Results 121 to 130 of about 2,349 (245)

Physics‐Informed Neural Networks for Predictive Modeling and Optimization of pH‐Triggered Drug Release from Quercetin‐Loaded Nanocomposites

ChemNanoMat, Volume 12, Issue 6, June 2026.
A physics‐informed neural network enables accurate and mechanistically consistent prediction of quercetin release from nanocomposites. Precise control of drug‐release kinetics remains a major challenge in nanomedicine, particularly for pH‐responsive delivery systems targeting the acidic tumor microenvironment. Here, we develop a physics‐informed neural
Abbas Rahdar, Sonia Fathi‐karkan, M. Ali Aboudzadeh   +2 more
wiley   +1 more source

Randomness and signal propagation in physics-informed neural networks (PINNs): a neural PDE perspective

The European Physical Journal Plus
Physics-informed neural networks (PINNs) often exhibit weight matrices that appear statistically random after training, yet their implications for signal propagation and stability remain unsatisfactorily understood, let alone the interpretability. In this work, we analyze the spectral and statistical properties of trained PINN weights using viscous and
Jean-Michel Tucny, Abhisek Ganguly, Santosh Ansumali, Sauro Succi   +3 more
openaire   +2 more sources

An introduction to programming Physics-Informed Neural Network-based computational solid mechanics

, 2023
Physics-informed neural network (PINN) has recently gained increasing interest in computational mechanics. In this work, we present a detailed introduction to programming PINN-based computational solid mechanics.
Jeong, Hyogu, Rathnayaka, C. M., Liu, Gui-Rong, Bai, Jinshuai, Xiao, Shusheng, Gu, Yuantong, Alzubaidi, Laith, Wang, Qingxia, Batuwatta-Gamage, C. P.   +8 more
core  

Defense Algorithm Based on Reinforcement Learning and Digital Twin for Distribution Protection Devices Adversarial Samples

Engineering Reports, Volume 8, Issue 6, June 2026.
Power system protection devices are vulnerable to adversarial samples. We propose a digital twin and reinforcement learning framework. It trains a virtual model within safe operational boundaries, reducing the false operation rate to below 3.5%. The model's inference delay is under 10 ms, meeting real‐time protection requirements.
Wei Zhang, Shuai Zhang, Song Wang, Zheran Zheng   +3 more
wiley   +1 more source

A Short Note on Physics-Guided GAN to Learn Physical Models without Gradients

Algorithms
This study briefly describes the concept of guided training of deep neural networks (DNNs) to learn physically reasonable solutions. The proposed method does not need the gradients of the physical equations, although the conventional physics-informed ...
Kazuo Yonekura
doaj   +1 more source

A physics-informed neural network enhanced importance sampling (PINN-IS) for data-free reliability analysis [PDF]

Reliability analysis of highly sensitive structures is crucial to prevent catastrophic failures and ensure safety. Therefore, these safety-critical systems are to be designed for extremely rare failure events. Accurate statistical quantification of these
Adhikari, Sondipon, Chatterjee, Tanmoy, Roy, Atin   +2 more
core   +1 more source

A Fuzzy‐Logic and Machine Learning‐Based Framework for Water Quality Index Classification in Extensive and Intensive Aquaculture Systems

Engineering Reports, Volume 8, Issue 6, June 2026.
This study presents an Internet of Things (IoT)‐to‐Cloud framework for real‐time monitoring and prediction of the Water Quality Index (WQI) across both extensive and intensive aquaculture systems. By integrating Fuzzy Logic biological thresholds with ML classification, the Random Forest model achieves over 99.5% accuracy in both environments ...
Mohammod Abul Kashem, Mehedi Hasan Shuvo, Shabnom Mustary, Md. Mithun Ali, Nayeem Ullah, Md. Delwar Hossain, Md. Asaduzzaman Chowdhury, Jia Uddin   +7 more
wiley   +1 more source

Physics-Informed Neural Networks for Gravitational Potential Estimation

reservedMachine learning is continuously evolving through new research and development of network architectures. One notable recent advancement is physics-informed neural networks (PINNs), which are capable of solving complex differential equations and ...
BREJC, GIOVANNI
core  

From Gauged to Ungauged: Using Catchment Morphology to Guide the Transfer of Physics‐Informed Neural Network Discharge Predictions

Hydrological Processes, Volume 40, Issue 6, June 2026.
This study develops a transferability framework that combines ensemble clustering with hybrid PINN‐GRU models for discharge prediction in ungauged catchments. Using 10 catchment morphometrics, 117 subcatchments were grouped into four clusters, achieving strong within‐cluster transferability.
Mehran Khan, Kirstie Fryirs, Lucy Marshall   +2 more
wiley   +1 more source

Diffusion Simulations for HVDC Cables Using Physics-Informed Neural Network (PINN)

This study evaluates and demonstrates the capabilities of the neural network (NN) and physics-informed neural network (PINN) to model the diffusion of chemical concentration within the geometry of High Voltage Direct Current (HVDC) cables.
Retistianto, Muhammad Farid
core   +1 more source