2023年 01期

摘要(Abstract)：

为了提高电力变压器故障检测的准确性和稳定性，提出一种基于一维卷积神经网络和优化自适应神经模糊推理系统的检测方法；将利用溶解气体分析法得到的14个特征属性作为自适应神经模糊推理系统的初始未处理输入，通过一维卷积神经网络从中选择8个最具指示性的属性；采用改进帝王蝶优化算法对自适应神经模糊推理系统进行训练，并通过真实数据集实验与其他电力变压器故障诊断算法进行检测性能对比。结果表明，所提出方法的电力变压器故障检测准确率达98.91%,50次独立运行中故障检测的标准偏差为±0.01,具有检测准确性高、性能稳健、运行时间短的优点。

关键词(KeyWords)： 自适应神经模糊推理系统;一维卷积神经网络;电力变压器;故障检测;特征属性

基金项目(Foundation): 国家自然科学基金项目(51778097);; 国网新疆电力有限公司2020年科技项目(5230DK200006)

作者(Author): 游溢,赵普志,刘冬,晏致涛,刘欣鹏

DOI: 10.13349/j.cnki.jdxbn.20221109.001

参考文献(References)：

[1] KHALILI SENOBARI R,SADEH J,BORSI H.Frequency response analysis (FRA) of transformers as a tool for fault detection and location:a review[J].Electric Power Systems Research,2018,155(7):172-183.

[2] 赵蓓蓓，赵一名，詹翔灵，等.基于组合权重及改进可拓原理的电力变压器部件风险等级评估[J].电测与仪表，2017,54(5):107-112.

[3] 连鸿松，李文琦，赖永华，等.变压器绝缘油溶解气体及含气量现场快速检测一体化装置研究[J].高压电器，2020,56(3):79-86.

[4] XIAO G W,CHEN W G,PENG S Y,et al.Competitive adsorption of gases dissolved in transformer oil on co-doped ZnO(0001) surface[J].Computational Materials Science,2018,142(10):72-81.

[5] 邓先钦，彭伟，厉敏宪，等.应用氦离子化气相色谱法测定变压器油中溶解气体[J].中国电力，2017,50(10):148-152.

[6] TAHA I B M,HOBALLAH A,GHONEIM S S M.Optimal ratio limits of rogers’ four-ratios and IEC 60599 code methods using particle swarm optimization fuzzy-logic approach[J].IEEE Transactions on Dielectrics and Electrical Insulation,2020,27(1):222-230.

[7] 张朝龙，何怡刚，杜博伦，等.基于深度学习的电力变压器智能故障诊断方法[J].电子测量与仪器学报，2020,32(1):81-89.

[8] 张镱议，焦健，汪可，等.基于帝国殖民竞争算法优化支持向量机的电力变压器故障诊断模型[J].电力自动化设备，2018,38(1):99-104.

[9] MALABANAN D R,NERVES A C.Power transformer condition assessment using an immune neural network approach to dissolved gas analysis[C]//TENCON 2014:2014 IEEE Region 10 Conference,October 22-25,2014,Bangkok,Thailand.New York:IEEE,2014:75-82.

[10] HUANG X Y,HUANG X L,WANG B R,et al.Fault diagnosis of transformer based on modified grey wolf optimization algorithm and support vector machine[J].IEEJ Transactions on Electrical and Electronic Engineering,2020,15(3):409-417.

[11] 刘云鹏，罗世豪，王博闻，等.基于Mel时频谱-卷积神经网络的变压器铁芯夹件松动故障声纹模式识别[J].华北电力大学学报(自然科学版),2020,47(6):52-60,67.

[12] LI X,ZHU Y.Optimizing depth discrimination restricted Boltzmann machine based on genetic algorithm for fault diagnosis of transformer[J].International Core Journal of Engineering,2019,5(10):108-116.

[13] ZHAO B,YANG M,DIAO H R,et al.A novel approach to transformer fault diagnosis using IDM and naive credal classifier[J].International Journal of Electrical Power & Energy Systems,2019,105:846-855.

[14] 王维博，张斌，曾文入，等.基于特征融合一维卷积神经网络的电能质量扰动分类[J].电力系统保护与控制，2020,48(6):53-60.

[15] CHATTERJEE S,DAS A.A novel systematic approach to diagnose brain tumor using integrated type-II fuzzy logic and ANFIS (adaptive neuro-fuzzy inference system) model[J].Soft Computing,2020,24(15):11731-11754.

[16] FENG Y H,YANG J,WU C C,et al.Solving 0-1 knapsack problems by chaotic monarch butterfly optimization algorithm with Gaussian mutation[J].Memetic Computing,2018,10(3):135-150.

[17] 冯艳红，杨娟，贺毅朝，等.差分进化帝王蝶优化算法求解折扣{0-1}背包问题[J].电子学报，2018,46(6):1343-1350.

[18] 康晓锐，刘玉芝，翟宽宽，等.基于模糊差分进化算法的甲醇锅炉控制系统[J].济南大学学报(自然科学版),2020,34(6):582-587.

[19] FAN J M,WANG F,SUN Q Q,et al.Application of polycrystalline SnO2 sensor chromatographic system to detect dissolved gases in transformer oil[J].Sensors Actuators:B:Chemical,2018,267(6):636-646.

[20] TIGHTIZ L,NASAB M A,YANG H,et al.An intelligent system based on optimized ANFIS and association rules for power transformer fault diagnosis[J].ISA Transactions,2020,103:63-74.