Issue |
E3S Web Conf.
Volume 185, 2020
2020 International Conference on Energy, Environment and Bioengineering (ICEEB 2020)
|
|
---|---|---|
Article Number | 01027 | |
Number of page(s) | 6 | |
Section | Energy Engineering and Power System | |
DOI | https://doi.org/10.1051/e3sconf/202018501027 | |
Published online | 01 September 2020 |
The Key Techniques of Constructing the Database of Treatment Measures for Hidden Troubles in Electric Power System
Changchun Power Supply Company, State Grid Jilin Electric Power Co., Ltd. Changchun, Jilin 130000, China
* Corresponding author’s e-mail: 798291078@qq.com
This article adopts a research method that combined with theoretical analysis and system design, analyzes multiple dimensions of common safety hazard events, uses support vector machine classification algorithms to filter and mine valuable information in massive data, and establishes a common safety hazard event feature set. This kind of technology can realize the automatic classification of safety hazards and extract their characteristic information, introduce the semantic analysis, word segmentation clustering method to determine the typical processing measures of events, and generate knowledge items to add methods and models to the processing measures database, which can solve the grid safety hazard data entry specifications, In-depth analysis and other issues.
© The Authors, published by EDP Sciences, 2020
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.