Refine
Document Type
- Article (135)
- Conference Proceeding (1)
Institute
- Institut für Strukturmechanik (ISM) (136) (remove)
Keywords
- Angewandte Mathematik (118)
- Strukturmechanik (117)
- Stochastik (17)
- Finite-Elemente-Methode (4)
- Wärmeleitfähigkeit (4)
- Biodiesel (2)
- Bruchmechanik (2)
- Elastizität (2)
- Fehlerabschätzung (2)
- Maschinelles Lernen (2)
- OA-Publikationsfonds2018 (2)
- Optimierung (2)
- Transfer learning (2)
- ANN modeling (1)
- Activation function (1)
- Angewandte Informatik (1)
- Architektur <Informatik> (1)
- Artificial Intelligence (1)
- Batterie (1)
- Bornitrid (1)
- Chirurgie (1)
- Collocation method (1)
- Computer Science Models in Engineering; Multiscale and Multiphysical Models; Scientific Computing (1)
- Computerunterstütztes Verfahren (1)
- Deep learning (1)
- Domain Adaptation (1)
- Druckluft (1)
- Energiespeicherung (1)
- Feststoff (1)
- Graphen (1)
- Graphene (1)
- Kaverne (1)
- Kollokationsmethode (1)
- MDLSM method (1)
- Mechanische Eigenschaft (1)
- MoS2 (1)
- Modellierung (1)
- Molekülstruktur (1)
- Multi-objective Evolutionary Optimization, Elitist Non- Dominated Sorting Evolution Strategy (ENSES), Sandwich Structure, Pareto-Optimal Solutions, Evolutionary Algorithm (1)
- NURBS (1)
- NURBS geometry (1)
- Nanomechanik (1)
- Nanopore (1)
- Nanoporöser Stoff (1)
- Nanoribbons, thermal conductivity (1)
- Navier–Stokes equations (1)
- Neuronales Lernen (1)
- Peridynamik (1)
- Physikalische Eigenschaft (1)
- Potential problem (1)
- Riss (1)
- Schubspannung (1)
- Stahlbau (1)
- Steifigkeit (1)
- Werkstoff (1)
- biodiesel (1)
- deep learning (1)
- diesel engines (1)
- energy form (1)
- energy, exergy (1)
- explicit time integration (1)
- extreme learning machine (1)
- machine learning (1)
- mathematical modeling (1)
- molecular dynamics (1)
- nanoreinforced composites (1)
- neural architecture search (1)
- peridynamics (1)
- randomized spectral representation (1)
- response surface methodology (1)
- support vector machine (1)
- variational principle (1)
- weak form (1)
In this work, we present a deep collocation method (DCM) for three-dimensional potential problems in non-homogeneous media. This approach utilizes a physics-informed neural network with material transfer learning reducing the solution of the non-homogeneous partial differential equations to an optimization problem. We tested different configurations of the physics-informed neural network including smooth activation functions, sampling methods for collocation points generation and combined optimizers. A material transfer learning technique is utilized for non-homogeneous media with different material gradations and parameters, which enhance the generality and robustness of the proposed method. In order to identify the most influential parameters of the network configuration, we carried out a global sensitivity analysis. Finally, we provide a convergence proof of our DCM. The approach is validated through several benchmark problems, also testing different material variations.