检索结果-内蒙古大学图书馆

8th International Symposium on Reliability engineering and Risk Management, ISRERM 2022

作者： Anton, D. Wessels, H. Institute for Computational Modeling in Civil Engineering Technische Universität Braunschweig Germany

ISBN: (纸本)9789811851841

For the condition assessment of existing infrastructure buildings the current parameters of the building material, such as the Young’s modulus and Poisson’s ratio, are of great interest. These parameters indicate damage or material degradation, since they reflect the resistance of the structures to external impacts. Provided the displacement field data is available, the material parameters can be identified by solving the momentum equation inversely. It was recently shown that there is a method in the growing field of scientific machine learning, known as physics-informed neural networks [1], that is particularly suitable for the inverse solution of partial differential equations. In contrast to purely data-driven approaches, physics-informed neural networks do not only use the displacement data but also the physics behind the data formulated as partial differential equation. It has been shown that physics-informed neural networks can in principle be used to identify material parameters [2], [3]. In the present paper, we first develop a three-stage adaptation of the method to realistic one-dimensional applications. Second, we verify the adapted method on two-dimensional displacement data. We conclude the paper with an outlook on ongoing and future work to further improve the method. © 2022 ISRERM Organizers. Published by Research Publishing, Singapore.

关键词： Poisson ratio

来源：评论

学校读者我要写书评

暂无评论

An Inverse Neural Particle Method for Flow Field Reconstruction

An Inverse Neural Particle Method for Flow Field Reconstruct...

引用

92nd Annual Meeting of the International Association of Applied Mathematics and Mechanics, GAMM 2022

作者： Wessels, Henning Institute for Computational Modeling in Civil Engineering Pockelsstr. 3 Braunschweig38106 Germany

Physics-Informed Neural Networks (PINNs) are a novel discretization scheme for the solution of partial differential equations (PDEs), where a neural network is chosen as global ansatz function. The problem of solving the PDE is then cast as an optimization problem and addressed by training the neural network. PINNs have been promoted to perform particularly well in inverse problems. This contribution presents recent advances of the Neural Particle Method, an updated Lagrangian Physics-Informed Neural Network, in the inverse problem of reconstructing flow fields from sparse data. © 2023 The Authors.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Towards model-guided feedback control of hydrogels bioprinting

Towards model-guided feedback control of hydrogels bioprinti...

引用

94th Annual Meeting of the International Association of Applied Mathematics and Mechanics, GAMM 2024

作者： Urrea-Quintero, Jorge-Humberto Wessels, Henning Wick, Thomas Institute for Computational Modeling in Civil Engineering Technische Universtität Braunschweig Braunschweig Germany Institute of Applied Mathematics Leibniz University Hannover Hannover Germany

This contribution addresses the problem of controlling the Degree of Crosslinking(DoC) in printed hydrogels through feedback control as a product quality indicator from a modeling approach. We set up a simulation that resemblesco-axial printing of calcium-alginate (Ca-Alg) hydrogel as a case study. A well-known Ca-Alg gelation model composed of a set of nonlinear coupled diffusion-reactions equations is adopted as a high-fidelitymodel (HFM). A traditional proportional-integral (PI) controller is designed based on a reduced-orderstate-space linear model of the gelation process. The linear state-space modelis identified from input-output data collected from the HFM. We formulate an optimization problem to find optimal PI controller parameters that minimize aclosed-loop performance index. The PI controller is directly applied to the nonlinear diffusion-reaction model to guide the printing process towards a desired DoC. We show its efficacy via some numerical simulations. © 2024 The Author(s).

关键词： Gelation

来源：评论

学校读者我要写书评

暂无评论

An Alternative Approach to Automated Code Checking – Application of Graph Neural Networks Trained on Synthetic Data for an Accessibility Check Case Study 19th

An Alternative Approach to Automated Code Checking – Applic...

引用

19th International Conference on Computing in civil and Building engineering, ICCCBE 2022

作者： Bloch, Tanya Borrmann, André Pauwels, Pieter Faculty of Civil and Environmental Engineering Technion Israel Institute of Technology Haifa Israel Chair of Computational Modeling and Simulation Technical University of Munich Munich Germany Faculty of Built Environment Eindhoven University of Technology Eindhoven Netherlands

ISBN: (纸本)9783031353987

Automated Code Checking (ACC) can be defined as a classification task aiming to classify building objects as compliant or not compliant to a code provision at hand. While Machine Learning (ML) is a useful tool to perform such classification tasks, it presents several drawbacks and limitations. Buildings are complex compositions of instances that are related to each other by functional and topological relationships. This type of data can be easily supported by property graphs that provide a flexible representation of attributes for every instance as well as the relationships between the instances. This, together with the recent developments in the field of graph-based learning led the authors to explore a novel approach for ACC supported by Graph Neural Networks (GNN). This paper presents a new workflow that implements GNNs for ACC to leverage the advantages of ML but alleviate the limitations. We illustrate the suggested workflow by training a GNN model on a synthetic data set and using the trained classifier to check compliance of a real BIM model to accessibility requirements. The accuracy of the classifier on a test set is 86% and the accuracy of obtained results during the accessibility check is 82%. This suggests that GNNs are applicable to ACC and that classifiers trained on synthetic data can be used to classify building design provided by the industry. While the results are encouraging, they also point to the need for further research to establish the scope and boundary conditions of applying GNNs to ACC. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

TwinGen: Advanced technologies to automatically generate digital twins for operation and maintenance of existing bridges 14th

TwinGen: Advanced technologies to automatically generate dig...

引用

14th European Conference on Product and Process Modelling, ECPPM 2022

作者： Vilgertshofer, S. Mafipour, M.S. Borrmann, A. Martens, J. Blut, T. Becker, R. Blankenbach, J. Göbels, A. Beetz, J. Celik, F. Faltin, B. König, M. Computational Modeling and Simulation Technical University of Munich Germany Geodetic Institute and Chair for Computing in Civil Engineering & Geo Information Systems RWTH Aachen University Germany Design Computation RWTH Aachen University Germany Computing in Engineering Ruhr University Bochum Germany

ISBN: (纸本)9781032406732

The high effort of operating and maintaining existing infrastructure facilities resulted in a large stock of structurally deficient bridges in most industrialized countries. Today, the condition assessment of bridges is conducted mostly manually. To relieve effort and costs, the digitization and automation of conventional manual, labour-intensive methods is necessary. We interpret the ambiguously used term "digital twin" (DT) in this study as a semantic-geometric model of an existing asset (here, a bridge) that contains all information required for assessing its current condition. This paper proposes an approach to automatically generate the DT of existing bridges from point cloud data (PCD) and images captured from the structure. The PCD of the bridge is semantically segmented by means of ML techniques, and a digital model is created using parametric modeling. Subsequently, detected damages and data from existing bridge maintenance systems are linked to the model to create a full DT. This paper reports the main results of the TwinGen research project: The digital twinning process of bridges can be automated to a large extent, in order to efficiently support the maintenance process of bridges. © 2023 the Author(s).

关键词： Bridges

来源：评论

学校读者我要写书评

暂无评论

Lattice Boltzmann for linear elastodynamics: periodic problems and Dirichlet boundary conditions

arXiv

引用

arXiv 2024年

作者： Boolakee, Oliver Geier, Martin De Lorenzis, Laura Department of Mechanical and Process Engineering ETH Zürich Zürich8092 Switzerland Institute for Computational Modeling in Civil Engineering TU Braunschweig Braunschweig38106 Germany

We propose a new second-order accurate lattice Boltzmann formulation for linear elastodynamics that is stable for arbitrary combinations of material parameters under a CFL-like condition. The construction of the numerical scheme uses an equivalent first-order hyperbolic system of equations as an intermediate step, for which a vectorial lattice Boltzmann formulation is introduced. The only difference to conventional lattice Boltzmann formulations is the usage of vector-valued populations, so that all computational benefits of the algorithm are preserved. Using the asymptotic expansion technique and the notion of pre-stability structures we further establish second-order consistency as well as analytical stability estimates. Lastly, we introduce a second-order consistent initialization of the populations as well as a boundary formulation for Dirichlet boundary conditions on 2D rectangular domains. All theoretical derivations are numerically verified by convergence studies using manufactured solutions and long-term stability tests. © 2024, CC BY.

关键词： Boundary conditions

来源：评论

学校读者我要写书评

暂无评论

Dirichlet and Neumann Boundary Conditions for a Lattice Boltzmann Scheme for Linear Elastic Solids on Arbitrary Domains

SSRN

引用

SSRN 2023年

We propose novel, second-order accurate boundary formulations of Dirichlet and Neumann boundary conditions for arbitrary curved boundaries, within the scope of our recently introduced lattice Boltzmann method for linear elasticity. The proposed methodology systematically constructs and analyzes the boundary formulations on the basis of the asymptotic expansion technique;thus, it is expected to be of general applicability to boundary conditions for lattice Boltzmann formulations, well beyond the focus of this paper. For Dirichlet boundary conditions, a modified version of the bounce-back method is developed, whereas the Neumann boundary conditions are based on a novel generalized ansatz proposed in this work. The Neumann boundary formulation requires information from one additional neighbor node, for which a finite difference algorithm is introduced that enables the handling of very general boundary geometries. The theoretical derivations are verified by convergence studies using manufactured solutions, as well as by comparison with the analytical solution of the classical plate with hole problem. © 2023, The Authors. All rights reserved.

关键词： Boundary conditions

来源：评论

学校读者我要写书评

暂无评论

A Direct Effective Viscosity Approach for modeling and Simulating Bingham Fluids with the Cumulant Lattice Boltzmann Method

引用

Open Journal of Fluid Dynamics 2021年第1期11卷 34-54页

作者： Martin Geier Konstantin Kutscher Manfred Krafczyk Institute for Computational Modeling in Civil Engineering TU Braunschweig Braunschweig Germany

modeling of fluids with complex rheology in the lattice Boltzmann method (LBM) is typically realized through the introduction of an effective viscosity. For fluids with a yield stress behavior, such as so-called Bingham fluids, the effective viscosity has a singularity for low shear rates and may become negative. This is typically avoided by regularization such as Papanastasiou’s method. Here we argue that the effective viscosity model can be re-interpreted as a generalized equilibrium in which no violation of the stability constraint is observed. We implement a Bingham fluid model in a three-dimensional cumulant lattice Boltzmann framework and compare the direct analytic effective viscosity/generalized equilibrium method to the iterative approach first introduced by Vikhansky which avoids the singularity in viscosity that can arise in the analytic method. We find that both methods obtain similar results at coarse resolutions. However, at higher resolutions the accuracy of the regularized method levels off while the accuracy of the direct method continuously improves. We find that the accuracy of the proposed direct method is not limited by the singularity in viscosity indicating that a regularization is not strictly necessary.

关键词： Lattice Boltzmann Method Bingham Fluids Generalized Equilibrium

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional microstructure generation using generative adversarial neural networks in the context of continuum micromechanics

arXiv

引用

arXiv 2022年

作者： Henkes, Alexander Wessels, Henning Institute for Computational Modeling in Civil Engineering Technical University of Braunschweig Pockelsstr. 3 Braunschweig38106 Germany

Multiscale simulations are demanding in terms of computational resources. In the context of continuum micromechanics, the multiscale problem arises from the need of inferring macroscopic material parameters from the microscale. If the underlying microstructure is explicitly given by means of µCT-scans, convolutional neural networks can be used to learn the microstructure-property mapping, which is usually obtained from computational homogenization. The CNN approach provides a significant speedup, especially in the context of heterogeneous or functionally graded materials. Another application is uncertainty quantification, where many expansive evaluations are required. However, one bottleneck of this approach is the large number of training microstructures needed. This work closes this gap by proposing a generative adversarial network tailored towards three-dimensional microstructure generation. The lightweight algorithm is able to learn the underlying properties of the material from a single µCT-scan without the need of explicit descriptors. During prediction time, the network can produce unique three-dimensional microstructures with the same properties of the original data in a fraction of seconds and at consistently high quality. © 2022, CC BY.

关键词： Microstructure

来源：评论

学校读者我要写书评

暂无评论

Physics-Informed Neural Networks for Material Model Calibration from Full-Field Displacement Data

arXiv

引用

arXiv 2022年

作者： Anton, David Wessels, Henning Institute for Computational Modeling in Civil Engineering Technische Universität Braunschweig Pockelsstr. 3 Braunschweig38106 Germany

The identification of material parameters occurring in constitutive models has a wide range of applications in practice. One of these applications is the monitoring and assessment of the actual condition of infrastructure buildings, as the material parameters directly reflect the resistance of the structures to external impacts. Physics-informed neural networks (PINNs) have recently emerged as a suitable method for solving inverse problems. The advantages of this method are a straightforward inclusion of observation data. Unlike grid-based methods, such as the least square finite element method (LS-FEM) approach, no computational grid and no interpolation of the data is required. In the current work, we propose PINNs for the calibration of constitutive models from full-field displacement and global force data in a realistic regime on the example of linear elasticity. We show that conditioning and reformulation of the optimization problem play a crucial role in real-world applications. Therefore, among others, we identify the material parameters from initial estimates and balance the individual terms in the loss function. In order to reduce the dependency of the identified material parameters on local errors in the displacement approximation, we base the identification not on the stress boundary conditions but instead on the global balance of internal and external work. We demonstrate that the enhanced PINNs are capable of identifying material parameters from both experimental one-dimensional data and synthetic full-field displacement data in a realistic regime. Since displacement data measured by, e.g., a digital image correlation (DIC) system is noisy, we additionally investigate the robustness of the method to different levels of noise. © 2022, CC BY.

关键词： Inverse problems

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：