Laser ultrasonic damage identification of composites based on empirical mode decomposition and neural network

被引:0
作者
Fu, Lan-Ling [1 ,2 ]
Wu, Jian-Hao [1 ,2 ]
Yang, Jin-Shui [1 ,2 ]
Li, Shuang [1 ,2 ]
Wu, Lin-Zhi [2 ]
机构
[1] Harbin Engn Univ, Qingdao Innovat & Dev Base, Qingdao 266000, Peoples R China
[2] Harbin Engn Univ, Coll Aerosp & Civil Engn, Harbin 150001, Peoples R China
基金
中国国家自然科学基金;
关键词
Non-destructive testing; Composites; Laser ultrasonic; Empirical mode decomposition; Artificial neural network; Long short-term memory; PROPAGATION IMAGING METHOD; CLASSIFICATION; DELAMINATION; GENERATION;
D O I
10.1016/j.optlaseng.2024.108397
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
In order to ensure the safety and reliability of equipment during service, the implementation of non-destructive testing (NDT) plays a crucial role. Laser ultrasonic technology (LUT) offers several advantages over traditional ultrasonic technology, including non-contact operation, high frequency, wide frequency band. The utilization of LUT to evaluate the condition of composite materials has emerged as a significant approach to ensure safety. Nevertheless, the unsatisfactory surface optical quality of composite materials often results in indistinct imaging outcomes. Moreover, human factors frequently introduce unavoidable biases in the interpretation of the imaging results. As a solution, a neural network-based method for damage detection using LUT has been proposed. Initially, the empirical mode decomposition (EMD) is employed to decompose the signal and select the relevant intrinsic mode functions (IMFs) for signal reconstruction, which yields time-domain features. Subsequently, these features are inputted into the neural network to recognize the state of the material, and the recognition outcomes are incorporated into the pixel matrix. Lastly, C-scan images are created by stacking the pixel matrix and applying a threshold to reduce noise. The results demonstrate that the accuracy of delamination detection reaches 98.5%. Compared to conventional methods, the C-scan images obtained through neural network are more precise and easier to interpret, thereby effectively minimizing misinterpretations caused by manual intervention.
引用
收藏
页数:12
相关论文
共 47 条
  • [1] Complete noncontact laser ultrasonic imaging for automated crack visualization in a plate
    An, Yun-Kyu
    Park, Byeongjin
    Sohn, Hoon
    [J]. SMART MATERIALS AND STRUCTURES, 2013, 22 (02)
  • [2] THE CLASSIFICATION OF DEFECTS FROM ULTRASONIC DATA USING NEURAL NETWORKS - THE HOPFIELD METHOD
    BAKER, AR
    WINDSOR, CG
    [J]. NDT INTERNATIONAL, 1989, 22 (02): : 97 - 105
  • [3] Ultra-fast laser ultrasonic imaging method for online inspection of metal additive manufacturing
    Chen, Yang
    Jiang, Linzhao
    Peng, Yunchao
    Wang, Mengmeng
    Xue, Zhixiang
    Wu, Jinfeng
    Yang, Yang
    Zhang, Jun
    [J]. OPTICS AND LASERS IN ENGINEERING, 2023, 160
  • [4] Automatic defect depth estimation for ultrasonic testing in carbon fiber reinforced composites using deep learning
    Cheng, Xiaoying
    Ma, Gaoshen
    Wu, Zhenyu
    Zu, Hongfei
    Hu, Xudong
    [J]. NDT & E INTERNATIONAL, 2023, 135
  • [5] Laser ultrasonic anomalous wave propagation imaging method with adjacent wave subtraction: Application to actual damages in composite wing
    Chia, Chen Ciang
    Lee, Jung-Ryul
    Park, Chan-Yik
    Jeong, Hyo-Mi
    [J]. OPTICS AND LASER TECHNOLOGY, 2012, 44 (02) : 428 - 440
  • [6] In-situ measurement of Ti-6Al-4V grain size distribution using laser-ultrasonic technique
    Dong, Feng
    Wang, Xiaochen
    Yang, Quan
    Liu, Huaqiang
    Xu, Dong
    Sun, Youzhao
    Zhang, Yanjie
    Xue, Renjie
    Krishnaswamy, Sridhar
    [J]. SCRIPTA MATERIALIA, 2018, 154 : 40 - 44
  • [7] Through-needle all-optical ultrasound imaging in vivo: a preclinical swine study
    Finlay, Malcolm C.
    Mosse, Charles A.
    Colchester, Richard J.
    Noimark, Sacha
    Zhang, Edward Z.
    Ourselin, Sebastien
    Beard, Paul C.
    Schilling, Richard J.
    Parkin, Ivan P.
    Papakonstantinou, Ioannis
    Desjardins, Adrien E.
    [J]. LIGHT-SCIENCE & APPLICATIONS, 2017, 6 : e17103 - e17103
  • [8] Damage characterization using CNN and SAE of broadband Lamb waves
    Gao, Fei
    Hua, Jiadong
    [J]. ULTRASONICS, 2022, 119
  • [9] Multi-frequency localized wave energy for delamination identification using laser ultrasonic guided wave
    Gao, Tianfang
    Liu, Xiao
    Zhu, Jianjian
    Zhao, Bowen
    Qing, Xinlin
    [J]. ULTRASONICS, 2021, 116
  • [10] Towards a multi-fidelity deep learning framework for a fast and realistic generation of ultrasonic multi-modal Total Focusing Method images in complex geometries
    Granados, G. E.
    Miorelli, R.
    Gatti, F.
    Robert, S.
    Clouteau, D.
    [J]. NDT & E INTERNATIONAL, 2023, 139