基于特征融合卷积神经网络的绝缘子无损检测  

Insulator Nondestructive Testing Based on Feature Fusion CNN

作　　者：马立新 豆晨飞 宋晨灿 杨天笑 MA Lixin;DOU Chenfei;SONG Chencan;YANG Tianxiao(School of Mechanical Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China)

机构地区：[1]上海理工大学机械工程学院,上海200093

出　　处：《电子科技》2021年第7期26-30,共5页Electronic Science and Technology

基　　金：国家自然科学基金(61205076)。

摘　　要：针对目前存在的电力输配电网络难以检测运营中的绝缘子绝缘劣化问题,文中在分析绝缘劣化机理的基础上,提出了一种基于特征融合卷积神经网络检测绝缘子绝缘劣化的智能方法。该方法首先通过对绝缘子进行闪络实验使其产生无放电、弱放电、强放电三种状态;然后使用紫外成像仪采集不同放电状态下的绝缘子紫外图像构成样本库;采用卷积神经网络对样本进行特征提取,并将提取的浅层特征和深层特征进行融合;最后对融合特征图进行识别与分类,判断绝缘子劣化情况。结果表明,该方法正确率最高达到97.4%。同AlexNet算法对比,文中所提方法具有更高的准确率和更快的收敛速度。Currently,it is difficult for the electric power transmission and distribution network to detect the insulator's insulation deterioration in operation.In view of this problem,on the basis of the analysis of the insulation deterioration mechanism,this study proposes an intelligent method based on the feature-fused CNN to detect whether the insulator produces the insulation deterioration.Firstly,the flashover experiment is conducted on the insulator to produce three states as follows:no discharge,weak discharge and strong discharge.Subsequently,the ultraviolet imager is applied to collect the CNN insulator's ultraviolet images in different discharge state to form the sample library.Then,the CNN is adopted to extract the sample's features and fuse the extracted shallow and deep features.Finally,the fusion feature map is identified and classified to judge whether the insulator is degraded.The result reveals that this method has a high detection rate,and the highest correct rate reachs 97.4%.Compared to the AlexNet algorithm,this method has a higher accuracy and quicker convergence speed.

关 键 词：深度学习 卷积神经网络 闪络实验 紫外放电 特征提取 特征融合 无损检测 绝缘子 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]