U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Search Publications

NIST Authors in Bold

Displaying 1 - 25 of 48

Real-Time Flashover Prediction Model for Multi-Compartment Building Structures Using Attention Based Recurrent Neural Networks

March 17, 2023
Author(s)
Wai Cheong Tam, Eugene Yujun Fu, Jiajia Li, Richard D. Peacock, Paul A. Reneke, Thomas Cleary, Grace Ngai, Hong Va Leong, Michael Xuelin Huang
This paper presents the development of an attention based bi-directional gated recurrent unit model, P-Flashv2, for the prediction of potential occurrence of flashover in a traditional 111 m2 single story ranch-style family home. Synthetic temperature data

Measurements and Predictions of the Aerosol Dynamics of Smoke

September 30, 2022
Author(s)
Amy Mensch, Haley Hamza, Thomas Cleary
Better understanding and ability to predict the aerosol dynamics of soot can improve life safety predictions generated by fire modeling tools. NIST's fire modeling tool, Fire Dynamics Simulator (FDS), is commonly used by the international fire protection

Real-time Forecast of Compartment Fire and Flashover based on Deep Learning

April 6, 2022
Author(s)
Tianhang Zhang, Zilong Wang, Ho Yin Wong, Wai Cheong Tam, Xinyan Huang, Fu Xiao
Forecasting building fire development and critical fire events in real-time is of great significance for firefighting and rescue operations. This work proposes an artificial intelligence (AI) system to fast forecast the compartment fire development and

A Generic Flashover Prediction Model for Residential Buildings Using Graph Neural Network

November 11, 2021
Author(s)
Wai Cheong Tam, Eugene Yujun Fu, Paul A. Reneke, Richard D. Peacock, Thomas Cleary
A generic graph neural network-based model is developed to predict the potential occurrence of flashover for different building structures. The proposed model transforms multivariate temperature data into graph-structure data. Utilizing graph convolution

Validation of Aerosol Dynamics in a Well-Stirred Isothermal Enclosure

September 30, 2021
Author(s)
Amy Mensch, Thomas Cleary
Modeling of aerosol dynamics in fire simulations enables predictions of the effects of soot, such as visibility and detection, and the fate of soot, such as deposition and emissions. NIST's fire modeling tool, Fire Dynamics Simulator (FDS), has implemented

Sensors and Machine Learning Models to Prevent Cooktop Ignition and Ignore Normal Cooking

July 28, 2021
Author(s)
Amy Mensch, Anthony Hamins, Wai Cheong Tam, John Lu, Kathryn Markell, Christina You, Matthew Kupferschmid
According to a recent NFPA report, 49 % of reported home fires involve cooking equipment, with cooktops accounting for 87 % of cooking-fire deaths and 80 % of the civilian injuries [1, 2]. Between 2014–2018, U.S. fire departments responded to an estimated

Sensors and Machine Learning Models to Prevent Cooktop Ignition and Ignore Normal Cooking

March 18, 2021
Author(s)
Amy Mensch, Anthony Hamins, Andy Tam, John Lu, Kathryn Markell, Christina You, Matthew Kupferschmid
Cooking equipment is involved in nearly half of home fires in the United States, with cooktop fires the leading cause of deaths and injuries in cooking-related fires. In this study, we evaluate 16 electrochemical, optical, temperature and humidity sensors

Predicting Flashover Occurrence using Surrogate Temperature Data

February 9, 2021
Author(s)
Andy Tam, Eugene Yujun Fu, Richard Peacock, Paul A. Reneke, Jun Wang, Grace Ngai, Hong Va Leong, Thomas Cleary
Fire fighter fatalities and injuries in the U.S. remain too high and fire fighting too hazardous. Until now, fire fighters rely only on their experience to avoid life-threatening fire events, such as flashover. In this paper, we describe the development of

On the Use of Machine Learning Models to Forecast Flashover Occurrence in a Compartment

September 15, 2020
Author(s)
Jun Wang, Andy Tam, Paul A. Reneke, Richard Peacock, Thomas Cleary, Eugene Yujun Fu, Grace Ngai, Hong Va Leong
This paper presents a study to examine the potential use of machine learning algorithms to build a model to forecast the likelihood of flashover occurrence for a single-floor multi-room compartment. Synthetic temperature data for heat detectors from

Time Series Feature Extraction and Selection Tool for Fire Data

September 15, 2020
Author(s)
Jun Wang, Youwei Jia, Eugene Yujun Fu, Jiajia Li, Andy Tam
This paper aims to facilitate the use of machine learning to carry out supervised classification/regression tasks for time series data in fire research. Specifically, a feature engineering tool, FAST (Feature extrAction and Selection for Time-series), is

Assessing Fire Smoke to Predict Backdraft and Smoke Explosion Potential

June 3, 2020
Author(s)
Ryan Falkenstein-Smith, Thomas Cleary
The Fire Research Division at the National Institute of Standards and Technology is investigating the ability to forecast backdraft or smoke explosions during a fire event using a phi meter. Compared to other gas sensors, a phi meter can measure the global

Prevention of Cooktop Ignition Using Detection and Multi-Step Machine Learning Algorithms

May 8, 2020
Author(s)
Wai Cheong Tam, Eugene Yujun Fu, Amy E. Mensch, Anthony P. Hamins, Christina Yu, Grace Ngai, Hong va Leong
This paper presents a study to examine the potential use of machine learning models to build a real-time detection algorithm for prevention of kitchen cooktop fires. Sixteen sets of time- dependent sensor signals were obtained from 60 normal/ignition

Prevention of Cooktop Ignition Using Detection and Multi-Step Machine Learning Algorithms

April 27, 2020
Author(s)
Wai Cheong Tam, Eugene Yujun Fu, Amy E. Mensch, Anthony P. Hamins, Christina Yu, Grace Ngai, Hong va Leong
This paper presents a study to examine the potential use of machine learning models to build a real-time detection algorithm for prevention of unattended cooking fires. 16 sets of time- dependent sensor signals were obtained from 60 normal/ignition cooking
Displaying 1 - 25 of 48