Defect monitoring system of the internal structures of a sodium fast reactor using an artificial intelligence model
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This study developed a defect-monitoring system with an artificial intelligence model, YOLOv7, which is tailored for processing image data from an ultrasonic visualization system within sodium fast reactor (SFR) internal structures. For the safety of SFR internal structures, although it is a crucial inspection for defect monitoring, it is difficult to identify structural defects because of the invisible environment. Therefore, we applied the YOLOv7 model in this study; however, we encountered challenges including decreased accuracy with complex defect shapes and complications from data augmentation during pre-training. To solve these problems, we additionally applied the enhanced super-resolution generative adversarial network for higher resolution and a Sobel noisefiltering algorithm to enhance the defect detection accuracy. And we evaluated our system by comparing it with a confidence score. This underscores the effectiveness of the approach in enhancing the defect detection capabilities. Therefore, this defect-monitoring system should be designed to preemptively identify internal structure deformations and enhance SFR safety and maintenance practices.
Abstract
This study developed a defect-monitoring system with an artificial intelligence model, YOLOv7, which is tailored for processing image data from an ultrasonic visualization system within sodium fast reactor (SFR) internal structures. For the safety of SFR internal structures, although it is a crucial inspection for defect monitoring, it is difficult to identify structural defects because of the invisible environment. Therefore, we applied the YOLOv7 model in this study; however, we encountered challenges including decreased accuracy with complex defect shapes and complications from data augmentation during pre-training. To solve these problems, we additionally applied the enhanced super-resolution generative adversarial network for higher resolution and a Sobel noisefiltering algorithm to enhance the defect detection accuracy. And we evaluated our system by comparing it with a confidence score. This underscores the effectiveness of the approach in enhancing the defect detection capabilities. Therefore, this defect-monitoring system should be designed to preemptively identify internal structure deformations and enhance SFR safety and maintenance practices.
참고문헌 (23)
- Structural materials for liquid metal cooled fast reactor fuel assembliesoperational behaviour, nuclear energy series No. NF-T-4.3, "IAEA", Int. Atomic Energy Agen, ~ (2012)
- Status and trends of nuclear fuels technology for sodium cooled fast reactors, nuclear energy series No. NF-T-4.1, "IAEA", Int. Atomic Energy Agen, ~ (2012)
- T. Yamaguchi, "New approach for the detection of defects in the core support structure of SFRs using EMAT based on a Halbach magnet", Nucl. Eng. Des, 401, pp.112084~ (2023)[DOI]
- Y. Joo, "Development of ultrasonic waveguide sensor for under-sodium inspection in a sodium-cooled fast reactor", NDT&E International, 44, pp.239~246 (2011)[DOI]
- A. Kumar, "An ultrasonic methodology for in-service inspection of shell weld of core support structure in a sodium cooled fast reactor", Nucl. Eng. Des, 282, pp.83~92 (2015)[DOI]
- J. Wessels, "Inservice inspection of the reactor block of sodium-cooled fast breeder reactors", Nucl. Eng. Des, 130, pp.33~42 (1991)[DOI]
- F. Reverdy, "Simulation of ultrasonic inspection for sodium cooled reactors using CIVA", 2011 2nd International Conference on Advancements in Nuclear Instrumentation, Measurement Methods and Their Applications (2011)
- Under Sodium Ultrasonic Viewing for Fast Breeder Reactors: A Review, "BARC", Bhabha Atomic Research Centre, ~, pp.BARC (2016), 2016[DOI]
- Y. Dai, "A simple prior-free method for non-rigid structure-frommotion factorization", 2012 IEEE Conference on Computer Vision and Pattern Recognition (2012)
- R. Cucchiara, "A Hough transform-based method for radial lens distortion correction", 12th International Conference on Image Analysis and Processing (2003)
- C. Yu, "An improved wavelet transform using singular spectrum analysis for wind speed forecasting based on Elman neural network", Energy Convers. Manag, 148, pp.895~904 (2017)[DOI]
- F. Sunar, "Rectification of remotely sensed images with artificial neural network", Int. Archiv. Photogrammet. Rem. Sens, XXXIII (2000)
- S. Yip, "Content adaptive watermarking using a 2-stage predictor", IEEE International Conference on Image Processing (2005)
- F. Huang, "Genetic algorithm-based power system information security risk assessment method", J. Phys. Conf, 1852(2), pp.022063~[DOI]
- Y. Liu, "A shift and invert reorthogonalization Arnoldi algorithm for solving the chemical master equation", Appl. Math. Comput, 349, pp.1~13 (2019)[DOI]
- L. L. Jeune, "2D ultrasonic antenna system for imaging in liquid sodium", Sensors, 19(19), pp.4334~ (2019)[DOI]
- P. Jiang, "A review of yolo algorithm developments", Procedia Comput. Sci, 199, pp.1066~1073 (2022)[DOI]
- Y. Zhou, "A YOLO-NL object detector for real-time detection", Expert Syst. Appl, pp.122256~ (2024)[DOI]
- K. Wang, "Development of ultrasonic waveguide techniques for under-sodium viewing", NDT E Int, 49, pp.71~76 (2012)[DOI]
- T. Yamaguchi, "New approach for the detection of defects in the core support structure of SFRs using EMAT based on a Halbach magnet", Nucl. Eng. Des, 401, pp.112084~ (2023)[DOI]
- C. Y. Wang, "YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors", 2023 IEEE, 2023, ~
- C. Ledig, "Photo-realistic single image super-resolution using a generative adversarial network", 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
- W. Shi, "Real-time single image and video super-resolution using an efficient subpixel convolutional neural network", 2016 IEEE Conference on Computer Vision and Pattern Recognition (2016)