Superpixel perception graph neural network for intelligent defect detection of aero-engine blade

被引:1
|
作者
Shang, Hongbing [1 ]
Yang, Qixiu [1 ]
Sun, Chuang [1 ]
Chen, Xuefeng [1 ]
Yan, Ruqiang [1 ]
机构
[1] Xi An Jiao Tong Univ, Sch Mech Engn, Xian 710049, Shaanxi, Peoples R China
关键词
Aero-engine blade; Intelligent borescope inspection; Diagnosis and monitoring; Defect detection; Superpixel perception graph neural network;
D O I
10.1016/j.jmsy.2024.08.009
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Aero-engine is the core component of aircraft and other spacecraft. The high-speed rotating blades provide power by sucking in air and fully combusting, and various defects will inevitably occur, threatening the operation safety of aero-engine. Therefore, regular inspections are essential for such a complex system. However, existing traditional technology which is borescope inspection is labor-intensive, time-consuming, and experiencedependent. To endow this technology with intelligence, a novel superpixel perception graph neural network (SPGNN) is proposed by utilizing a multi-stage graph convolutional network (MSGCN) for feature extraction and superpixel perception region proposal network (SPRPN) for region proposal. First, to capture complex and irregular textures, the images are transformed into a series of patches, to obtain their graph representations. Then, MSGCN composed of several GCN blocks extracts graph structure features and performs graph information processing at graph level. Last but not least, the SPRPN is proposed to generate perceptual bounding boxes by fusing graph representation features and superpixel perception features. Therefore, the proposed SPGNN always implements feature extraction and information transmission at the graph level in the whole SPGNN pipeline, to alleviate the reduction of receptive field and information loss. To verify the effectiveness of SPGNN, we construct a simulated blade dataset with 3000 images. A public aluminum dataset is also used to validate the performances of different methods. The experimental results demonstrate that the proposed SPGNN has superior performance compared with the state-of-the-art methods.
引用
收藏
页码:112 / 126
页数:15
相关论文
共 50 条
  • [31] Laser Displacement Sensor in the Application of Aero-Engine Blade Measurement
    Sun, Bin
    Li, Bing
    IEEE SENSORS JOURNAL, 2016, 16 (05) : 1377 - 1384
  • [32] Calibration of Sensor Pose Error in Aero-Engine Blade Measurement
    Wei, Xiang
    Li, Bing
    Yan, Xiao
    Chen, Lei
    Su, Wenchao
    Xin, Meiting
    Shang, Zhongyu
    2019 IEEE INTERNATIONAL INSTRUMENTATION AND MEASUREMENT TECHNOLOGY CONFERENCE (I2MTC), 2019, : 274 - 279
  • [33] A Novel Ensemble Model on Defects Identification in Aero-Engine Blade
    Jiao, Yingkui
    Li, Zhiwei
    Zhu, Junchao
    Xue, Bin
    Zhang, Baofeng
    PROCESSES, 2021, 9 (06)
  • [34] Perforation of aero-engine fan casing by a single rotating blade
    He, Qing
    Xuan, Haijun
    Liu, Lulu
    Hong, Weirong
    Wu, Rongren
    AEROSPACE SCIENCE AND TECHNOLOGY, 2013, 25 (01) : 234 - 241
  • [35] Repetition count: application to aero-engine blade counting tasks
    Li, Kaiyu
    Zhao, Huitao
    Zhou, Jun
    Wang, Jialu
    SIGNAL IMAGE AND VIDEO PROCESSING, 2025, 19 (06)
  • [37] A Survey of Aero-Engine Blade Modeling and Dynamic Characteristics Analyses
    Zhang, Yaqiong
    Wang, Fubin
    Liu, Jinchao
    Zhao, Heng
    Fu, Chao
    Zhai, Weihao
    Lu, Kuan
    AEROSPACE, 2024, 11 (08)
  • [38] Vibration equation and frequency computation of an aero-engine rotor blade
    Li, K. (likean5@163.com), 1600, Chinese Society of Astronautics (34):
  • [39] Forward polishing process planning of aero-engine blisk blade
    Chen Z.
    Zhao P.
    Shi Y.
    Li F.
    Ding Y.
    Lu D.
    Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University, 2023, 41 (06): : 1107 - 1113
  • [40] Research on the intelligent design system for investment casting die of aero-engine turbine blade based on knowledge
    JIANG RuisongZHANG DinghuaWANG WenhuThe Key Laboratory of Contemporary Design and Integrated ManufacturingMinistry of EducationSchool of Mechanical EngineeringNorthwestern Polytechnical UniversityXian China
    航空动力学报, 2010, (05) : 1061 - 1067