A Real-Time Polygonal Wheel-Rail Force Identification Method Based on Convolutional Neural Networks (CNN)

Abstract

Wheel-rail force identification is one of the most challenging issues in the railway industry, which can provide real-time safety evaluation and fault diagnosis for railway vehciles in operation. A new real-time polygonal wheel-rail force identification method is proposed. Firstly, aiming at the characteristic of high-order polygon feature frequency of wheelset, multi-rigid dynamics model and flexibility-rigid dynamics model are established in SIMPACK to obtain data. Then, the data of rail force and vibration acceleration of vehicle components are normalized, graphically and discretized processed. Finally, the data are input into the designed real-time polygonal wheel-rail force identification network for learning. Simulation data are used for network learning and comparison. The experimental results demonstrate that the vibration acceleration of vehicle components along with the vertical displacement data of primary springs, exhibit optimal performance in the identification of wheel-rail forces when employed as inputs for the network. Interval usage polygonal data of different orders to fine-tuning the network yield the most accurate identification of polygonal wheel-rail forces. For the multi-rigid model, the average absolute error and determination coefficient of vertical force identification are 1039 N and 0.895, and the lateral force is 362 N and 0.833. For the flexibility-rigid model are 1529.2 N and 0.929 in vertical force identification, and 1734.5 N and 0.948 in lateral force identification. Furthermore, the wheel-rail identification can be real-time because the average calculation time is far less than the sampling time. Consequently, the proposed method can provide strong support for the safety evaluation of running railway vehicles based on monitoring data.

Keywords

Wheel-rail forces / Forces identification / Deep learning / Vehicle system dynamics / Wheel polygonization

References

[1] WilsonNG, GuruleST, BrittoR. Application of instrumented wheel set technology to transit system research and development. Am Soc Mech Eng, 1997, 18312: 89-96

[2] MicheleM, ToreV, NielsenJCO, et al.. Railway wheel tread damage and axle bending stress-Instrumented wheelset measurements and numerical simulations. Int J Rail Transp, 2021, 10: 275-297

[3] Lechowicz S, Hunt C (2000) Monitoring and managing wheel condition and loading. In: Transportation recording: 2000 and Beyond. In: International symposium on transportation recorders national transportation safety board international transportation safety association, May, 1999, pp 205–239

[4] NielsenJCO, JohanssonA. Out-of-round railway wheels—a literature survey. Proc Inst Mech Eng Part F: J Rail Rapid Transit, 2000, 214(2): 79-91

[5] Chudzikiewicz A (1991) Selected elements of the contact problems necessary for investigating the rail vehicle system. In: Advanced railway vehicle system dynamics. Wireless Network Technology, Warszawa, pp 97–108

[6] Chudzikiewicz A (2022) Elements of vehicle diagnostics. Institute of Traffic Engineers, Radom pp 207–220

[7] XiaFJ, ColeC, WolfsP. Grey box -based inverse wagon model to predict wheel-rail contact forces from measured wagon body responses. Veh Syst Dyn, 2008, 46(1): 469-479

[8] StarkeyJM, MerrillGL. On the ill-conditioned nature of indirect force measurement techniques. Int J Anal Exp Modal Anal, 1989, 4(3): 103-108

[9] BartlettFD, FlannellyWG. Model verification of force determination for measuring vibratory loads. J Am Helicopter Soc, 1979, 19(4): 10-18

[10] GiansanteN, JonesR, CalapodasNJ. Determination of in-flight helicopter loads. J Am Helicopter Soc, 1982, 27(3): 58-64

[11] Ory H, Glaser H, Holzdeppe D (1986) Quality of modal analysis and reconstruction of forcing function based on measured output data. In: Proceedings of 4th IMAC, pp 350–357

[12] KreitingerTJ, WangML, SchreyerHL. Non-parametric force identification from structural response. Soil Dyn Earthq Eng, 1992, 11(5): 269-277

[13] MaCK, LinDC, ChangJM. Estimation of forces generated by a machine mounted upon isolators under operating conditions. J Franklin Inst, 1999, 336(5): 875-892

[14] UhlT. The inverse identification problem and its technical application. Arch Appl Mech, 2007, 77(5): 325-337

[15] Xia F, Bleakley S, Wolfs P (2005) The estimation of wheel rail interaction forces form wagon accelerations. In: Advances in Applied Mechanics. Institute of Materials Engineering Australasia, Melbourne, pp 333–338

[16] XiaF, ColeC, WolfsP. An inverse railway wagon model and its applications. Veh Syst Dyn, 2007, 45(6): 583-605

[17] LiuY, ChenZ, LiW, et al.. Dynamic analysis of traction motor in a locomotive considering surface waviness on races of a motor bearing. Railway Eng Sci, 2021, 29(4): 379-393

[18] WangJ, YangJ, ZhaoY, et al.. Nonsmooth dynamics of a gear-wheelset system of railway vehicles under traction/braking conditions. J Comput Nonlinear Dyn, 2020, 15(8) ArticleID: 081003

[19] YangJ, ZhaoY, WangJ, et al.. Investigation on impact response feature of railway vehicles with wheel flat fault under variable speed conditions. J Vib Acoust, 2020, 142 3): 031009

[20] WangJ, YangJ, LiQ. Quasi-static analysis of the nonlinear behavior of a railway vehicle gear system considering time-varying and stochastic excitation. Nonlinear Dyn, 2018, 93(2): 463-485

[21] WangJ, YangJ, BaiY. A comparative study of the vibration characteristics of railway vehicle axlebox bearings with inner/outer race faults. Proc Inst Mech Eng Part F J Rail Rapid Transit, 2021, 235(8): 1035-1047

[22] Nefti S, Oussalah M (2004) A neural network approach for railway safety prediction, In: Proceedings of IEEE international conference on systems, man and cybernetics; 2004 Oct 10–13; The Hague. IEEE, The Hague, vol 4, pp 3915–3920. https://doi.org/10.1109/ICSMC.2004.1400956

[23] El-Sibaie M (2000) Computer model developed to predict rail passenger car response to track geometry, Research results.Federal Railroad Administration, USA

[24] IwnickiSD, ParkinsonH, StowJM Assessing railway vehicle derailment potential using neural networks, 1999 Manchester Rail Technology Unit, Manchester Metropolitan University

[25] Pang XM, Qin Y, Xing ZY, et al. (2011) The prediction of derailment coefficient using NARX neural network, In: Proceeding of first international conference on transportation information and safety (ICTIS); 2011 June 30–July 2; ASCE, Wuhan, China. San Diego, pp 2235–2244. https://doi.org/10.1061/41177(415)283

[26] Martin TP, Zaazaa KE, Whitten B, et al. (2007) Using a multibody dynamic simulation code with neural network technology to predict railroad vehicle-track interaction performance in real time. In: Proceedings of 6th international conference on multibody systems, nonlinear dynamics and control; 2007 Sep 4–7: ASME, Las Vegas, Nevada, US. New York, pp 1881–1891. https://doi.org/10.1115/DETC2007-34859

[27] GadhaveR, VyasNS. Rail-wheel contact forces and track irregularity estimation from on-board accelerometer data. Veh Syst Dyn, 2020, 60(6): 2145-2166

[28] Li YF, Liu JX, Wang KY, et al. (2011) Continuous measurement method of wheel/rail contact force based on neural network. In: The 3rd international conference on transportation engineering. American Society of Civil Engineers, Chengdu, China, 2011. https://doi.org/10.1061/41184(419)418.

[29] Gualano L, Iwnicki S, Ponnapalli PV, et al. (2006) Prediction of wheel-rail forces, derailment and passenger comfort using artificial neural networks. In: Proceedings of the EURNEX-ZEL conference, May. 2006

[30] UrdaP, AceitunoJF, MuñozS, 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, 2020, 153: 103968

[31] BengioY, CourvilleA, VincentP. Representation learning: a review and new perspectives. IEEE Trans Pattern Anal Mach Intell, 2013, 35(8): 1798-1828

Funding

National Natural Science Foundation of China(52205083)

Beijing Natural Science Foundation(L231016)

Beijing Engineering and Technology Research Center of Food Additives(JDYC20220827)

RIGHTS & PERMISSIONS

The Author(s)