Preliminary study of artificial intelligence-based fuel-rod pattern analysis of low-quality tomographic image of fuel assembly
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Single-photon emission computed tomography is one of the reliable pin-by-pin verification techniques for spent-fuel assemblies. One of the challenges with this technique is to increase the total fuel assembly verification speed while maintaining high verification accuracy. The aim of the present study, therefore, was to develop an artificial intelligence (AI) algorithm-based tomographic image analysis technique for partial-defect verification of fuel assemblies. With the Monte Carlo (MC) simulation technique, a tomographic image dataset consisting of 511 fuel-rod patterns of a 3 3 fuel assembly was generated, and with these images, the VGG16, GoogLeNet, and ResNet models were trained. According to an evaluation of these models for different training dataset sizes, the ResNet model showed 100% pattern estimation accuracy. And, based on the different tomographic image qualities, all of the models showed almost 100% pattern estimation accuracy, even for low-quality images with unrecognizable fuel patterns. This study verified that an AI model can be effectively employed for accurate and fast partial-defect verification of fuel assemblies
Abstract
Single-photon emission computed tomography is one of the reliable pin-by-pin verification techniques for spent-fuel assemblies. One of the challenges with this technique is to increase the total fuel assembly verification speed while maintaining high verification accuracy. The aim of the present study, therefore, was to develop an artificial intelligence (AI) algorithm-based tomographic image analysis technique for partial-defect verification of fuel assemblies. With the Monte Carlo (MC) simulation technique, a tomographic image dataset consisting of 511 fuel-rod patterns of a 3 3 fuel assembly was generated, and with these images, the VGG16, GoogLeNet, and ResNet models were trained. According to an evaluation of these models for different training dataset sizes, the ResNet model showed 100% pattern estimation accuracy. And, based on the different tomographic image qualities, all of the models showed almost 100% pattern estimation accuracy, even for low-quality images with unrecognizable fuel patterns. This study verified that an AI model can be effectively employed for accurate and fast partial-defect verification of fuel assemblies
참고문헌 (18)
- Additional Detection Techniques under Development, Spent Nuclear Fuel Safeguards, "D. Sweeney", Texas A&M University, Nuclear Security and Safeguards Education Portal, ~ (2017)
- Safeguards in the Design of Facilities for Long Term Spent Fuel Management, IAEA NUCLEAR ENERGY SERIES, "I. A. E. A. International", 10~42, pp.NF-T-3.1 (2018)
- M. Zendel, "IAEA safeguards equipment", Int. J. Nucl. Sci. Technol, 4(1), pp.72~80 (2008)
- T. Honkamaa, "Prototype Tomographic Partial Defect Tester", IAEA-CN–148, ~ (2006)
- T. Honkamaa, "Prototype tomographic partial defect tester : project status update", Proceedings of an International Safeguards Symposium on Addressing Verification Challenges (2007)
- T. Honkamaa, "A Prototype for passive gamma emission tomography", IAEA Symposium on International Safeguards: Linking Strategy, Implementation and People (2014)
- S. Holcombe, "A Novel gamma emission tomography instrument for enhanced fuel characterization capabilities within the OECD Halden Reactor Project", Ann. Nucl. Energy, 85, pp.837~845 (2015)
- Viability Study of Gamma Emission Tomography for Spent Fuel Verification:JNT 1955 Phase I Technical Report, "E.L. Smith", ~ (2016)
- Hybrid Gama Emission Tomography (HGET): FY16Annual Report NO. PNNL-26213, "E.A. Miller", Pacific Northwest National Lab, ~ (2017)
- H. J. Choi, "Optimization of singlephoton emission computed tomography system for fast verification of spent fuel assembly: a Monte Carlo study", J. Instrum, 14, pp.T07002~ (2019)[DOI]
- 최세환, "Development of de-noised image reconstruction technique using Convolutional AutoEncoder for fast monitoring of fuel assemblies", Nuclear Engineering and Technology, 53(3), pp.888~893 (2021), 한국원자력학회[DOI]
- M.D. Zeiler, "Visualizing and Understanding Convolutional Networks", Computer Vision-ECCV, 818~833 (2014)
- A. Krizhevsky, "Imagenet classification with deep convolutional neural networks", Adv. Neural Inf. Process. Syst, pp.1097~1105 (2012)
- K. Simonyan, "Very deep convolutional networks for large-scale image recognition", arXiv preprint arXiv:1409, ~ (2014)
- C. Szegedy, "Going deeper with convolutions", IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn, pp.1~9 (2015)
- L. Wang, "Training Deeper Convolutional Networks with Deep Supervision", arXiv preprint arXiv:1505, ~ (2015)
- C. Y. Lee, "Deeply-supervised nets", Int. Conf. Artif. Intell. Stat, pp.562~570 (2015)
- S. Targ, "Resnet in Resnet: Generalizing Residual Architectures", arXiv preprint arXiv:1603, ~ (2016)