Logo PTI Logo FedCSIS

Position Papers of the 21st Conference on Computer Science and Intelligence Systems

Annals of Computer Science and Information Systems, Volume 48

Physics-Based State-of-Charge Modelling and Operational Optimization for a Battery-Electric Shunting Locomotive Digital Twin

,

DOI: http://dx.doi.org/10.15439/2026F1984

Citation: Tsvetomir Gotsov,

Full text

Abstract. Battery-electric shunting locomotives in non-electrified industrial environments require reliable State-of-Charge~(SoC) prediction to ensure uninterrupted shift operation and avoid unexpected battery depletion. This paper presents an empirical study and digital twin framework for the ES3000 shunting locomotive, equipped with a flooded lead-acid traction battery of~2752~Ah at~80~V. Correlation analysis of real operational telemetry collected via a Teltonika GPS tracking system and the Wialon cloud platform reveals that cumulative Ampere-hour~(Ah) integration achieves a Pearson correlation of~$r = -0.9975$ with the onboard Battery Discharge Indicator~(BDI), while instantaneous features such as terminal voltage~($r = 0.08$) and traction current~($r = 0.14$) carry negligible predictive power. A physics-based model combining Coulomb counting with Peukert high-rate capacity correction is calibrated from a single 3-hour real-world session~(1079 records, BDI 100\\% to 54\\%) and achieves a prediction RMSE of~1.81\\%. Building on the calibrated model, we derive a recharge threshold optimization that balances autonomy reserve against recharge frequency, identifying BDI~30--40\\% as the optimal trigger for mid-shift charging. A route simulation mode forecasts SoC from GPS waypoints and an operational scenario, enabling pre-shift mission planning without live telemetry. The complete pipeline is implemented as an open Python application compatible with both Wialon and PLC telemetry export formats.

References

  1. A. El Saddik, “Digital twins: The convergence of multimedia technologies,” IEEE MultiMedia, vol. 25, no. 2, pp. 87–92, 2018, https://dx.doi.org/10.1109/MMUL.2018.023121167.
  2. S. Ghaboura, R. Ferdousi, F. Laamarti, C. Yang, and A. El Saddik, “Digital twin for railway: A comprehensive survey,” IEEE Access, vol. 11, pp. 120237–120257, 2023, https://dx.doi.org/10.1109/ACCESS.2023.3327042.
  3. M. Spiryagin, E. Bernal, S. Ahmad, Q. Wu, C. Cole, and T. McSweeney, “Digital twin framework and platform for zero-emission heavy haul locomotive design and development,” Digital Twins and Applications, vol. 1, no. 2, pp. 182–197, 2024, https://dx.doi.org/10.1049/dgt2.12017.
  4. R. Issa, M. M. Badr, O. Shalash, A. A. Othman, E. Hamdan, M. S. Hamad, A. S. Abdel-Khalik, S. Ahmed, and S. M. Imam, “A data-driven digital twin of electric vehicle Li-ion battery state-ofcharge estimation enabled by driving behavior application programming interfaces,” Batteries, vol. 9, no. 10, Art. no. 521, 2023, https://dx.doi.org/10.3390/batteries9100521.
  5. M. Cipek, D. Pavković, and Z. Kljaić, “Optimized energy management control of a hybrid electric locomotive,” Machines, vol. 11, no. 6, Art. no. 589, 2023, https://dx.doi.org/10.3390/machines11060589.
  6. M. A. Hannan, M. S. Hossain Lipu, A. Hussain, P. J. Ker, T. M. I. Mahlia, M. Mansor, A. Ayob, M. H. Saad, and Z. Y. Dong, “Toward enhanced state of charge estimation of lithium-ion batteries using optimized machine learning techniques,” Scientific Reports, vol. 10, Art. no. 4687, 2020, https://dx.doi.org/10.1038/s41598-020-61464-7.
  7. J. N. Njoku, E. C. Nkoro, R. M. Medina, C. I. Nwakanma, J. M. Lee, and D.-S. Kim, “Leveraging digital twin technology for battery management: A case study review,” IEEE Access, vol. 13, pp. 21382–21412, 2025, https://dx.doi.org/10.1109/ACCESS.2025.3531833.
  8. J. Yang, Y. Sun, Y. Cao, and X. Hu, “Predictive maintenance for switch machine based on digital twins,” Information, vol. 12, no. 11, Art. no. 485, 2021, https://dx.doi.org/10.3390/info12110485.
  9. J. Sresakoolchai and S. Kaewunruen, “Track geometry prediction using three-dimensional recurrent neural network-based models crossfunctionally co-simulated with BIM,” Sensors, vol. 23, no. 1, Art. no. 391, 2023, https://dx.doi.org/10.3390/s23010391.
  10. M. T. Khalid, M. Yousif, S. A. A. Kazmi, M. U. Iftikhar, S. Alghamdi, and M. Waseem, “Coordinated scheduling and multi-energy storage planning for electric train operations,” Results in Engineering, vol. 27, Art. no. 106751, 2025, https://dx.doi.org/10.1016/j.rineng.2025.106751.
  11. W. Peukert, “Über die Abhängigkeit der Kapazität von der Entladestromstärke bei Bleiakkumulatoren,” Elektrotechnische Zeitschrift, vol. 18, no. 20, pp. 287–288, 1897.