基于CNN-BiLSTM-Attention的励磁涌流识别方法  

Excitation inrush current identification method based on CNN-BiLSTM-Attention

作　　者：杨建峥 王建 赵洪峰[1] 高超杰 YANG Jianzheng;WANG Jian;ZHAO Hongfeng;GAO Chaojie(College of Electric Engineering,Xinjiang University,Urumqi 830017,China;Electric Power Research Institute,State Grid Xinjiang Electric Power Co.,Ltd.,Urumqi 830011,China)

机构地区：[1]新疆大学电气工程学院,乌鲁木齐830017 [2]国网新疆电力有限公司电力科学研究院,乌鲁木齐830011

出　　处：《国外电子测量技术》2025年第1期10-16,共7页Foreign Electronic Measurement Technology

基　　金：新疆维吾尔自治区自然科学基金(2022D01C21)。

摘　　要：由于变压器铁芯材料工艺的改进,导致传统励磁涌流识别方法准确度逐渐降低,从而引起变压器差动保护误动作这一问题。针对上述问题,提出了一种融合注意力机制的CNN-BiLSTM励磁涌流识别模型。首先通过PSCAD仿真平台搭建变压器空载合闸,变压器并联运行及各种内部故障模型,通过仿真在以上模型中采集各种瞬时电流数据,据此作为本识别模型的数据集;其次在MATLAB平台上搭建并训练CNN-BiLSTM-Attention识别模型;最后使用不同模型进行对比实验,并进行抗噪性分析。结果表明:相比于其他故障识别方法,CNN-BiLSTM-Attention神经网络不仅可以100%区分出励磁涌流、和应涌流和故障电流,而且对于不同故障电流之间识别准确率也更高。证明了该模型具有泛化性能好、拟合能力高和抗噪性强的优点。Due to advancements in the manufacturing techniques of transformer core materials,the precision of traditional excitation inrush current detection methods has progressively diminished,thereby precipitating the issue of erroneous operation in transformer differential protection systems.To address this issue,a novel CNN-BiLSTM excitation inrush current identification model incorporating an attention mechanism was proposed.Initially,various instantaneous current data were collected using the PSCAD simulation platform,simulating transformer energization,parallel operation,and internal faults,forming the dataset for the model.Subsequently,the CNN-BiLSTM-Attention model was constructed and trained on MATLAB.Finally,comparative experiments are conducted using different models,followed by an analysis of noise resistance.Results demonstrate that the CNN-BiLSTM-Attention neural network not only distinguishes excitation inrush,over-excitation,and fault currents with 100%accuracy,but also exhibits superior differentiation among different fault currents.The model has been shown to exhibit strengths including robust generalization performance,high fitting capacity,and resilient noise resistance.

关 键 词：励磁涌流 和应涌流 故障电流 卷积神经网络 双向长短期记忆网络 注意力机制 故障识别 

分 类 号：TM406[电气工程—电器] TP305[自动化与计算机技术—计算机系统结构]