检测器和分类器级联的飞机发动机损伤检测
Detector and classifier cascaded aero-engine detection method
- 2022年27卷第11期 页码:3232-3242
收稿日期:2021-08-30,
修回日期:2021-10-21,
录用日期:2021-10-28,
纸质出版日期:2022-11-16
DOI: 10.11834/jig.210734
移动端阅览
浏览全部资源
扫码关注微信
收稿日期:2021-08-30,
修回日期:2021-10-21,
录用日期:2021-10-28,
纸质出版日期:2022-11-16
移动端阅览
目的
2
基于深度学习的飞机发动机损伤检测是计算机视觉中的一个新问题。当前的目标检测方法没有考虑飞机发动机损伤检测问题的特殊性,将其直接用于发动机损伤检测的效果较差,无法满足实际使用的要求。为了提高损伤检测的精度,提出检测器和分类器级联的发动机损伤检测方法:Cascade-YOLO(cascade-you only look once)。
方法
2
首先,将损伤区域作为正例、正常区域作为负例,训练损伤检测网络,初始化特征提取网络的网络参数;其次,固定特征提取网络,使用多个检测头分别检测不同类型的发动机损伤,每个检测头独立进行检测,从而提高单类别损伤的检测召回率;最后,对于置信度在一定范围内的损伤,训练一个多分类判别器,用于校正检测头输出的损伤类别。基于检测结果,利用语义分割分支可以准确分割出损伤区域。
结果
2
构建了一个具有1 305幅且包含9种损伤类型的孔探图像数据集,并在该数据集上量化、对比了6个先进的目标检测方法。本文方法的平均精确率(mean average precision,MAP)、准确率、召回率相比单阶段检测器YOLO v5分别提高了2.49%、12.59%和12.46%。
结论
2
本文提出的检测器和分类器级联的发动机损伤检测模型通过对每类缺陷针对性地训练单独的检测头,充分考虑了不同缺陷间的分布差异,在提高召回率的同时提升了检测精度。同时该模型易于扩展类别,并可以快速应用于分割任务,符合实际的应用需求。
Objective
2
The healthy issue of aero-engine is threatened due to high temperature and extreme pressure environment in common. The commonly-used manual inspection method for damage detection is very labor-intensive. Therefore
a high detection accuracy-based computer vision algorithm is cost-effective to detect aero-engine status automatically. The existing bore-scope image damage detection methods are divided into two categories: traditional manual-based and deep learning-based. Traditional detection methods are focused on edge detection or filter detection-like image processing for crack or burn detection. Although traditional methods perform well on simple scenes
they cannot generalize well on the complex images like the erosion and oil contamination-derived regions
and it cannot be extended to the other damages like nick and dent. Most aero-engine damage detection methods are based on deep learning technique to resilient designing features and tuning parameters of traditional methods. Multi-objects detection methods like single shot multibox detector(SSD)
you only look once(YOLO) series models are used to detect different damages. However
most of the deep learning-based aero-engine detection methods do not concern about the detection of multiple types of damage in the same region and the low differentiation of damage in the evolution process
which is a limiting factor for the existing state-of-the-art object detectors. To improve the accuracy of detection
we develop an aero-engine damage-oriented detection method via the cascade detector and classifier (Cascade-YOLO). Cascade-YOLO is used to train independent damage detector for each type of damage
which can fully develop the detector of other types of similar damage excluded. Furthermore
a classifier is adopted to modify damage labels after detecting the damages
which is trained with all types of damages.
Method
2
Our YOLO v5-originated cascade-YOLO is developed on object detection benchmarks. There are mainly two differences between Cascade-YOLO and YOLO v5. The first one is that Cascade-YOLO has multiple detection heads for various types of damage detection. The second one is that a multi-class classifier is used to correct damage label in Cascade-YOLO. Specifically
a YOLO v5-based damage detection network is trained by seeing all types' damages as target objects. As the parameters of our backbone network
the parameters of this pre-trained network are used for feature extraction. Thus
the extracted features are suitable for representing all kinds of damages. All parameters of the backbone network are fixed in latter training. Our multiple damage detection heads is employed to extract features based on the backbone network. Each damage detection head is responsible for detecting a single type of damage
which can fully explore the discrimination ability of different types of damages and increase the recall of single type of damage. However
multiple detection heads may fail to classify the damage into correct damage category. To modify the detected label
we adopt a cascade manner via a multi-class classifier after the multi-head detector. We can segment the damage using a modified semantic segmentation method.
Result
2
We build a bore-scope image dataset with 1 305 images in the context of nine different types of damages
and evaluate six state-of-the-art one-stage object detectors (e.g.
single shot multibox detector(SSD)
object detector based on multi-level feature pyramid network(M2Det) and YOLO v5) and two-stage object detectors (e.g.
region convolutional neural network(Mask R-CNN) and BMask R-CNN) on this dataset. The mean average precision(MAP) of Cascade-YOLO is higher than that of YOLO v5 by 2.49%
and is higher than that of Mask R-CNN by 3.3%. The accuracy and recall of Cascade-YOLO are higher than those of YOLO v5 by 12.59% and 12.46%
respectively.
Conclusion
2
Our cascade detector and classifier-based aero-engine damage detection is developed in terms of the tailored bore-scope image. The recall of the damage detection can be increased using a single type damage-oriented independent detection head. The integrated multiple detection heads can detect multiple types of damage. Multiple detection heads share a feature extraction backbone network
which improves the detection efficiency. We adopt a multi-class classifier to correct the labels of the detected damages that having low confidence. Furthermore
we also employ a clear modified semantic segmentation method to segment the damage region. The experiment results show that Cascade-YOLO performances can be qualified for various types of damage detection problem. The Cascade-YOLO is optimized in detection precision
recall and accuracy compared to YOLO v5 and Mask R-CNN. The potential independent detection head method is feasible for the extended damages detection.
Bian X, Lim S N and Zhou N. 2016. Multiscale fully convolutional network with application to industrial inspection//Proceedings of 2016 IEEE Winter Conference on Applications of Computer Vision (WACV). Lake Placid, USA: IEEE: 1-8 [ DOI: 10.1109/WACV.2016.7477595 http://dx.doi.org/10.1109/WACV.2016.7477595 ]
Chen L C, Zhu Y K, Papandreou G, Schroff F and Adam H. 2018. Encoder-decoder with atrous separable convolution for semantic image segmentation//Proceedings of the 15th European Conference on Computer Vision (ECCV). Munich, Germany: Springer: 833-851 [ DOI: 10.1007/978-3-030-01234-2_49 http://dx.doi.org/10.1007/978-3-030-01234-2_49 ]
Chen L Q, Zou L, Fan C E and Liu Y F. 2020. Feature weighting network for aircraft engine defect detection. International Journal of Wavelets, Multiresolution and Information Processing, 18(3): #2050012 [DOI: 10.1142/S0219691320500125]
Cheng T H, Wang X G, Huang L C and Liu W Y. 2020. Boundary-preserving mask R-CNN//Proceedings of the 16th European Conference on Computer Vision (ECCV). Glasgow, UK: Springer: 660-676 [ DOI: 10.1007/978-3-030-58568-6_39 http://dx.doi.org/10.1007/978-3-030-58568-6_39 ]
Guo Y Y, Liu Z G and Gao Q J. 2019. Based on weighted morphology aero-engine bore scope cracks image segmentation//Proceedings of the 11th International Conference on Machine Learning and Computing. Zhuhai, China: ACM: 451-455 [ DOI: 10.1145/3318299.3318371 http://dx.doi.org/10.1145/3318299.3318371 ]
He K M, Zhang X Y, Ren S Q and Sun J. 2016. Deep residual learning for image recognition//Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, USA: IEEE: 770-778 [ DOI: 10.1109/CVPR.2016.90 http://dx.doi.org/10.1109/CVPR.2016.90 ]
He K M, Gkioxari G, Dollár P and Girshick R. 2017. Mask R-CNN//Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy: IEEE: 2961-2969 [ DOI: 10.1109/ICCV.2017.322 http://dx.doi.org/10.1109/ICCV.2017.322 ]
Kim Y H and Lee J R. 2019. Videoscope-based inspection of turbofan engine blades using convolutional neural networks and image processing. Structural Health Monitoring, 18(5/6): 2020-2039 [DOI: 10.1177/1475921719830328]
Kuang K J. 2017. Research on Deep Learning and Its Application on the Defects Detection for Aero Engine. Guangzhou: South China University of Technology
旷可嘉. 2017. 深度学习及其在航空发动机缺陷检测中的应用研究. 广州: 华南理工大学
Li C Y, Ma Q S and Yao H Y. 2007. Analysis of coarseness of edges extracted from borescope images based on wavelet transform. Journal of Beijing University of Aeronautics and Astronautics, 33(6): 705-708
李长有, 马齐爽, 姚红宇. 2017. 基于小波变换的孔探图像边缘粗糙度分析. 北京航空航天大学学报, 33(6): 705-708 [DOI: 10.3969/j.issn.1001-5965.2007.06.018]
Li D W, Li Y D, Xie Q, Wu Y X, Yu Z H and Wang J.2021. Tiny defect detection in high-resolution aero-engine blade images via a coarse-to-fine framework. IEEE Transactions on Instrumentation and Measurement, 70: 1-12 [DOI: 10.1109/TIM.2021.3062175]
Li H, Chen G, Chen X B and Wang H M. 2016. Study on automatic measurement method for aero-engine inner damage crack. Computer Engineering and Applications, 52(11): 233-237
李华, 陈果, 陈新波, 王洪民. 2016. 航空发动机内部裂纹自动测量方法研究. 计算机工程与应用, 52(11): 233-237 [DOI: 10.3778/j.issn.1002-8331.1407-0423]
Li Y D, Han Z Q, Xu H Y, Liu L Z, Li X Q and Zhang K K. 2019. YOLOv3-lite: a lightweight crack detection network for aircraft structure based on depthwise separable convolutions. Applied Sciences, 9(18): #3781 [DOI: 10.3390/app9183781]
Lin T Y, Dollár P, Girshick R, He K M, Hariharan B and Belongie S. 2017. Feature pyramid networks for object detection//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA: IEEE: 2117-2125 [ DOI: 10.1109/CVPR.2017.106 http://dx.doi.org/10.1109/CVPR.2017.106 ]
Liu D X, Wen L M and Zhu M Q. 2007. Research of the adaptive image processing arithmetic for detecting crack of airplane engine blade. Measurement and Control Technology, 26(6): 31-33
刘笃喜, 温立民, 朱名铨. 2007. 飞机发动机叶片裂纹自适应检测算法的研究. 测控技术, 26(6): 31-33 [DOI: 10.3969/j.issn.1000-8829.2007.06.011]
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C Y and Berg A C. 2016. SSD: single shot multibox detector//Proceedings of the 14th European Conference on Computer Vision (ECCV). Amsterdam, the Netherlands: Springer: 21-37 [ DOI: 10.1007/978-3-319-46448-0_2 http://dx.doi.org/10.1007/978-3-319-46448-0_2 ]
Pei G D. 2000. Borescope inspection and modern aeroengine maintenance. Aviation Maintenance and Engineering, (5): 27-28
裴广达. 2000. 孔探与现代航空发动机维护. 航空维修与工程, (5): 27-28
Qiao S Y, Chen L C and Yuille A. 2020. DetectoRS: detecting objects with recursive feature pyramid and switchable atrous convolution [EB/OL]. [2021-05-19] . https://arxiv.org/pdf/2006.02334.pdf https://arxiv.org/pdf/2006.02334.pdf
Qin Z W, Chen J, Hong R J and Wu W W. 2019. Visual salience detection algorithm for surface defects of friction sheets. Journal of Zhejiang University (Engineering Science), 53(10): 1883-1891
秦钟伟, 陈捷, 洪荣晶, 吴伟伟. 2019. 摩擦片表面缺陷的视觉显著性检测算法. 浙江大学学报(工学版), 53(10): 1883-1891 [DOI: 10.3785/j.issn.1008-973X.2019.10.005]
Redmon J, Divvala S, Girshick R and Farhadi A. 2016. You only look once: unified, real-time object detection//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, USA: IEEE: 779-788 [ DOI: 10.1109/CVPR.2016.91 http://dx.doi.org/10.1109/CVPR.2016.91 ]
Shen Z J, Wan X L, Ye F, Guan X J and Liu S W. 2019. Deep learning based framework for automatic damage detection in aircraft engine borescope inspection//Proceedings of 2019 IEEE International Conference on Computing, Networking and Communications (ICNC). Honolulu, USA: IEEE: 1005-1010 [ DOI: 10.1109/ICCNC.2019.8685593 http://dx.doi.org/10.1109/ICCNC.2019.8685593 ]
Yuan Z D. 2018. Borescope inspection for HPT blade of CFM56-7B engine. IOP Conference Series: Materials Science and Engineering, 382(3): #032028 [DOI: 10.1088/1757-899X/382/3/032028]
Zhang D W, Zeng N Y and Lin L. 2020. Detection of blades damages in aero engine//Proceedings of 2020 Chinese Automation Congress (CAC). Shanghai, China: IEEE: 6129-6134 [ DOI: 10.1109/CAC51589.2020.9327202 http://dx.doi.org/10.1109/CAC51589.2020.9327202 ]
Zhang S F, Wen L Y, Bian X, Lei Z and Li S Z. 2018. Single-shot refinement neural network for object detection//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE: 4203-4212 [ DOI: 10.1109/CVPR.2018.00442 http://dx.doi.org/10.1109/CVPR.2018.00442 ]
Zhao Q J, Sheng T, Wang Y T, Tang Z, Chen Y, Cai L and Ling H B. 2019. M2Det: a single-shot object detector based on multi-level feature pyramid network. Proceedings of the AAAI Conference on Artificial Intelligence, 33(1): 9259-9266 [DOI: 10.1609/aaai.v33i01.33019259]
Zhao Y Q, Rao Y, Dong S P and Zhang J Y. 2020. Survey on deep learning object detection. Journal of Image and Graphics, 25(4): 629-654
赵永强, 饶元, 董世鹏, 张君毅. 2020. 深度学习目标检测方法综述. 中国图象图形学报, 25(4): 629-654 [DOI:10. 11834 /jig. 190307]
Zou F Q. 2020. Review of aero-engine defect detection technology//Proceedings of the 4th IEEE Information Technology, Networking, Electronic and Automation Control Conference (ITNEC). Chongqing, China: IEEE: 1524-1527 [ DOI: 10.1109/ITNEC48623.2020.9084849 http://dx.doi.org/10.1109/ITNEC48623.2020.9084849 ]
相关作者
相关机构