science and Simulation Technology Faculty of Mathematics and Physics Leibniz Universität Hannover30167 Germany Synchrotron SOLEIL Gif-sur-YvetteSaint-Aubin91192 France Institute of Structural Mechanics Bauhaus University of Weimar Weimar99423 Germany

Synthesis of graphene with reduced use of chemical reagents is essential for manufacturing scale-up and to control its structure and properties. In this paper, we report on a novel chemical-free mechanism of graphene exfoliation from graphite using laser impulse. Our experimental setup consists of a graphite slab irradiated with an Nd:YAG laser of wavelength 532 nm and 10 ns pulse width. The results show the formation of graphene layers with conformational morphology from electron microscopy and Raman spectra. Based on the experimental results, we develop a simulation set up within the framework of the molecular dynamics that supplies the laser-induced electromagnetic energies to atoms in the graphite slab. We investigate the influence of different laser fluence on the exfoliation process of graphene. The variations in inter-layer interaction energy and inter-layer distance are the confirmative measures for the possible graphene layer formation. The simulation results confirm the exfoliation of a single layer graphene sheet for the laser power ranging from 100 × 10 to 2000 × 10 J/nm2. With an increase of laser fluence from 2000 × 10 to 4000 × 10 J/nm2, there is an increase in the graphene yield via the layer-after-layer exfoliation. The bridging bond dynamics between the successive graphene layers govern the possibility of second-layer exfoliation. The experimental and simulation observations are useful and promising for producing chemical-free graphene on a large scale for industrial and commercial applications. © 2020, CC-BY.

关键词： Graphene

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：