Deep Learning based Discharge Information Extraction for Ultraviolet Image of Electrical Equipment. (October 2019)

• Record Type: Journal Article
• Authors: Lin, Ying; Qin, Jiafeng; Zhou, Jiabin; Li, Chengqi; Zhang, Zhenjun; Zhu, Mei
• Is Part Of: Journal of physics. Volume 1335(2019)
• Publication Date: 2019-10
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1335/1/012023
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: Convolutional networks are powerful visual models that transform images into more effective representations. To make full use of this technique, we propose a new method based on deep learning and convolutional network to effectively get the discharge information of an ultraviolet (UV) image. We firstly segment the equipment region and the UV spot region separately by using the DeepLab network, and then several properties which can show the discharge information are extracted on the basis of the segmentation. The use of the DeepLab network helps to get a reliable segmentation result, and more accurate discharge information. We take 5000 UV images to test our network, and use the concept mean IOU to evaluate its performance. The results show the advantage of the method, and it can meet the demands of further fault diagnosis.