Author:
Yang Jian,Qiang Wang,Jing Wenchuan,Wang Tao,Li Gang
Abstract
Abstract
In the construction of extra high voltage and ultra-high voltage paying-off, the national code requires the unified use of “tension stringing” technology. The site selection of stretch field is an important part of tension stringing. The traditional site selection of the stretch field is mainly determined by the experience of the designer, which has many disadvantages. This paper presents a method of automatic site selection for stretch field. First, two-dimensional and three-dimensional map data are fused in order to obtain the geographic information data on the line; secondly, according to the geographic information data, combined with the line segmentation rules, the segmentation of the entire line is realized to obtain the preliminary site location; finally, according to the factors affecting the establishment of the site, such as the length of the segment, the type of towers, the number of block, buildings, vegetation, road conditions, as well as site area, etc., a mathematical model for optimal site selection of the stretch field is established , with the goal of minimizing the cost of construction, automatic iterative optimization of the model is conducted, to find the optimal site location The proposed method of automatic site selection of the stretch field combines accurate geographic information data, considers various influencing factors, avoids various problems caused by manual experience site selection, improves site selection efficiency and construction safety, and saves construction cost. Experimental results show that this method can get better position of the stretch field.
Subject
Computer Science Applications,History,Education
Reference13 articles.
1. Two-stage optimal planning method of substation site selection and capacity determination;Wang;Power System Automation,2005
2. A new algorithm for power distribution system planning;Ranjan;Electric Power Systems Research,2002
3. Deep Learning Image-Based Defect Detection in High Voltage Electrical Equipment;Ullah;Energies,2020
4. Component identification and defect detection in transmission lines based on deep learning;Zheng;Journal of Intelligent & Fuzzy Systems,2021