Next Article in Journal
CMOS Voltage Reference using a Self-Cascode Composite Transistor and a Schottky Diode
Previous Article in Journal
Comparing the Effectiveness of Scratch and App Inventor with Regard to Learning Computational Thinking Concepts
Previous Article in Special Issue
Characterization and Correction of the Geometric Errors Using a Confocal Microscope for Extended Topography Measurement, Part II: Experimental Study and Uncertainty Evaluation
Open AccessArticle

OTL-Classifier: Towards Imaging Processing for Future Unmanned Overhead Transmission Line Maintenance

by Fan Zhang 1,2, Yalei Fan 2,3,*, Tao Cai 2,3, Wenda Liu 2,3, Zhongqiu Hu 2,3, Nengqing Wang 2,3 and Minghu Wu 1,2,*
1
Hubei Collaborative Innovation Center for High-efficiency Utilization of Solar Energy, Hubei University of Technology, Wuhan 430068, China
2
Hubei Power Grid Intelligent Control and Equipment Engineering Technology Research Center, Hubei University of Technology, Wuhan 430068, China
3
Hubei Key Laboratory for High-efficiency Utilization of Solar Energy and Operation Control of Energy Storage System, School of Electrical and Electronic Engineering, Hubei University of Technology, Wuhan 430068, China
*
Authors to whom correspondence should be addressed.
Electronics 2019, 8(11), 1270; https://doi.org/10.3390/electronics8111270
Received: 19 September 2019 / Revised: 23 October 2019 / Accepted: 29 October 2019 / Published: 1 November 2019
The global demand for electric power has been greatly increasing because of industrial development and the change in people’s daily life. A lot of overhead transmission lines have been installed to provide reliable power across long distancess. Therefore, research on overhead transmission lines inspection is very important for preventing sudden wide-area outages. In this paper, we propose an Overhead Transmission Line Classifier (OTL-Classifier) based on deep learning techniques to classify images returned by future unmanned maintenance drones or robots. In the proposed model, a binary classifier based on Inception architecture is incorporated with an auxiliary marker algorithm based on ResNet and Faster-RCNN(Faster Regions with Convolutional Neural Networks features). The binary classifier defines images with foreign objects such as balloons and kites as abnormal class, regardless the type, size, and number of the foreign objects in a single image. The auxiliary marker algorithm marks foreign objects in abnormal images, in order to provide additional help for quick location of hidden foreign objects. Our OTL-Classifier model achieves a recall rate of 95% and an error rate of 10.7% in the normal mode, and a recall rate of 100% and an error rate of 35.9% in the Warning–Review mode. View Full-Text
Keywords: smart grid; foreign object; binary classification; convolutional network smart grid; foreign object; binary classification; convolutional network
Show Figures

Figure 1

MDPI and ACS Style

Zhang, F.; Fan, Y.; Cai, T.; Liu, W.; Hu, Z.; Wang, N.; Wu, M. OTL-Classifier: Towards Imaging Processing for Future Unmanned Overhead Transmission Line Maintenance. Electronics 2019, 8, 1270.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop