基于改进YOLOv4的扫描电镜磨粒图像智能识别  

Intelligent Recognition of Wear Particle Images in Scanning Electron Microscope Based on Improved YOLOv4

作　　者：王雨薇 陈果[2] 何超 郝腾飞 马佳丽 WANG Yuwei;CHEN Guo;HE Chao;HAO Tengfei;MA Jiali(College of Civil Aviation,Nanjing University of Aeronautics and Astronautics,Jiangsu Nanjing 210016,China;College of General Aviation and Flight,Nanjing University of Aeronautics and Astronautics,Jiangsu Changzhou 213300,China;School of Automotive and Rail Transit,Nanjing Institute of Technology,Jiangsu Nanjing 211167,China)

机构地区：[1]南京航空航天大学民航学院,江苏南京210016 [2]南京航空航天大学通用航空与飞行学院,江苏常州213300 [3]南京工程学院汽车与轨道交通学院,江苏南京211167

出　　处：《摩擦学学报》2023年第7期809-820,共12页Tribology

基　　金：国家科技重大专项(J2019-IV-004-0071);中国航发商用航空发动机有限责任公司项目资助.

摘　　要：磨损颗粒分析是设备磨损故障诊断和预测的有效手段,为了提高磨粒检测的自动化和智能化程度,提出1种基于改进YOLOv4的目标检测算法,并应用于航空发动机扫描电镜磨粒图像识别.首先,新算法采用VoVNetv2-39替换YOLOv4原主干网络CSPDarknet53,并引入BiFPN特征金字塔结构与新主干相连,同时调整模型中所有3×3标准卷积为深度可分离卷积,以加强多层次特征融合,构造轻量级网络;其次,利用迁移学习解决扫描电镜磨粒图像数量较少的问题,并通过冻结训练加速模型训练过程;最后,应用实际发动机扫描电镜磨粒图像验证,结果表明:新算法相较于原YOLOv4网络,在保证精度的前提下,网络参数量大幅降低,识别速度提升51.1%,满足实际扫描电镜磨粒图像快速、简洁和高精度的检测需求,具备潜在的工程应用价值.Wear particle analysis is an effective method for equipment wear fault diagnosis and prediction.In order to improve the automation and intelligence degree of wear particle detection,a target detection algorithm based on improved YOLOv4 was proposed to automatically extract and identify target particles from wear particle images with complex backgrounds.It overcame the error caused by the traditional method of image segmentation in the face of multi-wear particle images,and was applied to wear particle image recognition in aeroengine Scanning Electron Microscope(SEM).Firstly,VoVNetv2-39 was used to replace YOLOv4’s original backbone network CSPDarknet53.Its unique improved OSA module guaranteed the gradient and direction propagation without interference,and maintained channel information while owning deeper network depth,thus improved the network performance.Secondly,BiFPN feature pyramid structure was introduced to connect with the new backbone.BiFPN could not only completed the feature extraction from top to bottom,but also achieved the weighted fusion of features with different resolutions from bottom to top.At the same time,BiFPN increased the horizontal connection between the input and output of the same level,enriching the semantic information of the feature map.Finally,all 3×3 standard convolutions in the model were adjusted by depthwise separable convolution,in order to build a lightweight network.The improved YOLOv4’s network architecture for image target detection consist of three parts.The first part was the new backbone feature extraction network—VoVNetv2-39.It preliminarily extracted the feature of wear particle images in SEM with the input size of 416×416×3.Three initial effective feature layers were obtained by convolution,combination and addition.The second part was the strengthen feature extraction network—SPP and BiFPN.The first feature layer was passed into BiFPN after OSA Module Stage3 and a convolution block.The second feature layer was passed into BiFPN after OSA Module Stage4 and

关 键 词：航空发动机 磨损颗粒 扫描电镜 深度学习 YOLOv4 图像识别 

分 类 号：TH117.1[机械工程—机械设计及理论]