Physics-Informed Deep Learning for Dynamic Friction Coefficient Prediction in the Pantograph–Catenary System Under Complex Current-Carrying Conditions

Chen, Jinhui; Gao, Guoqiang; Fu, Rong; Wang, Qingsong; Lan, Tianwei; Qian, Pengyu; Huang, Guizao; Wang, Hong; Wu, Guangning

doi:10.3390/lubricants14080284

Open AccessArticle

Physics-Informed Deep Learning for Dynamic Friction Coefficient Prediction in the Pantograph–Catenary System Under Complex Current-Carrying Conditions

by

Jinhui Chen

¹,

Guoqiang Gao

^1,*,

Rong Fu

¹

,

Qingsong Wang

¹,

Tianwei Lan

¹,

Pengyu Qian

¹,

Guizao Huang

¹,

Hong Wang

² and

Guangning Wu

¹

School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, China

²

College of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China

^*

Author to whom correspondence should be addressed.

Lubricants 2026, 14(8), 284; https://doi.org/10.3390/lubricants14080284

Submission received: 22 June 2026 / Revised: 20 July 2026 / Accepted: 21 July 2026 / Published: 23 July 2026

Download

Browse Figures

Versions Notes

Abstract

The pantograph–catenary system is the critical pathway for energy collection for high-speed trains, and its interfacial state directly affects current-collection quality and operational safety. Due to the coupled effects of multiple factors, the friction coefficient at the interface exhibits significant nonlinearity, time variability, and stochastic fluctuations, posing substantial challenges for friction-behavior prediction. To improve the prediction accuracy and generalization capability of friction-coefficient models under complex current-carrying conditions, a CNN-LSTM model optimized by a physics-informed Sparrow Search Algorithm, namely PISSA-CNN-LSTM, is proposed in this study. Based on current-carrying friction tests, the effects of current, contact load, and sliding speed on the dynamic evolution of the friction coefficient are analyzed. The physics-based regularities associated with operating conditions are further incorporated into the SSA-based hyperparameter optimization process, enabling directed optimization under physical constraints. The results show that PISSA-CNN-LSTM outperforms CNN-LSTM and SSA-CNN-LSTM in prediction accuracy, convergence speed, and optimization efficiency. The test-set R² reaches 0.9904, and the optimization time is reduced by 49.38% compared with SSA-CNN-LSTM. This work provides a more accurate, robust, and interpretable modeling approach for predicting pantograph–catenary interfacial friction behavior under complex current-carrying conditions.

Keywords: high-speed railway; C/Cu contact pair; friction coefficient; physics-informed deep learning

Share and Cite

MDPI and ACS Style

Chen, J.; Gao, G.; Fu, R.; Wang, Q.; Lan, T.; Qian, P.; Huang, G.; Wang, H.; Wu, G. Physics-Informed Deep Learning for Dynamic Friction Coefficient Prediction in the Pantograph–Catenary System Under Complex Current-Carrying Conditions. Lubricants 2026, 14, 284. https://doi.org/10.3390/lubricants14080284

AMA Style

Chen J, Gao G, Fu R, Wang Q, Lan T, Qian P, Huang G, Wang H, Wu G. Physics-Informed Deep Learning for Dynamic Friction Coefficient Prediction in the Pantograph–Catenary System Under Complex Current-Carrying Conditions. Lubricants. 2026; 14(8):284. https://doi.org/10.3390/lubricants14080284

Chicago/Turabian Style

Chen, Jinhui, Guoqiang Gao, Rong Fu, Qingsong Wang, Tianwei Lan, Pengyu Qian, Guizao Huang, Hong Wang, and Guangning Wu. 2026. "Physics-Informed Deep Learning for Dynamic Friction Coefficient Prediction in the Pantograph–Catenary System Under Complex Current-Carrying Conditions" Lubricants 14, no. 8: 284. https://doi.org/10.3390/lubricants14080284

APA Style

Chen, J., Gao, G., Fu, R., Wang, Q., Lan, T., Qian, P., Huang, G., Wang, H., & Wu, G. (2026). Physics-Informed Deep Learning for Dynamic Friction Coefficient Prediction in the Pantograph–Catenary System Under Complex Current-Carrying Conditions. Lubricants, 14(8), 284. https://doi.org/10.3390/lubricants14080284

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Physics-Informed Deep Learning for Dynamic Friction Coefficient Prediction in the Pantograph–Catenary System Under Complex Current-Carrying Conditions

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI