Suchergebnisse - "Physics-Informed Neural Networks (PINNs)"

Investigating neural networks with groundwater flow equation loss

Autoren: Vincenzo Schiano Di Cola Vittorio Bauduin Marco Berardi et al.

Quelle: Mathematics and Computers in Simulation. 230:80-93

Schlagwörter: physics-informed neural networks (PINNs), Groundwater flow, Physics-Informed Neural Networks (PINNs), Neural network optimization, Flows in porous media, filtration, seepage, neural network optimization, groundwater flow, PDEs in connection with fluid mechanics, Artificial neural networks and deep learning

Dateibeschreibung: application/xml; application/pdf

Zugangs-URL: https://zbmath.org/8031631
https://doi.org/10.1016/j.matcom.2024.10.039

Physics-Informed Neural Networks in Aerospace: A Structured Taxonomy with Literature Review

Autoren: Tkachov, Yurii Murashko, Oleh

Quelle: Challenges and Issues of Modern Science (2025)
Challenges and Issues of Modern Science

Schlagwörter: літальні апарати, аерокосмічна інженерія, Aerospace vehicles, машинне навчання, математичне моделювання, фізично-інформовані нейронні мережі (PINNs), mathematical simulation, TK1-9971, aerospace design, Environmental sciences, Machine Learning, Aerospace engineering, machine learning, aerospace engineering, Machine learning, аерокосмічне проєктування, GE1-350, Electrical engineering. Electronics. Nuclear engineering, Physics-Informed Neural Networks (PINNs), flight vehicles

Dateibeschreibung: application/pdf

Zugangs-URL: https://doaj.org/article/09d18698a0a1471cb6d664dedb8225dc

Analysis of the EMHD nanofluid flow for geothermal pipelines using physics-driven deep learning

Autoren: Faiza Waseem Saeed Islam et al.

Quelle: Scientific Reports, Vol 15, Iss 1, Pp 1-18 (2025)

Schlagwörter: Electro-magneto-hydrodynamics (EMHD), Physics-informed neural networks (PINNs), Heat transfer enhancement, Hybrid intelligent modeling, Computational fluid dynamics (CFD), Medicine, Science

Dateibeschreibung: electronic resource

Relation: https://doaj.org/toc/2045-2322

Zugangs-URL: https://doaj.org/article/c19006b89ef446278bf0be1af2a24849

Constructing hidden differential equations using a data-driven approach with the alternating direction method of multipliers (ADMM)

Autoren: Jye Ying Sia Yong Kheng Goh How Hui Liew et al.

Quelle: Electronic Research Archive, Vol 33, Iss 2, Pp 890-906 (2025)

Schlagwörter: T57-57.97, Applied mathematics. Quantitative methods, data-driven differential equations, physics-informed neural networks (pinns), QA1-939, coupled first-order ode, sparse optimization, Mathematics, alternating direction method of multipliers (admm)

Zugangs-URL: https://doaj.org/article/cbd3e92a5fad443988bed45e6b27dc93

A collocation point sampling method for solving the Helmholtz equation using physics-informed neural networks

Autoren: Lianpu SHAN Caixia YU Yanfei WANG

Quelle: Meitian dizhi yu kantan, Vol 53, Iss 9, Pp 182-190 (2025)

Schlagwörter: physics-informed neural networks (pinns), helmholtz equation, forward modeling, collocation point, adaptive distribution, Geology, QE1-996.5, Mining engineering. Metallurgy, TN1-997

Dateibeschreibung: electronic resource

Relation: https://doaj.org/toc/1001-1986

Zugangs-URL: https://doaj.org/article/4695387cc26d47e8a2d9768cc70a8164

Numerical modeling and neural network optimization for advanced solar panel efficiency

Autoren: Udit Mamodiya Indra Kishor Mohammed Amin Almaiah et al.

Quelle: Scientific Reports, Vol 15, Iss 1, Pp 1-23 (2025)

Schlagwörter: Numerical modeling, Neural network optimization, Solar panel efficiency, Physics-informed neural networks (PINNs), Reinforcement learning, Edge AI, Medicine, Science

Dateibeschreibung: electronic resource

Relation: https://doaj.org/toc/2045-2322

Zugangs-URL: https://doaj.org/article/2875e1859dbd41d3a136ad6ca6e88809

Physics-informed neural networks for robust equivalent damping parameter inversion and fault diagnosis in gas-insulated switchgear vibration systems

Autoren: Yuhang Li Yuhui Lv Yingjie Yan et al.

Quelle: Scientific Reports, Vol 15, Iss 1, Pp 1-14 (2025)

Schlagwörter: Parameter inversion, Physics-informed neural networks(PINNs), Damping vibration system, GIS fault diagnosis, Medicine, Science

Dateibeschreibung: electronic resource

Relation: https://doaj.org/toc/2045-2322

Zugangs-URL: https://doaj.org/article/2fad477ce2bf42d7a2b39eff5314e9bf

ADVANCED APPLICATIONS OF PHYSICS-INFORMED NEURAL NETWORKS (PINNS) IN R FOR SOLVING DIFFERENTIAL EQUATIONS

Autoren: Melih Agraz

Quelle: Volume: 25, Issue: 4530-541
Eskişehir Technical University Journal of Science and Technology A-Applied Sciences and Engineering

Schlagwörter: Uygulamalı Matematik (Diğer), 0103 physical sciences, Applied Mathematics (Other), Physics-Informed Neural Networks (PINNs), Differential Equations, R-programming language, Burgers' Equation, 01 natural sciences

Dateibeschreibung: application/pdf

Zugangs-URL: https://dergipark.org.tr/tr/pub/estubtda/issue/89101/1470050

Physics-Guided Neural Networks for Intraventricular Vector Flow Mapping

Autoren: Ling, Hang Jung Bru, Salomé Puig, Julia et al.

Weitere Verfasser: Ling, Hang Jung Bru, Salomé Puig, Julia et al.

Quelle: IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control. 71:1377-1388

Schlagwörter: [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], FOS: Computer and information sciences, Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Heart Ventricles, Computer Vision and Pattern Recognition (cs.CV), [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, Computer Science - Computer Vision and Pattern Recognition, [SPI.MECA.MEFL] Engineering Sciences [physics]/Mechanics [physics.med-ph]/Fluids mechanics [physics.class-ph], [SPI.MECA.MEFL]Engineering Sciences [physics]/Mechanics [physics.med-ph]/Fluids mechanics [physics.class-ph], [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Machine Learning (cs.LG), Physics-informed neural networks (PINNs), [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [SDV.MHEP.CSC]Life Sciences [q-bio]/Human health and pathology/Cardiology and cardiovascular system, Ultrasound, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Image Processing, Computer-Assisted, FOS: Electrical engineering, electronic engineering, information engineering, Vector flow imaging, Humans, Image and Video Processing (eess.IV), Physics-guided neural networks (PGNNs), [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], Electrical Engineering and Systems Science - Image and Video Processing, [SDV.MHEP.CSC] Life Sciences [q-bio]/Human health and pathology/Cardiology and cardiovascular system, Echocardiography, Doppler, Color, Artificial Intelligence (cs.AI), Echocardiography, Deep learning (DL), Color Doppler, Neural Networks, Computer, Cardiac flow, Algorithms, Blood Flow Velocity

Dateibeschreibung: application/pdf

Zugangs-URL: https://pubmed.ncbi.nlm.nih.gov/38857144
http://arxiv.org/abs/2403.13040

Robust Flow Field Reconstruction Using PINN for 3D Lagrangian Particle Tracking

Autoren: Shin, Hyungmin Schröder, Andreas

Schlagwörter: fluid flow reconstruction, SOAP optimizer, Lagrangian Particle Tracking (LPT), Physics-Informed Neural Networks (PINNs)

Zugangs-URL: https://elib.dlr.de/215584/

Solving the (3+1)D Zakharov-Kuznetsov-Burgers equation using physics-informed neural networks: Lump and soliton wave dynamics in plasma

Autoren: Md. Towhiduzzaman Md. Abdul Al Mohit A. Z. M Asaduzzaman

Quelle: Results in Physics, Vol 79, Iss , Pp 108512- (2025)

Schlagwörter: Zakharov-Kuznetsov-Burgers (ZKB) equation, Physics-informed neural networks (PINNs), Lump wave solutions, Soliton interactions, Plasma wave dynamics, Nonlinear partial differential equations, Physics, QC1-999

Dateibeschreibung: electronic resource

Relation: http://www.sciencedirect.com/science/article/pii/S2211379725004061; https://doaj.org/toc/2211-3797

Zugangs-URL: https://doaj.org/article/06df5eb8497a4571ab0818a5a4b04f8a

From the Schrödinger equation to cross section: A comprehensive PINN-based approach for elastic scattering analysis

Autoren: Vahid Mirzaei Mahmoud Abadi

Quelle: Physics Open, Vol 25, Iss , Pp 100343- (2025)

Schlagwörter: Neutron-nucleus scattering, Physics-informed neural networks (PINNs), Woods–saxon potential, Partial wave analysis, Physics, QC1-999

Dateibeschreibung: electronic resource

Relation: http://www.sciencedirect.com/science/article/pii/S2666032625000936; https://doaj.org/toc/2666-0326

Zugangs-URL: https://doaj.org/article/bb856e71a1e948d69e0bcfa8dee66c5b

Deep learning approaches for $ \beta- $conformable fractional differential equations: A PINN, NRPINN-s, and NRPINN-un based solutions

Autoren: Sadullah Bulut Muhammed Yiğider

Quelle: AIMS Mathematics, Vol 10, Iss 6, Pp 13721-13740 (2025)

Schlagwörter: physics-informed neural networks (pinns), $ \beta- $conformable fractional differential equations, nr-pinn, deep learning, Mathematics, QA1-939

Dateibeschreibung: electronic resource

Relation: https://doaj.org/toc/2473-6988

Zugangs-URL: https://doaj.org/article/329635583acc4cdc8a1714fef222b7db

Beyond p-y method: A review of artificial intelligence approaches for predicting lateral capacity of drilled shafts in clayey soils

Autoren: M.E. Al-Atroush A.E. Aboelela Ezz El-Din Hemdan

Quelle: Journal of Rock Mechanics and Geotechnical Engineering, Vol 16, Iss 9, Pp 3812-3840 (2024)

Schlagwörter: Physics-informed neural networks (PINNs), P-y curves, Laterally loaded drilled shaft, TA703-712, load transfer and failure mechanisms, Engineering geology. Rock mechanics. Soil mechanics. Underground construction, Artificial intelligence (AI), Dataset

Zugangs-URL: https://doaj.org/article/666d711e2e6743ff8705a8f3e9a91b9a

SCALABLE PHYSICS-INFORMED NEURAL SOLVERS FOR HIGH-DIMENSIONAL SCIENTIFIC SIMULATIONS IN HETEROGENEOUS COMPUTING ENVIRONMENTS ENHANCED ADAPTIVE SPARSE APPROXIMATION FRAMEWORK INTEGRATING DEEP LEARNING, FINITE ELEMENT METHODS, AND PARALLEL GPU-CPU CO-PROCESSING

Autoren: Researcher

Schlagwörter: Physics-Informed Neural Networks (PINNs), Finite Element Methods (FEM), GPU-CPU Co-processing, High-Dimensional Simulations, Adaptive Sparse Approximation, Scientific Computing

Multi-Objective Loss Balancing for Physics-Informed Deep Learning

Autoren: Bischof, Rafael Kraus, Michael Anton

Quelle: Computer Methods in Applied Mechanics and Engineering, 439

Schlagwörter: Machine Learning, Physics informed neural networks (PINNs), Multi objective optimization, Partial differential equations, Scientific machine learning, Helmholtz equation, Burgers equation, PINNacle, Loss balancing, Multi-objective optimisation

Dateibeschreibung: application/application/pdf

Zugangs-URL: http://hdl.handle.net/20.500.11850/727362

PHYSICS-INFORMED MACHINE LEARNING FOR PARAMETER IDENTIFICATION ON SHALLOW-WATER EQUATIONS

Autoren: Boulenc, Hugo Bouclier, Robin Garambois, Pierre-André et al.

Weitere Verfasser: Boulenc, Hugo Bouclier, Robin Garambois, Pierre-André et al.

Schlagwörter: Inverse Problems, Shallow-Water Equations, Parameter Identification, [MATH] Mathematics [math], Physics-Informed Neural Networks (PINNs), Data Assimilation

Zugangs-URL: https://hal.science/hal-04963071v1

Physics-Informed Neural Networks for Solving Forward and Inverse Problems in Complex Beam Systems

Autoren: Taniya Kapoor Hongrui Wang Alfredo Núnez et al.

Quelle: IEEE Transactions on Neural Networks and Learning Systems

Schlagwörter: FOS: Computer and information sciences, Computer Science - Machine Learning, Complex system, 02 engineering and technology, Numerical Analysis (math.NA), Timoshenko beam, 01 natural sciences, 0201 civil engineering, Machine Learning (cs.LG), physics-informed neural networks (PINNs), double-beam system, Euler–Bernoulli beam, FOS: Mathematics, Mathematics - Numerical Analysis, 0101 mathematics

Zugangs-URL: https://pubmed.ncbi.nlm.nih.gov/37725741
http://arxiv.org/abs/2303.01055
http://resolver.tudelft.nl/uuid:4721619c-39a4-49d4-aec7-bfba11584a4c

I-FENN for thermoelasticity based on physics-informed temporal convolutional network (PI-TCN)

Autoren: Diab W. Abueidda Mostafa E. Mobasher

Quelle: Computational Mechanics. 74:1229-1259

Schlagwörter: physics-informed neural networks (PINNs), Computational Engineering, Finance, and Science (cs.CE), FOS: Computer and information sciences, multiphysics, 0203 mechanical engineering, Mechanics of deformable solids, transient thermoelasticity, thermo-mechanical analysis, temporal convolutional networks (TCN), 02 engineering and technology, 0101 mathematics, Computer Science - Computational Engineering, Finance, and Science, 01 natural sciences

Dateibeschreibung: application/xml

Zugangs-URL: http://arxiv.org/abs/2305.17799
https://zbmath.org/7966093
https://doi.org/10.1007/s00466-024-02475-3

Strengthening Structural Dynamics for Upcoming Eurocode 8 Seismic Standards Using Physics-Informed Machine Learning

Autoren: Ahad Amini Pishro Konstantinos Daniel Tsavdaridis Yuetong Liu et al.

Quelle: Buildings, Vol 15, Iss 21, p 3960 (2025)

Schlagwörter: structural dynamics, single-degree-of-freedom (SDOF), Extended Kalman Filter (EKF), Physics-Informed Neural Networks (PINNs), Eurocode 8, optimization algorithms, Building construction, TH1-9745

Dateibeschreibung: electronic resource

Relation: https://www.mdpi.com/2075-5309/15/21/3960; https://doaj.org/toc/2075-5309

Zugangs-URL: https://doaj.org/article/d5fd10fd626d449c9ed58898b5a33691