Research on small target damage detection of aero-engine based on improved YOLOv4

被引：0

作者：

Cai S. ^{[1
]}

Yan Z. ^{[1
]}

机构：

[1] College of Aeronautical Engineering, Civil Aviation University of China, Tianjin

来源：

Hangkong Dongli Xuebao/Journal of Aerospace Power | 2023年 / 38卷 / 02期

关键词：

depthwise separable convolution; multi-scale feature fusion; path aggregation network; small target detection; YOLOv4; model;

D O I：

10.13224/j.cnki.jasp.20220557

中图分类号：

学科分类号：

摘要：

Intelligent aero-engines damage detection is an important research direction in aircraft fault diagnosis. An improved multi-scale target detection method based on You Only Look Once version 4 (YOLOv4) was proposed for the problem that existing target detection model has a poor effect on the detection of small target damage of aero-engine. A new shallow feature fusion layer was constructed in path aggregation network （PANet）， which fused shallower features with deep features to improve the network detection performance for small target damage. In order to reduce redundant parameters in the network， depthwise separable convolution was introduced in neck and the standard convolution was reconstructed into the form of depthwise separable convolution. Experiments showed that the improved YOLOv4 improved the detection accuracy of small target damage by 3.43%， reduced the model size by 54.06 MB， and increased the detection speed of the model by 31.03%. The results of the study indicated that the improved YOLOv4 model had better detection performance for small target damage. © 2023 BUAA Press. All rights reserved.

引用

页码：445 / 452

页数：7

共 21 条

[1]

ZHANG Yong, Research on the application of endoscopic image feature extraction technology in aeroengine diagnosis, (2006)

[2]

LECUN Y，, BENGIO Y，, HINTON G., Deep learning[J], Nature, 521, 7553, pp. 436-444, (2015)

[3]

JANG J，, AN H, LEE J H, Et al., Construction of faster R-CNN deep learning model for surface damage detection of blade systems[J], Journal of the Korea Institute for Structural Maintenance and Inspection, 23, 7, pp. 80-86, (2019)

[4]

LI Longpu, Research on damage identification of aeroengine blades based on borescope data, (2020)

[5]

LI Hao, Research on the blade crack detection of aero-engine based on image recognition, (2019)

[6]

CHEN Z H, JUANG J C., Attention-based YOLOv4 algorithm in non-destructive radiographic testing for civic aviation maintenance

[7]

CHEN Wei, LIANG Chenhong, Aeroengine target defect detection based on improved SSD, Control Engineering of China, 28, 12, pp. 2329-2335, (2021)

[8]

SUN Q S, ZENG S G，, LIU Y, Et al., A new method of feature fusion and its application in image recognition[J], Pattern Recognition, 38, 12, pp. 2437-2448, (2005)

[9]

ZHAO Q，, SHENG T, Et al., M2det: a single-shot object detector based on multi-level feature pyramid network, Proceedings of the AAAI Conference on Artificial Intelligence, pp. 9259-9266, (2019)

[10]

KIM S W，, KOOK H K, SUN J Y，, Et al., Parallel feature pyramid network for object detection, Proceedings of the European Conference on Computer Vision (ECCV), pp. 234-250, (2018)

← 1 2 3 →