基于神经网络和控制图法的换流变铁心夹件电流异常诊断方法

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (4871 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要换流变压器在线监测系统是根据特征参数评估变压器状态的系统,记录换流变压器的油中气体组分、套管SF₆气体压力、铁心夹件泄漏电流等重要参数。其中,铁心夹件电流是判定换流变压器铁心接地状态及绝缘强度的重要依据。然而,换流变压器运行时的内部电磁环境较为复杂,并且受传感器精度和工况限制,定阈值的铁心夹件电流异常诊断方法的误报警率较高,给精益化运维工作带来了挑战。本文建立基于神经网络的铁心夹件电流预测模型,并将预测值与在线值的误差作为观测值,提出基于控制图法的铁心夹件电流异常诊断方法。利用某±800kV换流站内的换流变铁心夹件电流数据验证方法的可行性,实验结果表明,所提方法可以避免误告警,并准确判断出真告警。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	於杨
	陈意
	张豹
	仲金龙
	王静

关键词 ：换流变压器, 铁心夹件电流, 神经网络, 多层感知机, 控制图法, 异常诊断

Abstract：The online monitoring system for converter transformers is a system that evaluates the transformer condition based on characteristic parameters. This system records various parameters during the operation of the converter transformer, including gas composition in the oil, SF₆ gas pressure in the bushings, and leakage current in the core clamps. Among these, the core clamp current is a crucial indicator for determining the grounding condition and insulation strength of the transformer core. However, the internal electromagnetic environment of a converter transformer is quite complex during operation, and due to the limitations of sensor precision and operational conditions, the traditional threshold-based abnormal diagnosis methods for core clamp current have a high false alarm rate, posing challenges for refined operation and maintenance. This paper establishes a neural network-based core clamp current prediction model and uses the error between the predicted values and the online values as the observation metric. An abnormal diagnosis method for core clamp current based on the control chart method is proposed. The feasibility of this method is validated using core clamp current data from a ±800kV converter station. The experimental results show that the proposed method can avoid false alarms and accurately diagnose true alarms.

Key words： converter transformer core and clamps current neural network multi-layer perceptron control chart method anomaly diagnosis

收稿日期: 2024-12-04

作者简介: 於杨（1993—）,男,本科,工程师,主要研究方向为特高压直流输电技术和电工电力新技术。

引用本文:

於杨, 陈意, 张豹, 仲金龙, 王静. 基于神经网络和控制图法的换流变铁心夹件电流异常诊断方法[J]. 电气技术, 2025, 26(4): 65-72. YU Yang, CHEN Yi, ZHANG Bao, ZHONG Jinlong, WANG Jing. The diagnosis method for abnormal current in converter transformer core and clamps based on neural networks and control chart method. Electrical Engineering, 2025, 26(4): 65-72.

链接本文:

https://dqjs.cesmedia.cn/CN/Y2025/V26/I4/65

[1] 陆晶晶, 贺之渊, 赵成勇, 等. 直流输电网规划关键技术与展望[J].电力系统自动化, 2019,43(2): 182-191.
[2] 汤奕, 陈斌, 皮景创, 等. 特高压直流分层接入方式下受端交流系统接纳能力分析[J].中国电机工程学报, 2016, 36(7): 1790-1800.
[3] 谢季平, 张文, 杨浩. 特高压直流分层接入下交直流系统中长期电压稳定协调控制[J].电力系统自动化, 2020, 44(6): 37-44.
[4] 熊华强, 杨程祥, 马亮, 等. 含分层接入特高压直流的交直流混联电网机电-电磁暂态混合仿真研究[J].电力系统保护与控制, 2020, 48(24): 145-153.
[5] 李清泉, 王良凯, 王培锦, 等. 换流变压器油纸绝缘局部放电及电荷分布特性研究综述[J].高电压技术, 2020, 46(8): 2815-2829.
[6] 陈生栋, 孙海峰. 特高压换流站三柱四绕组结构换流变压器谐波抑制研究[J].电网技术, 2021, 45(8): 3155-3163.
[7] MOSES A J, ANDERSON P I, PHOPHONGVIWAT T.Localized surface vibration and acoustic noise emitted from laboratory-scale transformer cores assembled from grain-oriented electrical steel[J].IEEE Transa- ctions on Magnetics, 2016, 52(10): 7100615.
[8] 王兵, 陈益萍, 徐华生, 等. 变压器铁心及夹件接地电流在线监测装置[J].电气技术, 2023, 24(6): 69-73, 78.
[9] 李辰辉, 褚继峰, 龙潇, 等. 基于弧触头接触振动特征分析的高压SF₆断路器电寿命在线监测方法[J].电工技术学报, 2024, 39(15): 4883-4895.
[10] 方舟, 张伟, 刘辉, 等. 基于图像形态学特征的GIS局部放电模式识别算法与监测系统[J].电气技术, 2024, 25(10): 48-54, 71.
[11] 电力设备预防性试验规程: DL/T 596—2021[S].北京: 中国电力出版社, 2021.
[12] ZHU Lixun, YOON H S, CHO H J, et al.Finite- element analysis of magnetostriction force in power transformer based on the measurement of anisotropic magnetostriction of highly grain-oriented electrical steel sheet[J].IEEE Transactions on Magnetics, 2016, 52(3): 6100304.
[13] HAMZEHBAHMANI H, ANDERSON P, HALL J, et al.Eddy current loss estimation of edge burr-affected magnetic laminations based on equivalent electrical network-part I: fndamental concepts and FEM modeling[J].IEEE Transactions on Power Delivery, 2014, 29(2): 642-650.
[14] HAMZEHBAHMANI H, ANDERSON P, HALL J, et al.Eddy current loss estimation of edge burr-affected magnetic laminations based on equivalent electrical network-part II: analytical modeling and experimental results[J].IEEE Transactions on Power Delivery, 2014, 29(2): 651-659.
[15] 高博, 陈钟华. 超高压大型变压器铁心故障诊断的试验研究[J].宁夏电力, 2013(6): 11-14, 22.
[16] 张冠军, 田丰, 刘力强, 等. 换流变压器夹件接地电流偏大计算与分析[J].变压器, 2023, 60(12): 12-17.
[17] 苗彭, 王启斌, 武文杰, 等. 换流变压器铁心夹件接地电流谐波特性分析[J].广东电力, 2024, 37(3): 90-97.
[18] 杨明, 侯春光, 高有华. 变压器铁心接地线局放脉冲电流与泄漏电流联合诊断的研究[J].电器与能效管理技术, 2023(12): 1-7.
[19] 赵廷志, 冯新岩, 李承振, 等. 基于套管高频和特高频电流监测的换流变局放监测[J].变压器, 2020, 57(9): 33-37.
[20] 包玉树, 胡永建, 吕佳, 等. 变压器铁芯接地电流在线监测系统设计及其带电检测不确定度评定[J].电测与仪表, 2023, 60(4): 150-154.
[21] 何宁辉, 吴旭涛, 张佩, 等. 基于多分类支持向量机的变压器在线监测数据错误模式识别[J].高压电器, 2024, 60(7): 173-181.
[22] 王鹤蓉. 基于卷积算法的换流变铁芯接地电流谐波检测方法[D].沈阳: 沈阳工程学院, 2021.
[23] 高树国, 汲胜昌, 孟令明, 等. 基于在线监测系统与声振特征预测模型的高压并联电抗器运行状态评估方法[J].电工技术学报, 2022, 37(9): 2179-2189.
[24] 雷蕾潇, 何怡刚, 姚其新, 等. 基于变权属性矩阵的变压器零样本故障诊断技术[J].电工技术学报, 2024, 39(20): 6577-6590.
[25] 胡睿喆, 杨晓峰. 基于小波散射网络-贝叶斯优化门控循环单元的电力变压器声纹识别方法[J].电气技术, 2024, 25(8): 35-40, 46.
[26] 王玎君. 变压器铁心多点接地故障分析与处理[J].电工技术, 2023(15): 151-155.
[27] KIM J, ABDELLA G M, KIM S, et al.Control charts for variability monitoring in high-dimensional pro- cesses[J].Computers & Industrial Engineering, 2019, 130: 309-316.
[28] SUNTHORNWAT R, AREEPONG Y, SUKPARUNGSEE S.Evaluating the performance of modified EWMA control schemes for serially correlated obser- vations[J].Thailand Statistician, 2024, 22(3): 657-673.