4.3.4 Enhanced performance of thermographic asset monitoring by an interpolation-based correction algorithm
- Event
- 20. GMA/ITG-Fachtagung Sensoren und Messsysteme 2019
2019-06-25 - 2019-06-26
Nürnberg, Germany - Chapter
- 4.3 Machine Learning und Signalverarbeitung
- Author(s)
- A. Boyaci, S. Wildermuth, H. Kaul - ABB AG, Ladenburg (Deutschland), T. Kozel - ABB s.r.o., Brno (Tschechische Republik)
- Pages
- 362 - 365
- DOI
- 10.5162/sensoren2019/4.3.4
- ISBN
- 978-3-9819376-0-2
- Price
- free
Abstract
Thermal condition monitoring of electrical assets requires an accurate temperature sensing to improve the lifetime and to prevent catastrophic overheating failures of the equipment. Low-resolution infrared (IR) cameras allow a permanent installation of temperature supervision in medium voltage switchgears. Besides their benefits of contactless measurement of temperature and capturing a large section of the electrical asset, low-resolution IR cameras lack in accuracy if the hot spot is spread over a small number of pixels in the thermal image. This contribution introduces an interpolation based temperature correction algorithm to enhance the accuracy considerably of the temperature in the hot spot region. The feasibility of the proposed algorithm is demonstrated for a temperature rise test of a medium voltage switchgear under realistic conditions over the range of hot spot temperatures from 40°C to 100°C.