检索结果-内蒙古大学图书馆

37th ASME International Conference on Ocean, Offshore and Arctic Engineering

作者： Mao, X. Joshi, V. Miyanawala, T. P. Jaiman, Rajeev K. Natl Univ Singapore Dept Mech Engn Singapore 117575 Singapore

ISBN: (纸本)9780791851210

Fluctuating wave force on a bluff body is of great significance in many offshore and marine engineering applications. We present a Convolutional Neural Network (CNN) based data-driven computing to predict the unsteady wave forces on bluff bodies due to the free-surface wave motion. For the full-order modeling and high-fidelity data generation, the air-water interface for such wave-body problems must be captured accurately for a broad range of physical and geometric parameters. Originated from the thermodynamically consistent theories, the physically motivated Allen-Cahn phase-field method has many advantages over other interface capturing techniques such as level-set and volume-of-fluid methods. The Allen-Cahn equation is solved in the mass-conservative form by imposing a Lagrange multiplier technique. While a tremendous amount of wave-body interaction data is generated in offshore engineering via both CFD simulations and experiments, the results are generally underutilized. Design space exploration and flow control of such practical scenarios are still time-consuming and expensive. An alternative to semi-analytical modeling, CNN is a class of deep neural network for solving inverse problems which is efficient in parametric data-driven computation and can use the domain knowledge. It establishes a model with arbitrarily generated model parameters, makes predictions using the model and existing input parametric settings, and adjusts the model parameters according to the error between the predictions and existing results. The computational cost of this prediction process, compared with high-fidelity CFD simulation, is significantly reduced, which makes CNN an accessible tool in design and optimization problems. In this study, CNN-based data-driven computing is utilized to predict the wave forces on bluff bodies with different geometries and distances to the free surface. The discrete convolution process with a non-linear rectification is employed to approximate the ma

关键词： data-driven computing CNN-based deep learning Allen-Cahn phase-field Parametric deep kernel learning Wave-structure interaction

来源：评论

学校读者我要写书评

暂无评论

An investigation on the coupling of data-driven computing and model-driven computing

引用

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 2022年 393卷

作者： Yang, Jie Huang, Wei Huang, Qun Hu, Heng Wuhan Univ Sch Civil Engn 8 South Rd East Lake Wuhan 430072 Peoples R China

The aim of this work is to investigate the coupling of data-driven (DD) computing and model-driven (MD) computing for the analyses of engineering structures. The data-driven computing was initially introduced by Kirchdoerfer and Ortiz (2016), the main idea of which is to directly embedding the experimental material data into mechanical simulations, thus bypassing the empirical material constitutive modeling. The model-driven computing in this work refers to the standard constitutive model-based simulations, which allows to benefit from its computational efficiency. The idea of this proposed DD-MD solver is to employ the data-driven computing for the local region of the solution domain where the material constitutive models are difficult to be determined, whilst the model-driven computing is applied to the remaining regions where the material models can be easily accessed. Several numerical examples are presented to demonstrate the robustness and reliability of the proposed method.(c) 2022 Elsevier B.V. All rights reserved.

关键词： data-driven computing Model-driven computing Coupling

来源：评论

学校读者我要写书评

暂无评论

Coupling of data-driven and model-driven computing within non-matching meshes

引用

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 2025年 441卷

作者： Bai, Xiaowei Yang, Jie Huang, Qun Huang, Wei Li, Huicui Damil, Noureddine Hu, Heng Wuhan Univ Sch Civil Engn 8 South Rd East Lake Wuhan 430072 Peoples R China Ningxia Univ Sch Math & Stat Yinchuan 750021 Peoples R China Hassan II Univ Casablanca Fac Sci Ben MSik Lab Ingn Mat LIMAT BP7955 Casablanca Morocco Ctr Rech Syst Complexes & Interact Cent Casablanca Bouskoura 27182 Morocco

This work aims to couple distance-minimizing data-driven computing with model-driven computing (standard constitutive model-based simulations), allowing for non-matching interfaces between computational regions meshed with both full and reduced finite elements. Specifically, data-driven (DD) computing is employed for regions where the material constitutive models are difficult to determine, whilst model-driven (MD) computing is applied to the remaining regions to take advantage of its computational efficiency. To connect non-matching interfaces, a penalty-based technique is utilized to ensure the continuity of displacements and the accurate transfer of interaction forces across these interfaces. In this manner, the proposed method becomes more versatile and practical for engineering applications, enabling separate modeling of data-driven and model-driven regions with different mesh refinements or types of elements (e.g., coarse and fine meshes, full and reduced finite elements) based on their specific needs. Several examples are provided to illustrate the effectiveness and robustness of the proposed method.

关键词： data-driven computing Non-matching meshes Coupling

来源：评论

学校读者我要写书评

暂无评论

GPM-PeNN: A generalized plasticity model-based data-driven constitutive modeling framework using physics-encoded neural network

引用

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 2025年 436卷

作者： Wang, Jingzhou Ma, Gang Qu, Tongming Guan, Shaoheng Zhou, Wei Chang, Xiaolin Wuhan Univ State Key Lab Water Resources Engn & Management Wuhan Peoples R China Wuhan Univ Inst Water Engn Sci Wuhan Peoples R China Wuhan Univ Key Lab Rock Mech Hydraul Struct Engn Minist Educ Wuhan Peoples R China Hong Kong Univ Sci & Technol Dept Civil & Environm Engn Kowloon Hong Kong Peoples R China Graz Univ Technol Inst Theoret Phys Computat Phys A-8010 Graz Styria Austria

data-driven surrogate modeling provides a new way to characterize and predict the mechanical behavior of materials. However, pure data-driven models tend to suffer from problems with stress path generalization ability. The model's performance is not stable enough especially when dealing with boundary value problems because of the various loading paths and historical influences. In this study, a physics-encoded data-driven constitutive modeling framework based on generalized plasticity, known as GPM-PeNN (Generalized Plasticity Model-based Physics-encoded Neural Network), is proposed, aiming to improve the stress path generalization ability and robustness of the model for extrapolated predictions. In this framework, the theory of generalized plasticity model is encoded as the physical priori. By leveraging generalized plasticity knowledge for task decomposition, the complex relationships of materials have been transformed into subrelations that are more easily discernible by neural networks. Additionally, the generalized plasticity theory-consistent information flow structure limits the scope of fitting in traditional constitutive modeling, enhancing the robustness. Considering the assumptions like elastoplastic decomposition and associated flow rule, this framework is suitable for the modeling of small strain elastoplastic materials. The GPM-PeNN is also embedded into the general finite element program Abaqus through UMAT subroutine to solve boundary value problems and accurately reproduce ground truth solutions. Sensitivity analysis of data quantity and noise level is conducted to evaluate the model's performance on small datasets and resistance to noise. The results show that the GPM-PeNN trained with even limited data or noisy datasets can still provide stable solutions against boundary value problems, which unequivocally demonstrates its stress path generalization ability and robustness.

关键词： Physics-encoded neural networks Constitutive modeling data-driven computing Generalized plasticity Boundary value problem

来源：评论

学校读者我要写书评

暂无评论

Computationally efficient and noise resilient data-driven mechanics via a continuous data space

引用

European Journal of Mechanics - A/Solids 2025年 113卷

作者： K. Karaca R.H.J. Peerlings M.G.D. Geers Department of Mechanical Engineering Eindhoven University of Technology 5600 MB Eindhoven The Netherlands

In this study, a continuous data space driven computational mechanics framework that enhances the original data-driven methodology is presented. The traditional data-driven approach relies on finite, discrete datasets and direct projections between the dataset and the constraint space dictated by the problem settings. The use of a discrete dataset entails accuracy problems as the dataset is inherently subject to noise and outliers. Moreover, finding the optimal datapoint in the dataset is computationally demanding especially for large sized datasets and geometrically higher dimensional problems. The proposed framework addresses these limitations by leveraging a continuous data space constructed via Gaussian mixture modeling to replace the discrete dataset. The continuous data space can be interpreted as a data density field that can be used to assess the likelihood of a point capturing the underlying material behavior. Hence the effect of noise and outlier on the solution accuracy is reduced. By eliminating search queries in the discrete dataset, the computational cost is significantly reduced as well. Moreover, the data-to-constraint space projection is conducted efficiently via a search direction deduced from the continuous data space. Numerical experiments demonstrate the capability of the framework to enhance accuracy and computational efficiency.

关键词： data-driven computing Gaussian mixture modeling Noise Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

A physics-informed GAN framework based on model-free data-driven computational mechanics

引用

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 2024年 424卷

作者： Ciftcei, Kerem Hackl, Klaus Ruhr Univ Bochum Inst Mech Mat Univ Str 150 D-44801 Bochum Germany

Model -free data -driven computational mechanics, first proposed by Kirchdoerfer and Ortiz, replace phenomenological models with numerical simulations based on sample datasets in strain-stress space. In this study, we integrate this paradigm within physics -informed generative adversarial networks (GANs). We enhance the conventional physics -informed neural network framework by implementing the principles of data -driven computational mechanics into GANs. Specifically, the generator is informed by physical constraints, while the discriminator utilizes the closest strain-stress data to discern the authenticity of the generator's output. This combined approach presents a new formalism to harness data -driven mechanics and deep learning to simulate and predict mechanical behaviors.

关键词： Model-free data-driven Generative adversarial networks data-driven computing Physics-informed neural networks

来源：评论

学校读者我要写书评

暂无评论

Model-Free data-driven inelasticity

引用

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 2019年第Jun.15期350卷 81-99页

作者： Eggersmann, R. Kirchdoerfer, T. Reese, S. Stainier, L. Ortiz, M. Rhein Westfal TH Aachen Inst Appl Mech Mies van der Rohe Str 1 D-52074 Aachen Germany CALTECH Div Engn & Appl Sci 1200 E Calif Blvd Pasadena CA 91125 USA Ecole Cent Nantes UMR 6183 CNRS ECN UN Inst Civil & Mech Engn 1 Rue Noe F-44321 Nantes France

We extend the data-driven formulation of problems in elasticity of Kirchdoerfer and Ortiz (2016) to inelasticity. This extension differs fundamentally from data-driven problems in elasticity in that the material data set evolves in time as a consequence of the history dependence of the material. We investigate three representational paradigms for the evolving material data sets: (i) materials with memory, i. e., conditioning the material data set to the past history of deformation;(ii) differential materials, i. e., conditioning the material data set to short histories of stress and strain;and (iii) history variables, i. e., conditioning the material data set to ad hoc variables encoding partial information about the history of stress and strain. We also consider combinations of the three paradigms thereof and investigate their ability to represent the evolving data sets of different classes of inelastic materials, including viscoelasticity, viscoplasticity and plasticity. We present selected numerical examples that demonstrate the range and scope of data-driven inelasticity and the numerical performance of implementations thereof. (C) 2019 Elsevier B.V. All rights reserved.

关键词： data-driven computing Inelasticity Viscoelasticity Plasticity

来源：评论

学校读者我要写书评

暂无评论

A constraint-driven approach to food supply chain management

引用

INDUSTRIAL MANAGEMENT & data SYSTEMS 2017年第9期117卷 2115-2138页

作者： Sitek, Pawel Wikarek, Jaroslaw Nielsen, Peter Kielce Univ Technol Dept Informat Syst Kielce Poland Aalborg Univ Dept Mech & Mfg Engn Aalborg Denmark

Purpose - The purpose of this paper is the need to build a novel approach that would allow flexible modeling and solving of food supply chain management (FSCM) problems. The models developed would use the data (data-driven modeling) as early as possible at the modeling phase, which would lead to a better and more realistic representation of the problems being modeled. Design/methodology/approach - An essential feature of the presented approach is its declarativeness. The use of a declarative approach that additionally includes constraint satisfaction problems and provides an opportunity of fast and easy modeling of constrains different in type and character. Implementation of the proposed approach was performed with the use of an original hybrid method in which constraint logic programming (CLP) and mathematical programming (MP) are integrated and transformation of a model is used as a presolving technique. Findings - The proposed constraint-driven approach has proved to be extremely flexible and efficient. The findings obtained during part of experiments dedicated to efficiency were very interesting. The use of the constraint-driven approach has enabled finding a solution depending on the instance data up to 1,000 times faster than using the MP. Research limitations/implications - Due to the limited use of exact methods for NP-hard problems, the future study should be to integrate the CLP with environments other than the MP. It is also possible, e.g., with metaheuristics like genetic algorithms, ant colony optimization, etc. Practical implications - There is a possibility of using the approach as a basis to build a decision support system for FSCM, simple integration with databases, enterprise resource planning systems, management information systems, etc. Originality/value - The new constraint-driven approach to FSCM has been proposed. The proposed approach is an extension of the hybrid approach. Also, a new decision-making model of distribution and logistics for

关键词： Mathematical programming Decision support Food supply chain management Constraint logic programming Constraint satisfaction problem data-driven computing

来源：评论

学校读者我要写书评

暂无评论

A physics-constrained data-driven approach based on locally convex reconstruction for noisy database

引用

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 2020年 363卷 112791-000页

作者： He, Qizhi Chen, Jiun-Shyan Univ Calif San Diego Dept Struct Engn La Jolla CA 92093 USA

Physics-constrained data-driven computing is an emerging hybrid approach that integrates universal physical laws with data-driven models of experimental data for scientific computing. A new data-driven simulation approach coupled with a locally convex reconstruction, termed the local convexity data-driven (LCDD) computing, is proposed to enhance accuracy and robustness against noise and outliers in data sets in the data-driven computing. In this approach, for a given state obtained by the physical simulation, the corresponding optimum experimental solution is sought by projecting the state onto the associated local convex manifold reconstructed based on the nearest experimental data. This learning process of local data structure is less sensitive to noisy data and consequently yields better accuracy. A penalty relaxation is also introduced to recast the local learning solver in the context of non-negative least squares that can be solved effectively. The reproducing kernel approximation with stabilized nodal integration is employed for the solution of the physical manifold to allow reduced stress-strain data at the discrete points for enhanced effectiveness in the LCDD learning solver. Due to the inherent manifold learning properties, LCDD performs well for high-dimensional data sets that are relatively sparse in real-world engineering applications. Numerical tests demonstrated that LCDD enhances nearly one order of accuracy compared to the standard distance-minimization data-driven scheme when dealing with noisy database, and a linear exactness is achieved when local stress-strain relation is linear. (C) 2019 Elsevier B.V. All rights reserved.

关键词： data-driven computing Locally convex reconstruction Manifold learning Noisy data Local convexity data-driven (LCDD) Reproducing kernel (RK) approximation

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional data-driven magnetostatic field computation using real-world measurement data

引用

COMPEL-THE INTERNATIONAL JOURNAL FOR COMPUTATION AND MATHEMATICS IN ELECTRICAL AND ELECTRONIC ENGINEERING 2022年第2期41卷 615-627页

作者： Galetzka, Armin Loukrezis, Dimitrios De Gersem, Herbert Tech Univ Darmstadt Inst Accelerator Sci & Electromagnet Fields Darmstadt Germany Tech Univ Darmstadt Ctr Computat Engn Darmstadt Germany

Purpose The purpose of this paper is to present the applicability of data-driven solvers to computationally demanding three-dimensional problems and their practical usability when using real-world measurement data. Design/methodology/approach Instead of using a hard-coded phenomenological material model within the solver, the data-driven computing approach reformulates the boundary value problem such that the field solution is directly computed on raw measurement data. The data-driven formulation results in a double minimization problem based on Lagrange multipliers, where the sought solution must conform to Maxwell's equations while at the same time being as close as possible to the available measurement data. The data-driven solver is applied to a three-dimensional model of a direct current electromagnet. Findings Numerical results for data sets of increasing cardinality verify that the data-driven solver recovers the conventional solution. Additionally, the practical usability of the solver is shown by using real-world measurement data. This work concludes that the data-driven magnetostatic finite element solver is applicable to computationally demanding three-dimensional problems, as well as in cases where a prescribed material model is not available. Originality/value Although the mathematical derivation of the data-driven problem is well presented in the referenced papers, the application to computationally demanding real-world problems, including real measurement data and its rigorous discussion, is missing. The presented work closes this gap and shows the applicability of data-driven solvers to challenging, real-world test cases.

关键词： Electromagnetic fields Finite element method Computational electromagnetics Three-dimensional electromagnetic field simulation data-driven computing data science Finite element analysis Magnetic materials Scientific computing

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：