Low voltage current transformer defect detection method based on Hausdorff distance algorithm under charged state
by Kai Sun; Xiaohui Zhai; Yanling Sun; Yan Du; Yuning Fa
International Journal of Energy Technology and Policy (IJETP), Vol. 19, No. 1/2, 2024

Abstract: In order to accurately detect the defects of low-voltage current transformers, a defect detection method of low-voltage current transformers based on Hausdorff distance algorithm under charged state is proposed. In the charged state, the noise variance of the defect image of low-voltage current transformer is calculated, the grey variance in the bilateral filter function is adjusted, and the defect image of low-voltage current transformer after noise removal is obtained. The Canny edge results are calculated to obtain the distance transform map. The mask convolution processing is performed on the distance transform map to cluster the results, and then the defect characteristics of different types of low-voltage current transformers are obtained. At the same time, the Hausdorff distance algorithm and elastic graph matching are effectively combined to realise defect detection of low-voltage current transformers. The experimental results show that the proposed method can quickly and accurately detect the defects of low-voltage current transformers.

Online publication date: Fri, 10-May-2024

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Energy Technology and Policy (IJETP):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com