Suchergebnisse - "Rabczuk, Timon"
-
1
Transfer learning enhanced physics informed neural network for phase-field modeling of fracture
ISSN: 0167-8442, 1872-7638Veröffentlicht: Amsterdam Elsevier Ltd 01.04.2020Veröffentlicht in Theoretical and applied fracture mechanics (01.04.2020)“… •First physic informed neural network for phase field modeling of fracture.•The model treats the problem one level higher on the model hierarchy than classical …”
Volltext
Journal Article -
2
A peridynamics formulation for quasi-static fracture and contact in rock
ISSN: 0013-7952, 1872-6917Veröffentlicht: Elsevier B.V 20.07.2017Veröffentlicht in Engineering geology (20.07.2017)“… We present a dual-horizon peridynamics (DH-PD) formulation for fracture in granular and rock-like materials. In contrast to discrete crack methods such as …”
Volltext
Journal Article -
3
Dual-horizon peridynamics
ISSN: 0029-5981, 1097-0207Veröffentlicht: Bognor Regis Blackwell Publishing Ltd 21.12.2016Veröffentlicht in International journal for numerical methods in engineering (21.12.2016)“… Summary In this paper, we develop a dual‐horizon peridynamics (DH‐PD) formulation that naturally includes varying horizon sizes and completely solves the …”
Volltext
Journal Article -
4
An efficient optimization approach for designing machine learning models based on genetic algorithm
ISSN: 0941-0643, 1433-3058Veröffentlicht: London Springer London 01.03.2021Veröffentlicht in Neural computing & applications (01.03.2021)“… Machine learning (ML) methods have shown powerful performance in different application. Nonetheless, designing ML models remains a challenge and requires …”
Volltext
Journal Article -
5
Phase field modeling of brittle compressive-shear fractures in rock-like materials: A new driving force and a hybrid formulation
ISSN: 0045-7825, 1879-2138Veröffentlicht: Amsterdam Elsevier B.V 01.10.2019Veröffentlicht in Computer methods in applied mechanics and engineering (01.10.2019)“… Compressive-shear fracture is commonly observed in rock-like materials. However, this fracture type cannot be captured by current phase field models (PFMs), …”
Volltext
Journal Article -
6
Artificial Neural Network Methods for the Solution of Second Order Boundary Value Problems
ISSN: 1546-2226, 1546-2218, 1546-2226Veröffentlicht: Henderson Tech Science Press 2019Veröffentlicht in Computers, materials & continua (2019)“… We present a method for solving partial differential equations using artificial neural networks and an adaptive collocation strategy. In this procedure, a …”
Volltext
Journal Article -
7
Application of silicene, germanene and stanene for Na or Li ion storage: A theoretical investigation
ISSN: 0013-4686, 1873-3859Veröffentlicht: Elsevier Ltd 20.09.2016Veröffentlicht in Electrochimica acta (20.09.2016)“… [Display omitted] Silicene, germanene and stanene likely to graphene are atomic thick material with interesting properties. We employed first-principles …”
Volltext
Journal Article -
8
A Deep Collocation Method for the Bending Analysis of Kirchhoff Plate
ISSN: 1546-2226, 1546-2218, 1546-2226Veröffentlicht: Henderson Tech Science Press 2019Veröffentlicht in Computers, materials & continua (2019)“… In this paper, a deep collocation method (DCM) for thin plate bending problems is proposed. This method takes advantage of computational graphs and …”
Volltext
Journal Article -
9
Optimizing the neural network hyperparameters utilizing genetic algorithm
ISSN: 1673-565X, 1862-1775Veröffentlicht: Hangzhou Zhejiang University Press 01.06.2021Veröffentlicht in Journal of Zhejiang University. A. Science (01.06.2021)“… Neural networks (NNs), as one of the most robust and efficient machine learning methods, have been commonly used in solving several problems. However, choosing …”
Volltext
Journal Article -
10
Borophene as an anode material for Ca, Mg, Na or Li ion storage: A first-principle study
ISSN: 0378-7753, 1873-2755Veröffentlicht: Elsevier B.V 15.10.2016Veröffentlicht in Journal of power sources (15.10.2016)“… Borophene, the boron atom analogue to graphene, being atomic thick have been just recently experimentally fabricated. In this work, we employ first-principles …”
Volltext
Journal Article -
11
High correlated variables creator machine: Prediction of the compressive strength of concrete
ISSN: 0045-7949, 1879-2243Veröffentlicht: New York Elsevier Ltd 15.04.2021Veröffentlicht in Computers & structures (15.04.2021)“… •High correlated creator variables (HCVCM) uses functions to create stronger inputs.•A case study with two inputs and one output was solved.•The effect of …”
Volltext
Journal Article -
12
Anisotropic mechanical properties and strain tuneable band-gap in single-layer SiP, SiAs, GeP and GeAs
ISSN: 1386-9477, 1873-1759Veröffentlicht: Elsevier B.V 01.09.2018Veröffentlicht in Physica. E, Low-dimensional systems & nanostructures (01.09.2018)“… Group IV–V-type two-dimensional (2D) materials, such as GeP, GeAs, SiP and SiAs with anisotropic atomic structures, have recently attracted remarkable …”
Volltext
Journal Article -
13
Subdivision-based isogeometric analysis for second order partial differential equations on surfaces
ISSN: 0178-7675, 1432-0924Veröffentlicht: Berlin/Heidelberg Springer Berlin Heidelberg 01.11.2021Veröffentlicht in Computational mechanics (01.11.2021)“… We investigate the isogeometric analysis approach based on the extended Catmull–Clark subdivision for solving the PDEs on surfaces. As a compatible technique …”
Volltext
Journal Article -
14
A Survey of Deep Learning Techniques: Application in Wind and Solar Energy Resources
ISSN: 2169-3536, 2169-3536Veröffentlicht: Piscataway IEEE 2019Veröffentlicht in IEEE access (2019)“… Nowadays, learning-based modeling system is adopted to establish an accurate prediction model for renewable energy resources. Computational Intelligence (CI) …”
Volltext
Journal Article -
15
Stochastic analysis of the fracture toughness of polymeric nanoparticle composites using polynomial chaos expansions
ISSN: 0376-9429, 1573-2673Veröffentlicht: Dordrecht Springer Netherlands 01.08.2017Veröffentlicht in International journal of fracture (01.08.2017)“… The fracture energy is a substantial material property that measures the ability of materials to resist crack growth. The reinforcement of the epoxy polymers …”
Volltext
Journal Article -
16
Stochastic deep collocation method based on neural architecture search and transfer learning for heterogeneous porous media
ISSN: 0177-0667, 1435-5663Veröffentlicht: London Springer London 01.12.2022Veröffentlicht in Engineering with computers (01.12.2022)“… We present a stochastic deep collocation method (DCM) based on neural architecture search (NAS) and transfer learning for heterogeneous porous media. We first …”
Volltext
Journal Article -
17
Isogeometric analysis: An overview and computer implementation aspects
ISSN: 0378-4754, 1872-7166Veröffentlicht: Elsevier B.V 01.11.2015Veröffentlicht in Mathematics and computers in simulation (01.11.2015)“… Isogeometric analysis (IGA) represents a recently developed technology in computational mechanics that offers the possibility of integrating methods for …”
Volltext
Journal Article -
18
Thermal conductivity and mechanical properties of nitrogenated holey graphene
ISSN: 0008-6223, 1873-3891Veröffentlicht: Elsevier Ltd 01.09.2016Veröffentlicht in Carbon (New York) (01.09.2016)“… Nitrogenated holey graphene (NHG), a two-dimensional graphene-derived material with a C2N stoichiometry and evenly distributed holes and nitrogen atoms in its …”
Volltext
Journal Article -
19
A simple and robust three-dimensional cracking-particle method without enrichment
ISSN: 0045-7825, 1879-2138Veröffentlicht: Kidlington Elsevier B.V 01.08.2010Veröffentlicht in Computer methods in applied mechanics and engineering (01.08.2010)“… A new robust and efficient approach for modeling discrete cracks in meshfree methods is described. The method is motivated by the cracking-particle method …”
Volltext
Journal Article -
20
State of the Art of Machine Learning Models in Energy Systems, a Systematic Review
ISSN: 1996-1073, 1996-1073Veröffentlicht: Basel MDPI AG 01.04.2019Veröffentlicht in Energies (Basel) (01.04.2019)“… Machine learning (ML) models have been widely used in the modeling, design and prediction in energy systems. During the past two decades, there has been a …”
Volltext
Journal Article