AUTHOR=Hoppman Isaac , Alhadhrami Saeed , Wang Jun 

TITLE=Deep learning health management diagnostics applied to the NIST smoke experiments

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 11 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2023.1175102

DOI=10.3389/fenrg.2023.1175102

ISSN=2296-598X

ABSTRACT=Fire is one of the most important hazards that must be considered in advanced nuclear power plant safety assessments. The Nuclear Regulatory Commission (NRC) has developed a large collection of experimental data as well as associated analyses related to the study of fire safety. In fact, computational fire models are based on quantitative comparisons to those experimental data. During the modeling process, it is important to develop diagnostic health management to check the equipment status in the fire process. As an example, this work developed several models to predict the type and location of the fire. In order to improve the predictive capabilities, this work demonstrated how the Deep Learning Classification Method could be used as a diagnostic tool in a specific set of fire experiments. Through a single input from a sensor, the Deep Learning tool can predict the location and type of fire. This tool also has the capability to provide automatic signals to potential passive fire safety systems. In this work, test data is taken from a specific set of NIST fire experiments in a residential home, and analyzed by Machine Learning Classification models. The networks chosen for comparison and evaluation are: The dense Neural Networks, Convolutional Neural Networks, Long Short-Term Memory Networks, and Decision Trees. The dense neural network and long short-term memory network produced similar levels of accuracy, but the convolutional neural network produced the highest accuracy.