基于卷积神经网络的电力设备缺陷文本分类模型研究A Classification Model of Power Equipment Defect Texts Based on Convolutional Neural Network
刘梓权;王慧芳;曹靖;邱剑;
摘要(Abstract):
电网生产管理系统中存在大量闲置的设备缺陷记录文本。针对电力设备缺陷文本的特点,构建了基于卷积神经网络的缺陷文本分类模型。首先通过分析大量电力设备缺陷记录,归纳了电力设备缺陷文本的特点;然后参考中文文本分类的一般流程,并考虑缺陷文本的特点,建立了一种基于卷积神经网络的电力缺陷文本分类模型;最后通过算例对基于卷积神经网络的缺陷分类模型和多种传统机器学习分类模型进行全面比较。算例结果表明,所提出的缺陷文本分类模型能显著降低分类错误率,在分类效率上也比较可观。
关键词(KeyWords): 电力文本处理;缺陷分类;卷积神经网络;机器学习
基金项目(Foundation):
作者(Author): 刘梓权;王慧芳;曹靖;邱剑;
Email:
DOI: 10.13335/j.1000-3673.pst.2017.1377
参考文献(References):
- [1]宋亚奇,周国亮,朱永利.智能电网大数据处理技术现状与挑战[J].电网技术,2013,37(4):927-935.Song Yaqi,Zhou Guoliang,Zhu Yongli.Present status and challenges of big data processing in smart grid[J].Power System Technology,2013,37(4):927-935(in Chinese).
- [2]苗新,张东霞,孙德栋.在配电网中应用大数据的机遇与挑战[J].电网技术,2015,39(11):3122-3127.Miao Xin,Zhang Dongxia,Sun Dedong.The opportunity and challenge of big data’s application in power distribution networks[J].Power System Technology,2015,39(11):3122-3127(in Chinese).
- [3]赵腾,张焰,张东霞.智能配电网大数据应用技术与前景分析[J].电网技术,2014,38(12):3305-3312.Zhao Teng,Zhang Yan,Zhang Dongxia.Application technology of big data in smart distribution grid and its prospect analysis[J].Power System Technology,2014,38(12):3305-3312(in Chinese).
- [4]曹靖,陈陆燊,邱剑,等.基于语义框架的电网缺陷文本挖掘技术及其应用[J].电网技术,2017,41(2):637-643.Cao Jing,Chen Lushen,Qiu Jian,et al.Semantic framework-based defect text mining technique and application in power grid[J].Power System Technology,2017,41(2):637-643(in Chinese).
- [5]Zheng J,Dagnino A.An initial study of predictive machine learning analytics on large volumes of historical data for power system applications[C]//2014 IEEE International Conference on Big Data.Washington DC,USA:IEEE,2014:952-959.
- [6]Rudin C,Waltz D,Anderson R N,et al.Machine learning for the New York City power grid[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(2):328-345.
- [7]马润泽,王龙响,余佳文,等.考虑历史缺陷文本信息的断路器状态评价研究[J].机电工程,2015,32(10):1375-1379.Ma Runze,Wang Longxiang,Yu Jiawen,et al.Circuit breakers’condition evaluation considering the information in historical defect texts[J].Journal of Mechanical&Electrical Engineering,2015,32(10):1375-1379(in Chinese).
- [8]邱剑,王慧芳,应高亮,等.文本信息挖掘技术及其在断路器全寿命状态评价中的应用[J].电力系统自动化,2016,40(6):107-112.Qiu Jian,Wang Huifang,Ying Gaoliang,et al.Text mining technique and application of lifecycle condition assessment for circuit breaker[J].Automation of Electric Power Systems,2016,40(6):107-112(in Chinese).
- [9]浙江省电力公司.Q/ZDJ 44—2005电网变电一次设备缺陷用语规范[S].2005.
- [10]王相伟,史玉良,张建林,等.基于Hadoop的用电信息大数据计算服务及应用[J].电网技术,2015,39(11):3128-3133.Wang Xiangwei,Shi Yuliang,Zhang Jianlin,et al.Computation services and applications of electricity big data based on Hadoop[J].Power System Technology,2015,39(11):3128-3133(in Chinese).
- [11]吕万里.中文文本分类技术研究[D].青岛:山东科技大学,2010.
- [12]李晓红.中文文本分类技术研究[D].兰州:兰州理工大学,2009.
- [13]邱剑.电力中文文本数据挖掘技术及其在可靠性中的应用研究[D].杭州:浙江大学,2016.
- [14]周志华.机器学习[M].北京:清华大学出版社,2016.
- [15]Hinton G E.Learning distributed representations of concepts[C]//Proceedings of the Eighth Annual Conference of the Cognitive Science Society.Amherst,USA:Eighth Annual Conference of the Cognitive Science Society,1986:1-12.
- [16]于政.基于深度学习的文本向量化研究与应用[D].上海:华东师范大学,2016.
- [17]Bengio Y,Ducharme R,Vincent P,et al.A neural probabilistic language model[J].Journal of Machine Learning Research,2003,3(6):1137-1155.
- [18]Lai S,Liu K,He S,et al.How to generate a good word embedding[J].IEEE Intelligent Systems,2016,31(6):5-14.
- [19]国家电网公司.Q/GDW 1904输变电设备缺陷用语规范[S].2014.
- [20]Lecun Y,Bottou L,Bengio Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
- [21]Kim Y.Convolutional neural networks for sentence classification[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing(EMNLP 2014).Doha,Qatar:EMNLP 2014,2014:1746-1751.
- [22]吴杰.基于卷积神经网络的行为识别研究[D].成都:电子科技大学,2015.