Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2021 Feb 15;26(4):1022.
doi: 10.3390/molecules26041022.

Review on the Use of Artificial Intelligence to Predict Fire Performance of Construction Materials and Their Flame Retardancy

Hoang T Nguyen  1 , Kate T Q Nguyen  1 , Tu C Le  2 , Guomin Zhang  1
Affiliations
Review

Review on the Use of Artificial Intelligence to Predict Fire Performance of Construction Materials and Their Flame Retardancy

Hoang T Nguyen et al. Molecules. .

Abstract

The evaluation and interpretation of the behavior of construction materials under fire conditions have been complicated. Over the last few years, artificial intelligence (AI) has emerged as a reliable method to tackle this engineering problem. This review summarizes existing studies that applied AI to predict the fire performance of different construction materials (e.g., concrete, steel, timber, and composites). The prediction of the flame retardancy of some structural components such as beams, columns, slabs, and connections by utilizing AI-based models is also discussed. The end of this review offers insights on the advantages, existing challenges, and recommendations for the development of AI techniques used to evaluate the fire performance of construction materials and their flame retardancy. This review offers a comprehensive overview to researchers in the fields of fire engineering and material science, and it encourages them to explore and consider the use of AI in future research projects.

Keywords: artificial intelligence; chemical kinetics; combustion; flame retardants; machine learning; pyrolysis.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
The structure of a feedforward network. Adapted with permission from ref. [32]. Copyright 1997 Open Access & Nature Research.
Figure 2
Figure 2
Comparison of experimental data and an artificial neural network (ANN) model to predict the failure time of concrete columns on a (a) training set and (b) test set. Adapted with permission from ref. [70]. Copyright 2014 Journal of Structural Fire Engineering.
Figure 3
Figure 3
Comparison of the calculated flexural capability with the predicted flexural capability. Adapted with permission from ref. [79]. Copyright 2009 Advances in Engineering Software.
Figure 4
Figure 4
The structure of the ANN model to compute the fiberboard properties under fire conditions. Adapted with permission from ref. [98]. Copyright 2020 Open Access & Springer.
Figure 5
Figure 5
A comparison between the actual values (target) and predicted values (outputs) of the (a) Mass loss and (b) Modulus of Rupture in the cases of all data and train data. Adapted with permission from ref. [98]. Copyright 2020 Open Access & Springer.
Figure 6
Figure 6
The schematic architecture of the ANN model that was used to predict the mean fireproofing time of the intumescent flame-retardant coating. Adapted with permission from ref. [99]. Copyright 2013 Fire Safety Journal.
Figure 7
Figure 7
(a) The regression plot of the ANN-predicted result against the experimental data. (b) A comparison between the predicted outcomes of the ANN model and the practical results in terms of the mean fireproofing time (MFPT). Adapted with permission from ref. [99]. Copyright 2013 Fire Safety Journal.
Figure 8
Figure 8
A comparison between the fuzzy inference system (FIS) outputs and testing data. Adapted with permission from ref. [99]. Copyright 2013 Fire Safety Journal.
Figure 9
Figure 9
The schematic of the backpropagation network for the polyamide-66 (PA-66) formulation design model to predict the limiting oxygen index (LOI) value. Adapted with permission from ref. [101]. Copyright 2001 Journal of Fire Sciences.
Figure 10
Figure 10
The correlation between the predicted and observed LOI values of (a) the MNLR model and (b) the ANN model. Adapted with permission from ref. [101]. Copyright 2001 Journal of Fire Sciences.
Figure 11
Figure 11
The schematic of the ANN to predict the LOI, tensile strength (TS), and elongation (EL) values of flame-retardant composites. Adapted with permission from ref. [102]. Copyright 2001 Journal of Fire Sciences.
Figure 12
Figure 12
The correlation between the predicted and observed values of the (a) LOI, (b) TS, and (c) EL of the samples in the test set. Adapted with permission from ref. [102]. Copyright 2001 Journal of Fire Sciences.
See this image and copyright information in PMC

References

    1. International Organization for Standardization . ISO 5660-1: Reaction-to-Fire Tests-Heat Release, Smoke Production and Mass Loss Rate-Part 1:(Cone Calorimeter Method) International Organization for Standardization; Geneva, Switzerland: 2002.
    1. Tu J., Yeoh G.H., Liu C. Computational Fluid Dynamics: A Practical Approach. Butterworth-Heinemann; Oxford, UK: 2018.
    1. He K., Zhang X., Ren S., Sun J. Deep Residual Learning for Image Recognition; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Las Vegas, NV, USA. 27–30 June 2016; pp. 770–778. - DOI
    1. Hinton G., Deng L., Yu D., Dahl G.E., Mohamed A.-R., Jaitly N., Senior A., Vanhoucke V., Nguyen P., Sainath T.N., et al. Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups. IEEE Signal Process. Mag. 2012;29:82–97. doi: 10.1109/MSP.2012.2205597. - DOI
    1. Pazzani M., Billsus D. Learning and Revising User Profiles: The Identification of Interesting Web Sites. Mach. Learn. 1997;27:313–331. doi: 10.1023/a:1007369909943. - DOI

MeSH terms

Substances