基于多分类概率输出模型的变压器故障诊断.docVIP

第44卷 第504期 电测与仪表 Vol.44 No.504 2007年 第12期 Electrical Measurement Instrumentation Dec.2007 PAGE 1 - 基于多分类概率输出模型的变压器故障诊断* 王鹤1，姜鸿儒1，王振丁2 （1. 东北电力大学，吉林 吉林 132012；2. 国网山东省电力公司黄岛供电公司，山东 青岛 266000） 摘要：针对传统的SVM方法在辨别故障特征不明确的样本时会导致误诊断的问题，提出一种基于多分类概率输出(MCPO)模型的变压器故障诊断方法。利用Sigmoid函数构建了基于SVM的MCPO模型，模型的输入为DGA数据和变压器故障类型，输出为发生每种类型故障的概率估计，通过制定相关的故障诊断判据利用故障概率信息能够有效的辨识故障特征是否明确。仿真分析结果表明，MCPO模型的诊断结果能够有效识别故障特征不显著的样本，为进一步采取合理的校正措施提供一种参考。 关键词：电力变压器；故障诊断；SVM；概率输出 中图分类号：TM933 文献标识码：B 文章编号：1001-1390（2017）00-0000-00 Fault diagnosis of transformers based on multi-classified probability output model Wang He1, Jiang Hongru1, Wang Zhending2 (1. Northeast Electric Power University, Jilin Jilin 132012, Jilin, China. 2. State Grid Huangdao Power Supply Company, Qingdao Shandong 266002, Abstract：In view of the traditional SVM method may lead to false fault diagnosis when the sample fault feature is unclear, a fault diagnosis method is proposed based on the multi - classified probability output(MCPO) model in this paper. The multi - classified probability output model is constructed by using Sigmoid function based on SVM. The input of the model is the DGA data and the fault type of transformer, the output is the probability estimate for each failure type. The fault probability information can be used to identify whether the fault feature is clear by setting the relevant evaluation standards. The simulation example analysis result showss that the samples with unknown fault characteristics can be identified by using the diagnostic results of the MCPO model, and which provide provides a reference for further reasonable calibration measures. Keywords：power transformer, fault diagnosis, SVM, probability output PAGE 2 0　引 言 电力变压器作为电力系统中能量转换、传输的核心，能否快速、准确地诊断出变压器故障，直接影响系统的安全、稳定运行[1-2]。我国目前已有较多变压器在长期运行过程中出现绝缘老化、材质劣化等故障隐患，这将导致发生事故的概率不断增加[3]。由此有必要采取合理的方法来及时的发现变压器