Hybrid physics-machine learning digital twin for high-resolution traction substation power estimation
Email:
tvkhoi.ktd@utc.edu.vn
Từ khóa:
Digital Twin, Traction Power System, Constrained Reconstruction, Model Calibration, Physics-informed
Tóm tắt
Real-time estimation of traction power demand plays an important role in the operation and energy management of urban railway systems. This paper proposes a hybrid digital twin framework that integrates physics-based modeling with machine learning techniques to reconstruct real-time traction power profiles at traction substations using SCADA measurements of power and energy recorded at intervals of 3–5 minutes. The proposed digital twin framework consists of three main components. First, a physics-based load-flow model of the DC traction network is employed to ensure physical consistency in representing the electrical energy system of the railway line. Second, a residual learning module to identify the SCADA measurement instants within the physical model cycle, thereby enabling the prediction of substation power evolution in real time until the next measurement interval. Third, a post-prediction power correction module is implemented using an adaptive correction coefficient in order to minimize discrepancies between the model output and the actual system behavior. The proposed approach is validated using real operational data collected over several representative days from the Cat Linh – Ha Dong urban railway line. The verification results show that the proposed digital twin framework is capable of reconstructing high-fidelity real-time substation power profiles that closely follow the dynamic patterns observed in SCADA measurements. The framework successfully enforces strict energy conservation, driving the cumulative daily energy deviation to near zero, while maintaining robust generalization capability in tracking highly non-linear peak power demands throughout the entire operational duration across individual substations.Tài liệu tham khảo
[1]. Dimitrios Pliatsios, Panagiotis Sarigiannidis, Thomas Lagkas, Antonios G. Sarigiannidis, A Survey on SCADA Systems: Secure Protocols, Incidents, Threats and Tactics, IEEE Communications Surveys & Tutorials, 22 (2020) 1942-1976. https://doi.org/10.1109/COMST.2020.2987688
[2]. Shize Huang, Lingyu Yang, Ji Xue, Kai Yu, Urban Rail Transit Power Monitoring System Techniques Based on Synchronous Phasor Measurement Unit, in Proceedings of the 4th International Conference on Electrical and Information Technologies for Rail Transportation (EITRT), 2019, Springer Singapore, 251-268.
[3]. Marcel Nicola, Claudiu-Ionel Nicola, Florin Teișanu, Constantin Chelan, Automation System of Railway Level Crossings and SCADA Integration, International Journal on Engineering Applications, 7 (2019). https://doi.org/10.15866/irea.v7i3.17261
[4]. Zheng Pan, Liang Che, Chunming Tu, Pseudo‐measurement‐based state estimation for railway power supply systems with renewable energy resources, IET Generation, Transmission & Distribution, 18 (2024) 871-880. https://doi.org/10.1049/gtd2.13120
[5]. Shaofeng Lu, Stuart Hillmansen, Tin Kin Ho, Clive Roberts, Single-Train Trajectory Optimization, IEEE Transactions on Intelligent Transportation Systems, 14 (2013) 743-750. https://doi.org/10.1109/TITS.2012.2234118
[6]. Ling Wang, Xiang Chen, Feng Ding, Digital twin modeling and intelligent optimization for rail operation safety assessment, International Journal for Simulation and Multidisciplinary Design Optimization, 15 (2024) 1-10. https://doi.org/10.1051/smdo/2024002
[7]. Hammad Alnuman, Daniel Gladwin, Martin Foster, Electrical Modelling of a DC Railway System with Multiple Trains, Energies, 11, 3211, 2018. https://doi.org/10.3390/en11113211
[8]. Hwanhee Cho, Jaewon Kim, Hosung Jung, Hyungchul Kim, Simultaneous DC Railway Power System Analysis Method Using Model-Based TPS, Applied Sciences, 12, 6929, 2022. https://doi.org/10.3390/app12146929
[9]. Xinyang Yu, Xin Wang, Yuxin Qin, Urban Rail System Modeling and Simulation Based on Dynamic Train Density, Electronics, 13, 853, 2024. https://doi.org/10.3390/electronics13050853
[10]. Yulong Che, Xiaoru Wang, Leijiao Ge, Hongjian Lin, Xiaoqin Lyu, Hongsheng Su, Hao Wang, A review of research on traction load models and modeling methods for electrified railways, Renewable and Sustainable Energy Reviews, 219 (2025). https://doi.org/10.1016/j.rser.2025.115869
[11]. Thang Le-Xuan, Thanh Bui-Tien, Hoa Tran-Ngoc, A novel approach model design for signal data using 1DCNN combing with LSTM and ResNet for damaged detection problem, Structures, 59, 105784, 2024. https://doi.org/10.1016/j.istruc.2023.105784
[12]. Thang Le-Xuan, Thanh Nguyen-Chi, Thanh Bui-Tien, Hoa Tran-Ngoc, ResUNet4T: A potential deep learning model for damage detection based on a numerical case study of a large-scale bridge using time-series data, Engineering Structures, 340, 120668, 2025. https://doi.org/10.1016/j.engstruct.2025.120668
[13]. Michael Grieves, John Vickers, Digital Twin: Mitigating Unpredictable, Undesirable Emergent Behavior in Complex Systems, in Transdisciplinary Perspectives on Complex Systems, 2017, Springer, 85-113. https://doi.org/10.1007/978-3-319-38756-74
[14]. Yuqian Lu, Chao Liu, Kevin I-Kai Wang, Huiyue Huang, Xun Xu, Digital Twin-driven smart manufacturing: Connotation, reference model, applications and research issues, Robotics and Computer-Integrated Manufacturing, 61, 101837, 2020. https://doi.org/10.1016/j.rcim.2019.101837
[15]. Sara Ghaboura, Rahatara Ferdousi, Fedwa Laamarti, Chunsheng Yang, Abdulmotaleb El Saddik, Digital Twin for Railway: A Comprehensive Survey, IEEE Access, 11 (2023) 120237 - 120257. https://doi.org/10.1109/ACCESS.2023.3327042
[16]. Sylwia Werbińska-Wojciechowska, Robert Giel, Klaudia Winiarska, Digital Twin Approach for Operation and Maintenance of Transportation System-Systematic Review, Sensors, 24, 6069, 2024. https://doi.org/10.3390/s24186069
[17]. Dharmendra Kushwaha, Ankit Kumar, S. P. Harsha, Advancements and applications of digital twin in the railway industry: a literature review, International Journal of Rail Transportation, 13 (2025) 865-890. https://doi.org/10.1080/23248378.2024.2434834
[18]. Evelin Krmac, Boban Djordjevic, Digital Twins for Railway Sector: Current State and Future Directions, IEEE Access, 12 (2024) 108597 - 108615. https://doi.org/10.1109/ACCESS.2024.3439471
[19]. Zi-Yang Zhang, Du Shang, Shuai Su, Digital twin in railway industry: a bibliometric analysis and systematic review, Digital Twin, 2 (2025) 1-25. https://doi.org/10.1080/27525783.2025.2533858
[20]. Jian Guo, Xiaobo Wu, Hong Liang, Junfeng Hu, Baoming Liu, Digital-twin based Power Supply System Modeling and Analysis for Urban Rail Transportation, in IEEE International Conference on Energy Internet (ICEI), 2020. https://doi.org/10.1109/ICEI49372.2020.00022
[21]. Xin Li, Yingzhi Liu, A Hybrid Data and Mechanism Model-driven Digital Twin Modelling Approach for Novel Traction Power Systems, Urban Rail Transit, 11 (2025) 221-233. https://doi.org/10.1007/s40864-024-00236-2
[22]. Tran Van Khoi, An Thi Hoai Thu Anh, Dang Viet Phuc, An optimizing method of inverter location and capacity on the urban rail power supply system, Transport and Communications Science Journal, 72 (2021) 536-551. https://doi.org/10.47869/tcsj.72.5.3
[23]. Tran Van Khoi, An Thi Hoai Thu Anh, Optimization of supercapacitor energy storage systems and solar power systems integrated into urban railway lines to lessen CO2 emissions, Archives of Electrical Engineering, 74 (2025) 583-602. https://doi.org/10.24425/aee.2025.154985
[24]. Tran Van Khoi, An Thi Hoai Thu Anh, Dang Viet Phuc, Optimizing the urban train speed to minimize the energy consumption and comfort, Transport and Communications Science Journal, 72 (2021) 317-329. https://doi.org/10.47869/tcsj.72.3.7
[2]. Shize Huang, Lingyu Yang, Ji Xue, Kai Yu, Urban Rail Transit Power Monitoring System Techniques Based on Synchronous Phasor Measurement Unit, in Proceedings of the 4th International Conference on Electrical and Information Technologies for Rail Transportation (EITRT), 2019, Springer Singapore, 251-268.
[3]. Marcel Nicola, Claudiu-Ionel Nicola, Florin Teișanu, Constantin Chelan, Automation System of Railway Level Crossings and SCADA Integration, International Journal on Engineering Applications, 7 (2019). https://doi.org/10.15866/irea.v7i3.17261
[4]. Zheng Pan, Liang Che, Chunming Tu, Pseudo‐measurement‐based state estimation for railway power supply systems with renewable energy resources, IET Generation, Transmission & Distribution, 18 (2024) 871-880. https://doi.org/10.1049/gtd2.13120
[5]. Shaofeng Lu, Stuart Hillmansen, Tin Kin Ho, Clive Roberts, Single-Train Trajectory Optimization, IEEE Transactions on Intelligent Transportation Systems, 14 (2013) 743-750. https://doi.org/10.1109/TITS.2012.2234118
[6]. Ling Wang, Xiang Chen, Feng Ding, Digital twin modeling and intelligent optimization for rail operation safety assessment, International Journal for Simulation and Multidisciplinary Design Optimization, 15 (2024) 1-10. https://doi.org/10.1051/smdo/2024002
[7]. Hammad Alnuman, Daniel Gladwin, Martin Foster, Electrical Modelling of a DC Railway System with Multiple Trains, Energies, 11, 3211, 2018. https://doi.org/10.3390/en11113211
[8]. Hwanhee Cho, Jaewon Kim, Hosung Jung, Hyungchul Kim, Simultaneous DC Railway Power System Analysis Method Using Model-Based TPS, Applied Sciences, 12, 6929, 2022. https://doi.org/10.3390/app12146929
[9]. Xinyang Yu, Xin Wang, Yuxin Qin, Urban Rail System Modeling and Simulation Based on Dynamic Train Density, Electronics, 13, 853, 2024. https://doi.org/10.3390/electronics13050853
[10]. Yulong Che, Xiaoru Wang, Leijiao Ge, Hongjian Lin, Xiaoqin Lyu, Hongsheng Su, Hao Wang, A review of research on traction load models and modeling methods for electrified railways, Renewable and Sustainable Energy Reviews, 219 (2025). https://doi.org/10.1016/j.rser.2025.115869
[11]. Thang Le-Xuan, Thanh Bui-Tien, Hoa Tran-Ngoc, A novel approach model design for signal data using 1DCNN combing with LSTM and ResNet for damaged detection problem, Structures, 59, 105784, 2024. https://doi.org/10.1016/j.istruc.2023.105784
[12]. Thang Le-Xuan, Thanh Nguyen-Chi, Thanh Bui-Tien, Hoa Tran-Ngoc, ResUNet4T: A potential deep learning model for damage detection based on a numerical case study of a large-scale bridge using time-series data, Engineering Structures, 340, 120668, 2025. https://doi.org/10.1016/j.engstruct.2025.120668
[13]. Michael Grieves, John Vickers, Digital Twin: Mitigating Unpredictable, Undesirable Emergent Behavior in Complex Systems, in Transdisciplinary Perspectives on Complex Systems, 2017, Springer, 85-113. https://doi.org/10.1007/978-3-319-38756-74
[14]. Yuqian Lu, Chao Liu, Kevin I-Kai Wang, Huiyue Huang, Xun Xu, Digital Twin-driven smart manufacturing: Connotation, reference model, applications and research issues, Robotics and Computer-Integrated Manufacturing, 61, 101837, 2020. https://doi.org/10.1016/j.rcim.2019.101837
[15]. Sara Ghaboura, Rahatara Ferdousi, Fedwa Laamarti, Chunsheng Yang, Abdulmotaleb El Saddik, Digital Twin for Railway: A Comprehensive Survey, IEEE Access, 11 (2023) 120237 - 120257. https://doi.org/10.1109/ACCESS.2023.3327042
[16]. Sylwia Werbińska-Wojciechowska, Robert Giel, Klaudia Winiarska, Digital Twin Approach for Operation and Maintenance of Transportation System-Systematic Review, Sensors, 24, 6069, 2024. https://doi.org/10.3390/s24186069
[17]. Dharmendra Kushwaha, Ankit Kumar, S. P. Harsha, Advancements and applications of digital twin in the railway industry: a literature review, International Journal of Rail Transportation, 13 (2025) 865-890. https://doi.org/10.1080/23248378.2024.2434834
[18]. Evelin Krmac, Boban Djordjevic, Digital Twins for Railway Sector: Current State and Future Directions, IEEE Access, 12 (2024) 108597 - 108615. https://doi.org/10.1109/ACCESS.2024.3439471
[19]. Zi-Yang Zhang, Du Shang, Shuai Su, Digital twin in railway industry: a bibliometric analysis and systematic review, Digital Twin, 2 (2025) 1-25. https://doi.org/10.1080/27525783.2025.2533858
[20]. Jian Guo, Xiaobo Wu, Hong Liang, Junfeng Hu, Baoming Liu, Digital-twin based Power Supply System Modeling and Analysis for Urban Rail Transportation, in IEEE International Conference on Energy Internet (ICEI), 2020. https://doi.org/10.1109/ICEI49372.2020.00022
[21]. Xin Li, Yingzhi Liu, A Hybrid Data and Mechanism Model-driven Digital Twin Modelling Approach for Novel Traction Power Systems, Urban Rail Transit, 11 (2025) 221-233. https://doi.org/10.1007/s40864-024-00236-2
[22]. Tran Van Khoi, An Thi Hoai Thu Anh, Dang Viet Phuc, An optimizing method of inverter location and capacity on the urban rail power supply system, Transport and Communications Science Journal, 72 (2021) 536-551. https://doi.org/10.47869/tcsj.72.5.3
[23]. Tran Van Khoi, An Thi Hoai Thu Anh, Optimization of supercapacitor energy storage systems and solar power systems integrated into urban railway lines to lessen CO2 emissions, Archives of Electrical Engineering, 74 (2025) 583-602. https://doi.org/10.24425/aee.2025.154985
[24]. Tran Van Khoi, An Thi Hoai Thu Anh, Dang Viet Phuc, Optimizing the urban train speed to minimize the energy consumption and comfort, Transport and Communications Science Journal, 72 (2021) 317-329. https://doi.org/10.47869/tcsj.72.3.7
Tải xuống
Chưa có dữ liệu thống kê
Nhận bài
15/03/2026
Nhận bài sửa
02/06/2026
Chấp nhận đăng
03/09/2026
Xuất bản
15/09/2026
Chuyên mục
Công trình khoa học
Kiểu trích dẫn
Tran Van, K., & An Thi Hoai Thu, A. (1789405200). Hybrid physics-machine learning digital twin for high-resolution traction substation power estimation. Tạp Chí Khoa Học Giao Thông Vận Tải, 77(7), 983-1000. https://doi.org/10.47869/tcsj.77.7.8
