ANS is committed to advancing, fostering, and promoting the development and application of nuclear sciences and technologies to benefit society.
Explore the many uses for nuclear science and its impact on energy, the environment, healthcare, food, and more.
Division Spotlight
Aerospace Nuclear Science & Technology
Organized to promote the advancement of knowledge in the use of nuclear science and technologies in the aerospace application. Specialized nuclear-based technologies and applications are needed to advance the state-of-the-art in aerospace design, engineering and operations to explore planetary bodies in our solar system and beyond, plus enhance the safety of air travel, especially high speed air travel. Areas of interest will include but are not limited to the creation of nuclear-based power and propulsion systems, multifunctional materials to protect humans and electronic components from atmospheric, space, and nuclear power system radiation, human factor strategies for the safety and reliable operation of nuclear power and propulsion plants by non-specialized personnel and more.
Meeting Spotlight
2024 ANS Winter Conference and Expo
November 17–21, 2024
Orlando, FL|Renaissance Orlando at SeaWorld
Standards Program
The Standards Committee is responsible for the development and maintenance of voluntary consensus standards that address the design, analysis, and operation of components, systems, and facilities related to the application of nuclear science and technology. Find out What’s New, check out the Standards Store, or Get Involved today!
Latest Magazine Issues
Aug 2024
Jan 2024
Latest Journal Issues
Nuclear Science and Engineering
September 2024
Nuclear Technology
Fusion Science and Technology
August 2024
Latest News
Nuclear new build procurement considerations
It may seem counterintuitive, but the best time to enhance the ability to support operations and maintenance for a new plant is before construction starts. This is one of many lessons learned by the currently operating nuclear fleet. As construction and startup of many nuclear facilities was completed, it quickly became evident that the ability to efficiently support operations and maintenance was limited. Most of the information necessary to establish and manage procurement of spare and replacement items, maintenance, and configuration of the facilities was unavailable and had to be gathered on a case-by-case, “on-demand” basis. Absence of necessary information and the associated challenges resulted in the need for staff augmentation and multiyear-long projects to develop equipment bills of material and maintenance programs and to perform technical evaluations for the huge quantities of spare and replacement items being requested.
Nicolas Martin, Zachary Prince, Vincent Labouré, Mauricio Tano-Retamales
Nuclear Science and Engineering | Volume 197 | Number 7 | July 2023 | Pages 1406-1435
Technical Paper | doi.org/10.1080/00295639.2022.2159220
Articles are hosted by Taylor and Francis Online.
We investigate using deep learning, a type of machine-learning algorithm employing multiple layers of artificial neurons, for the mathematical representation of multigroup cross sections for use in the Griffin reactor multiphysics code for two-step deterministic neutronics calculations. A three-dimensional fuel element typical of a high-temperature gas reactor as well as a two-dimensional sodium-cooled fast reactor lattice are modeled using the Serpent Monte Carlo code, and multigroup macroscopic cross sections are generated for various state parameters to produce a training data set and a separate validation data set. A fully connected, feedforward neural network is trained using the open-source PyTorch machine-learning framework, and its accuracy is compared against the standard piecewise linear interpolation model.
Additionally, we provide in this work a generic technique for propagating the cross-section model errors up to the keff using sensitivity coefficients with the first-order uncertainty propagation rule. Quantifying the eigenvalue error due to the cross-section regression errors is especially practical for appropriately selecting the mathematical representation of the cross sections. We demonstrate that the artificial neural network model produces lower errors and therefore enables better accuracy relative to the piecewise linear model when the cross sections exhibit nonlinear dependencies; especially when a coarse grid is employed, where the errors can be halved by the artificial neural network. However, for linearly dependent multigroup cross sections as found for the sodium-cooled fast reactor case, a simpler linear regression outperforms deeper networks.