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.
Explore membership for yourself or for your organization.
Conference Spotlight
Nuclear Energy Conference & Expo (NECX)
September 8–11, 2025
Atlanta, GA|Atlanta Marriott Marquis
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
Jul 2025
Jan 2025
Latest Journal Issues
Nuclear Science and Engineering
September 2025
Nuclear Technology
August 2025
Fusion Science and Technology
Latest News
Joint NEA project performs high-burnup test
An article in the OECD Nuclear Energy Agency’s July news bulletin noted that a first test has been completed for the High Burnup Experiments in Reactivity Initiated Accident (HERA) project. The project aim is to understand the performance of light water reactor fuel at high burnup under reactivity-initiated accidents (RIA).
Jichong Lei, Zhenping Chen, Jiandong Zhou, Chao Yang, Changan Ren, Wei Li, Chao Xie, Zining Ni, Gan Huang, Leiming Li, Jinsen Xie, Tao Yu
Nuclear Technology | Volume 208 | Number 7 | July 2022 | Pages 1223-1232
Technical Note | doi.org/10.1080/00295450.2021.2018270
Articles are hosted by Taylor and Francis Online.
The reactor core design involves the search for and detailed calculation of a large number of schemes. Four different machine learning algorithms were used in this technical note: the C4.5 algorithm (an algorithm of decision trees), Support Vector Machine, Random Forest, and Multi-layer Perceptron, respectively. Uranium enrichment, the number of fuel rods containing burnable poison, and the concentration of burnable poison were taken as independent variables in the calculation. The k-eff unevenness coefficient, the radial power nonuniformity coefficient, the radial flux nonuniformity coefficient, and the core life were taken as the number of core parameters fulfilled (CPF). Machine learning models were constructed through learning the training data set, which consisted of a large number of assembly and core schemes whose nuclear design parameters were already known. Using the models, the CPF values for the unknown core data set (the test data set) were quickly predicted. The results show that the cross-validation accuracy of each algorithm was above 94% and that the C4.5 algorithm had the highest accuracy for the overall prediction of the CPF values. For the CPF value prediction of the test data set, the time for the training data set was within 10s, while the Random Forest algorithm has the highest prediction accuracy for CPF = 4 or CPF ≠ 4.