Physics-informed Neural Networks (PINN) for computational solid mechanics: Numerical frameworks and applications

Thin-Walled Structures, Journal Year: 2024, Volume and Issue: 205, P. 112495 - 112495

Published: Sept. 24, 2024

Language: Английский

---

Inverse design of phononic meta-structured materials

Materials Today, Journal Year: 2024, Volume and Issue: 80, P. 824 - 855

Published: Oct. 4, 2024

Language: Английский

---

The Application of Physics-Informed Machine Learning in Multiphysics Modeling in Chemical Engineering

Industrial & Engineering Chemistry Research, Journal Year: 2023, Volume and Issue: 62(44), P. 18178 - 18204

Published: Oct. 26, 2023

Physics-Informed Machine Learning (PIML) is an emerging computing paradigm that offers a new approach to tackle multiphysics modeling problems prevalent in the field of chemical engineering. These often involve complex transport processes, nonlinear reaction kinetics, and coupling. This Review provides detailed account main contributions PIML with specific emphasis on momentum transfer, heat mass reactions. The progress method development (e.g., algorithm architecture), software libraries, applications coupling surrogate modeling) are detailed. On this basis, future challenges highlight importance developing more practical solutions strategies for PIML, including turbulence models, domain decomposition, training acceleration, modeling, hybrid geometry module creation.

Language: Английский

---

Dynamically configured physics-informed neural network in topology optimization applications

Computer Methods in Applied Mechanics and Engineering, Journal Year: 2024, Volume and Issue: 426, P. 117004 - 117004

Published: April 26, 2024

Language: Английский

---

Energy-based physics-informed neural network for frictionless contact problems under large deformation

Computer Methods in Applied Mechanics and Engineering, Journal Year: 2025, Volume and Issue: 437, P. 117787 - 117787

Published: Jan. 30, 2025

Language: Английский

---

Maximizing Triboelectric Nanogenerators by Physics‐Informed AI Inverse Design

Advanced Materials, Journal Year: 2023, Volume and Issue: 36(5)

Published: Dec. 7, 2023

Abstract Triboelectric nanogenerators offer an environmentally friendly approach to harvesting energy from mechanical excitations. This capability has made them widely sought‐after as efficient, renewable, and sustainable source, with the potential decrease reliance on traditional fossil fuels. However, developing triboelectric specific output remains a challenge mainly due uncertainties associated their complex designs for real‐life applications. Artificial intelligence‐enabled inverse design is powerful tool realize performance‐oriented nanogenerators. emerging scientific direction that can address concerns about optimization of leading next generation nanogenerator systems. perspective paper aims at reviewing principal analysis triboelectricity, summarizing current challenges designing optimizing nanogenerators, highlighting physics‐informed strategies develop Strategic particularly discussed in contexts expanding four‐mode analytical models by artificial intelligence, discovering new conductive dielectric materials, contact interfaces. Various development levels intelligence‐enhanced are delineated. Finally, intelligence propel prototypes multifunctional intelligent systems applications discussed.

Language: Английский

---

Optimal multiple tuned mass dampers for monopile supported offshore wind turbines using Genetic Algorithm

Ocean Engineering, Journal Year: 2024, Volume and Issue: 298, P. 117356 - 117356

Published: March 1, 2024

Language: Английский

---

Machine Learning in Biomaterials, Biomechanics/Mechanobiology, and Biofabrication: State of the Art and Perspective

Archives of Computational Methods in Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: May 4, 2024

Abstract In the past three decades, biomedical engineering has emerged as a significant and rapidly growing field across various disciplines. From an perspective, biomaterials, biomechanics, biofabrication play pivotal roles in interacting with targeted living biological systems for diverse therapeutic purposes. this context, silico modelling stands out effective efficient alternative investigating complex interactive responses vivo. This paper offers comprehensive review of swiftly expanding machine learning (ML) techniques, empowering to develop cutting-edge treatments addressing healthcare challenges. The categorically outlines different types ML algorithms. It proceeds by first assessing their applications covering such aspects data mining/processing, digital twins, data-driven design. Subsequently, approaches are scrutinised studies on mono-/multi-scale biomechanics mechanobiology. Finally, extends techniques bioprinting biomanufacturing, encompassing design optimisation situ monitoring. Furthermore, presents typical ML-based implantable devices, including tissue scaffolds, orthopaedic implants, arterial stents. challenges perspectives illuminated, providing insights academia, industry, professionals further apply strategies future studies.

Language: Английский

---

A systematic and bibliometric review on physics-based neural networks applications as a solution for structural engineering partial differential equations

Structures, Journal Year: 2024, Volume and Issue: 69, P. 107361 - 107361

Published: Oct. 1, 2024

Language: Английский

---

An advanced physics-informed neural network-based framework for nonlinear and complex topology optimization

Engineering Structures, Journal Year: 2024, Volume and Issue: 322, P. 119194 - 119194

Published: Oct. 30, 2024

Language: Английский

---