| 基于NLP技术实现停电原因智能分析的方法 |
投稿时间：2019-12-09 修订日期：2020-03-02  点此下载全文 |
| 引用本文： |
| 摘要点击次数: 20 |
| 全文下载次数: 0 |
|
|
| 中文摘要:针对用电网络中出现的各种电力不稳定现象,如何快速、高效地发现电力网络中停电问题,成为提升电网质量急需解决的关键问题。本研究提出了基于NLP技术分析停电原因的方法,该方法通过将NLP技术与互联网技术和大数据处理技术相结合的形式,实现电力、电网停电数据的智能处理。该系统包括电力设备检测层,数据存储层、数据分析层和数据运用层,在工作过程中,通过数据检测层将检测数据初步处理后存入相应数据库,之后经过降维与分析出便于用户处理、使用的数据,最后通过数据应用层按照根据用户需求自适应调用,进而实现了自然语言的高维度电力数据分析。通过试验分析,与传统的停电原因分析方法相比,本研究设计的方案分析误差数据小,具有较好的实用价值,为下一步电网安全工作提供了理论依据。 |
| 中文关键词:NLP技术 智能分析 用电网络 高维度电力数据分析 电网停电数据 |
| |
| Design and Implementation of Power Network Quality Monitoring System |
|
|
| Abstract:Aiming at various power instability phenomena in the power consumption network, how to quickly and efficiently find out power outages in the power network has become a key issue that needs to be solved to improve the quality of the power grid. This research proposes a method for analyzing the cause of power outages based on NLP technology. This method implements intelligent processing of power and grid outage data by combining NLP technology with Internet technology and big data processing technology. The system includes a power equipment detection layer, a data storage layer, a data analysis layer, and a data application layer. During the work process, the detection data is initially processed and stored in the corresponding database through the data detection layer, and then dimensionally reduced and analyzed to facilitate user processing. The data used is finally called by the data application layer adaptively according to user needs, and then high-dimensional power data analysis of natural language is realized. Through experimental analysis, compared with the traditional method of analyzing the cause of power outages, the analysis error of the scheme designed in this study is small, which has good practical value, and provides a theoretical basis for the next step of power grid security work. |
| keywords:NLP technology intelligent analysis power network high-dimensional power data analysis power grid outage data |
| 查看全文 查看/发表评论 下载pdf阅读器 |
|
|
|
次