Application of machine learning techniques to build digital twins for long train dynamics simulations

References

• Dimitrova E, Tomov S. Digital twins: An advanced technology for railways maintenance transformation. In: 2021 13th Electrical Engineering Faculty Conference (BulEF); 8–11 September; Varna, Bulgaria: IEEE; 2021.
   Google Scholar
• Yang J, Sun Y, Cao Y, et al. Predictive maintenance for switch machine based on digital twins. Information. 2021;12(11):1-12.
   Google Scholar
• Doubell GC, Kruger K, Basson AH, et al. The potential for digital twin applications in railway infrastructure management. In: Pinto JOP, Kimpara MLM, Reis RR, et al., editors. 15th WCEAM Proceedings; 15–18 August; Campo Grande: Springer Cham; 2022. p. 241–249.
   Google Scholar
• Futai MM, Bittencourt TN, Santos RR, et al. Utilization of digital twins for bridge inspection, monitoring and maintenance. In: Pellegrino C, Faleschini F, Zanini MA, et al., editors. Proceedings of the 1st Conference of the European Association on Quality Control of Bridges and Structures; 29 August-1 September; Padova, Italy: Springer Cham; 2022. p. 166–173.
   Google Scholar
• Pappaterra MJ. A literature review for the application of artificial intelligence in the maintenance of railway operations with an emphasis on data. In: Marrone S, De Sanctis M, Kocsis I, et al., editors. Dependable Computing – EDCC 2022 Workshops; 12 September; Zaragoza, Spain: Springer Cham; 2022. p. 59–75.
   Google Scholar
• Kampczyk A, Dybeł K. The fundamental approach of the digital twin application in railway turnouts with innovative monitoring of weather conditions. Sensors. 2021;21(17):1-14.
   Web of Science ®Google Scholar
• Meixedo A, Santos J, Ribeiro D, et al. Data-driven approach for detection of structural changes using train-induced dynamic responses. International Conference on Structural Health Monitoring of Intelligent Infrastructure: Transferring Research into Practice, SHMII; 30 June–2 July; Porto, Portugal 2021. p. 441–448.
   Google Scholar
• Hamarat M, Papaelias M, Kaewunruen S. Fatigue damage assessment of complex railway turnout crossings via peridynamics-based digital twin. Sci Rep. 2022 Aug 23;12(1):1-23.
   Web of Science ®Google Scholar
• Jiang R, Wang W, Xie Y, et al. Research and design of infrastructure monitoring platform of intelligent high speed railway. 2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC); 4-6 March; Chongqing, China: IEEE; 2022. p. 2096–2099.
   Google Scholar
• Kulkarni R, De Rosa A, Qazizadeh A, et al. Monitoring of alignment level (AL) and cross level (CL) track geometry irregularities from onboard vehicle dynamics measurements using probabilistic fault classifier. In: Orlova A, Cole D, editors. Advances in Dynamics of Vehicles on Roads and Tracks II; 17–19 August; Saint Petersburg, Russia: Springer Cham; 2022. p. 479–487.
   Google Scholar
• Wang Y, Zhang G, Chen R, et al. Analysis of digital twin application of urban rail power supply system for energy saving. 2021 IEEE 1st International Conference on Digital Twins and Parallel Intelligence (DTPI); 15 July–15 August; Beijing, China: IEEE; 2021. p. 29–32.
   Google Scholar
• Zheng X, Xu B, Zhao W, et al. Modeling method and application of metro power supply system based on digital twin. 2021 IEEE 2nd China International Youth Conference on Electrical Engineering (CIYCEE); 15–17 December; Chengdu, China: IEEE; 2021. p. 1–7.
   Google Scholar
• Chen L, Yu Y, Gong Z, et al. Multi-scale modeling and simulation method of urban rail traction power supply system for digital twin. In: Jia L, Qin Y, Liang J, et al., editors. Proceedings of the 5th International Conference on Electrical Engineering and Information Technologies for Rail Transportation (EITRT) 2021; 21–23 October; Singapore: Springer Singapore; 2022. p. 666–675.
   Google Scholar
• Li Y, Zhang W, Xiong Q, et al. A novel fault diagnosis model for bearing of railway vehicles using vibration signals based on symmetric alpha-stable distribution feature extraction. ShockVibr. 2016;2016:1–14.
   Web of Science ®Google Scholar
• Kreuzer M, Schmidt A, Kellermann W. Novel features for the detection of bearing faults in railway vehicles. The 50th International Congress and Exposition on Noise Control Engineering; 1–5 August; Online Conference 2021. p. 3833–3844.
   Google Scholar
• Jesussek M, Ellermann K. Fault detection and isolation for a full-scale railway vehicle suspension with multiple Kalman filters. Vehicle Syst Dynam. 2014;52(12):1695–1715.
   Web of Science ®Google Scholar
• Wei X, Jia L, Guo K, et al. On fault isolation for rail vehicle suspension systems. Vehicle Syst Dynam. 2014;52(6):847–873.
   Web of Science ®Google Scholar
• Karlsson H, Qazizadeh A, Stichel S, et al. Condition monitoring of rail vehicle suspension elements: a machine learning approach. In: Klomp M, Bruzelius F, Nielsen J, et al., editors. Advances in Dynamics of Vehicles on Roads and Tracks; 12–16 August 2019; Gothenburg, Sweden: Springer Cham; 2020. p. 119–127.
   Google Scholar
• Hesser DF, Altun K, Markert B. Monitoring and tracking of a suspension railway based on data-driven methods applied to inertial measurements. Mech Syst Signal Process. 2022;164:1–18.
   Web of Science ®Google Scholar
• Zhao Y, Liang B, Iwnicki S. Friction coefficient estimation using an unscented Kalman filter. Vehicle Syst Dynam. 2014;52(sup1):220–234.
   Web of Science ®Google Scholar
• Bernal E, Spiryagin M, Vollebregt E, et al. Prediction of rail surface damage in locomotive traction operations using laboratory-field measured and calibrated data. Eng Fail Anal. 2022;135:1–14.
   Web of Science ®Google Scholar
• Krishna VV, Wu Q, Hossein-Nia S, et al. Long freight trains & long-term rail surface damage – a systems perspective. Vehicle Syst Dynam. 2022: 1–24.
   Web of Science ®Google Scholar
• Spiryagin M, Wu Q, Polach O, et al. Problems, assumptions and solutions in locomotive design, traction and operational studies. Railw Eng Sci. 2022;30(3):265–288.
   Google Scholar
• Leonardi F, Alfi S, Bruni S. An application of Kalman filtering estimation to the condition monitoring of the geometric quality of the railway track. In: Zobory I, editor. Proceedings of the Mini Conference on Vehicle System Dynamics, Identification and Anomalies; 7–9 November; Budapest, Hungary. Budapest: Budapest University of Technology and Economics; 2016. p. 163–172.
   Google Scholar
• Yang Z, Lu ZG, Wang XC, et al. Wheelset states estimation using unscented Kalman filter. In: Spiryagin M, Gordon T, Cole C, et al., editors. The Dynamics of Vehicles on Roads and Tracks; 14–18 August 2017; Rockhampton, Queensland, Australia. London, UK: CRC Press; 2018. p. 1071–1076.
   Google Scholar
• Deng W, Huang J, Zhang Q. A method of the locomotive speed estimation based on Fuzzy logic and extended Kalman filter. 15th IEEE Conference on Industrial Electronics and Applications (ICIEA); 9–13 November; Kristiansand, Norway: IEEE; 2020. p. 1353–1358.
   Google Scholar
• Ulum Z, Nur Aini S. Model predictive control based Kalman filter for active suspension design of light rail vehicles. J Adv Res Dynam Contr Syst. 2020;12(3):261–267.
   Google Scholar
• Xiao X, Sun Z, Shen W. A Kalman filter algorithm for identifying track irregularities of railway bridges using vehicle dynamic responses. Mech Syst Signal Process. 2020;138:1–27.
   Web of Science ®Google Scholar
• Pichlík P, Bauer J. Adhesion characteristic slope estimation for wheel slip control purpose based on UKF. IEEE Trans Veh Technol. 2021;70(5):4303–4311.
   Web of Science ®Google Scholar
• Karttunen K, Kabo E, Ekberg A. Numerical assessment of the influence of worn wheel tread geometry on rail and wheel deterioration. Wear. 2014;317(1):77–91.
   Web of Science ®Google Scholar
• Wang J, Ren Z, Chen J, et al. Study on rail profile optimization based on the nonlinear relationship between profile and wear rate. Math Probl Eng. 2017;2017:1–13.
   Web of Science ®Google Scholar
• Ye Y, Sun Y, Dongfang S, et al. Optimizing wheel profiles and suspensions for railway vehicles operating on specific lines to reduce wheel wear: a case study. Multibody Syst Dynam. 2021;51(1):91–122.
   Web of Science ®Google Scholar
• Tsunashima H. Condition monitoring of railway tracks from Car-body vibration using a machine learning technique. Appl Sci. 2019;9(13):1–13.
   Google Scholar
• Li C, He Q, Wang P. Estimation of railway track longitudinal irregularity using vehicle response with information compression and Bayesian deep learning. Computer-Aided Civil Infrastruct Eng. 2022;37:1260–1276.
   Web of Science ®Google Scholar
• Cole C, Sun YQ. Simulated comparisons of wagon coupler systems in heavy haul trains. Proc Inst Mech Eng Part F J Rail and Rapid Transit. 2006;220(3):247–256.
   Web of Science ®Google Scholar
• Massa A, Stronati L, Aboubakr AK, et al. Numerical study of the noninertial systems: application to train coupler systems. Nonlin Dynam. 2012;68(1):215–233.
   Web of Science ®Google Scholar
• Wu Q, Cole C, Luo S, et al. A review of dynamics modelling of friction draft gear. Vehicle Syst Dynam. 2014;52(6):733–758.
   Web of Science ®Google Scholar
• Kalker JJ. A fast algorithm for the simplified theory of rolling contact. Vehicle Syst Dynam. 1982;11(1):1–13.
   Web of Science ®Google Scholar
• Polach O. A fast wheel-rail forces calculation computer code. Vehicle Syst Dynam. 1999;33(sup1):728–739.
   Web of Science ®Google Scholar
• Polach O. Creep forces in simulations of traction vehicles running on adhesion limit. Wear. 2005;258(7):992–1000.
   Web of Science ®Google Scholar
• EN. Railway applications - Testing and simulation for the acceptance of running characteristics of railway vehicles - Running Behaviour and stationary tests. Standard No.: 14363.
   Google Scholar
• Bosso N, Zampieri N. Long train simulation using a multibody code. Vehicle Syst Dynam. 2017;55(4):552–570.
   Web of Science ®Google Scholar
• Bosso N, Gugliotta A, Zampieri N. A mixed numerical approach to evaluate the dynamic behavior of long trains. Procedia Struct Integr. 2018;12:330–343.
   Google Scholar
• Petrenko V. Simulation of railway vehicle dynamics in universal mechanism software. Procedia Eng. 2016;134:23–29.
   Google Scholar
• Pogorelov D, Yazykov V, Lysikov N, et al. Train 3D: the technique for inclusion of three-dimensional models in longitudinal train dynamics and its application in derailment studies and train simulators. Vehicle Syst Dynam. 2017;55(4):583–600.
   Web of Science ®Google Scholar
• Krishna VV, Wu Q, Hossein-Nia S, et al. Long freight trains & Long-term rail surface damage: Towards digital twins that enable predictive maintenance of track. World Congress on Railway Research 2022 (WCRR2022); June 6-10; Birmingham, UK 2022.
   Google Scholar
• McKay MD, Beckman RJ, Conover WJ. A comparison of three methods for selecting values of input variables in the analysis of output from a computer code. Technometrics. 2000;42(1):55–61.
   Web of Science ®Google Scholar
• Bosso N, Magelli M, Zampieri N. Long train dynamic simulation by means of a new in-house code. In: Passerini G, Mera JM, Takagi R, editors. WIT Transactions on The Built Environment. 1-3 September; Online Conference. Southampton, UK: WIT Press; 2020. p. 249–259.
   Google Scholar
• Bosso N, Magelli M, Zampieri N. Development and validation of a new code for longitudinal train dynamics simulation. Proc Inst Mech Eng Part F: J Rail Rapid Transit. 2021;235(3):286–299.
   Web of Science ®Google Scholar
• Bosso N, Magelli M, Zampieri N. Validation of a new longitudinal train dynamics code for time domain simulations and modal analyses. Intern J Transport Develop Integr. 2021;5(1):41–56.
   Google Scholar
• Spiryagin M, Wu Q, Cole C. International benchmarking of longitudinal train dynamics simulators: benchmarking questions. Vehicle Syst Dynam. 2017;55(4):450–463.
   Web of Science ®Google Scholar
• Wu Q, Spiryagin M, Cole C, et al. International benchmarking of longitudinal train dynamics simulators: results. Vehicle Syst Dynam. 2018;56(3):343–365.
   Web of Science ®Google Scholar
• Bosso N, Magelli M, Rossi Bartoli L, et al. The influence of resistant force equations and coupling system on long train dynamics simulations. Proc Inst Mech Eng Part F J Rail Rapid Transit. 2022;236(1):35–47.
   Web of Science ®Google Scholar
• Wu Q, Wang B, Spiryagin M, et al. Curving resistance from wheel-rail interface. Vehicle Syst Dynam. 2022;60(3):1018–1036.
   Web of Science ®Google Scholar
• UIC. Wagons - Buffers with a stroke of 105 mm. Standard No.: 526-1.
   Google Scholar
• Zhang Z, Li G, Chu G, et al. Compressed stability analysis of the coupler and buffer system of heavy-haul locomotives. Vehicle Syst Dynam. 2015;53(6):833–855.
   Web of Science ®Google Scholar
• Bosso N, Gugliotta A, Soma A. Multibody simulation of a freight bogie with friction dampers. ASME/IEEE Joint Railroad Conference; 23–25 April; Washington, DC, USA IEEE; 2002. p. 47–56.
   Google Scholar
• Fang K-T, Li R, Sudjianto A. Design and modeling for computer experiments. London: Taylor & Francis Group, LLC; 2016.
   Google Scholar
• Trinchero R, Larbi M, Torun HM, et al. Machine learning and uncertainty quantification for surrogate models of integrated devices With a large number of parameters. IEEE Access. 2019;7:4056–4066.
   Web of Science ®Google Scholar
• Trinchero R, Canavero F. Machine learning regression techniques for the modeling of complex systems: An overview. IEEE Electromagn Compat Magazine. 2021;10(4):71–79.
   Google Scholar
• Vapnik VN. Statistical learning theory. New York (NY): Wiley; 1998.
   Google Scholar
• Suykens JAK, Van Gestel T, De Brabanter J, et al. Least squares support vector machines. London: World Scientific; 2002.
   Google Scholar
• Ghojogh B, Crowley M. The theory behind overfitting, cross validation, regularization, bagging, and boosting: tutorial. arXiv preprint arXiv:190512787; 2019.
   Google Scholar
• Statistics and Machine Learning Toolbox. 11.7. Natick (MA): The MathWorks.
   Google Scholar
• LS-SVMlab. 1.8. Leuven, Belgium: Department of Electrical Engineering (ESAT), Katholieke Universiteit Leuven; 2011. Available online: http://www.esat.kuleuven.be/sista/lssvmlab.
   Google Scholar