基于GRU神经网络的电网告警信息分类研究
|
摘要
电力系统规模的扩大对变电站后台监控系统的要求日益上升,主要体现在其告警信息处理能力上。论文设计了电力设备风险运行评估系统,在参考电力设备相关试验规程的基础上,建立基于电网监控数据的电力故障指标体系。遥信是将被监视厂站的设备状态信号远距离传给调度,以自然语言的形式记录的告警信息。论文将电网遥信数据进行预处理。词向量训练,并通过GRU神经网络将信号按照其对电网影响程度大小进行分类,构建了电网告警信息分类模型,实例分析证明了该方法的准确性。可行性,且能进一步改进与提升故障识别效率。分类结果可供电网工作人员参考,通过分类结果对不同级别的告警信息进行不同的处理操作,免去人工分类的资源浪费。
With the expansion of power system scale,the demand for substation monitoring system is increasing,which is mainly reflected in alarm information processing ability. In this paper,a power equipment risk operation evaluation system is designed,then a power fault index system is established based on monitoring data of power grid. Teleindication is an alarm information recorded in the form of natural language. In this paper,preprocessing and word vector training of teleindication signal are carried out,and the signals are classified by GRU neural network according to the degree of influence on the power grid,and the model of power grid alarm information classification is constructed. The simulation results show the model is feasible and effective,which can further improve the efficiency of fault identification. The classification results can be used as a reference for power grid operators,and different alarm information should be processed differently through the classification results,so as to avoid the waste of resources by manual classification. It is great significance to the safe and stable operation of power grid.
With the expansion of power system scale,the demand for substation monitoring system is increasing,which is mainly reflected in alarm information processing ability. In this paper,a power equipment risk operation evaluation system is designed,then a power fault index system is established based on monitoring data of power grid. Teleindication is an alarm information recorded in the form of natural language. In this paper,preprocessing and word vector training of teleindication signal are carried out,and the signals are classified by GRU neural network according to the degree of influence on the power grid,and the model of power grid alarm information classification is constructed. The simulation results show the model is feasible and effective,which can further improve the efficiency of fault identification. The classification results can be used as a reference for power grid operators,and different alarm information should be processed differently through the classification results,so as to avoid the waste of resources by manual classification. It is great significance to the safe and stable operation of power grid.
引文
[1]刘海峰,岳国良,何瑞东,等.电网设备运检等技术标准体系差异探讨[J].科技创新导报,2016,13(10):29-30.LIU Haifeng,YUE Guoliang,HE Ruidong,et al. Discussion on the Difference of Technical Standard System of Power Network Equipment Operation and Inspection[J].Science and Technology Innovation Herald, 2016, 13(10):29-30.
[2]朱意霞,邓建慎,邱俊宏,等. Oracle监控维护技术在变电站监控系统中的应用[J].电力系统保护与控制,2010,38(13):135-139.ZHU Yixia,DENG Jianshen,QIU Junhong,et al. Application on the monitoring and maintenance of Oracle in substation monitoring system[J]. Power System Protection and Control,2010,38(13):135-139.
[3]高艳春.浅析变电站后台监控系统[J].黑龙江科技信息,2017,V(10):74-74.GAO Yanchun. Analysis on Background Monitoring System of Substation[J]. Heilongjiang Science and Technology Information,2017,V(10):74-74.
[4]刘健,林涛,赵江河,等.面向供电可靠性的配电自动化系统规划研究[J].电力系统保护与控制,2014,42(11):52-60.LIU Jian,LIN Tao,ZHAO Jianghe,et al. Specific planning of distribution automation systems based on the requirement of service reliability[J]. Power System Protection and Control,2014,42(11):52-60.
[5]王锡生. 500kV变电站计算机监控系统若干问题的探讨[J].高电压技术,2004,30(Z1):122-123.WANG Xisheng. Disscusion on some problems of cpmputer supervisory and controlling system for 500 kV substation[J]. High-Voltage Technology,2004,30(Z1):122-123.
[6]刘方园,王水花,张煜东.支持向量机模型与应用综述[J].计算机系统应用,2018,27(4):1-9.LIU Fangyuan,WANG Shuihua,ZHANG Yudong. Overview on Models and Applications of Support Vector Machine[J]. Computer Systems&Applications,2018,27(4):1-9.
[7]田芳,周孝信,于之虹.基于支持向量机综合分类模型和关键样本集的电力系统暂态稳定评估[J].电力系统保护与控制,2017,45(22):1-8.TIAN Fang,ZHOU Xiaoxin,YU Zhihong. Power system transient stability assessment based on comprehensive SVM classification model and key sample set[J]. Power System Protection and Control,2017,45(22):1-8.
[8]周庆平,谭长庚,王宏君,等.基于聚类改进的KNN文本分类算法[J].计算机应用研究,2016,33(11):3374-3377,3382.ZHOU Qingping,TAN Changgeng,WANG Hongjun,et al.Improved INN text classification algorithm based on clustering[J]. Application Research of Computers,2016,33(11):3374-3377,3382.
[9]李丹.基于朴素贝叶斯方法的中文文本分类研究[D].保定:河北大学,2011.LI Dan. The Study of Chinese Text Categorization Based on Naive Bayes[D]. Baoding:Hebei University,2011.
[10]苑擎飏.基于决策树中文文本分类技术的研究与实现[D].沈阳:东北大学,2008.YUAN Qingyang. The Research and Implementation of Chinese Text Classification Technology Based on Decision Tree[D]. Shenyang:Northeastern University,2008.
[11]唐慧丰,谭松波,程学旗.基于监督学习的中文情感分类技术比较研究[J].中文信息学报,2007,21(6):88-94,108.TANG Huifeng,TAN Songbo,CHENG Xueqi. Research on Sentiment Classification of Chinese Reviews Based on Supervised Machine Learning Techniques[J]. Journal of ChineseInformationProcessing,2007,21(6):88-94,108.
[12]李婷婷,姬东鸿.基于SVM和CRF多特征组合的微博情感分析[J].计算机应用研究,2015,32(4):978-981.LI Tingting,JI Donghong. Sentiment CRF analysis of micro-log based on SVM and using various combinations of features[J]. Application Research of Computers,2015,32(4):978-981.
[13]李荣陆,王建会,陈晓云,等.使用最大熵模型进行中文文本分类[J].计算机研究与发展,2005,42(1):94-101.LI Ronglu,WANG Jianhui,CHEN Xiaoyun,et al. Using Maximum Entropy Model for Chinese Text Categorization[J]. Journal of Computer Research and Development,2005,42(1):94-101.
[14]熊富林,邓怡豪,唐晓晟. Word2vec的核心架构及其应用[J].南京师范大学学报(工程技术版),2015,15(01):43-48.XIONG Fulin,DENG Yihao,KANG Xiaosheng. The Architecture of Word2vec and Its Applications[J]. Journal of nanjing normal university(engineering),2015,15(1):43-48.
[15]李晓,解辉,李立杰.基于Word2vec的句子语义相似度计算研究[J].计算机科学,2017,44(09):256-260.LI Xiao,XIE Hui,LI Lijie. Research on Sentence Semantic Similarity Calculation Based on Word2vec[J].Computer Science,2017,44(09):256-260.
[16]李雪莲,段鸿,许牧.基于GRU神经网络的中文分词法[EB/OL].厦门大学学报(自然科学版):[2018-04-25].http://kns.cnki.net/kcms/detail/35.1070.N.20170117.1127.012.html.LI Xuelian,DUAN Hong,XU Mu. Chinese Partitioning Method Based on GRU Neural Network[EB/OL]. Journal of Xiamen University(Natural Science):[2018-04-25]. http://kns.cnki.net/kcms/detail/35.1070.N.20170117.1127.012. html.
[2]朱意霞,邓建慎,邱俊宏,等. Oracle监控维护技术在变电站监控系统中的应用[J].电力系统保护与控制,2010,38(13):135-139.ZHU Yixia,DENG Jianshen,QIU Junhong,et al. Application on the monitoring and maintenance of Oracle in substation monitoring system[J]. Power System Protection and Control,2010,38(13):135-139.
[3]高艳春.浅析变电站后台监控系统[J].黑龙江科技信息,2017,V(10):74-74.GAO Yanchun. Analysis on Background Monitoring System of Substation[J]. Heilongjiang Science and Technology Information,2017,V(10):74-74.
[4]刘健,林涛,赵江河,等.面向供电可靠性的配电自动化系统规划研究[J].电力系统保护与控制,2014,42(11):52-60.LIU Jian,LIN Tao,ZHAO Jianghe,et al. Specific planning of distribution automation systems based on the requirement of service reliability[J]. Power System Protection and Control,2014,42(11):52-60.
[5]王锡生. 500kV变电站计算机监控系统若干问题的探讨[J].高电压技术,2004,30(Z1):122-123.WANG Xisheng. Disscusion on some problems of cpmputer supervisory and controlling system for 500 kV substation[J]. High-Voltage Technology,2004,30(Z1):122-123.
[6]刘方园,王水花,张煜东.支持向量机模型与应用综述[J].计算机系统应用,2018,27(4):1-9.LIU Fangyuan,WANG Shuihua,ZHANG Yudong. Overview on Models and Applications of Support Vector Machine[J]. Computer Systems&Applications,2018,27(4):1-9.
[7]田芳,周孝信,于之虹.基于支持向量机综合分类模型和关键样本集的电力系统暂态稳定评估[J].电力系统保护与控制,2017,45(22):1-8.TIAN Fang,ZHOU Xiaoxin,YU Zhihong. Power system transient stability assessment based on comprehensive SVM classification model and key sample set[J]. Power System Protection and Control,2017,45(22):1-8.
[8]周庆平,谭长庚,王宏君,等.基于聚类改进的KNN文本分类算法[J].计算机应用研究,2016,33(11):3374-3377,3382.ZHOU Qingping,TAN Changgeng,WANG Hongjun,et al.Improved INN text classification algorithm based on clustering[J]. Application Research of Computers,2016,33(11):3374-3377,3382.
[9]李丹.基于朴素贝叶斯方法的中文文本分类研究[D].保定:河北大学,2011.LI Dan. The Study of Chinese Text Categorization Based on Naive Bayes[D]. Baoding:Hebei University,2011.
[10]苑擎飏.基于决策树中文文本分类技术的研究与实现[D].沈阳:东北大学,2008.YUAN Qingyang. The Research and Implementation of Chinese Text Classification Technology Based on Decision Tree[D]. Shenyang:Northeastern University,2008.
[11]唐慧丰,谭松波,程学旗.基于监督学习的中文情感分类技术比较研究[J].中文信息学报,2007,21(6):88-94,108.TANG Huifeng,TAN Songbo,CHENG Xueqi. Research on Sentiment Classification of Chinese Reviews Based on Supervised Machine Learning Techniques[J]. Journal of ChineseInformationProcessing,2007,21(6):88-94,108.
[12]李婷婷,姬东鸿.基于SVM和CRF多特征组合的微博情感分析[J].计算机应用研究,2015,32(4):978-981.LI Tingting,JI Donghong. Sentiment CRF analysis of micro-log based on SVM and using various combinations of features[J]. Application Research of Computers,2015,32(4):978-981.
[13]李荣陆,王建会,陈晓云,等.使用最大熵模型进行中文文本分类[J].计算机研究与发展,2005,42(1):94-101.LI Ronglu,WANG Jianhui,CHEN Xiaoyun,et al. Using Maximum Entropy Model for Chinese Text Categorization[J]. Journal of Computer Research and Development,2005,42(1):94-101.
[14]熊富林,邓怡豪,唐晓晟. Word2vec的核心架构及其应用[J].南京师范大学学报(工程技术版),2015,15(01):43-48.XIONG Fulin,DENG Yihao,KANG Xiaosheng. The Architecture of Word2vec and Its Applications[J]. Journal of nanjing normal university(engineering),2015,15(1):43-48.
[15]李晓,解辉,李立杰.基于Word2vec的句子语义相似度计算研究[J].计算机科学,2017,44(09):256-260.LI Xiao,XIE Hui,LI Lijie. Research on Sentence Semantic Similarity Calculation Based on Word2vec[J].Computer Science,2017,44(09):256-260.
[16]李雪莲,段鸿,许牧.基于GRU神经网络的中文分词法[EB/OL].厦门大学学报(自然科学版):[2018-04-25].http://kns.cnki.net/kcms/detail/35.1070.N.20170117.1127.012.html.LI Xuelian,DUAN Hong,XU Mu. Chinese Partitioning Method Based on GRU Neural Network[EB/OL]. Journal of Xiamen University(Natural Science):[2018-04-25]. http://kns.cnki.net/kcms/detail/35.1070.N.20170117.1127.012. html.