English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The goal of this work is to develop accurate Machine Learning (ML) models forpredicting the assembly axial neutron flux profiles in the SAFARI-1 researchreactor, trained by measurement data from historical cycles. The data-drivennature of ML models makes them susceptible to uncertainties which areintroduced by sources such as noise in training data, incomplete coverage ofthe domain, extrapolation and imperfect model architectures. To this end, wealso aim at quantifying the approximation uncertainties of the ML modelpredictions. Previous work using Deep Neural Networks (DNNs) has beensuccessful for fuel assemblies in SAFARI-1, however, not as accurate forcontrol follower assemblies. The aim of this work is to improve the ML modelsfor the control assemblies by a combination of supervised and unsupervised MLalgorithms. The $k$-means and Affinity Propagation unsupervised ML algorithmsare employed to identify clusters in the set of the measured axial neutron fluxprofiles. Then, regression-based supervised ML models using DNN (withprediction uncertainties quantified with Monte Carlo dropout) and GaussianProcess (GP) are trained for different clusters and the prediction uncertaintyis estimated. It was found that applying the proposed procedure improves theprediction accuracy for the control assemblies and reduces the predictionuncertainty. Flux shapes predicted by DNN and GP are very close, and theoverall accuracy became comparable to the fuel assemblies. The predictionuncertainty is however smaller for GP models.

Clustering and Uncertainty Analysis to Improve the Machine  Learning-based Predictions of SAFARI-1 Control Follower Assembly Axial  Neutron Flux Profiles