BibTeX

@inproceedings{GrothPSAM2018Data,
title = {Commentary on use of model-augmented data analytics for improved operational efficiency of nuclear power plants },
author = {Katrina Groth and Michelle Bensi},
url = {http://psam14.org/proceedings/paper/paper_299_1.pdf},
year = {2018},
date = {2018-09-16},
booktitle = {Proceedings of the 14th Probabilistic Safety Assessment and Management Conference (PSAM 14)},
address = {Los Angeles, CA},
keywords = {big data, data analytics, efficiency, operations},
pubstate = {published},
tppubtype = {inproceedings}
}

Abstract

Machine learning and data science have the potential for improving the operational efficiency and productivity of the current fleet of light water reactors. However, to date, the nuclear industry has not leveraged recent advances in these fields. This paper provides commentary on the potential advantages and challenges of using recent advances in data analytics and probabilistic modeling techniques that support mixed inference application. This paper proposes an initial, highlevel machine-learning-derived framework for integrating nuclear plant data streams in near-real time for improved diagnostics, online risk-management, and decision-making. This paper also outlines several challenges that must be overcome before realizing the benefits of machine learning and data
science for improving nuclear power plant operations.