The increasing frequency and intensity of extreme meteorological events attributed to climate change have necessitated a paradigm shift in power grid resilience. Initiatives such as the RESISTO project address this challenge by bolstering critical infrastructure through the integration of advanced technologies, specifically artificial intelligence (AI) and thermal imaging. By prioritising proactive prediction, prevention, and detection, these interventions seek to ensure grid stability and service continuity under evolving environmental stressors. This study proposes a real-time novelty detection architecture for the thermal monitoring of power transformers, leveraging AI to provide early-warning signals for thermal anomalies. The experimental methodology involved the deployment of a distributed network of thermal cameras within Doñana National Park (Spain), supported by a robust backend architecture for data ingestion, analysis, and automated alerting. The analytical system’s long-term performance was validated using a thermodynamically simulated synthetic dataset spanning the full 2023 year, with performance evaluated through an event-based confusion matrix. Short-term efficacy was assessed using high-fidelity real thermal imaging. The root mean square error (RMSE) was used to quantify the predictive accuracy across both approaches, which produced values below 2.65% and 5.32% for synthetic data and real-world applications, respectively. These results confirm the system’s robustness in anomaly detection and underscore its significant potential for enhancing the resilience of electrical distribution networks.
Intergovernmental Panel on Climate Change (IPCC). Climate change 2021 – The physical science basis: working group I contribution to the sixth assessment report of the intergovernmental panel on climate change. Cambridge: Cambridge University Press, 2023.
2.
SantofimiaMJDel Toro GarciaXVillanuevaFJ, et al.A comprehensive common-sense-based architecture for understanding voltage-sag events in electrical grids. Integr Comput Aided Eng2018; 25: 397–416.
3.
SantofimiaMJDel ToroXRoncero-SánchezP, et al.A qualitative agent-based approach to power quality monitoring and diagnosis. Integr Comput Aided Eng2010; 17: 305–319.
Rodríguez-RiveroJLópez-GarcíaDSegoviaF, et al.RESISTO project: safeguarding the power grid from meteorological phenomena. Cham, Switzerland: Springer Nature, 2024246261.
6.
López-GarcíaDSegoviaFRodríguez-RiveroJ, et al.RESISTO project: automatic detection of operation temperature anomalies for power electric transformers using thermal imaging. Cham, Switzerland: Springer Nature, 2024225245.
7.
Yazdani-AsramiMTaghipour-GorjikolaieMMohammad RazaviS, et al.A novel intelligent protection system for power transformers considering possible electrical faults, inrush current, CT saturation and over-excitation. Int J Electr Power Energy Syst2015; 64: 1129–1140.
8.
DolataBCoenenS. Online condition monitoring becomes standard configuration of transformers-practical application for optimized operation, maintenance and to avoid failures. In: E-ARWtr2016 Transformers, Advanced Research Workshop on Transformers, La Toja Island, Spain. Volume 2.
9.
AbbasiAR. Fault detection and diagnosis in power transformers: a comprehensive review and classification of publications and methods. Electr Power Syst Res2022; 209: 107990.
10.
Velasquez-ContrerasJLSanz-BobiMAGalceran ArellanoS. General asset management model in the context of an electric utility: application to power transformers. Electr Power Syst Res2011; 81: 2015–2037.
11.
PeimankarAWeddellSJJalalT, et al.Evolutionary multi-objective fault diagnosis of power transformers. Swarm Evol Comput2017; 36: 62–75.
12.
KunickiMBoruckiSZmarzłyD, et al.Data acquisition system for on-line temperature monitoring in power transformers. Measurement2020; 161: 107909.
13.
RamírezJMartínez-MurciaFJSegoviaF, et al.Power transformer forecasting in smart grids using NARX neural networks. In: Theory and applications of time series analysis: selected contributions from ITISE 2019 6. Springer, pp.401–414. 2020. doi: 10.1007/978-3-030-56219-9_26.
14.
AzadSSabrinaFWasimiS. Transformation of smart grid using machine learning. In: 2019 29th Australasian universities power engineering conference, AUPEC 2019, 2019, pp.0–5. DOI: 10.1109/AUPEC48547.2019.211809.
15.
HossainEKhanIUn-NoorF, et al.Application of big data and machine learning in smart grid, and associated security concerns: a review. IEEE Access2019; 7: 13960–13988.
16.
SuccettiFRosatoAPanellaM. Multi-label classification with imbalanced classes by fuzzy deep neural networks. Integr Comput Aided Eng2024; 32: 25–38.
17.
PimentelMACliftonDACliftonL, et al.A review of novelty detection. Signal Process2014; 99: 215–249.
18.
KrassnigPJHaselmannMKremnitzerM, et al.Efficient surface defect detection in industrial screen printing with minimized labeling effort. Integr Comput Aided Eng2025; 32: 3–23.
19.
GohGDHamzahNMBYeongWY. Anomaly detection in fused filament fabrication using machine learning. 3D Print Addit Manuf2023; 10: 428–437.
20.
SegoviaFRamírezJSalas-GonzalezD, et al.Connected system for monitoring electrical power transformers using thermal imaging. Integr Comput Aided Eng2023; 30: 353–368.
21.
de MeloASCalilWVPaz SalazarPD, et al.Applied methodology for temperature numerical evaluation on high current leads in power transformers. Int J Electr Power Energy Syst2021; 131: 107014.
22.
MariprasathTKirubakaranV. A real time study on condition monitoring of distribution transformer using thermal imager. Infrared Phys Technol2018; 90: 78–86.
23.
SircaGFAdeliH. Infrared thermography for detecting defects in concrete structures. J Civil Eng Manag2018; 24: 508–515.
24.
LuLDaiFZaniewskiJP. Automatic roller path tracking and mapping for pavement compaction using infrared thermography. Comput-Aided Civ Infrastruct Eng2021; 36: 1416–1434.
25.
BagavathiappanSSaravananTGeorgeNP, et al.Condition monitoring of exhaust system blowers using infrared thermography. Insight-Non-Destr Test Cond Monit2008; 50: 512–515.
26.
ItamiKSugieTVayakisG, et al.Multiplexing thermography for International Thermonuclear Experimental Reactor divertor targets. Rev Sci Instrum2004; 75: 4124–4128.
27.
Zarco-PeriñánPJMartínez-RamosJLZarco-SotoFJ. A novel method to correct temperature problems revealed by infrared thermography in electrical substations. Infrared Phys Technol2021; 113: 103623.
28.
SegoviaFRamírezJSalas-GonzalezD, et al.Connected system for monitoring electrical power transformers using thermal imaging. Integr Comput Aided Eng2023; 30: 353–368.
29.
RamirezJSegoviaFOrtizA, et al.Prediction of transformer temperature for energy distribution smart grids using recursive neural networks. In: ITISE 2019. Proceedings of papers. Vol 1, September 2019. 2019, pp.167–177.
30.
OtsuN. A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern1996; 9: 62–66.
31.
MatasJChumOUrbanM, et al.Robust wide-baseline stereo from maximally stable extremal regions. Image Vis Comput2004; 22: 761–767.
32.
SegoviaFRamírezJSalas-GonzalezD, et al.Temperature control and monitoring system for electrical power transformers using thermal imaging. Cham, Switzerland: Springer International Publishing, 2022573582.
33.
BoxGEP. Time series analysis: forecasting and control. 4th ed. Wiley Series in Probability and Statistics. Hoboken, NJ: J. Wiley & Sons, 2008.
34.
AbbracciaventoFFormentinSBaloccoJ, et al.Anomaly detection via distributed sensing: a VAR modeling approach. IFAC-PapersOnLine2021; 54: 85–90.
35.
GoyalVXuMKapatJ. Use of vector autoregressive model for anomaly detection in utility gas turbines. In: Volume 3: Coal, biomass, hydrogen, and alternative fuels; cycle innovations; electric power; industrial and cogeneration; organic rankine cycle power systems. Phoenix, Arizona, USA: American Society of Mechanical Engineers, p. V003T08A004. DOI: 10.1115/GT2019-90995.
36.
De LuelmoSPGarcia-EspinosaFJMontemayorAS, et al.Combining deep learning methods and rule-based systems for automatic parking space detection. Integr Comput Aided Eng2024; 32: 97–108.
37.
ParisPCDPedrinoEC. A high-level simulator for network-on-chip. Integr Comput Aided Eng2024; 32: 57–73.
38.
AllenJC. A modified sine wave method for calculating degree days 1. Environ Entomol1976; 5: 388–396.
39.
BaskervilleGLEminP. Rapid estimation of heat accumulation from maximum and minimum temperatures. Ecology1969; 50: 514–517.
40.
PartonWJLoganJA. A model for diurnal variation in soil and air temperature. Agric Meteorol1981; 23: 205–216.
