Ultrasonic tomography imaging enhancement approach based on deep convolutional neural networks
Tóm tắt
The containment liner plate (CLP) is a thin layer of carbon steel material applied as a base for concrete structures protecting nuclear material. The structural health monitoring of the CLP is critical to ensure the safety of nuclear power plants. Hidden defects in the CLP can be identified utilizing ultrasonic tomographic imaging techniques such as the reconstruction algorithm for the probabilistic inspection of damage (RAPID) methodology. However, Lamb waves have a multimodal dispersion feature, which makes the selection of a single mode more difficult. Thus, sensitivity analysis was utilized since it allows for the determination of each mode's level of sensitivity as a function of frequency; the S0 mode was chosen after examining the sensitivity. Even though proper Lamb wave mode was selected, the tomographic image had blurred zones. Blurring reduces the precision of an ultrasonic image and makes it more difficult to distinguish the dimensions of the flaw. To enhance the tomographic image of the CLP, deep learning architecture such as U-Net was utilized for the segmentation of the experimental ultrasonic tomographic image, which includes an encoder and decoder part for better visualization of the tomographic image. Nevertheless, collecting enough ultrasonic images to train the U-Net model was not economically feasible, and only a small number of the CLP specimens can be tested. Thus, it was necessary to utilize transfer learning and get the values of the parameters from a pre-trained model with a much larger dataset as a starting point for a new task, rather than training a new model from scratch. Through these deep learning approaches, we were able to eliminate the blurred section of the ultrasonic tomography, leading to images with clear edges of defects and no blurred zones.
Tài liệu tham khảo
Almansouri H, Venkatakrishnan S V, Buzzard GT et al (2019) Deep neural networks for non-linear model-based ultrasound reconstruction. In: 2018 IEEE global conference on signal and information processing, GlobalSIP 2018—proceedings 6–10. https://doi.org/10.1109/GlobalSIP.2018.8646704
Antonioli L, Pella A, Ricotti R et al (2021) Convolutional neural networks cascade for automatic pupil and iris detection in ocular proton therapy. Sensors 21:1–14. https://doi.org/10.3390/s21134400
Bao Y, Tan C, Dong F (2022) Oil–water two-phase flow volume fraction measurement based on nonlinear ultrasound technique. IEEE Trans Instrum Meas https://doi.org/10.1109/TIM.2022.3157368
Basu S, Thirumalaiselvi A, Sasmal S, Kundu T (2021) Nonlinear ultrasonics-based technique for monitoring damage progression in reinforced concrete structures. Ultrasonics 115:106472. https://doi.org/10.1016/j.ultras.2021.106472
De Carvalho OLF, Junior OADC, De Albuquerque AO et al (2022) Bounding box-free instance segmentation using semi-supervised iterative learning for vehicle detection. IEEE J Select Top Appl Earth Obs Remote Sens 15:3403–3420. https://doi.org/10.1109/JSTARS.2022.3169128
Cheng Y, Song Z, Jin J, Yang T (2019) Attenuation characteristics of stress wave peak in sandstone subjected to different axial stresses. Adv Mater Sci Eng. https://doi.org/10.1155/2019/6320601
da Costa MVCV, de Carvalho OLF, Orlandi AG et al (2021) Remote sensing for monitoring photovoltaic solar plants in Brazil using deep semantic segmentation. Energies 14:1–15. https://doi.org/10.3390/en14102960
Deng J, Dong W, Socher R et al (2009) ImageNet: a large-scale hierarchical image database, pp 248–255. https://doi.org/10.1109/cvprw.2009.5206848
Le Dinh T, Kwon S-G, Lee S-H, Kwon K-R (2021) Breast tumor cell nuclei segmentation in histopathology images using EfficientUnet++ and multi-organ transfer learning. J Korea Multimed Soc 24:1000–1011
Duan W, Gan TH (2019) Investigation of guided wave properties of anisotropic composite laminates using a semi-analytical finite element method. Compos Part B Eng 173:106898. https://doi.org/10.1016/j.compositesb.2019.106898
Gao H, Rose JL (2010) Goodness dispersion curves for ultrasonic guided wave based SHM: a sample problem in corrosion monitoring. Aeronaut J 114:49–56. https://doi.org/10.1017/S0001924000003523
Guo J, Zeng X, Liu Q, Qing X (2022) Lamb wave-based damage localization and quantification in composites using probabilistic imaging algorithm and statistical method. Sensors. https://doi.org/10.3390/s22134810
Hay TR, Royer RL, Gao H et al (2006) A comparison of embedded sensor Lamb wave ultrasonic tomography approaches for material loss detection. Smart Mater Struct 15:946–951. https://doi.org/10.1088/0964-1726/15/4/007
Hussain M, Bird JJ, Faria DR (2019) A study on CNN transfer learning for image classification. Adv Intell Syst Comput 840:191–202. https://doi.org/10.1007/978-3-319-97982-3_16
Jin Z, Li X, Zhang Y et al (2022) Boundary regression-based reep neural network for thyroid nodule segmentation in ultrasound images. Neural Comput Appl 34:22357–22366. https://doi.org/10.1007/S00521-022-07719-Y/METRICS
Li W, Xu Y, Qing X, Yang Z (2019) Quantitative imaging of surface cracks in polymer bonded explosives by surface wave tomographic approach. Polym Test 74:63–71. https://doi.org/10.1016/j.polymertesting.2018.12.020
Liu J, Kim JH (2022) A variable attention nested UNet++ network-based NDT X-ray image defect segmentation method. Coatings. https://doi.org/10.3390/coatings12050634
Lyu J, Tan C, Dong F (2020) image reconstruction for ultrasonic tomography using multi-channel convolutional neural network. In: Chinese control conference, CCC 2020-July:7304–7309. https://doi.org/10.23919/CCC50068.2020.9188702
Malikov AKU, Cho Y, Kim YH et al (2021) Ultrasonic assessment of thickness and bonding quality of coating layer based on short-time fourier transform and convolutional neural networks. Coatings. https://doi.org/10.3390/coatings11080909
Martucci D, Civera M, Surace C (2021) The extreme function theory for damage detection: an application to civil and aerospace structures. Appl Sci (switzerland) 11:1–23. https://doi.org/10.3390/app11041716
Medak D, Posilović L, Subašić M et al (2022) DefectDet: a deep learning architecture for detection of defects with extreme aspect ratios in ultrasonic images. Neurocomputing 473:107–115. https://doi.org/10.1016/j.neucom.2021.12.008
Mei Y, Jin H, Yu B et al (2021) Visual geometry Group-UNet: deep learning ultrasonic image reconstruction for curved parts. J Acoust Soc Am 149:2997–3009. https://doi.org/10.1121/10.0004827
Mushtaq Z, Su SF, Tran QV (2021) Spectral images based environmental sound classification using CNN with meaningful data augmentation. Appl Acoust 172:107581. https://doi.org/10.1016/j.apacoust.2020.107581
Nayak DR, Padhy N, Mallick PK et al (2022) Brain tumor classification using dense efficient-net. Axioms. https://doi.org/10.3390/axioms11010034
Nguon LS, Seo J, Seo K et al (2022) Reconstruction for plane-wave ultrasound imaging using modified U-Net-based beamformer. Comput Med Imaging Graph. https://doi.org/10.1016/J.COMPMEDIMAG.2022.102073
Pedrayes OD, Lema DG, Usamentiaga R et al (2022) Semantic segmentation for non-destructive testing with step-heating thermography for composite laminates. Meas J Int Meas Confed 200:111653. https://doi.org/10.1016/j.measurement.2022.111653
Pramanik R, Arockiarajan A (2019) Effective properties and nonlinearities in 1–3 piezocomposites: a comprehensive review. Smart Mater Struct. https://doi.org/10.1088/1361-665X/ab350a
Sharma N, Gupta S, Koundal D et al (2023) U-Net model with transfer learning model as a backbone for segmentation of gastrointestinal tract. Bioengineering 10:119. https://doi.org/10.3390/bioengineering10010119
Shi Z, Zhao Y, Ma C, Zhang J (2020) Parametric study of ultrasonic De-icing method on a plate with coating. Coatings. https://doi.org/10.3390/coatings10070631
Siddique N, Paheding S, Elkin CP, Devabhaktuni V (2021) U-net and its variants for medical image segmentation: a review of theory and applications. IEEE Access 9:82031–82057. https://doi.org/10.1109/ACCESS.2021.3086020
Šofer M, Šofer P, Ferfecki P et al (2021) Lamb wave mode scattering analysis on adhesively bonded single lap joint using modal decomposition method. Appl Math Model 89:413–427. https://doi.org/10.1016/j.apm.2020.08.017
ugli Malikov AK, Cho Y, Kim YH et al (2023) A novel ultrasonic inspection method of the heat exchangers based on circumferential waves and deep neural networks. Sci Prog 106:003685042211460. https://doi.org/10.1177/00368504221146081
ugli Malikov AK, Kim YH, Yi J-H et al (2022) Neural-network-based ultrasonic inspection of offshore coated concrete specimens. Coatings 12:773. https://doi.org/10.3390/coatings12060773
Wang B, Li J, Luo J et al (2021) Intelligent deblending of seismic data based on U-net and transfer learning. IEEE Trans Geosci Remote Sens 59:8885–8894. https://doi.org/10.1109/TGRS.2020.3048746
Wang S, Wu W, Shen Y et al (2020) Influence of the pzt sensor array configuration on lamb wave tomography imaging with the rapid algorithm for hole and crack detection. Sensors (switzerland). https://doi.org/10.3390/s20030860
Wu J, Chen XY, Zhang H et al (2019) Hyperparameter optimization for machine learning models based on Bayesian optimization. J Electron Sci Technol 17:26–40. https://doi.org/10.11989/JEST.1674-862X.80904120
Wu J, Xu X, Liu C et al (2021) Lamb wave-based damage detection of composite structures using deep convolutional neural network and continuous wavelet transform. Compos Struct 276:114590. https://doi.org/10.1016/j.compstruct.2021.114590
Zhang J, Cho Y, Kim J et al (2021) Non-destructive evaluation of coating thickness using water immersion ultrasonic testing. Coatings 11:1–10. https://doi.org/10.3390/COATINGS11111421
Zhang J, Cho Y, Kim J et al (2023) Nondestructive inspection of underwater coating layers using ultrasonic lamb waves
Zhao X, Gao H, Zhang G et al (2007) Active health monitoring of an aircraft wing with embedded piezoelectric sensor/actuator network: I. Defect detection, localization and growth monitoring. Smart Mater Struct 16:1208–1217. https://doi.org/10.1088/0964-1726/16/4/032
Zhou Q, Wang Q, Bao Y et al (2022) LAEDNet: a lightweight attention encoder–decoder network for ultrasound medical image segmentation. Comput Electr Eng 99:107777. https://doi.org/10.1016/J.COMPELECENG.2022.107777
Zhuang F, Qi Z, Duan K et al (2021) A comprehensive survey on transfer learning. Proc IEEE 109:43–76. https://doi.org/10.1109/JPROC.2020.3004555