Computational Technology Resources - CCC

Y. Song¹, H. Wang², P. Navik¹ and A. Ronnquist¹

¹Department of Structural Engineering, Norwegian University of Science and Technology, Trondheim, Norway
²Department of Engineering Structures, Delft University of Technology, Delft, The Netherlands

doi:10.4203/ccc.1.4.8

Y. Song, H. Wang, P. Navik, A. Ronnquist, "The Digitalisation of Railway Pantograph- Catenary System for Predicting Dynamic Performance Based on Recurrent Neural Network", in J. Pombo, (Editor), "Proceedings of the Fifth International Conference on Railway Technology: Research, Development and Maintenance", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 1, Paper 4.8, 2022, doi:10.4203/ccc.1.4.8

Keywords: high-speed railway, pantograph-catenary interaction, deep learning, LSTM, contact force, digital model.

Abstract

In high-speed rail operations, the interaction performance of the pantograph-catenary system is of great importance as it directly determines the current collection quality and operational safety of the high-speed train. In this work, addressing the tremendous computational cost of the finite element method (FEM), a digital tool for fast simulations of pantograph-catenary interaction, is proposed using the deep learning technique. A dataset containing 30000 cases of pantograph-catenary interaction is generated by a mature FE model. An LSTM-based neural network is proposed to handle the inherent nonlinearity between the input model parameters and the output contact force. The analysis of the prediction performance indicates that the contact forces predicted by the digital model and FEM have high similarity, but the computational efforts of the proposed digital model can be neglected. The statistical analysis points out that almost all the prediction results have an error of less than 5.75% in terms of the contact force standard deviation.

download the full-text of this paper (PDF, 7 pages, 521 Kb)

go to the previous paper
go to the next paper
return to the table of contents
return to the volume description

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCC CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Conferences ISSN 2753-3239 CCC: 1 PROCEEDINGS OF THE FIFTH INTERNATIONAL CONFERENCE ON RAILWAY TECHNOLOGY: RESEARCH, DEVELOPMENT AND MAINTENANCE Edited by: J. Pombo Paper 4.8 The Digitalisation of Railway Pantograph- Catenary System for Predicting Dynamic Performance Based on Recurrent Neural Network Y. Song¹, H. Wang², P. Navik¹ and A. Ronnquist¹ ¹Department of Structural Engineering, Norwegian University of Science and Technology, Trondheim, Norway ²Department of Engineering Structures, Delft University of Technology, Delft, The Netherlands doi:10.4203/ccc.1.4.8 Full Bibliographic Reference for this paper Y. Song, H. Wang, P. Navik, A. Ronnquist, "The Digitalisation of Railway Pantograph- Catenary System for Predicting Dynamic Performance Based on Recurrent Neural Network", in J. Pombo, (Editor), "Proceedings of the Fifth International Conference on Railway Technology: Research, Development and Maintenance", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 1, Paper 4.8, 2022, doi:10.4203/ccc.1.4.8 Keywords: high-speed railway, pantograph-catenary interaction, deep learning, LSTM, contact force, digital model. Abstract In high-speed rail operations, the interaction performance of the pantograph-catenary system is of great importance as it directly determines the current collection quality and operational safety of the high-speed train. In this work, addressing the tremendous computational cost of the finite element method (FEM), a digital tool for fast simulations of pantograph-catenary interaction, is proposed using the deep learning technique. A dataset containing 30000 cases of pantograph-catenary interaction is generated by a mature FE model. An LSTM-based neural network is proposed to handle the inherent nonlinearity between the input model parameters and the output contact force. The analysis of the prediction performance indicates that the contact forces predicted by the digital model and FEM have high similarity, but the computational efforts of the proposed digital model can be neglected. The statistical analysis points out that almost all the prediction results have an error of less than 5.75% in terms of the contact force standard deviation. download the full-text of this paper (PDF, 7 pages, 521 Kb) go to the previous paper go to the next paper return to the table of contents return to the volume description
Back to top	©Civil-Comp Limited 2023 - terms & conditions