摘要
为了提高电力集控系统安全隐患数据处理的效果,提出一种基于来自变换器的双向编码器表示-双向长短期记忆网络-条件随机场(Bidirectional Encoder Representations from Transformers-Bidirectional Long Short Term Memory-Conditional Random Fields,BERT-BiLSTM-CRF)的电力集控安全隐患数据处理方法。构建电力集控隐患数据检测模型,应用改进长短时记忆网络(Long Short Term Memory,LSTM)来构建电力集控安全隐患数据修复网络,实现电力集控安全隐患数据处理。实验结果表明,采用所提方法能够更好地完成电力集控安全隐患数据检测与修复,应用效果较好。
In order to improve the data processing effect of potential safety hazards in power centralized control system,In this paper,a data processing method of hidden dangers in centralized power control based on Bidirectional Encoder Representations from Transformers-Bidirectional Long Short Memory Network-Conditional Random Fields(BERT-BiLSTM-CRF)is proposed.The hidden danger data detection model of power centralized control is constructed,and the improved Long Short Term Memory(LSTM)is applied to construct the data repair network of power centralized control hidden danger,so as to realize the data processing of power centralized control hidden danger.The experimental results show that the proposed method can better detect and repair the hidden danger data of centralized power control,and the application effect is good.
作者
张滈辰
屈红军
牛雪莹
耿琴兰
ZHANG Yingchen;QU Hongjun;NIU Xueying;GENG Qinlan(Qinghai Green Energy Data Co.,Ltd.,Xining 810000,China)
出处
《通信电源技术》
2023年第21期24-27,共4页
Telecom Power Technology
作者简介
张滈辰(1988-),男,山西临汾人,硕士研究生,工程师,主要研究方向为电力调度自动化、网络。
