南方电网技术2024，Vol.18Issue(11)：13-22,10.DOI:10.13648/j.cnki.issn1674-0629.2024.11.002
基于CNN-GRU深度学习的模块化多电平矩阵变换器故障诊断
Fault Diagnosis of Modular Multilevel Matrix Converter Based on CNN-GRU Deep Learning
摘要
Abstract
Modular multilevel matrix converter(M3C)is a low-frequency power transmission AC-AC converter used for offshore wind power generation.In order to improve the reliability and stability of M3C operation,it is necessary to have an efficient and ac-curate diagnosis method for the open circuit fault of IGBT in its submodules.Therefore,a deep learning fault diagnosis method based on the combination of convolutional neural network(CNN)and gated loop unit(GRU)is proposed.On the basis of analyzing the operating conditions of M3C submodule,wavelet packet analysis is performed on the original fault data,the high-frequency components of which are converted into two-dimensional fault images through temporal image conversion as the training and valida-tion dataset for deep learning,and the features of the high-dimensional data are extracted by CNN,and then the data is optimized and trained by GRU,so as to realize the diagnosis identification of the M3C fault categories.Compared to traditional methods,this method has more accurate and fast fault diagnosis capabilities.关键词
模块化多电平矩阵变换器/小波包分析/卷积神经网络/门控循环单元/故障诊断Key words
modular multilevel matrix converter/wavelet packet analysis/convolutional neural network/gate recurrent unit/fault diagnosis分类
动力与电气工程引用本文复制引用
朱晋,程启明,程尹曼..基于CNN-GRU深度学习的模块化多电平矩阵变换器故障诊断[J].南方电网技术,2024,18(11):13-22,10.基金项目
国家自然科学基金资助项目(62303301) （62303301）
上海市电站自动化技术重点实验室资助项目(13DZ2273800). Supported by the National Natural Science Foundation of China(62303301) （13DZ2273800）
the Project of Shanghai Key Laboratory of Power Station Automation Technology(13DZ2273800). （13DZ2273800）
