Available Technologies

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

A finite element approach integrated with a novel constitute model to predict phase change, residual stresses and part deformation.

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.

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

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.

This invention is directed to a machine leaning methodology to quantify the association of a set of input variables to a set of output variables, specifically for the one-to-many scenarios in which the output exhibits a range of variations under the same replicated input condi

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.

The use of biomass fiber reinforcement for polymer composite applications, like those in buildings or automotive, has expanded rapidly due to the low cost, high stiffness, and inherent renewability of these materials. Biomass are commonly disposed of as waste.