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.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.