Addi. Archivo Digital para la Docencia y la Investigación
Publication
Artículo científico (JournalArticle)
Residual-based attention Physics-informed Neural Networks for spatio-temporal ageing assessment of transformers operated in renewable power plants
Transformers are crucial for reliable and efficient power system operations, particularly in supporting the integration of renewable energy. Effective monitoring of transformer health is critical to maintain grid stability and performance. Thermal insulation ageing is a key transformer failure mode, which is generally tracked by monitoring the hotspot temperature (HST). However, HST measurement is complex, costly, and often estimated from indirect measurements. Existing HST models focus on space-agnostic thermal models, providing worst-case HST estimates. This article introduces a spatio-temporal model for transformer winding temperature and ageing estimation, which leverages physics-based partial differential equations (PDEs) with data-driven Neural Networks (NN) in a Physics Informed Neural Networks (PINNs) configuration to improve prediction accuracy and acquire spatio-temporal resolution. The computational accuracy of the PINN model is improved through the implementation of the Residual-Based Attention (PINN-RBA) scheme that accelerates the PINN model convergence. The PINN-RBA model is benchmarked against self-adaptive attention schemes and classical vanilla PINN configurations. For the first time, PINN based oil temperature predictions are used to estimate spatio-temporal transformer winding temperature values, validated through PDE numerical solution and fiber optic sensor measurements. Furthermore, the spatio-temporal transformer ageing model is inferred, which supports transformer health management decision-making. Results are validated with a distribution transformer operating on a floating photovoltaic power plant., This research was funded by the Department of Education of the Basque Government (EJ-GV), IKUR Strategy and by the EU NextGenerationEU/PRTR and Spanish State Research Agency (AEI) (grant No. CPP2021-008580). J. I. A. acknowledges financial support (FS) from AEI, Ramón y Cajal Fellowship (grant number RYC2022-037300-I), co-funded by MCIU/AEI/10.13039/501100011033 and FSE+; and from the EJ-GV through the Elkartek (grant number KK-2024/00030) and Consolidated Research Group (grant No. IT1504-22) programs. KM acknowledges FS from Vinnova (grant No. 2021-03748 & 2023-00241). DP acknowledges FS from PID2023-146678OB-I00 funded by MICIU/AEI/10.13039/501100011033 and by the EU NextGenerationEU/PRTR; “BCAM Severo Ochoa” accreditation of excellence CEX2021-001142-S funded by MICIU/AEI/10.13039/501100011033; EJ-GV through the BERC 2022–2025; Elkartek (grant No. KK-2023/00012 & KK-2024/00086); and Consolidated Research Group MATHMODE (IT1456-22) programs. MS acknowledges FS from HORIZON-CL4-2022-QUANTUM01-SGA project 101113946 OpenSuperQPlus100 EU Flagship on Quantum Tech., AEI grants RYC-2020-030503-I & PID2021-125823NA-I00 MCIN/AEI/10.13039/501100011033, “ERDF A way of making EU”, “ERDF Invest in your Future”, and EJ-GV (grant No. IT1470-22). The authors would like to thank Iker Lasa at Tecnalia Research & Innovation for his comments and useful discussions.
Project:
EC / H2020 101113946
View at: http://hdl.handle.net/10810/72295