基于DGA和AO-PNN的变压器故障诊断方法研究  

Transformer Fault Diagnosis Method Based on DGA and AO-PNN

作　　者：张晓虎 李斌 ZHANG Xiaohu;LI Bin(College of Electrical and Information Engineering,Hunan University of Technology,Zhuzhou 412000,China)

机构地区：[1]湖南工业大学电气与信息工程学院,湖南株洲412000

出　　处：《电工技术》2023年第3期66-69,共4页Electric Engineering

基　　金：国家重点研发计划项目(编号2022YFE0105200)。

摘　　要：为提高油浸式电力变压器故障诊断的准确率,提出了一种将AO-PNN模型与油中溶解气体分析法(DGA)相结合的故障诊断方法。该方法引入天鹰优化算法对概率神经网络进行优化,将DGA比值输入模型最终得到变压器的故障诊断结果。仿真结果表明,与其他常用的机器学习模型相比,提出的模型有更高的准确率,可有效运用到变压器故障诊断领域。In order to improve the accuracy of fault diagnosis of oil immersed power transformer,a fault diagnosis method combining AO PNN model and dissolved gas analysis in oil(DGA)is proposed in this paper.In this method,Aquila optimization algorithm is introduced to optimize the probabilistic neural network,and the DGA ratios are input into the model to obtain the fault diagnosis result of transformer.Simulation results show that compared with other commonly used machine learning models,the proposed model has higher accuracy and can be effectively applied to transformer fault diagnosis.

关 键 词：变压器故障诊断 油中溶解气体分析 天鹰优化算法 概率神经网络 

分 类 号：TM411[电气工程—电器]