DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Impurity gas detection for SNF canisters using probabilistic deep learning and acoustic sensing *

Journal Article · · Measurement Science and Technology

Abstract Monitoring impurity gases in spent nuclear fuel (SNF) canisters is a novel structural health monitoring approach for SNF in dry storage. The SNF canisters are sealed containers that do not facilitate visual access to the inside. Acoustic sensing can be deployed by taking advantage of the pathways unobstructed by internal hardware. Although the ultrasonic time-of-flight measurement can provide valuable information, it is limited in its ability to discern the concentration of only one impurity gas. As such, deep learning algorithms, particularly convolutional neural networks (CNNs), offer a promising solution. In this study, CNN-based probabilistic deep learning models were implemented to detect and quantify multiple impurity gases in helium. An experimental platform was established to simulate canister conditions, and ultrasonic test data were collected. The presence of argon and air in helium at concentrations ranging from 0% to 1.2% at increments of 0.05% was considered. The multi-layer perceptron, decision tree, and logistic regression classifiers achieved high accuracies when distinguishing pure helium from helium with impurities. CNN with dropout layers and CNN using maximum likelihood estimation showed a similar performance, indicating their ability to capture uncertainties. The ensemble CNN model exhibited improved predictions and the ability to balance individual gas concentration by integrating 1D- and 2D-CNN models. These findings contribute probabilistic deep learning solutions for impurity gas detection and analysis within SNF canisters, thus ensuring safe storage and management of SNFs.

Sponsoring Organization:
USDOE
Grant/Contract Number:
NE0009171
OSTI ID:
2439783
Journal Information:
Measurement Science and Technology, Journal Name: Measurement Science and Technology Journal Issue: 12 Vol. 35; ISSN 0957-0233
Publisher:
IOP PublishingCopyright Statement
Country of Publication:
United Kingdom
Language:
English

References (30)

Google Colaboratory book January 2019
Measuring Sound Speed in Gas Mixtures Using a Photoacoustic Generator journal November 2017
Understanding the Mechanism of Stress Corrosion Cracking Resistance in Stainless Steel Welds Subjected to Laser Shock Peening without Coating for Nuclear Canister Applications journal January 2024
The sound velocity of a mixture of He and N2 up to 10 kbar and from 157 K to 298 K journal November 1992
An ultrasonic sensor for the analysis of binary gas mixtures journal October 1993
Experimental investigation of vacuum drying for removal of residual water in canister journal March 2021
A numerical study of spent nuclear fuel dry storage systems under extreme impact loading journal April 2018
Estimation of the energy content of propanated biomethane using ultrasonic measurements journal February 2021
Stress corrosion cracking of stainless-steel canister for concrete cask storage of spent fuel journal September 2008
Xenon migration in UO2 under irradiation studied by SIMS profilometry journal September 2013
Cladding stress during extended storage of high burnup spent nuclear fuel journal September 2015
Chloride-induced stress corrosion cracking of used nuclear fuel welded stainless steel canisters: A review journal November 2015
Impurity gas monitoring using ultrasonic sensing and neural networks: forward and inverse problems journal December 2023
Topics of research and development on concrete cask storage of spent nuclear fuel journal May 2008
Thermal modeling of a vertical dry storage cask for used nuclear fuel journal May 2016
Dynamic structural response of reinforced concrete dry storage casks subjected to impact considering material degradation journal December 2017
Evaluation of gas leaks from canisters by using a vertical small-scale canister model journal January 2021
A versatile acoustic gas sensing method via extracting intrinsic molecular internal specific heat journal June 2021
Could spent nuclear fuel be considered as a non-conventional mine of critical raw materials? journal January 2017
Momentum informed muon scattering tomography for monitoring spent nuclear fuels in dry storage cask journal March 2024
Theory for a gas composition sensor based on acoustic properties journal December 2002
Decoupling Multiple Rotational Relaxations of Hydrogen to Detect Gas Mixtures journal January 2019
Application of ultrasonic to a hydrogen sensor conference November 2010
Improving deep neural networks using softplus units conference July 2015
Optimizing transmission of acoustic signals to monitor internal conditions of canisters for dry storage of commercial spent nuclear fuel
  • Zhuang, Bozhou; Sinkov, Anton; Good, Morris
  • Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2024 https://doi.org/10.1117/12.3007502
conference May 2024
Acoustic attenuation in a three-gas mixture: Results journal December 2001
Introduction to Digital Speech Processing journal January 2007
A Survey on Gas Sensing Technology journal July 2012
Gas Classification Using Deep Convolutional Neural Networks journal January 2018
A New Method of Mixed Gas Identification Based on a Convolutional Neural Network for Time Series Classification journal April 2019