基于深度神经网络的飞机产品铆钉连接缺陷识别。

Deep Neural Network Recognition of Rivet Joint Defects in Aircraft Products.

机构信息

Laboratory of Intellectual Control Systems and Modeling, V.A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences, 117997 Moscow, Russia.

Laboratory of Cyber-Physical Systems, V.A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences, 117997 Moscow, Russia.

出版信息

Sensors (Basel). 2022 Apr 29;22(9):3417. doi: 10.3390/s22093417.

DOI:10.3390/s22093417

PMID:35591107

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9105654/

Abstract

The mathematical statement of the problem of recognizing rivet joint defects in aircraft products is given. A computational method for the recognition of rivet joint defects in aircraft equipment based on video images of aircraft joints has been proposed with the use of neural networks YOLO-V5 for detecting and MobileNet V3 Large for classifying rivet joint states. A novel dataset based on a real physical model of rivet joints has been created for machine learning. The accuracy of the result obtained during modeling was 100% in both binary and multiclass classification.

摘要

给出了飞机产品中铆钉连接缺陷识别问题的数学表述。提出了一种基于飞机接头视频图像的飞机设备铆钉连接缺陷识别计算方法，该方法使用 YOLO-V5 神经网络进行检测，MobileNet V3 Large 进行铆钉连接状态分类。为机器学习创建了一个基于真实物理模型的新型铆钉数据集。在建模过程中获得的结果的准确率在二进制和多类分类中均达到了 100%。