Temperature Control and Monitoring System for Electrical Power Transformers Using Thermal Imaging

  1. F. Segovia 1
  2. J. Ramírez 1
  3. D. Salas-Gonzalez 1
  4. I. A. Illán 1
  5. F. J. Martinez-Murcia 1
  6. J. Rodriguez-Rivero 1
  7. F.J. Leiva 2
  8. C. Gaitan 2
  9. J. M. Górriz 1
  1. 1 University of Granada, Granada, Spain
  2. 2 Endesa Distribución, Madrid, Spain
Libro:
Bio-inspired Systems and Applications: from Robotics to Ambient Intelligence: 9th International Work-Conference on the Interplay Between Natural and Artificial Computation, IWINAC 2022, Puerto de la Cruz, Tenerife, Spain, May 31 – June 3, 2022, Proceedings, Part II
  1. José Manuel Ferrández Vicente (dir. congr.)
  2. José Ramón Alvarez Sánchez (dir. congr.)
  3. Félix de la Paz López (dir. congr.)
  4. Hojjat Adeli

Editorial: Springer Suiza

ISBN: 978-3-031-06527-9

Año de publicación: 2022

Páginas: 573-582

Tipo: Capítulo de Libro

Resumen

New societal challenges due to the climate emergency will change countries’ energy systems in the short and medium term. In this context, electrical energy and its production, distribution, transformation and storage will play a decisive role. The irruption of the electric car and the increased use of renewable production sources (of an intermittent character in the majority of cases), will cause greater stress on electrical systems. In order to address these challenges, the electrical infrastructure is adapting by including semi-autonomous monitoring systems that allow more efficient management of resources and potential failures.In this work, a thermal camera-based monitoring system for electrical power transformers is demonstrated. By appropriate processing of the thermal images obtained by a camera it is possible to obtain a time series of both transformer and room temperatures. These measurements are highly correlated with operating failures, which makes it possible to predict them and thus minimize their effects. Compared to previous sensor-based monitoring systems, this approach has the advantage of being totally independent of the transformer system and has no physical contact with it. This prevents transformer failures from affecting the monitoring system. The proposed approach was applied and evaluated in 14 transformer stations of the Spanish distribution grid, obtaining accurate and reliable temperature time series, which provides some advantages over sensor-based monitoring systems.