A Novel Neural Network Cell Method for Solving Nonlinear Electromagnetic Problems

Zhu, G; Li, L; Fu, W; Xue, M; Liu, T; Zhu, J

A Novel Neural Network Cell Method for Solving Nonlinear Electromagnetic Problems

Zhu, G Li, L Fu, W Xue, M Liu, T Zhu, J

Permalink

Publisher:: Wiley
Publication Type:: Journal Article
Citation:: Advanced Theory and Simulations, 2021, 4, (12), pp. 2100216
Issue Date:: 2021-12-01

Closed Access

	Filename	Description	Size
	Advcd Theory and Sims - 2021 - Zhu - A Novel Neural Network Cell Method for Solving Nonlinear Electromagnetic Problems.pdf	Published version	2.81 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Zhu, G
dc.contributor.author	Li, L
dc.contributor.author	Fu, W
dc.contributor.author	Xue, M
dc.contributor.author	Liu, T
dc.contributor.author	Zhu, J https://orcid.org/0000-0002-9763-4047
dc.date.accessioned	2022-02-25T20:04:45Z
dc.date.available	2022-02-25T20:04:45Z
dc.date.issued	2021-12-01
dc.identifier.citation	Advanced Theory and Simulations, 2021, 4, (12), pp. 2100216
dc.identifier.issn	2513-0390
dc.identifier.issn	2513-0390
dc.identifier.uri	http://hdl.handle.net/10453/154857
dc.description.abstract	Effective analysis of nonlinear electromagnetic fields is essential for the accurate modeling of electromagnetic devices, such as transformers, generators, and motors. This paper proposes a novel approach of coupled neural network (NN) and cell method (CM) or NNCM for solving nonlinear electromagnetic problems with ferromagnetic domains. While the topologically linear relations of the cell complexes are mathematically assembled through a transformation in the Tonti diagram by the CM, and the constitutive nonlinear magnetic relations are dealt with by partially connected NN for the fast prediction of the permeability distribution inside the ferromagnetic domain. Since the construction of NN is directly related to the grid connections, a partially connected NN structure with a small number of neurons can reduce the computational cost of the training process. By using a compact NN, the proposed NNCM can effectively eliminate the time consuming iterations for determining the nonlinear permeability distribution, and improve the computational efficiency significantly. The NNCM is employed to analyze the transient electromagnetic field distribution inside a cylindrical ferromagnetic core. The results are compared with those obtained by the traditional iterative CM, which determines the nonlinear permeability distribution by lengthy numerical iterations, to verify the feasibility and effectiveness of the proposed NNCM.
dc.language	en
dc.publisher	Wiley
dc.relation.ispartof	Advanced Theory and Simulations
dc.relation.isbasedon	10.1002/adts.202100216
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	A Novel Neural Network Cell Method for Solving Nonlinear Electromagnetic Problems
dc.type	Journal Article
utslib.citation.volume	4
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - CCET - Centre for Clean Energy Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
utslib.copyright.status	closed_access	*
dc.date.updated	2022-02-25T20:04:41Z
pubs.issue	12
pubs.publication-status	Published
pubs.volume	4
utslib.citation.issue	12

Abstract:

Effective analysis of nonlinear electromagnetic fields is essential for the accurate modeling of electromagnetic devices, such as transformers, generators, and motors. This paper proposes a novel approach of coupled neural network (NN) and cell method (CM) or NNCM for solving nonlinear electromagnetic problems with ferromagnetic domains. While the topologically linear relations of the cell complexes are mathematically assembled through a transformation in the Tonti diagram by the CM, and the constitutive nonlinear magnetic relations are dealt with by partially connected NN for the fast prediction of the permeability distribution inside the ferromagnetic domain. Since the construction of NN is directly related to the grid connections, a partially connected NN structure with a small number of neurons can reduce the computational cost of the training process. By using a compact NN, the proposed NNCM can effectively eliminate the time consuming iterations for determining the nonlinear permeability distribution, and improve the computational efficiency significantly. The NNCM is employed to analyze the transient electromagnetic field distribution inside a cylindrical ferromagnetic core. The results are compared with those obtained by the traditional iterative CM, which determines the nonlinear permeability distribution by lengthy numerical iterations, to verify the feasibility and effectiveness of the proposed NNCM.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/154857