最优知识传递宽残差网络输电线路螺栓缺陷图像分类  

Image classification method of transmission line bolt defects using the optimal knowledge transfer wide residual network

作　　者：戚银城[1,2] 金超熊 赵振兵[1,2] 丁洁涛 吕斌 Qi Yincheng;Jin Chaoxiong;Zhao Zhenbing;Ding Jietao;Lyu Bin(School of Electrical and Electronic Engineering,North China Electric Power University,Baoding 071003,China;Hebei Key Laboratory of Power Internet of Things Technology,North China Electric Power University,Baoding 071003,China;State Grid Zhejiang Hangzhou Xiaoshan Power Supply CO.,LTD.,Hangzhou 310000,China)

机构地区：[1]华北电力大学电气与电子工程学院,保定071003 [2]华北电力大学河北省电力物联网技术重点实验室,保定071003 [3]国网浙江杭州萧山区供电有限公司,杭州310000

出　　处：《中国图象图形学报》2021年第11期2571-2581,共11页Journal of Image and Graphics

基　　金：国家自然科学基金项目(61871182,61773160);北京市自然科学基金项目(4192055);河北省自然科学基金项目(F2020502009);中央高校基本科研业务费专项资金资助(2018MS095,2020YJ006);模式识别国家重点实验室开放课题基金项目(201900051)。

摘　　要：目的输电线路螺栓图像具有分辨率低和视觉信息较差的特点,针对螺栓缺陷图像分类时教师网络(大模型)参数量大、学生网络(小模型)分类精度低的问题,提出了一种最优知识传递宽残差网络输电线路螺栓缺陷图像分类方法,来弥补使用大小模型进行分类任务的局限性。方法首先改变大模型宽度,即拓宽网络特征表达维度来增加向小模型传递的螺栓缺陷知识和简化小模型结构至3个残差块;然后为了选出传递螺栓缺陷知识性能最优的大模型,提出知识偏差的概念来可视化大模型向小模型螺栓缺陷知识传递的程度,综合分析不同宽度大模型利用知识蒸馏算法与注意力转移算法分别指导小模型训练后的分类准确率,并用知识偏差来确定最优知识传递模型;最后将最优知识传递模型利用知识蒸馏算法与注意力转移算法相结合指导小模型训练,尽可能提升小模型的螺栓缺陷分类性能。结果在自建螺栓缺陷图像分类数据集上进行了验证,结果表明宽度为5的大模型向小模型传递螺栓缺陷知识性能最优,使小模型的螺栓缺陷分类准确率提高了5.56%,小模型与最优大模型的分类准确率只差2.17%,知识偏差为0.28,且小模型的参数量仅为大模型参数量的0.56%。结论本文提出的最优知识传递宽残差网络输电线路螺栓缺陷图像分类方法,弥补了大小模型螺栓缺陷图像分类的局限性,实现了精度与资源消耗的平衡。Objective Bolts play a key role in fixing and connecting various metal parts in transmission lines.Defects seriously affect the power transmission of transmission lines.The imaging background of an inspection image is complicated,the imaging distance and angle are variable,and the bolts occupy a small proportion in the inspection image.Thus,bolt defect images of transmission lines have low resolution and scarce visual information,and they usually require a large model with high complexity and excellent performance to classify bolt defects and ensure accuracy.A large model has a complex structure and numerous parameters,and deploying it on a large scale is difficult due to a large amount of computing resources needed in data analysis.A small model has a simple structure and few parameters,but it cannot completely guarantee the accuracy of bolt defect classification.This study proposes an image classification method of transmission line bolt defects based on the optimal knowledge transfer network to compensate for the limitations of bolt defect classification using large and small models.Method The width of the large model is changed,that is,the dimension of network feature expression is broadened,to fully mine the target information in the bolt image,thereby increasing the bolt defect knowledge of the transferability of the large model to the small model.To reduce the parameters of the small model considerably and improve its operation and maintenance capabilities,the structure of the small model is simplified to a 10-layer residual network with three residual blocks.The number of convolution kernels of each residual block is 16,32,and 64.Therefore,the small model still has obvious features that focus on the low gradient of the bolt image in the low layer,the high difference area in the middle layer,and the overall characteristics of the bolt image in the high layer.Then,the large models of different widths use the attention transfer algorithm and the knowledge distillation algorithm to guide the training of the s

关 键 词：螺栓缺陷分类 最优知识传递 知识偏差 知识蒸馏 注意力转移 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TM75[自动化与计算机技术—计算机科学与技术]