Dipl.-Ing. Lennart Linden
Dipl.-Ing. Lennart Linden
Send encrypted email via the SecureMail portal (for TUD external users only).
Chair of Computational and Experimental Solid Mechanics
Visiting address:
Zeunerbau, Room 350 George-Bähr-Straße 3c
01069 Dresden
Research
- Data-driven material modeling and simulation methods
- Application of neural networks in solid mechanics
- Embedding basic physical principles in neural networks
- ResearchGate, GoogleScholar
Teaching
- Tutorial Continuum Mechanics (main studies)
- Tutorial Finite Element Method (main studies)
- Tutorial Statics (basic studies)
Publications
2024
-
Neural network-based multiscale modeling of finite strain magneto-elasticity with relaxed convexity criteria , Mar 2024, In: Computer methods in applied mechanics and engineering. 421, 116739Electronic (full-text) versionResearch output: Contribution to journal > Research article
2023
-
Neural networks meet hyperelasticity: A guide to enforcing physics , Oct 2023, In: Journal of the Mechanics and Physics of Solids. 179, 105363Electronic (full-text) versionResearch output: Contribution to journal > Research article
-
FEANN: an efficient data-driven multiscale approach based on physics-constrained neural networks and automated data mining , 8 Feb 2023, In: Computational mechanics. 71, 5, p. 827-851, 25 p.Electronic (full-text) versionResearch output: Contribution to journal > Research article
2022
-
FEANN - An efficient data-driven multiscale approach based on physics-constrained neural networks and automated data mining , 3 Jul 2022, 22 p.Electronic (full-text) versionResearch output: Preprint/documentation/report > Preprint
-
Automated constitutive modeling of isotropic hyperelasticity based on artificial neural networks , Jan 2022, In: Computational mechanics. 69, p. 213-232, 20 p.Electronic (full-text) versionResearch output: Contribution to journal > Research article
2021
-
Thermodynamically consistent constitutive modeling of isotropic hyperelasticity based on artificial neural networks , 2021, In: Proceedings in applied mathematics and mechanics : PAMM. 21, 1, p. e202100144, 3 p.Electronic (full-text) versionResearch output: Contribution to journal > Conference article
Talks
- L. Linden, K. A. Kalina, J. Brummund, M. Kästner, Automated constitutive modeling of isotropic hyperelasticity based on artificial neural networks, 91st Annual Meeting of the International Association of Applied Mathematics and Mechanics, Online, 2021
- L. Linden, K. A. Kalina, J. Brummund, M. Kästner, Constitutive modeling of isotropic and anisotropic hyperelastic solids based on physically informed artificial neural networks, 18th European Mechanics of Materials Conference, Oxford, 2022
- L. Linden, K. A. Kalina, J. Brummund, M. Kästner, An efficient data-driven multiscale scheme based on physics-constrained neural networks and autonomous data mining, 92nd Annual Meeting of the International Association of Applied Mathematics and Mechanics, Aachen, 2022
- L. Linden, K. A. Kalina, J. Brummund, M. Kästner, An automated data-driven multiscale scheme based on physically informed neural networks, 9th GACM Colloquium on Computational Mechanics 2022, Essen, 2022
Monographs
- L. Linden, Implementierung eines datengetriebenen Algorithmus zur Simulation von Fachwerken mit nicht linear elastischem Materialverhalten, Bachelor Thesis Mathematics, 2022
- L. Linden, Datengetriebene Modellierung anisotroper Elastizität bei finiten Deformationen mittels künstlicher neuronaler Netze, Diploma Thesis Mechanical Engineering, 2020