基于多源Mallat-NIN-CNN网络的变压器绕组故障诊断  

Transformer Winding Fault Diagnosis Based on Multi-Source Mallat-NIN-CNN Network

作　　者：申刘飞 何怡刚 吴晓欣 SHEN Liu-fei;HE Yi-gang;WU Xiao-xin(School of Electrical Engineering,Wuhan University,Wuhan 430000,China)

机构地区：[1]武汉大学电气工程学院,湖北武汉430000

出　　处：《测控技术》2020年第12期80-85,共6页Measurement & Control Technology

基　　金：国家自然科学基金项目(51577046);国家自然科学基金重点项目(51637004);国家重点研发计划“重大科学仪器设备开发”项目(2016YFF0102200);装备预先研究重点项目(41402040301)。

摘　　要：变压器绕组形变是常见的故障,传统的诊断方法参数过多且受噪音干扰导致诊断性能较差。提出了一种基于灰度转换的特征提取方法,该方法将振动信号转换为灰度图像,有效地提取特征。针对单源信号特性信息强度随距离变化的问题,利用多源通道采集振动信息,并利用图像融合手段抑制多源图像中大量冗余信息、信噪比低的问题,提出基于多源Mallat-NIN-CNN网络的电力变压器绕组故障诊断模型,利用Mallat算法对多源振动信号灰度图像分解,通过基于区域特性量测和加权平均方法分别对各分解层的高频分量和低频分量进行融合,将重构的灰度图像输入NIN-CNN网络进行故障诊断。经实验验证,该方法有效抑制了多源信号中的噪声,提高特征信息的完整性,降低了计算量,提高了故障诊断准确性。Transformer winding deformation is a common fault.The traditional method has too many parameters and large noise interference,resulting in poor diagnostic performance.A feature extraction method based on gray scale conversion is proposed,which converts the vibration signals into a gray images and extracts the features effectively.In order to solve the problem that the intensity of the characteristic information of a singlesource signal changes with distance,multi-source channels are used to collect vibration information,and image fusion is used to suppress a large amounts of redundant information and low signal-to-noise ratio in multisource images.A fault diagnosis model for power transformer windings based on multi-source Mallat-NIN-CNN network is proposed.The gray image of multi-source vibration signals is decomposed by Mallat algorithm.The high-frequency components and low-frequency components of each decomposition layer are measured and fused separately based on regional characteristics measurement and weighted average,and the reconstructed gray image is input into the NIN-CNN network for fault diagnosis.Experiments show that this method can effectively suppress the noise in multi-source signals,improve the integrity of feature information,reduce the amount of calculation,and improve the accuracy of fault diagnosis.

关 键 词：变压器绕组 灰度转换 多源信息融合 NIN-CNN网络 

分 类 号：TM41[电气工程—电器]