Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Automated detection of corrosion in used nuclear fuel dry storage canisters using residual neural networks

  • Papamarkou, Theodore (Computational Sciences and Engineering Division, Oak Ridge National Laboratory) ;
  • Guy, Hayley (Department of Mathematics, North Carolina State University) ;
  • Kroencke, Bryce (Department of Computer Science, University of California) ;
  • Miller, Jordan (Center for Cognitive Ubiquitous Computing, Arizona State University) ;
  • Robinette, Preston (Presbyterian College) ;
  • Schultz, Daniel (Innovative Computing Laboratory, University of Tennessee) ;
  • Hinkle, Jacob (Computational Sciences and Engineering Division, Oak Ridge National Laboratory) ;
  • Pullum, Laura (Computer Science and Mathematics Division, Oak Ridge National Laboratory) ;
  • Schuman, Catherine (Computer Science and Mathematics Division, Oak Ridge National Laboratory) ;
  • Renshaw, Jeremy (Electric Power Research Institute) ;
  • Chatzidakis, Stylianos (Reactor and Nuclear Systems Division, Oak Ridge National Laboratory)
  • Received : 2020.03.05
  • Accepted : 2020.07.13
  • Published : 2021.02.25
Download PDF
⟨ Previous Next ⟩

Abstract

Nondestructive evaluation methods play an important role in ensuring component integrity and safety in many industries. Operator fatigue can play a critical role in the reliability of such methods. This is important for inspecting high value assets or assets with a high consequence of failure, such as aerospace and nuclear components. Recent advances in convolution neural networks can support and automate these inspection efforts. This paper proposes using residual neural networks (ResNets) for real-time detection of corrosion, including iron oxide discoloration, pitting and stress corrosion cracking, in dry storage stainless steel canisters housing used nuclear fuel. The proposed approach crops nuclear canister images into smaller tiles, trains a ResNet on these tiles, and classifies images as corroded or intact using the per-image count of tiles predicted as corroded by the ResNet. The results demonstrate that such a deep learning approach allows to detect the locus of corrosion via smaller tiles, and at the same time to infer with high accuracy whether an image comes from a corroded canister. Thereby, the proposed approach holds promise to automate and speed up nuclear fuel canister inspections, to minimize inspection costs, and to partially replace human-conducted onsite inspections, thus reducing radiation doses to personnel.

Keywords

Acknowledgement

This manuscript has been authored by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). The US government retains and the publisher, by accepting the article for publication, acknowledges that the US government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for US government purposes. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public- access-plan). This work was funded by the AI Initiative at the Oak Ridge National Laboratory. This research used resources of the Compute and Data Environment for Science (CADES) at the Oak Ridge National Laboratory, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725. The authors would like to thank Guannan Zhang for helping with the co-supervision of the nuclear project interns at the artificial intelligence summer institute (AISI) 2019 of ORNL.

References

  1. J. Kusnick, M. Benson, S. Lyons, Finite Element Analysis of Weld Residual Stresses in Austenitic Stainless Steel Dry Cask Storage System Canisters, Tech. Rep. (2013) 1-32. https://www.nrc.gov/docs/ML1333/ML13330A512.pdf.
  2. D.B. Rigby, Evaluation of the Technical Basis for Extended Dry Storage and Transportation of Used Nuclear Fuel: Executive Summary, US Nuclear Waste Technical Review Board, 2010.
  3. B. Hanson, H. Alsaed, C. Stockman, D. Enos, R. Meyer, K. Sorenson, Gap Analysis to Support Extended Storage of Used Nuclear Fuel (rev.0), Tech. Rep, US Department of Energy Used Fuel Disposition Campaign, 2012.
  4. O.K. Chopra, D.R. Diercks, R.R. Fabian, Z.H. Han, Y.Y. Liu, Managing Aging Effects on Dry Cask Storage Systems for Extended Long-Term Storage and Transportation of Used Fuel (Rev. 2), Tech. Rep, Argonne National Laboratory, Argonne, IL, 2014.
  5. S. Chu, Flaw Growth and Flaw Tolerance Assessment for Dry Cask Storage Canisters, 2014.
  6. J. Gorman, K. Fuhr, J. Broussard, Literature Review of Environmental Conditions and Chloride-Induced Degradation Relevant to Stainless Steel Canisters in Dry Cask Storage Systems, Tech. Rep, Electric Power Research Institute, Palo Alto, CA, 2014.
  7. K. Fuhr, J. Broussard, G. White, Aging Management Guidance to Address Potential Chloride-Induced Stress Corrosion Cracking of Welded Stainless Steel Canisters, Tech. Rep, Electric Power Research Institute, Palo Alto, CA, 2017.
  8. J. Broussard, S. Chu, Susceptibility Assessment Criteria for Chloride-Induced Stress Corrosion Cracking (CISCC) of Welded Stainless Steel Canisters for Dry Cask Storage Systems, Tech. Rep, Electric Power Research Institute, Palo Alto, CA, 2015.
  9. R.M. Meyer, Nondestructive Examination Guidance for Dry Storage Casks, Tech. Rep. September, Pacific Northwest National Laboratory, 2016.
  10. R.M. Meyer, NDE to Manage Atmospheric SCC in Canisters for Dry Storage of Spent Fuel, Tech. Rep, Pacific Northwest National Laboratory, 2013.
  11. J. Renshaw, S. Chu, Dry canister storage system inspection and robotic delivery system development, in: Tran Sactions of the American Nuclear Society, vol. 115, 2016, pp. 199-200. Palo Alto, CA.
  12. S. Chu, Dry Cask Storage Welded Stainless Steel Canister Breach Consequence Analysis, Tech. Rep, Electric Power Research Institute, Palo Alto, CA, 2019.
  13. C. Bryan, D. Enos, Diablo Canyon Stainless Steel Dry Storage Canister Inspection, Tech. Rep, Electric Power Research Institute, Palo Alto, CA, 2016.
  14. W. Tang, S. Chatzidakis, R. Miller, J. Chen, D. Kyle, J. Scaglione, C. Schrad, Welding process development for spent nuclear fuel canister repair, in: American Society of Mechanical Engineers, Pressure Vessels and Piping Division (Publication) PVP, vol. 1, 2019, https://doi.org/10.1115/PVP2019-93946.
  15. S. Chatzidakis, A.I. Adeniyi, T.F. Severynse, R. Jones, J. Jarrell, J.M. Scaglione, A novel mobile examination and remediation facility for On-site remediation of dry storage systems, in: Proceedings of the Waste Management Conference, Phoenix, AZ, 2018.
  16. S. Chatzidakis, E. Kurt, J. Coleman, J.M. Scaglione, J. Jarrell, System-wide impacts of resolution options for a nonconforming dry storage system, in: Proceedings of Global/TopFuel 2019, American Nuclear Society, 2019, pp. 1040-1047. Seattle, Washington.
  17. S. Chatzidakis, W. Tang, R. Miller, A. Payzant, J. Bunn, C. Bryan, J. Scaglione, J.A. Wang, Neutron diffraction illustrates residual stress behavior of welded alloys used as radioactive confinement boundary, Int. J. Pres. Ves. Pip., 2020.
  18. S. Chatzidakis, W. Tang, J. Chen, R. Miller, A. Payzant, J. Bunn, J.A. Wang, Neutron residual stress mapping of repaired spent nuclear fuel welded stainless-steel canisters, in: International High-Level Radioactive Waste Management 2019, IHLRWM, 2019, pp. 249-253, 2019.
  19. S. Chatzidakis, S. Cetiner, H. Santos-Villalobos, J.J. Jarrell, J.M. Scaglione, Sensor requirements for detection and characterization of stress corrosion cracking in welded stainless steel canisters, in: Proceedings of the 2018 International Congress on Advances in Nuclear Power Plants, ICAPP, 2018, pp. 714-720, 2018.
  20. S. Chatzidakis, J.J. Jarrell, J.M. Scaglione, High-resolution ultrasound imaging using model-based iterative reconstruction for canister degradation detection, in: ANS IHLRWM 2017 - 16th International High-Level Radioactive Waste Management Conference, American Nuclear Society, 2017, pp. 518-523.
  21. B. Lin, D. Dunn, R. Meyer, Evaluating the effectiveness of nondestructive examinations for spent fuel storage canisters, in: AIP Conference Proceedings, vol. 2102, 2019, https://doi.org/10.1063/1.5099781.
  22. Dry Canister Storage System Inspection and Robotic Delivery System Development, Tech. Rep, Electric Power Research Institute, Palo Alto, CA, 2016.
  23. J.B. Renshaw, S. Chu, J.H. Kessler, K. Waldrop, Inspection and monitoring of dry canister storage systems, in: 15th International High-Level Radioactive Waste Management Conference 2015, IHLRWM, 2015, pp. 824-828, 2015.
  24. J. Renshaw, J. Beard, J. Stadler, S. Chu, M. Orihuela, Robotically-deployed NDE inspection development for dry storage systems for used nuclear fuel, in: International Conference on the Management of Spent Fuel from Nuclear Power Reactors: Learning from the Past, Enabling the Future, 2019. Vienna, Austria.
  25. S.A. Chu, J. Renshaw, H. Akkurt, Csontos, Aging management for dry storage canisters, in: International Conference on the Management of Spent Fuel from Nuclear Power Reactors: Learning from the Past, Enabling the Future, 2019. Austria, Vienna.
  26. H. Jones Jr., Robert, Dry Storage Cask Inventory Assessment. Prepared for DOE, Nuclear Fuels Storage and Transportation Planning Project, Tech. Rep, United States Department of Energy, 2015.
  27. C.M. Yeum, S.J. Dyke, Vision-based automated crack detection for bridge inspection, Comput. Aided Civ. Infrastruct. Eng. 30 (10) (2015) 759-770. https://doi.org/10.1111/mice.12141
  28. L.I. Rudin, S. Osher, E. Fatemi, Nonlinear total variation based noise removal algorithms, Phys. Nonlinear Phenom. 60 (1-4) (1992) 259-268. https://doi.org/10.1016/0167-2789(92)90242-F
  29. Y.-J. Cha, K. You, W. Choi, Vision-based detection of loosened bolts using the Hough transform and support vector machines, Autom. ConStruct. 71 (2016) 181-188. https://doi.org/10.1016/j.autcon.2016.06.008
  30. M. O'Byrne, B. Ghosh, F. Schoefs, V. Pakrashi, Regionally enhanced multiphase segmentation technique for damaged surfaces, Comput. Aided Civ. Infrastruct. Eng. 29 (9) (2014) 644-658. https://doi.org/10.1111/mice.12098
  31. L. Wu, S. Mokhtari, A. Nazef, B. Nam, H.-B. Yun, Improvement of crackdetection accuracy using a novel crack defragmentation technique in image-based road assessment, J. Comput. Civ. Eng. 30 (1) (2016) 4014118. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000451
  32. Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition, Proc. IEEE 86 (11) (1998) 2278-2324. https://doi.org/10.1109/5.726791
  33. J.B. Butcher, C.R. Day, J.C. Austin, P.W. Haycock, D. Verstraeten, B. Schrauwen, Defect detection in reinforced concrete using random neural architectures, Comput. Aided Civ. Infrastruct. Eng. 29 (3) (2014) 191-207. https://doi.org/10.1111/mice.12039
  34. D. Soukup, R. Huber-Mork, Convolutional neural networks for steel surface defect detection from photometric stereo images, in: International Symposium on Visual Computing, Springer, 2014, pp. 668-677.
  35. Y.-J. Cha, W. Choi, O. Buyukozturk, Deep learning-based crack damage detection using convolutional neural networks, Comput. Aided Civ. Infrastruct. Eng. 32 (5) (2017) 361-378. https://doi.org/10.1111/mice.12263
  36. F. Chen, M.R. Jahanshahi, Nb-cnn: deep learning-based crack detection using convolutional neural network and naive bayes data fusion, IEEE Trans. Ind. Electron. 65 (5) (2018) 4392-4400. https://doi.org/10.1109/tie.2017.2764844
  37. W.S. McCulloch, W. Pitts, A logical calculus of the ideas immanent in nervous activity, Bull. Math. Biophys. 5 (4) (1943) 115-133. https://doi.org/10.1007/BF02478259
  38. B. Farley, W. Clark, Simulation of self-organizing systems by digital computer, Trans. IRE Prof. Group.Inf. Theor. 4 (4) (1954) 76-84. https://doi.org/10.1109/TIT.1954.1057468
  39. F. Rosenblatt, The perceptron: a probabilistic model for information storage and organization in the brain, Psychol. Rev. 65 (6) (1958) 386. https://doi.org/10.1037/h0042519
  40. K. Fukushima, Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position, Biol. Cybern. 36 (4) (1980) 193-202. https://doi.org/10.1007/BF00344251
  41. Y. LeCun, B. Boser, J.S. Denker, D. Henderson, R.E. Howard, W. Hubbard, L.D. Jackel, Back-propagation applied to handwritten zip code recognition, Neural Comput. 1 (4) (1989) 541-551. https://doi.org/10.1162/neco.1989.1.4.541
  42. Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition, Proc. IEEE 86 (11) (1998) 2278-2324. https://doi.org/10.1109/5.726791
  43. I. Goodfellow, Y. Bengio, A. Courville, Deep Learning, MIT press, 2016.
  44. G. Cybenko, Approximation by superpositions of a sigmoidal function, Mathematics of control, signals and systems 2 (4) (1989) 303-314. https://doi.org/10.1007/BF02551274
  45. L.Y. Pratt, Discriminability-based transfer be- tween neural networks, in: Advances in Neural Information Processing Systems, 1993, pp. 204-211.
  46. K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
  47. G. Facco, ASME Code Cases Not Approved for Use (rev.5), Tech. Rep, Office of Nuclear Regulatory Research, 2017.
  48. L.N. Smith, No more pesky learning rate guessing games, CoRR 5 (2015) abs/1506.01186.
  49. L.N. Smith, A Disciplined Approach to Neural Network Hyper-Parameters: Part 1-learning Rate, Batch Size, Momentum, and Weight Decay, 2018 arXiv preprint arXiv:1803.09820.