Enhanced Neural Real-Time Digital Twin for Electrical Drives
Source abstract
Abstract
This paper presents a real-time digital twin (DT) of the power conversion system used in offshore wind applications. The proposed DT is exploited to identify key electrical parameters of both the permanent magnet synchronous generator (PMSG) and the three-phase boost rectifier and has been developed with a Condition Monitoring (CM)-oriented approach. A Gated Recurrent Unit (GRU) neural network is adopted as a real-time digital model (RTDM) to estimate online the PMSG phase resistance and synchronous inductance, as well as the DC-link capacitance at the rectifier output. The network is trained in MATLAB using data generated by a Typhoon HIL 606 emulator, covering both balanced and unbalanced operating conditions and a wide range of parameter variations. The trained GRU is then deployed on the control board and implemented in LabVIEW Real-Time for embedded execution. Experimental tests on a PMSG-based generating unit confirm the effectiveness of the proposed RTDM, achieving low root-mean-square and mean percentage errors in parameter estimation. The results demonstrate that the enhanced neural real-time DT is a promising tool for condition monitoring and predictive maintenance of power conversion systems in offshore wind applications.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Fault Diagnosis Techniques · Real-time simulation and control systems · Wind Turbine Control Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Industrial, Electronic and Mechanical Engineering, Roma Tre University, 00146 Rome, Italy
Department of Electronics and Telecommunication (DET), Politecnico di Torino, 10129 Turin, Italy
Department of Civil, Computer and Aeronautical Technologies Engineering, Roma Tre University, 00146 Rome, Italy
Institute of Marine Engineering (INM), Section of Palermo, National Research Council of Italy (CNR), 90146 Palermo, Italy
Laboratory LTI, University of Picardie Jules Verne, 80025 Amiens, France
Funding
Ministero dell’Università e della Ricerca
References (34)
Show source-provided references
1. Field-Experience Based Root-Cause Analysis of Power-Converter Failure in Wind Turbines10.1109/TPEL.2014.2361733 ↗
2. Di Nezio, G., Di Benedetto, M., Ghione, G., Randazzo, V., and Solero, L. (2024, January 20–24). Digital twin based identification of passive parameters of three-phase boost rectifier using a gru neural network. Proceedings of the 2024 IEEE Energy Conversion Congress and Exposition (ECCE), Phoenix, AZ, USA.10.1109/ECCE55643.2024.10860740 ↗
3. Failure analysis of power electronic devices and their applications under extreme conditions10.23919/CJEE.2016.7933119 ↗
4. Power electronic converter reliability and prognosis review focusing on power switch module failures10.1007/s43236-021-00228-6 ↗
5. Yang, S., Bryant, A., Mawby, P., Xiang, D., Ran, L., and Tavner, P. (2009). An industry-based survey of reliability in power electronic converters. 2009 IEEE Energy Conversion Congress and Exposition, IEEE.10.1109/ECCE.2009.5316356 ↗
6. Overview of Real-Time Lifetime Prediction and Extension for SiC Power Converters10.1109/TPEL.2019.2962503 ↗
7. Bęczkowski, S., Ghimre, P., de Vega, A.R., Munk-Nielsen, S., Rannestad, B., and Thøgersen, P. (2013). Online Vce measurement method for wear-out monitoring of high power IGBT modules. Proceedings of the 2013 15th European Conference on Power Electronics and Applications (EPE), Lille, France, 3–5 September 2013, IEEE.10.1109/EPE.2013.6634390 ↗
8. Evaluation of Vce Monitoring as a Real-Time Method to Estimate Aging of Bond Wire-IGBT Modules Stressed by Power Cycling10.1109/TIE.2012.2196894 ↗
9. Gate–Emitter Pre-threshold Voltage as a Health-Sensitive Parameter for IGBT Chip Failure Monitoring in High-Voltage Multichip IGBT Power Modules10.1109/TPEL.2018.2884276 ↗
10. Investigation of gate voltage oscillations in an IGBT module after partial bond wires lift-off10.1016/j.microrel.2012.08.024 ↗
11. Dupont, L., Avenas, Y., and Jeannin, P.-O. (2012). Comparison of junction temperature evaluations in a power IGBT module using an IR camera and three thermo-sensitive electrical parameters. Proceedings of the 2012 Twenty-Seventh Annual IEEE Applied Power Electronics Conference and Exposition (APEC), Orlando, FL, USA, 5–9 February 2012, IEEE.10.1109/APEC.2012.6165817 ↗
12. Andrade, J.M. (2019). Electrolytic Capacitor Degradation Monitoring using an On-line Parameter Estimation Scheme involving Sliding Mode Differentiators and a Kalman Filter. Proceedings of the 2019 21st European Conference on Power Electronics and Applications (EPE ‘19 ECCE Europe), Genova, Italy, 2–5 September 2019, IEEE.10.23919/EPE.2019.8915429 ↗
13. Condition Monitoring of DC-Link Capacitors in Aerospace Drives10.1109/TIA.2012.2222333 ↗
14. Condition Monitoring for Device Reliability in Power Electronic Converters: A Review10.1109/TPEL.2010.2049377 ↗
15. Active Online System Identification of Switch Mode DC–DC Power Converter Based on Efficient Recursive DCD-IIR Adaptive Filter10.1109/TPEL.2012.2190754 ↗
16. Di Nezio, G., Marini, G., Di Benedetto, M., Lidozzi, A., and Solero, L. (2024). Digital Twin Based Identification of Passive Parameters for PMSM-Based Generating Unit by an Extended Kalman Filter for Wind Off-Shore Applications. Proceedings of the 2024 International Symposium on Power Electronics, Electrical Drives, Automation and Motion (SPEEDAM), Napoli, Italy, 19–21 June 2024, IEEE.10.1109/SPEEDAM61530.2024.10609157 ↗
17. Digital twin: Manufacturing excellence through virtual factory replication
18. Chen, S., Wang, S., Wen, P., and Zhao, S. (2021). Digital Twin for Degradation Parameters Identification of DC-DC Converters Based on Bayesian Optimization. Proceedings of the 2021 IEEE International Conference on Prognostics and Health Management (ICPHM), IEEE.10.1109/ICPHM51084.2021.9486446 ↗
19. Wunderlich, A., and Santi, E. (2021). Digital Twin Models of Power Electronic Converters Using Dynamic Neural Networks. Proceedings of the 2021 IEEE Applied Power Electronics Conference and Exposition (APEC), IEEE.10.1109/APEC42165.2021.9487201 ↗
20. Di Nezio, G., De López Diz, S., Di Benedetto, M., Lidozzi, A., Peña, E.J.B., and Solero, L. (2023). Parameters Estimation of a 3-Phase AC-DC Converter based on the Digital Twin Method. Proceedings of the 2023 IEEE Energy Conversion Congress and Exposition (ECCE), Nashville, TN, USA, 29 October–2 November 2023, IEEE.10.1109/ECCE53617.2023.10362069 ↗
21. Self-Evolving Digital Twin-Based Online Health Monitoring of Multiphase Boost Converters10.1109/TPEL.2023.3311710 ↗
22. Digital-Twin Based Health Monitoring for Multi-Phase Boost Rectifier in Wind Offshore Applications
23. Digital Twin Techniques for Power Electronics-Based Energy Conversion Systems: A Survey of Concepts, Application Scenarios, Future Challenges, and Trends10.1109/MIE.2022.3216719 ↗
24. Soliman, H., Wang, H., and Blaabjerg, F. (2016). Capacitance estimation for dc-link capacitors in a back-to-back converter based on Artificial Neural Network algorithm. Proceedings of the 2016 IEEE 8th International Power Electronics and Motion Control Conference (IPEMC-ECCE Asia), Hefei, China, 22–26 May 2016, IEEE.10.1109/IPEMC.2016.7512885 ↗
25. She, Z., and Chen, G. (2022). Full-Parameter Identification of BUCK Converter Based on Time-Domain Mapping Neural Network. Proceedings of the 2022 IEEE International Power Electronics and Application Conference and Exposition (PEAC), Guangzhou, China, 4–7 November 2022, IEEE.10.1109/PEAC56338.2022.9959303 ↗
26. Lu, C., Li, J., Chen, K., Zhou, W., Wu, Q., and Ke, J. (2023). System-level Parameters Identification for DC-DC Converters Based on Artificial Neural Network Algorithm. Proceedings of the 2023 IEEE Energy Conversion Congress and Exposition (ECCE), Nashville, TN, USA, 29 October–2 November 2023, IEEE.10.1109/ECCE53617.2023.10362646 ↗
27. Lu, Y., Zhang, M., Nordström, L., and Xu, Q. (2023). An Online Digital Twin based Health Monitoring Method for Boost Converter using Neural Network. Proceedings of the 2023 IEEE Energy Conversion Congress and Exposition (ECCE), Nashville, TN, USA, 29 October–2 November 2023, IEEE.10.1109/ECCE53617.2023.10362778 ↗
28. A Non-Invasive Method for Estimating Circuit and Control Parameters of Voltage Source Converters10.1109/TCSI.2019.2929783 ↗
29. Online Stator and Rotor Resistance Estimation Scheme Using Artificial Neural Networks for Vector Controlled Speed Sensorless Induction Motor Drive10.1109/TIE.2006.888778 ↗
30. FPGA Implementation of the Multilayer Neural Network for the Speed Estimation of the Two-Mass Drive System10.1109/TII.2011.2158843 ↗
31. Toward Physics-Informed Machine-Learning-Based Predictive Maintenance for Power Converters—A Review10.1109/TPEL.2023.3328438 ↗
32. Ghione, G., Macha, J., Randazzo, V., Di Nezio, G., Di Benedetto, M., Badami, M., Pasero, E., and Faundez-Zanuy, M. (2025). Passive parameters identification of a threephase ac–dc converter via a gru network and derivative approximations. Neural Networks: Overview of Current Theories and Applications, Springer.
33. Chen, S., Zhang, J., Wang, S., Wen, P., and Zhao, S. (2022). Circuit Parameter Identification of Degrading DC-DC Converters Based on Physics-informed Neural Network. Proceedings of the 2022 Prognostics and Health Management Conference (PHM-2022 London), London, UK, 27–29 May 2022, IEEE.10.1109/PHM2022-London52454.2022.00053 ↗
34. Delrio, F., Randazzo, V., Cirrincione, G., and Pasero, E. (2025). Physics informed neural network for continuous and cuffless arterial blood pressure. Proceedings of the 2025 IEEE International Conference on Artificial Intelligence for Learning and Optimization (ICoAILO), IEEE.10.1109/ICoAILO66760.2025.11156047 ↗