Journal
IEEE TRANSACTIONS ON POWER DELIVERY
Volume 36, Issue 6, Pages 3640-3648Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TPWRD.2020.3046161
Keywords
Videos; Corona; Discharges (electric); Cameras; Insulators; Fault diagnosis; Power distribution lines; Corona; electric power distribution network; Faster R-CNN; intelligent diagnosis; incipient fault; partial discharge; power equipment detection; ultraviolet imaging
Categories
Funding
- Shahid Chamran University of Ahvaz (SCU)
- Khouzestan Electricity Power Distribution Company (KEPDC) [SCU.EE99.269]
Ask authors/readers for more resources
This research introduces a deep learning-based UV-Visible video processing method to identify issues in power distribution lines by detecting incipient fault types and severity levels. The method extracts video frames, detects power devices, identifies corona discharges using color thresholding, and ultimately determines the severity of incipient faults.
As one of the non-contact methods for incipient fault diagnosis of power distribution lines, UV-Visible imaging has become popular due to its good performance and robustness against environmental parameters. This paper presents a deep learning-based method for UV-Visible video processing. First, for preparing the dataset, some videos are acquired from distribution lines using CoroCam 6D2 considering observation distance, the imager's gain, air pressure, and humidity as effective parameters on the discharge area in the images. Then, based on the logged information of unplanned power outages in the system and also planned inspections over a year, the incipient fault type and the severity level of the incipient fault are determined for each video. For processing each video, frames are extracted with the rate according to the nominal voltage of the line. Power devices are detected in each frame using Faster R-CNN and are tracked through the whole video frames to compensate the camera movement. Then, color thresholding is used for each device to identify corona discharges in the frames. In-depth median filtering is also used through the video to eliminate noises in the UV channel. Finally, based on the ratio of the detected discharge area to the area of the equipment, the severity level of the incipient fault is determined. The proposed method not only performs better than the state-of-the-art but also is a practical method, and with the least dependence on environmental conditions, can automatically identify incipient faults in distribution lines, even in videos containing several possible defective devices.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available