Train wheel-rail force collaborative calibration based on GNN-LSTM

Abstract

Accurate wheel-rail force data serves as the cornerstone for analyzing the wheel-rail relationship. However, achieving continuous and precise measurement of this force remains a significant challenge in the field. This article introduces a calibration algorithm for the wheel-rail force that leverages graph neural networks and long short-term memory networks. Initially, a comprehensive wheel-rail force detection system for trains was constructed, encompassing two key components: an instrumented wheelset and a ground wheel-rail force measuring system. Subsequently, utilizing this system, two distinct datasets were acquired from the track inspection vehicle: instrumented wheelset data and ground wheel-rail force data, a feedforward neural network was employed to calibrate the instrumented wheelset data, referencing the ground wheel-rail force data. Furthermore, ground wheel-rail force data for the locomotive was obtained for the corresponding road section. This data was then integrated with the calibrated instrumented wheelset data from the track inspection vehicle. Leveraging the GNN-LSTM network, the article establishes a mapping relationship model between the wheel-rail force of the track inspection vehicle and the locomotive wheel-rail force. This model facilitates continuous measurement of locomotive wheel-rail forces across three typical scenarios: straight sections, long and steep downhill sections, and small curve radius sections.

Keywords

Railway / Wheel-rail force / Deep learning / Instrumented wheelset / Ground wheel-rail force measuring system

Declaration of Competing Interest

The authors declare that they have no competing interests.

Acknowledgements

This work was supported by the National Key R&D Program of China (Grant No. 2021YFF0501101), the National Natural Science Foundation of China (Grant Nos. 62173137, 62303178), the Project of Hunan Provincial Department of Education of China (Grant Nos. 23A0426, 22B0577).

References

[1] C. Yang, G. Tian, M. Robinson, et al., Wheel-rail force measurement based on wireless LC resonance sensing. IEEE Sens. J., 23(15)(2023), pp. 17470-17479.

[2] S.C. Sun. Identification and application of wheel-rail forces of HSR track-vehicle system. China Railw., 6 (2018), pp. 82-84.

[3] X. Zhao, S. Huang, P. Zhang, et al., On the modelling of normal wheel-rail contact for high-frequency vehicle–track dynamics analyses. Int. J. Rail Transp., 10(6)(2022), pp. 695-716.

[4] L. Li, C. Li, P. Wang, et al., Research on estimating lateral car-body acceleration with track irregularity based on deep learning. J. Beijing Jiaotong Univ., 47(4)(2023), pp. 103-109.

[5] C. Chi, S. Liang, M. Chi, et al., Mechanical model of yaw damper and vehicle dynamics simulation. J. Vib. Meas. Diagn., 42(3)(2022), pp. 518-523.

[6] S. Vishnu, S.P. Singh, S.K. Saha. Equivalent linkage representation of a railway wheelset for dynamic simulation with kinematic non-linearities. Veh. Syst. Dyn., 61(1)(2023), pp. 318-335.

[7] P. Urda, J.F. Aceituno, S. Muñoz, et al., Artificial neural networks applied to the measurement of lateral wheel-rail contact force: A comparison with a harmonic cancellation method. Mech. Mach. Theory, 153 (2020) 103968.

[8] L. Gao, C. Zhou, H. Xiao, et al., Continuous vertical wheel-rail force reconstruction method based on the distributed acoustic sensing technology. Measurement, 197 (2022) 111297.

[9] G. Li, H.L. Zu, G.F. Chu, et al., Development and application of measurement system of wheel-rail force for track inspection vehicle. China Railw. (10) (2018), pp. 74-78.

[10] Y. Cao, Y. Sun, G. Xie, et al., A sound-based fault diagnosis method for railway point machines based on two-stage feature selection strategy and ensemble classifier. IEEE Trans. Intel. Transp. Syst., 23(8)(2021), pp. 12074-12083.

[11] Q. Liu, X. Lei, J.G. Rose, et al., Vertical wheel-rail force waveform identification using wavenumber domain method. Mech. Syst. Signal Proc., 159 (2021) 107784.

[12] P.C. Kuo, Y.T. Chou, K.Y. Li, et al., GNN-LSTM-based fusion model for structural dynamic responses prediction. Eng. Struct., 306 (2024) 117733.

[13] L. Xu, W. Zhai. Train-track coupled dynamics analysis: system spatial variation on geometry, physics and mechanics. Railw. Eng. Sci., 28 (2020), pp. 36-53.

[14] Y. Zhou, J.J. Ding, F. Li, et al., Research and development of wheel/rail force testing method. Railw. Stand. Des., 63(3)(2019), pp. 38-44.

[15] G.R. Tian, H.K. Wang, Z.H. Bian, et al., Study on online monitoring and evaluation method of curving negotiation performance of rolling stock. Railw. Locomot. Car, 43(1)(2023), pp. 106-110.

[16] D. Zhang, S. Lou. The application research of neural network and BP algorithm in stock price pattern classification and prediction. Future Gener. Comput. Syst., 115 (2021), pp. 872-879.

[17] R. Rajesh. Measuring the barriers to resilience in manufacturing supply chains using grey clustering and VIKOR approaches. Measurement, 126 (2018), pp. 259-273.

[18] X. Liu, Y. Wang, Z. Ji. Short-term wind electric power prediction method based on random forest. J. Syst. Simul., 33(11)(2021), pp. 2606-2614.