1 - 10 of 19 Results
ORNL researchers have developed a deep learning-based approach to rapidly perform high-quality reconstructions from sparse X-ray computed tomography measurements.
How fast is a vehicle traveling? For different reasons, this basic question is of interest to other motorists, insurance companies, law enforcement, traffic planners, and security personnel. Solutions to this measurement problem suffer from a number of constraints.
A finite element approach integrated with a novel constitute model to predict phase change, residual stresses and part deformation.
Ruthenium is recovered from used nuclear fuel in an oxidizing environment by depositing the volatile RuO4 species onto a polymeric substrate.
We have been working to adapt background oriented schlieren (BOS) imaging to directly visualize building leakage, which is fast and easy.
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
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.
Spherical powders applied to nuclear targetry for isotope production will allow for enhanced heat transfer properties, tailored thermal conductivity and minimize time required for target fabrication and post processing.
This invention utilizes new techniques in machine learning to accelerate the training of ML-based communication receivers.
The technologies provide a coating method to produce corrosion resistant and electrically conductive coating layer on metallic bipolar plates for hydrogen fuel cell and hydrogen electrolyzer applications.