Nuclear Canister Corrosion Detection
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
The software titled "nccd" is used for running residual neural networks (ResNets) on images of nuclear canisters. The software provides only the code for the implementation (based on the fastai library), but it does not share the image data. The compute code allows the use of residual nets (and more generally of other deep learning models) for classifying images from nuclear canisters as corroded. or intact. An image is considered to be corroded if it contains pitting or stress corrosion cracks. The code trains ResNets on image tiles extracted from original images from nuclear canisters, and then implements a classification rule, which can be applied to a validation set to decide if each original image is corroded or intact. The software automates the process of using images taken from nuclear canisters to detect corrosion. It provides also scope for future research directions on the basis of the existing research and code.
- Short Name / Acronym:
- nccd
- Project Type:
- Open Source, Publicly Available Repository
- Site Accession Number:
- 8146
- Software Type:
- Scientific
- License(s):
- BSD 3-clause "New" or "Revised" License
- Programming Language(s):
- Python (v3.6 onwards)
- Research Organization:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Sponsoring Organization:
- USDOEPrimary Award/Contract Number:AC05-00OR22725
- DOE Contract Number:
- AC05-00OR22725
- Code ID:
- 48780
- OSTI ID:
- 1631690
- Country of Origin:
- United States
Similar Records
Real-Time Canister Welding Health Monitoring and Prediction System for Spent Fuel Dry Storage
FY18 Status Report: SNL Research into Stress Corrosion Cracking of SNF Interim Storage Canisters