摘要
针对传统配电网局部放电诊断中提取的特征面临自适应能力不足、难以匹配特定故障等问题,提出了一种基于格拉姆角场(Gramian Angular Field,GAF)和卷积神经网络(Convolutional Neural Networks,CNN)的绝缘架空导线局部放电诊断方法。该方法将局部放电数据使用格拉姆角场构造二维图像,并将其图片输入构建的卷积神经网络来对正常信号和局部放电信号进行分类。实验表明,使用GAF-CNN模型对局部放电的识别精度可以达到99.77%。
In view of the problems that the features extracted in the traditional partial discharge diagnosis of distribution network face insufficient adaptive ability and are difficult to match specific faults,a partial discharge diagnosis method for insulated overhead conductors based on Gramian Angular Field(GAF)and Convolutional Neural Networks(CNN)is proposed.In this method,two-dimensional images of partial discharge data are constructed by Gram angle field,and the images are input into the constructed convolutional neural network to classify normal signals and partial discharge signals.The experiment shows that the recognition accuracy of partial discharge using GAF-CNN model can reach 99.77%.
作者
刘洪笑
向勉
周丙涛
朱黎
段亚穷
张晓艳
LIU Hongxiao;XIANG Mian;ZHOU Bingtao;ZHU Li;DUAN Yaqiong;ZHANG Xiaoyan(College of Intelligent Systems Science and Engineering,Hubei Minzu University,Enshi 445000,China)
出处
《通信电源技术》
2022年第14期10-12,16,共4页
Telecom Power Technology
基金
国家自然科学基金项目(61961017)
2020年湖北省教育厅科学技术研究计划青年人才项目(Q20201902)
2019年湖北民族大学博士启动基金项目(MD2020B009)。
