학술논문
基于SW-YOLO模型的航空发动机叶片损伤实时检测 / Real time detection of aircraft engine blade damage based on SW-YOLO model
Document Type
Academic Journal
Author
Source
推进技术 / Journal of Propulsion Technology. 45(2):192-198
Subject
Language
Chinese
ISSN
1001-4055
Abstract
孔探检测技术是航空发动机叶片损伤检测的主要手段,但目前依赖人工操作,耗时耗力.本文提出了一个孔探视频检测的SW-YOLO模型,该模型包括输入端、主干网络、颈部网络、头部网络4个模块.首先,在主干网络加入了空间通道注意力模块(Spatial Channel-Convolutional Block Attention Module,SC-CBAM),有效避免位置信息丢失,提高目标边界回归能力,相较于YOLOv5,其平均精度均值(P)A@0.5提高了5.4％.其次,在颈部网络对特征金字塔网络(Feature Pyramid Network,FPN)进行了改进,通过融合低层特征,扩大了模型感受野,有利于较小损伤区域的检测,如烧蚀损伤,平均精度提高了8.1％.最后,通过与YOLOv5,Faster R-CNN,SSD模型的对比实验,结果表明SW-YOLO模型的平均精度均值分别提高了7％,6.2％,6.3％,检测速度满足实时检测需求,有利于提高航空发动机孔探检测的自动化和智能化水平.
Borescope detection technology is one of the main means for detecting damage of aero-engine blades,but currently it mainly relies on manual operation and is time-consuming and labor-intensive.This paper proposes a SW-YOLO model for aero-engine blade damage borescope video detection.The model includes 4 modules:input terminal,backbone network,neck network and head network.Firstly,by adding a space chan-nel attention module Spatial Channel-Convolutional Block Attention Module(SC-CBAM)to the backbone net-work to alleviate the loss of location information and improve the ability of target boundary regression,and its av-erage accuracy (P)A@0.5 increases by 5.4％compared with YOLOv5.Secondly,the structure of Feature Pyramid Network(FPN)is improved in the neck network,and the low-level features are fused to expand the receptive field of the model,which has a better detection effect for the smaller damage area,such as ablation,and the aver-age accuracy is improved by 8.1％.At last,compared with YOLOv5,Faster R-CNN and SSD models,the experi-mental results show that the average precision mean of the SW-YOLO model has been improved about 7％,6.2％,6.3％,respectively,and the detection speed meets the real-time detection requirements,which is condu-cive to improving the automation and intelligence level of aero-engine blade damage borescope detection.
Borescope detection technology is one of the main means for detecting damage of aero-engine blades,but currently it mainly relies on manual operation and is time-consuming and labor-intensive.This paper proposes a SW-YOLO model for aero-engine blade damage borescope video detection.The model includes 4 modules:input terminal,backbone network,neck network and head network.Firstly,by adding a space chan-nel attention module Spatial Channel-Convolutional Block Attention Module(SC-CBAM)to the backbone net-work to alleviate the loss of location information and improve the ability of target boundary regression,and its av-erage accuracy (P)A@0.5 increases by 5.4％compared with YOLOv5.Secondly,the structure of Feature Pyramid Network(FPN)is improved in the neck network,and the low-level features are fused to expand the receptive field of the model,which has a better detection effect for the smaller damage area,such as ablation,and the aver-age accuracy is improved by 8.1％.At last,compared with YOLOv5,Faster R-CNN and SSD models,the experi-mental results show that the average precision mean of the SW-YOLO model has been improved about 7％,6.2％,6.3％,respectively,and the detection speed meets the real-time detection requirements,which is condu-cive to improving the automation and intelligence level of aero-engine blade damage borescope detection.