基于XGBOOST算法的大型电力变压器运行故障诊断方法  

A Fault Diagnosis Method for Large Power Transformers Based on XGBOOST Algorithm

作　　者：洪奕添 陈伟华 陈统助 郑鑫 HONG Yitian;CHEN Weihua;CHEN Tongzhu;ZHENG Xin(School of Electronic and Information Engineering,Tongji University,Shanghai 201800,China;State Grid Tiantai Power Supply Company,Tiantai 317200,China;State Grid Taizhou Power Supply Company,Taizhou 318000,China)

机构地区：[1]同济大学电子与信息工程学院,上海201800 [2]国网浙江省电力有限公司天台县供电公司,浙江天台317200 [3]国网浙江省电力有限公司台州供电公司,浙江台州318000

出　　处：《电工技术》2024年第11期56-59,共4页Electric Engineering

摘　　要：作为电网中的关键枢纽设备,大型电力变压器运行状态的稳定关乎供电系统的可靠性,所以对其运行故障的诊断具有重要价值。基于XGBOOST算法的大型电力变压器运行故障诊断方法的研究,首先对变压器故障进行预处理,其次建立XGBOOST算法下的诊断模型,接着对故障特征进行选择,然后诊断不同的故障模型,最后进行实验验证,得出XGBOOST算法下大型电力变压器故障诊断方法具有最好适用性的结论。Large power transformers are key hub equipment in power grid,whose operational stability is of crucial importance to reliability of power supply and operational fault diagnosis deserves exploration.The present work introduces XGBOOST algorithm into fault diagnosis of large transformers by first preprocessing transformer faults,and second establishing a diagnostic model which involves selected fault features and diagnoses different fault models.The proposed method is indicated by experimental verification to obtain satisfactory applicability.

关 键 词：XGBOOST算法 变压器故障诊断 故障类型 

分 类 号：TM406[电气工程—电器]