The ORNL algorithm, originally designed to inspect additively manufactured metals, is now being adapted to examine irradiated nuclear fuels. "If we use this algorithm to reduce the scan time for radioactive fuels by 90%, it will increase worker safety and the rate we can evaluate new materials," said Bill Chuirazzi, INL's Diffraction and Imaging group leader.
The ORNL-developed tool, Simurgh, significantly reduces scan times for dense materials while enhancing defect detection capabilities. It uses a neural network trained on realistic data to reconstruct images with fewer X-ray scans. This advancement allows faster characterization of nuclear parts and materials, paving the way for innovations such as small modular reactors and high-temperature gas reactors.
Chuirazzi noted the impact of Simurgh on inspection timelines. "Including prep, it now takes about 15% of the time it did to scan something with our setup," he said. These efficiency gains also enhance safety, as less radiation exposure occurs during scans.
Ryan Dehoff, director of DOE's Manufacturing Demonstration Facility at ORNL, emphasized the technology's reliability: "The fact we're using this tool suite in the nuclear sphere speaks to the quality and reliability of the technology."
As Simurgh evolves, it promises to revolutionize X-ray CT imaging across multiple industries, offering enhanced efficiency, cost savings, and safety. Its development underscores the potential of computational and imaging advancements in addressing complex nuclear challenges.
Related Links
Oak Ridge National Laboratory
Nuclear Power News - Nuclear Science, Nuclear Technology
Powering The World in the 21st Century at Energy-Daily.com
Subscribe Free To Our Daily Newsletters |
Subscribe Free To Our Daily Newsletters |