Physics informed neural network for charged particles surrounded by conductive boundaries

2023/01/05 by Fatemeh Hafezianzade, Hafezianzade, Fatemeh, Morad Biagooi +3 · 1 citation
Computer Science · Engineering · Physics and Astronomy · #Computational Physics (physics.comp-ph) #FOS: Physical sciences #Materials Science (cond-mat.mtrl-sci) #Mathematical Physics (math-ph) #Model Reduction and Neural Networks #Neural Networks and Applications #Non-Destructive Testing Techniques

paper · pdf · doi:10.48550/arxiv.2301.02191

openalex publication_date 2023/01/05 · openalex created_date 2023/01/08 · openalex updated_date 2026/07/28

Abstract

In this paper, we developed a new PINN-based model to predict the potential of point-charged particles surrounded by conductive walls. As a result of the proposed physics-informed neural network model, the mean square error and R2 score are less than 7% and more than 90% for the corresponding example simulation, respectively. Results have been compared with typical neural networks and random forest as a standard machine learning algorithm. The R2 score of the random forest model was 70%, and a standard neural network could not be trained well. Besides, computing time is significantly reduced compared to the finite element solver.

Cited by

• Electrostatics from Laplacian Eigenbasis for Neural Network Interatomic Potentials

Related

• Boundary-Decoder network for inverse prediction of capacitor electrostatic analysis
• Deep learning in physics: a study of dielectric quasi-cubic particles in a uniform electric field
• Neural Network Potentials: A Concise Overview of Methods
• Physics-Guided, Physics-Informed, and Physics-Encoded Neural Networks in Scientific Computing
• Physics-informed ConvNet: Learning Physical Field from a Shallow Neural Network