Acoustic sensing and autoencoder approach for abnormal gas detection in a spent nuclear fuel canister mock-up

Zhuang, Bozhou; Gencturk, Bora; Oberai, Assad; Ramaswamy, Harisankar; Meyer, Ryan; Sinkov, Anton; Good, Morris

doi:10.1177/14759217241294042

Acoustic sensing and autoencoder approach for abnormal gas detection in a spent nuclear fuel canister mock-up

Journal Article · Sat Nov 16 00:00:00 EST 2024 · Structural Health Monitoring

DOI:https://doi.org/10.1177/14759217241294042· OSTI ID:2478365

Zhuang, Bozhou ^[1]; ^[1]; Oberai, Assad ^[1]; Ramaswamy, Harisankar ^[1]; Meyer, Ryan ^[2]; Sinkov, Anton ^[3]; Good, Morris ^[3]

Univ. of Southern California, Los Angeles, CA (United States)
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)

Currently, spent nuclear fuel (SNF) from commercial nuclear power plants is stored in stainless-steel canisters for interim dry storage. To provide an inert environment, these canisters are backfilled with helium after vacuum drying. However, the helium environment may be contaminated during extended storage because of the material degradation. For example, the heavier fission gas xenon may be released from the fuel rods into the canister cavity should the fuel cladding be breached. Other gases such as air and water vapor may also be present as a result of leakage caused by chloride-induced stress corrosion cracking on the canister walls or by insufficient vacuum drying. Therefore, monitoring the gas composition can provide critical information about the health of SNF canisters. In this study, noninvasive testing was conducted on a 2/3-scaled SNF canister mock-up using acoustic sensing. Ultrasonic transducers were placed on the exterior surface of the canister to probe the gas composition. A dataset was collected by sealing the canister mock-up and introducing up to 1.53% argon or 1.29% air into the helium background gas. Three methods were used to detect changes in the gas composition: the time-of-flight (TOF) method, the differential method, and the autoencoder method. Results showed that the TOF method had sufficient resolution to detect abnormal gas concentrations of less than 1.0%. The differential method demonstrated a periodic in-phase and out-of-phase behavior between the benchmark (i.e., pure helium) and abnormal (i.e., with argon or air) state signals. The variational autoencoder (VAE) and the Wasserstein autoencoder (WAE) were trained on the benchmark data and were applied directly to the abnormal state data. It was found that both the unsupervised VAE and the WAE were able to distinguish the benchmark and abnormal states of the canister mock-up based on the reconstruction error.

🛈

This content will become publicly available on Sun Nov 16 00:00:00 EST 2025

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE Office of Nuclear Energy (NE); USDOE

Grant/Contract Number:: AC05-00OR22725; NE0009171

OSTI ID:: 2478365

Alternate ID(s):: OSTI ID: 2477698

Journal Information:: Structural Health Monitoring, Journal Name: Structural Health Monitoring; ISSN 1475-9217

Publisher:: SAGECopyright Statement

Country of Publication:: United States

Language:: English

References (23)

An intelligent framework of upgraded CapsNets with massive transmissibility data for identifying damage in bridges Li, Shuai; Cao, Maosen; Bayat, Mahmoud Applied Soft Computing, Vol. 155 https://doi.org/10.1016/j.asoc.2024.111459	journal	April 2024
Spent nuclear fuel interim dry storage; Design requirements, most common methods, and evolution: A review El-Samrah, Moamen G.; Tawfic, A. F.; Chidiac, Samir E. Annals of Nuclear Energy, Vol. 160 https://doi.org/10.1016/j.anucene.2021.108408	journal	September 2021
Non-invasive ultrasonic sensing of internal conditions on a partial full-scale spent nuclear fuel canister mock-up Zhuang, Bozhou; Gencturk, Bora; Sinkov, Anton NDT & E International, Vol. 148 https://doi.org/10.1016/j.ndteint.2024.103242	journal	December 2024
In-Service Inspection of Extended Dry Storage of Spent Nuclear Fuel, Part I: Crawler Technology Development Meyer, Ryan M.; Renshaw, Jeremy; Beard, Jamie Volume 5: Operations, Applications, and Components; Seismic Engineering; Non-Destructive Examination https://doi.org/10.1115/PVP2021-62058	conference	July 2021
Temperature-compensated surface acoustic wave internal pressure sensor for nondestructive structural inspection of spent fuel canisters Vattaparambil Sreedharan, Sreejith; Desai, Mitali Hardik; Aslam, Muhammad Zubair Sensors and Actuators A: Physical, Vol. 360 https://doi.org/10.1016/j.sna.2023.114552	journal	October 2023
Unsupervised deep learning approach using a deep auto-encoder with a one-class support vector machine to detect damage Wang, Zilong; Cha, Young-Jin Structural Health Monitoring, Vol. 20, Issue 1 https://doi.org/10.1177/1475921720934051	journal	July 2020
Development and experimental verification of an active noise cancellation (ANC) method for non-invasive sensing Zhuang, Bozhou; Gencturk, Bora; Asareh, Iman Mechanical Systems and Signal Processing, Vol. 196 https://doi.org/10.1016/j.ymssp.2023.110330	journal	August 2023
Unsupervised long-term damage detection in an uncontrolled environment through optimal autoencoder Yang, Kang; Kim, Sungwon; Harley, Joel B. Mechanical Systems and Signal Processing, Vol. 199 https://doi.org/10.1016/j.ymssp.2023.110473	journal	September 2023
Measurement and analysis of fission gas release from BNFL's SBR MOX fuel White, R. J.; Fisher, S. B.; Cook, P. M. A. Journal of Nuclear Materials, Vol. 288, Issue 1 https://doi.org/10.1016/S0022-3115(00)00591-2	journal	January 2001
Source localization on large-scale canisters for used nuclear fuel storage using optimal number of acoustic emission sensors Ai, Li; Soltangharaei, Vafa; Bayat, Mahmoud Nuclear Engineering and Design, Vol. 375 https://doi.org/10.1016/j.nucengdes.2021.111097	journal	April 2021
Unsupervised fault diagnosis framework for underwater thruster system using estimated torques and multi-head convolutional autoencoder Gao, Shuang; Feng, Chen; Zhang, Xin Mechanical Systems and Signal Processing, Vol. 205 https://doi.org/10.1016/j.ymssp.2023.110814	journal	December 2023
Impurity gas detection for SNF canisters using probabilistic deep learning and acoustic sensing^* Zhuang, Bozhou; Gencturk, Bora; Oberai, Assad A. Measurement Science and Technology, Vol. 35, Issue 12 https://doi.org/10.1088/1361-6501/ad730d	journal	September 2024
Xenon migration in UO2 under irradiation studied by SIMS profilometry Marchand, B.; Moncoffre, N.; Pipon, Y. Journal of Nuclear Materials, Vol. 440, Issue 1-3 https://doi.org/10.1016/j.jnucmat.2013.04.005	journal	September 2013
Self-powered Through-wall communication for dry cask storage monitoring Sun, Kan; Wu, Yongjia; Qian, Feng Annals of Nuclear Energy, Vol. 177 https://doi.org/10.1016/j.anucene.2022.109306	journal	November 2022
Impurity gas monitoring using ultrasonic sensing and neural networks: forward and inverse problems Zhuang, Bozhou; Gencturk, Bora; Oberai, Assad Measurement, Vol. 223 https://doi.org/10.1016/j.measurement.2023.113822	journal	December 2023
Evaluation of gas leaks from canisters by using a vertical small-scale canister model Takeda, Hirofumi; Shimaike, Kohei Nuclear Engineering and Design, Vol. 371 https://doi.org/10.1016/j.nucengdes.2020.110958	journal	January 2021
Damage detection of spent nuclear fuel canisters using frequency response functions Aghagholizadeh, Mehrdad; Gencturk, Bora; Ghanem, Roger Annals of Nuclear Energy, Vol. 185 https://doi.org/10.1016/j.anucene.2023.109707	journal	June 2023
Inservice Inspection of Extended Dry Storage of Spent Nuclear Fuel, Part II: NDE/Sensor Technology Development and Codification Meyer, Ryan M.; Renshaw, Jeremy; Hunter, Kenn Volume 5: Operations, Applications, and Components; Seismic Engineering; Non-Destructive Examination https://doi.org/10.1115/PVP2021-62069	conference	July 2021
Google Colaboratory Bisong, Ekaba Building Machine Learning and Deep Learning Models on Google Cloud Platform https://doi.org/10.1007/978-1-4842-4470-8_7	book	January 2019
Evaluation of gas leaks from canisters by using a horizontal small-scale canister model Takeda, Hirofumi; Shimizu, Kosuke Nuclear Engineering and Design, Vol. 395 https://doi.org/10.1016/j.nucengdes.2022.111845	journal	August 2022
Machine learning-aided damage identification of mock-up spent nuclear fuel assemblies in a sealed dry storage canister Zhuang, Bozhou; Arcaro, Anna; Gencturk, Bora Engineering Applications of Artificial Intelligence, Vol. 128 https://doi.org/10.1016/j.engappai.2023.107484	journal	February 2024
An unsupervised structural health monitoring framework based on Variational Autoencoders and Hidden Markov Models Coraça, Eduardo M.; Ferreira, Janito V.; Nóbrega, Eurípedes G. O. Reliability Engineering & System Safety, Vol. 231 https://doi.org/10.1016/j.ress.2022.109025	journal	March 2023
Chloride-induced stress corrosion cracking of used nuclear fuel welded stainless steel canisters: A review Xie, Yi; Zhang, Jinsuo Journal of Nuclear Materials, Vol. 466 https://doi.org/10.1016/j.jnucmat.2015.07.043	journal	November 2015

Similar Records

Non-invasive ultrasonic sensing of internal conditions on a partial full-scale spent nuclear fuel canister mock-up

Journal Article · Sat Sep 21 00:00:00 EDT 2024 · NDT & E International · OSTI ID:2447542

Zhuang, Bozhou; Gencturk, Bora; Sinkov, Anton; +3 more

Related Subjects

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS
Spent nuclear fuel (SNF)
Canisters
Acoustic sensing
Non-invasive sensing
Gas detection
Variational auto-encoders (VAEs)
Wasserstein auto-encoders (WAEs)

Acoustic sensing and autoencoder approach for abnormal gas detection in a spent nuclear fuel canister mock-up

Citation Formats

References (23)

Similar Records

Related Subjects