Generalized Koopman Neural Operator for Data-Driven Modeling of Electric Railway Pantograph–Catenary Systems

Wang, Hui; Song, Yang; Yang, Haonan; Liu, Zhigang

doi:10.1109/tte.2025.3609347

articleIEEE Transactions on Transportation ElectrificationSep 29, 2025Closed access

Generalized Koopman Neural Operator for Data-Driven Modeling of Electric Railway Pantograph–Catenary Systems

HWHui Wang YSYang Song HYHaonan Yang ZLZhigang Liu

Southwest Jiaotong University

Indexed incrossref

Abstract

In electric railways, the interaction performance of the pantograph-catenary systems (PCS) is crucial for maintaining a stable current supply. Establishing high-fidelity numerical models based on the finite element method is a common practice but with substantial computational complexity. Koopman Operator, a promising candidate for data-driven modelling, provides a global linear representation of nonlinear dynamic systems. In this paper, we develop a novel Generalized Koopman Neural Operator (GKNO) implemented by an Autoencoder and an improved Transformer for modelling complex nonlinear dynamic systems with large-scale degrees of freedom. It consists of an observable function, an evolution function, and an…

Citation impact

57

total citations

FWCI: 31.92
Percentile: 100%
References: 46

Citations per year

Authors

4

Topics & keywords

Topics

Keywords

Embedding
Observable
Nonlinear system
Operator (biology)
State variable
Transformer
Invertible matrix
Representation (politics)

No related works found for this paper.