Results 11 to 20 of about 2,349 (245)

Stiff-PINN: Physics-Informed Neural Network for Stiff Chemical Kinetics [PDF]

The Journal of Physical Chemistry A, 2021
Recently developed physics-informed neural network (PINN) has achieved success in many science and engineering disciplines by encoding physics laws into the loss functions of the neural network, such that the network not only conforms to the measurements, initial and boundary conditions but also satisfies the governing equations.
Weiqi Ji, Weilun Qiu, Zhiyu Shi, Shaowu Pan, Sili Deng   +4 more
core   +7 more sources

Heat Transfer Modelling with Physics-Informed Neural Network (PINN)

, 2022
The numerical simulations of partial differential equations aid us in studying the nanofluid flow in the porous media, the analysis of the dispersion of pollutants, and many other physical phenomena. However, to simulate such phenomena requires tremendous computational power, and it increases with the number of parameters.
Najwa Zawani Dhamirah Mohamad, Akram Yousif, Nasiha Athira Binti Shaari, Hasreq Iskandar Mustafa, Samsul Ariffin Abdul Karim, Afza Shafie, Muhammad Izzatullah   +6 more
openaire   +3 more sources

Physics-Informed Neural Network for Solving a One-Dimensional Solid Mechanics Problem

Modelling
Our objective in this work is to demonstrate how physics-informed neural networks, a type of deep learning technology, can be utilized to examine the mechanical properties of a helicopter blade.
Vishal Singh, Dineshkumar Harursampath, Sharanjeet Dhawan, Manoj Sahni, Sahaj Saxena, Rajnish Mallick   +5 more
doaj   +2 more sources

A deep learning physics-informed neural network (PINN) for predicting drilled shaft axial capacity

Applied Computing and Geosciences
Accurately estimating the axial capacity of drilled shafts remains a persistent challenge in geotechnical engineering, as evidenced by significant discrepancies between measured load-test results and theoretical predictions.
M.E. Al-Atroush
doaj   +2 more sources

An Adaptive Weight Physics-Informed Neural Network for Vortex-Induced Vibration Problems

Buildings
Vortex-induced vibration (VIV) is a common fluid–structure interaction phenomenon in practical engineering with significant research value. Traditional methods to solve VIV issues include experimental studies and numerical simulations.
Ping Zhu, Zhonglin Liu, Ziqing Xu, Junxue Lv   +3 more
doaj   +2 more sources

Point neuron learning: a new physics-informed neural network architecture

EURASIP Journal on Audio, Speech, and Music Processing
Machine learning and neural networks have advanced numerous research domains, but challenges such as large training data requirements and inconsistent model performance hinder their application in certain scientific problems. To overcome these challenges,
Hanwen Bi, Thushara D. Abhayapala
doaj   +3 more sources

Multifidelity modeling for Physics-Informed Neural Networks (PINNs) [PDF]

Journal of Computational Physics, 2022
Multifidelity simulation methodologies are often used in an attempt to judiciously combine low-fidelity and high-fidelity simulation results in an accuracy-increasing, cost-saving way. Candidates for this approach are simulation methodologies for which there are fidelity differences connected with significant computational cost differences.
Michael Penwarden, Shandian Zhe, Akil Narayan 0001, Robert M. Kirby   +3 more
openaire   +3 more sources

Deeper-PINNs: Unlocking the power of deep physics-informed neural networks

Applied Soft Computing
Physics-Informed Neural Networks (PINNs) have emerged as a promising framework for solving partial differential equations (PDEs) and have garnered significant attention across industrial and scientific domains.
Feilong Jiang, Xiaonan Hou, Jianqiao Ye, Min Xia 0001   +3 more
openaire   +2 more sources

Physics-informed neural networks (PINNs) for fluid mechanics: a review [PDF]

Acta Mechanica Sinica, 2021
Despite the significant progress over the last 50 years in simulating flow problems using numerical discretization of the Navier-Stokes equations (NSE), we still cannot incorporate seamlessly noisy data into existing algorithms, mesh-generation is complex, and we cannot tackle high-dimensional problems governed by parametrized NSE.
Shengze Cai, Zhiping Mao, Zhicheng Wang 0018, Minglang Yin, George Em Karniadakis   +4 more
openaire   +2 more sources

Physics Informed Neural Networks (PINNs) For Approximating Nonlinear Dispersive PDEs [PDF]

Journal of Computational Mathematics, 2021
We propose a novel algorithm, based on physics-informed neural networks (PINNs) to efficiently approximate solutions of nonlinear dispersive PDEs such as the KdV-Kawahara, Camassa-Holm and Benjamin-Ono equations. The stability of solutions of these dispersive PDEs is leveraged to prove rigorous bounds on the resulting error.
Genming Bai, Ujjwal Koley, Siddhartha Mishra, Roberto Molinaro   +3 more
openaire   +2 more sources