Oak Ridge National Laboratory software optimizes testing of 3D printed parts for nuclear applications

A software algorithm developed by Oak Ridge National Laboratory (ORNL) has reduced the time required to test 3D-printed parts for nuclear applications by 85 percent.

Additive manufacturing, better known as 3D printing, enables the domestic production of complex nuclear parts within shorter time frames. The quality of these parts is typically checked using computed tomography (CT) scans, which use X-rays to inspect internal structures for weaknesses or defects. Traditionally, these CT scans require extensive time and resources, which lengthens production cycles and increases costs.

ORNL’s new algorithm uses machine learning to quickly analyze the reconstructed images, significantly reducing the number of scans needed and the overall duration of the inspection. Researchers at Idaho National Laboratory (INL) have successfully used the algorithm to analyze more than 30 3D-printed sample parts in less than five hours – a process that would have taken over 30 hours without the software. This increase in efficiency opens up new possibilities for use with radioactive materials and fuels.

“If we use this algorithm to reduce the scan time for radioactive materials and fuels, it will increase worker safety and the rate we can evaluate new materials, said Bill Chuirazzi, an instrument scientist and leader of INL’s Diffraction and Imaging group. “Down the road it enables us to expedite the life cycle of new nuclear ideas from conception to implementation in the power grid.”

ORNL researcher Amir Ziabari, who originally developed the algorithm for faster and more accurate analysis of 3D-printed metal parts, is now training the software for use with radioactive materials and fuels. The collaboration between ORNL and INL is intended to promote the development and use of new reactor types that contribute to the decarbonization of the energy sector. The project is supported by the DOE’s Advanced Materials and Manufacturing Technologies (AMMT) program, which aims to promote the commercialization of new materials and manufacturing technologies.