检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:段嘉珺 吴晓欣 何怡刚 宋文斌 殷奕恒 DUAN Jiajun;WU Xiaoxin;HE Yigang;SONG Wenbin;YIN Yiheng(School of Automation,Nanjing University of Information Science&Technology,Nanjing 210044,China;State Grid Nanjing Power Supply Company,Nanjing 210019,China;School of Electrical Engineering and Automation,Wuhan University,Wuhan 430072,China;NR Electric Co.,Ltd.,Nanjing 211102,China)
机构地区:[1]南京信息工程大学自动化学院,江苏南京210044 [2]国网南京供电公司,江苏南京210019 [3]武汉大学电气与自动化学院,湖北武汉430072 [4]南京南瑞继保电气有限公司,江苏南京211102
出 处:《电力自动化设备》2024年第9期212-218,共7页Electric Power Automation Equipment
基 金:南京信息工程大学科研启动经费资助项目(2023r104)。
摘 要:针对变压器绕组诊断的小样本场景,提出一种虚实特征融合的数据-机理驱动方法,通过引入仿真模型弥补实际样本特征不足的问题。提出虚实特征融合方法的原理,推导其基本公式,构建虚实特征融合的小样本故障诊断框架。搭建变压器绕组故障测试实验平台,采集包含不同故障位置、故障类型、故障程度的测试实验样本集,同时获得仿真模拟虚拟数据集。对比试验表明,所提数据-机理融合方法对多种智能算法在不同小样本程度下的诊断性能均有提升效果:在小样本程度为30%的小样本场景下,基于所提方法的平均诊断准确率提高了27.1%。针对虚实数据相似度对诊断结果的影响进行了探讨。Aiming at the small sample scenario of power transformer winding fault diagnosis,a data-mechanism driven method of virtual-real feature fusion is proposed,which introduces the simulation model to make up for the lack of actual sample features.The principle of virtual-real feature fusion method is proposed,its basic calculation formula is deduced,and a small sample fault diagnosis framework of virtual-real feature fusion is constructed.The transformer winding fault test experimental platform is established,and test sample sets containing samples of different fault locations,fault types and fault degrees are collected.Meanwhile,the corresponding simulation data set is obtained.Through comparative experiments,it is verified that the proposed data-mechanism driven method can improve the diagnostic performance of various intelligent algorithms at different small sample levels.Under the small sample scenario with a small sample level of 30%,the average diagnostic accuracy based on the proposed method is improved by 27.1%.The influence of the similarity of virtual and real data on diagnosis results is discussed.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:13.58.175.32