Results 81 to 90 of about 2,349 (245)

Evolution of physics-informed neural networks: Recent architectural variants and optimization strategies

Array
Physics-Informed Neural Networks (PINNs) are a machine learning technique that directly incorporates the governing physics of problems, such as partial differential equations (PDEs) and ordinary differential equations (ODEs), into the neural network ...
Ahmad, Husna Zafar, Aneeqa Zafar, Muhammad Noveel Sadiq, A.K. Awasthi, Homan Emadifar, Karim K. Ahmed   +6 more
doaj   +1 more source

Data‐driven simulation of crude distillation using Aspen HYSYS and comparative machine learning models

The Canadian Journal of Chemical Engineering, EarlyView.
Integrated Aspen HYSYS–machine learning framework for predicting product yields and quality variables. Abstract Crude oil refining is a complex process requiring precise modelling to optimize yield, quality, and efficiency. This study integrates Aspen HYSYS® simulations with machine learning techniques to develop predictive models for key refinery ...
Aldimiro Paixão Domingos, Heleno Bispo, Thiago Vaz da Costa, Sérgio Mauro da Silva Neiro   +3 more
wiley   +1 more source

Weighted physics-informed neural network (weighted PINN) for obtaining elastic responses under Hertzian-like contact

Friction
Physics-informed neural network (PINN) provides a novel method for understanding the mechanical behavior of tribology contacts, and the deformation of the contacting body plays a pivotal role in determining the contact scenario of dry and ...
Yang Zhao, Zhongxue Fu, Jianfeng Zhao
doaj   +1 more source

AI‐Enabled Precision Dosing in Pediatrics: Enhancing Model‐Informed Decision Making

Clinical Pharmacology &Therapeutics, EarlyView.
Ensuring safe and effective pharmacotherapy for children remains a central challenge in clinical pharmacology, yet rapid advances in AI have not translated into clinical practice. This Perspective highlights how AI‐enabled approaches can enhance model‐informed decision making for precision dosing.
Kei Irie, Tomoyuki Mizuno
wiley   +1 more source

Stability Evaluation and Parametric Optimization of Coal‐Concrete Composite Bearing Systems Under Mine‐Water‐Induced Deterioration: Experiments and FEINN Analysis

Energy Science &Engineering, EarlyView.
Mine‐water immersion tests reveal pronounced coal weakening (vs. minor concrete degradation), identifying coal pillars as the stability‐limiting component in composite dams. A coupled FEINN framework quantifies extreme‐pressure stability and ranks multi‐parameter designs via a normalized multi‐indicator scheme, enabling optimized dam configuration for ...
He Wen, Hongchuan Dai, Guixin Zhang, Pengzhe Li, Tong Yang, Cang Gong, Renbo Gao   +6 more
wiley   +1 more source

A Comprehensive Review of AI‐Powered Energy Systems

Energy Science &Engineering, EarlyView.
The role of Artificial Intelligence (AI) in developing next‐generation energy systems is getting more day by day. Therefore, incorporating AI enables real‐time decision‐making and advanced grid management, which are essential for optimizing the use of intermittent renewable sources like wind and solar power.
Armin Razmjoo, Pedram Asef, Masoumeh Javadi, Mousa Marzband, Shady S. Refaat, Muhyaddin Rawa   +5 more
wiley   +1 more source

A PINN framework for inverse physical design of metal-loaded electromagnetic devices

AIP Advances
To solve the difficulty of inverse design of metal-loaded electromagnetic devices, we propose a physics-informed neural network (PINN) framework. With the emergence of PINNs, some scholars within the field of electromagnetism have utilized them to design
Yu-Hang Liu, Jin-Pin Liu, Bing-Zhong Wang, Ren Wang   +3 more
doaj   +1 more source

SDD-PINN: Physics-informed neural network for single droplet drying

Digital Chemical Engineering
Single droplet drying, a fundamental process in spray drying, presents a challenging nonlinear moving boundary diffusion problem. This process is described by a parabolic partial differential equation in a shrinking spherical domain with a Robin mass ...
Narjes Malekjani, Andreas Bück, Abdolreza Kharaghani, Evangelos Tsotsas   +3 more
doaj   +1 more source

MRF-PINN: A Multi-Receptive-Field convolutional physics-informed neural network for solving partial differential equations

, 2022
Compared with conventional numerical approaches to solving partial differential equations (PDEs), physics-informed neural networks (PINN) have manifested the capability to save development effort and computational cost, especially in scenarios of ...
Zhang, Shihong, Wang, Bosen, Zhang, Chi
core  

Fourier Shell Analysis: k‐Space‐Based Metrics for Assessing Super‐Resolution in 4D Flow MRI

Magnetic Resonance in Medicine, EarlyView.
ABSTRACT Purpose To support the emerging field of super‐resolution (SR) in 4D flow MRI by proposing Fourier shell analysis to disentangle resolution enhancement from denoising effects during evaluation. Methods A thoracic aortic 4D flow MRI dataset was synthesized with various degrees of stenosis, providing ground truth flow fields generated using ...
Luuk Jacobs, Pietro Dirix, Sebastian Kozerke   +2 more
wiley   +1 more source