Visual analytics and prediction system based on deep belief networks for icing monitoring data of overhead power transmi
- PDF / 1,235,525 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 100 Downloads / 181 Views
R E G UL A R P A P E R
Chi Zhang • Qing-wu Gong
•
Koji Koyamada
Visual analytics and prediction system based on deep belief networks for icing monitoring data of overhead power transmission lines Received: 1 November 2017 / Revised: 10 August 2018 / Accepted: 9 October 2018 Ó The Visualization Society of Japan 2020
Abstract In this paper, a system is proposed for visualizing and analyzing icing monitoring data of power transmission lines. The distributions of temperature and humidity are visualized by two-dimensional maps with customizable map layers. The multi-dimensional monitoring data are visualized as parallel coordinates. Moreover, a prediction algorithm that is based on a hybrid deep belief network is integrated into the system for predicting the icing thickness. If the icing thickness of a certain location exceeds the threshold value, the historical meteorological data of the location can be visualized as line graphs, which helps to choose the appropriate de-icing measures. According to the experimental results, our system is capable of reflecting the statistical features of icing monitoring data with high accuracy of icing thickness prediction. Keywords Icing thickness Visualization Deep belief network Power transmission line
1 Introduction Icing of power transmission lines can cause accidents such as ice flash trips, phase flashovers, line breaks and tower collapses (Lv and He 2011). Although various thermal methods have been used for melting the ice on power transmission lines remotely (Laforte et al. 1998), the icing problem still exists when power transmission lines are influenced by extremely cold weather and the freezing speed exceeds the melting speed. Therefore, the visualization and prediction of icing thickness play important roles in preventing accidents in the electrical power system and maintaining its stability. Especially when facing chilling weather over large areas and the short staffing in power grid companies, it is necessary to obtain a comprehensive view of the icing conditions to determine the priority of manual de-icing. The types of icing of power transmission lines can be classified into precipitation icing and in-cloud icing (Farzaneh 2008). For precipitation icing, the influencing factors include the precipitation rate, surface air temperature, liquid water content of snow flakes, wind speed, wind direction, air temperature, relative humidity and visibility (Cigre´ 2006). According to previous researches (Makkonen 1998; Chen et al. 2012; C. Zhang Q. Gong (&) School of Electrical Engineering and Automation, Wuhan University, Wuhan, China E-mail: [email protected] C. Zhang E-mail: [email protected] C. Zhang Graduate School of Engineering, Kyoto University, Kyoto, Japan K. Koyamada Academic Center for Computing and Media Studies, Kyoto University, Kyoto, Japan E-mail: [email protected]
C. Zhang et al.
Ma et al. 2016), temperature, humidity, wind speed and wind direction are usually selected as influencing factors. In this paper, we used micrometeor
Data Loading...
