A laser ultrasonic intelligent inspection method for metal surface defects based on digital twin model

被引:2
|
作者
Zhang, Yunhao
Zhou, Hong
Yao, Rao
Wu, Mingyue
机构
关键词
Digital twin; Laser ultrasonic; Surface defect; Deep learning; Finite element; ALGORITHM;
D O I
10.1016/j.measurement.2024.115219
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
To enhance the efficiency and intelligence of laser ultrasonic detection of metal surface defects, a detection method based on digital twins is proposed. Given the scarcity of defect samples and the difficulty of obtaining labeled data in practical applications, the finite element method is used to construct a laser ultrasonic metal defect detection model, effectively generating twin data for defect detection. With the help of generative adversarial networks, the distribution difference between twin data and real data is minimized. Additionally, by using continuous wavelet transform, one-dimensional ultrasonic signals are converted into two-dimensional time-frequency images for detection input. In terms of detection algorithm development, a residual network with an optimized global attention mechanism is introduced to ensure real-time synchronization and updates between the digital twin model and the actual laser ultrasonic detection equipment. Finally, experimental validation of the proposed method shows that it effectively addresses the issue of small sample sizes in defect detection and achieves high detection accuracy. Moreover, comparative experiments on crack defect migration tasks under different settings demonstrate the method's good generalization ability.
引用
收藏
页数:16
相关论文
共 50 条
  • [1] An quantitative inspection method for internal defects based on laser ultrasonic technology
    Zeng, Wei
    Qi, Shikai
    Liu, Li
    Yao, Feiyan
    OPTIK, 2020, 216 (216):
  • [2] Laser ultrasonic inspection of surface and subsurface defects in materials based on deep learning
    Zhang, Jing
    Wan, Haopeng
    Sun, Feiyang
    Chen, Xingyu
    Jia, Kangning
    Fan, Li
    Cheng, Liping
    Xu, Xiaodong
    Yan, Xuejun
    Yuan, Peilong
    Zhang, Shuyi
    NONDESTRUCTIVE TESTING AND EVALUATION, 2024,
  • [3] Laser ultrasonic measurement of surface defects based on ratio method
    Li, Gang
    Yu, Hedong
    Zhang, Guoping
    ADVANCED LASER TECHNOLOGIES 2005, PTS 1 AND 2, 2006, 6344
  • [4] Function model construction method based on digital twin for intelligent products
    Zhou Y.
    Wu C.
    Sun J.
    Liu F.
    Li H.
    Jisuanji Jicheng Zhizao Xitong/Computer Integrated Manufacturing Systems, CIMS, 2019, 25 (06): : 1392 - 1404
  • [5] Intelligent inspection of surface defects in metal castings using machine learning
    Yousef, Nabhan
    Parmar, Chandrasinh
    Sata, Amit
    MATERIALS TODAY-PROCEEDINGS, 2022, 67 : 517 - 522
  • [6] A New Laser Ultrasonic Inspection Method for the Detection of Multiple Delamination Defects
    Gao, Tianfang
    Wang, Yishou
    Qing, Xinlin
    MATERIALS, 2021, 14 (09)
  • [7] Intelligent Inspection Method and System of Plastic Gear Surface Defects Based on Adaptive Sample Weighting Deep Learning Model
    Shi, Zhaoyao
    Fang, Yiming
    Song, Huixu
    SENSORS, 2024, 24 (14)
  • [8] Detection and Evaluation of Surface Defects Based on Critical Frequency Method by Laser Ultrasonic
    Li Haiyang
    Li Qiaoxia
    Wang Zhaoba
    Pan Qianghua
    ACTA OPTICA SINICA, 2018, 38 (07)
  • [9] MODEL FOR THE ULTRASONIC INSPECTION OF ROUGH DEFECTS
    OGILVY, JA
    ULTRASONICS, 1989, 27 (02) : 69 - 79
  • [10] Intelligent denoise laser ultrasonic imaging for inspection of selective laser melting components with rough surface
    Xu, Wanli
    Zhang, Jun
    Li, Xiaohong
    Yuan, Shuxian
    Ma, Guanbing
    Xue, Zhixiang
    Jing, Xuechao
    Cao, Jiancheng
    NDT & E INTERNATIONAL, 2022, 125