变压器绝缘纸老化状态与油中水分含量预测方法研究  

Study on prediction method of the aging status of transformer insulation paper and moisture content in oil

作　　者：王晓剑 胡磊 王健[3] 王锐[3] 何天磊 蒋佟佟 WANG Xiaojian;HU Lei;WANG Jian;WANG Rui;HE Tianlei;JIANG Tongtong(China Power Hua Chuang(Suzhou)Electricity Technology Research Co.,Ltd.,Suzhou 215123,China;China Power Hua Chuang Electricity Technology Research Co.,Ltd.,Shanghai 200086,China;Anhui Huainan Pingwei Power Generation Co.,Ltd.,Huainan 232000,China)

机构地区：[1]中电华创(苏州)电力技术研究有限公司,江苏苏州211512 [2]中电华创电力技术研究有限公司,上海200086 [3]安徽淮南平圩发电有限责任公司,安徽淮南232000

出　　处：《电气应用》2022年第5期54-59,共6页Electrotechnical Application

摘　　要：详细介绍了应用BP神经网络算法建立油纸绝缘状态评估系统的实现方法,主要用于预测绝缘纸聚合度和油中水分含量,并对现场多台不同运行年限的变压器进行分析。实验结果表明,基于BP神经网络方法开发的评估系统可有效评估变压器绝缘系统的老化状态。Focusing on the realization of the assessment system established by the application of BP neural network and using it to predict the degree of polymerization of the insulating paper and the moisture content of the insulating oil. Utilizing the developed system to test the transformers different operating year in site. The result shows that assessment system can be developed based on BP neural network method more accurate prediction of the moisture content of the oil and the degree of polymerization of the insulating paper.

关 键 词：油纸绝缘状态 BP神经网络 回复电压法 绝缘纸聚合度 油中水分含量 

分 类 号：TM41[电气工程—电器] TM215.6[一般工业技术—材料科学与工程]