Paper
15 March 2002 New detection method of faulty distribution power apparatus using thermal images
Author Affiliations +
Abstract
In automatic diagnosis of a power distribution apparatus is utilizing thermal images problems arise in that there are problems, that there are many thermal patterns similar to the thermal pattern of the target apparatus and that the temperature around the apparatus influences the diagnosis. In order to solve these problems, we developed a new method whereby images of the apparatus are extracted by an image processing technique based on high-order local autocorrelation features, the attachment pattern on a pole, and a disparity map; a faulty apparatus is identified based on the local temperature gradient. In the extraction method, the distance information provided by the disparity map narrows the search area of the apparatus. The search is conducted according to the rule that an apparatus feature that is defined by high-order local autocorrelation features appears at certain intervals, according to the attachment pattern on a pole, in the search area. The local temperature gradient detects local heat in the form of leakage current on the faulty apparatus. Experiments using the proposed method were conducted under different weather conditions, at different times and seasons. An error rate of 3% was obtained from experiments on the extraction of an apparatus, and an error rate of 17% was obtained from experiments on the detection of a faulty apparatus. The proposed method can extract and detect faulty apparatuses, such as a pin insulator, a section switch and a strain insulator, except in the case where the distance between the pole and the infrared camera is so large that the sensitivity is insufficient.
© (2002) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ryuichi Ishino "New detection method of faulty distribution power apparatus using thermal images", Proc. SPIE 4710, Thermosense XXIV, (15 March 2002); https://doi.org/10.1117/12.459584
Lens.org Logo
CITATIONS
Cited by 7 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Dielectrics

Thermography

Feature extraction

Cameras

Infrared cameras

Image processing

Inspection

Back to Top