Predicting traction return current in electric railway systems through physics-informed neural networks

Conference Paper (2022)
Author(s)

T. Kapoor (TU Delft - Railway Engineering)

H. Wang (TU Delft - Railway Engineering)

Alfredo Nunez (TU Delft - Railway Engineering)

R.P.B.J. Dollevoet (TU Delft - Railway Engineering)

Research Group
Railway Engineering
Copyright
© 2022 T. Kapoor, H. Wang, Alfredo Nunez, R.P.B.J. Dollevoet
DOI related publication
https://doi.org/10.1109/SSCI51031.2022.10022290
More Info
expand_more
Publication Year
2022
Language
English
Copyright
© 2022 T. Kapoor, H. Wang, Alfredo Nunez, R.P.B.J. Dollevoet
Research Group
Railway Engineering
Pages (from-to)
1460-1468
ISBN (print)
978-1-6654-8769-6
ISBN (electronic)
978-1-6654-8768-9
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

This paper addresses the problem of determining the distribution of the return current in electric railway traction systems. The dynamics of traction return current are simulated in all three space dimensions by informing the neural networks with the Partial Differential Equations (PDEs) known as telegraph equations. In addition, this work proposes a method of choosing optimal activation functions for training the physics-informed neural network to solve higher-dimensional PDEs. We propose a Monte Carlo based framework to choose the activation function in lower dimensions, mitigating the need for ensemble training in higher dimensions. To further strengthen the applicability of the Monte Carlo based framework, experiments are presented under two loss functions governed by L2 and L∞ norms. The presented method efficiently simulates the traction return current for electric railway systems, even for three-dimensional problems.

Files

Predicting_traction_return_cur... (pdf)
(pdf | 1.03 Mb)
- Embargo expired in 30-07-2023
License info not available