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

Taniya Kapoor; Hongrui  Wang; Alfredo Nunez; Rolf Dollevoet

doi:10.1109/SSCI51031.2022.10022290

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

Taniya Kapoor, Hongrui Wang, Alfredo Nunez, Rolf Dollevoet

Railway Engineering

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

1 Citation (Scopus)

26 Downloads (Pure)

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.

Original language	English
Title of host publication	Proceedings of the 2022 IEEE Symposium Series on Computational Intelligence (SSCI)
Editors	Hisao Ishibuchi, Chee-Keong Kwoh, Ah-Hwee Tan, Dipti Srinivasan, Chunyan Miao, Anupam Trivedi, Keeley Crockett
Place of Publication	Piscataway
Publisher	IEEE
Pages	1460-1468
Number of pages	9
ISBN (Electronic)	978-1-6654-8768-9
ISBN (Print)	978-1-6654-8769-6
DOIs	https://doi.org/10.1109/SSCI51031.2022.10022290
Publication status	Published - 2022
Event	2022 IEEE Symposium Series on Computational Intelligence (SSCI) - Singapore, Singapore Duration: 4 Dec 2022 → 7 Dec 2022

Conference

Conference	2022 IEEE Symposium Series on Computational Intelligence (SSCI)
Abbreviated title	SSCI 2022
Country/Territory	Singapore
City	Singapore
Period	4/12/22 → 7/12/22

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

Traction return current
electric railway systems
physics-informed neural networks
Monte Carlo
activation functions

Access to Document

10.1109/SSCI51031.2022.10022290

Predicting_traction_return_current_in_electric_railway_systems_through_physics-informed_neural_networksFinal published version, 978 KB

Cite this

Kapoor, T., Wang, H., Nunez, A., & Dollevoet, R. (2022). Predicting traction return current in electric railway systems through physics-informed neural networks. In H. Ishibuchi, C.-K. Kwoh, A.-H. Tan, D. Srinivasan, C. Miao, A. Trivedi, & K. Crockett (Eds.), Proceedings of the 2022 IEEE Symposium Series on Computational Intelligence (SSCI) (pp. 1460-1468). IEEE. https://doi.org/10.1109/SSCI51031.2022.10022290

Kapoor, Taniya ; Wang, Hongrui ; Nunez, Alfredo et al. / Predicting traction return current in electric railway systems through physics-informed neural networks. Proceedings of the 2022 IEEE Symposium Series on Computational Intelligence (SSCI). editor / Hisao Ishibuchi ; Chee-Keong Kwoh ; Ah-Hwee Tan ; Dipti Srinivasan ; Chunyan Miao ; Anupam Trivedi ; Keeley Crockett. Piscataway : IEEE, 2022. pp. 1460-1468

@inproceedings{024b5acb287e4fcb8c5ba8f8891ed75d,

title = "Predicting traction return current in electric railway systems through physics-informed neural networks",

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.",

keywords = "Traction return current, electric railway systems, physics-informed neural networks, Monte Carlo, activation functions",

author = "Taniya Kapoor and Hongrui Wang and Alfredo Nunez and Rolf Dollevoet",

note = "Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.; 2022 IEEE Symposium Series on Computational Intelligence (SSCI), SSCI 2022 ; Conference date: 04-12-2022 Through 07-12-2022",

year = "2022",

doi = "10.1109/SSCI51031.2022.10022290",

language = "English",

isbn = "978-1-6654-8769-6",

pages = "1460--1468",

editor = "Ishibuchi, {Hisao } and Kwoh, {Chee-Keong } and Tan, {Ah-Hwee } and Dipti Srinivasan and Miao, {Chunyan } and Trivedi, {Anupam } and Crockett, {Keeley }",

booktitle = "Proceedings of the 2022 IEEE Symposium Series on Computational Intelligence (SSCI)",

publisher = "IEEE",

address = "United States",

}

Kapoor, T , Wang, H , Nunez, A & Dollevoet, R 2022, Predicting traction return current in electric railway systems through physics-informed neural networks. in H Ishibuchi, C-K Kwoh, A-H Tan, D Srinivasan, C Miao, A Trivedi & K Crockett (eds), Proceedings of the 2022 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE, Piscataway, pp. 1460-1468, 2022 IEEE Symposium Series on Computational Intelligence (SSCI), Singapore, Singapore, 4/12/22. https://doi.org/10.1109/SSCI51031.2022.10022290

Predicting traction return current in electric railway systems through physics-informed neural networks. / Kapoor, Taniya ; Wang, Hongrui ; Nunez, Alfredo et al.
Proceedings of the 2022 IEEE Symposium Series on Computational Intelligence (SSCI). ed. / Hisao Ishibuchi; Chee-Keong Kwoh; Ah-Hwee Tan; Dipti Srinivasan; Chunyan Miao; Anupam Trivedi; Keeley Crockett. Piscataway: IEEE, 2022. p. 1460-1468.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Predicting traction return current in electric railway systems through physics-informed neural networks

AU - Kapoor, Taniya

AU - Wang, Hongrui

AU - Nunez, Alfredo

AU - Dollevoet, Rolf

N1 - Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2022

Y1 - 2022

N2 - 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.

AB - 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.

KW - Traction return current

KW - electric railway systems

KW - physics-informed neural networks

KW - Monte Carlo

KW - activation functions

UR - http://www.scopus.com/inward/record.url?scp=85147798124&partnerID=8YFLogxK

U2 - 10.1109/SSCI51031.2022.10022290

DO - 10.1109/SSCI51031.2022.10022290

M3 - Conference contribution

SN - 978-1-6654-8769-6

SP - 1460

EP - 1468

BT - Proceedings of the 2022 IEEE Symposium Series on Computational Intelligence (SSCI)

A2 - Ishibuchi, Hisao

A2 - Kwoh, Chee-Keong

A2 - Tan, Ah-Hwee

A2 - Srinivasan, Dipti

A2 - Miao, Chunyan

A2 - Trivedi, Anupam

A2 - Crockett, Keeley

PB - IEEE

CY - Piscataway

T2 - 2022 IEEE Symposium Series on Computational Intelligence (SSCI)

Y2 - 4 December 2022 through 7 December 2022

ER -

Kapoor T , Wang H , Nunez A , Dollevoet R. Predicting traction return current in electric railway systems through physics-informed neural networks. In Ishibuchi H, Kwoh CK, Tan AH, Srinivasan D, Miao C, Trivedi A, Crockett K, editors, Proceedings of the 2022 IEEE Symposium Series on Computational Intelligence (SSCI). Piscataway: IEEE. 2022. p. 1460-1468 doi: 10.1109/SSCI51031.2022.10022290

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

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this