91°µÍø

ORNL researchers have developed a deep learning-based approach to rapidly perform high-quality reconstructions from sparse X-ray computed tomography measurements. 

Often there are major challenges in developing diverse and complex human mobility metrics systematically and quickly.

In additive manufacturing, choice of process parameters for a given material and geometry can result in porosities in the build volume, which can result in scrap.

A pressure burst feature has been designed and demonstrated for relieving potentially hazardous excess pressure within irradiation capsules used in the ORNL High Flux Isotope Reactor (HFIR).

We have been working to adapt background oriented schlieren (BOS) imaging to directly visualize building leakage, which is fast and easy.

This manufacturing method uses multifunctional materials distributed volumetrically to generate a stiffness-based architecture, where continuous surfaces can be created from flat, rapidly produced geometries.

The lack of real-time insights into how materials evolve during laser powder bed fusion has limited the adoption by inhibiting part qualification.  The developed approach provides key data needed to fabricate born qualified parts.

Distortion generated during additive manufacturing of metallic components affect the build as well as the baseplate geometries. These distortions are significant enough to disqualify components for functional purposes.

A new nanostructured bainitic steel with accelerated kinetics for bainite formation at 200 C was designed using a coupled CALPHAD, machine learning, and data mining approach.

For additive manufacturing of large-scale parts, significant distortion can result from residual stresses during deposition and cooling. This can result in part scraps if the final part geometry is not contained in the additively manufactured preform.