Machine learning for expediting next-generation of fire-retardant polymer composites

Aug 2, 2026

Machine learning algorithms are widely used for solving complex engineering problems, and can accelerate the optimization of fire retardants for polymeric materials by reducing slow trial-and-error experimentation. However, designing polymeric fire retardants still lacks a focused, insightful review. This short review summarizes practical algorithms for predicting flame-retardancy features such as limiting oxygen index and cone calorimetry results, highlighting ANN, Lasso, Ridge, L-ANN, and XGB. It also discusses key challenges and future directions to expedite optimized next-generation formulations.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Introduction

Background: polymer materials and fire safety challenges

Motivation: ML for material property design

Review focus: ML algorithms for flame retardancy prediction

Target metrics: LOI and cone calorimetry

Representative models and their advantages

Challenges, solutions, and future directions

Composites Communications 45 (2024) 101806 Contents lists available at ScienceDirect Composites Communications journal [homepage: www.elsevier.com/locate/coco](homepage: www.elsevier.com/locate/coco) | Short Review
Machine learning for expediting next-generation of fire-retardant polymer composites | | | | | --- | --- | --- | --- | | Pooya Jafari a, Ruoran Zhang b, Siqi Huo a, Qingsheng Wang b, Jianming Yong a, Min Hong a, Ravinesh Deo c, Hao Wang a, Pingan Song a, d, *
a Centre for Future Materials, University of Southern Queensland, Springfield, 4300, Australia
b Artie McFerrin Department of Chemical Engineering, Texas A&M University, College Station, TX, 77843-3122, United States c School of Mathematics, Physics and Computing, University of Southern Queensland, Springfield, 4300, Australia
d School of Agriculture and Environmental Science, University of Southern Queensland, Springfield, 4300, Australia | | | | | A R T I C L E I N F O | | A B S T R A C T | | | Keywords:
Machine learning Fire retardants Polymeric materials Fire safety Algorithm | | Machine learning algorithms have emerged as an effective and popular decision-making tool for solving complicated engineering problems and challenges. Although introducing these algorithms can accelerate the optimization of fire retardants for polymeric materials by replacing traditional tedious and time-consuming trialand-error methods, this tool remains at the elementary stage of designing fire retardants for polymeric materials, and thus to date there is a lack of insightful yet review on this topic. Herein, we review the most practical and accurate algorithms used to predict flame retardancy features, such as limiting oxygen index (LOI) and cone calorimetry results, of their polymeric materials. We highlight the merits of some current algorithms, including artificial neural network (ANN), Lasso, Ridge, ANN (L-ANN), and extreme gradient boosting (XGB). Finally, key challenges with existing algorithms for predicting next-generation fire retardants, followed by some proposed solution and future directions. This review will help expedite the development of optimized fire retardants accelerated by machine learning. | | 1. Introduction Polymeric materials have become incredibly prevalent in contemporary civilization ever since their initial identification. These versatile substances have permeated nearly every aspect of modern life, finding extensive application across numerous industries and sectors [1–3]. The Current advancement in polymeric materials reaps many benefits to communities nowadays such as being widely employed in applications like manufacturing, construction, healthcare, electronics, commodities, transportation, and building [4–8]. Polymeric materials, however, can pose significant safety risks when utilized in applications that necessitate strong flame resistance, primarily due to their flammability [9–12]. New heat-resistant polymer materials must possess excellent thermal stability and significant processability [13], but high thermal resistance in polymers can lead to undesirable, weaker processing properties [14]. Developing flame-retardant polymers having high standards has always been a challenge due to the time-consuming traditional methods established on experiential intuition and trial-and-error screenings [15, 16]. In recent times, there has been a growing interest in the exploration of new materials using Machine Learning (ML) models. This approach has gained attention for its practical application in enhancing the design of material properties, leveraging the advancements in computing power and related algorithms [17–21]. ML regression algorithms, with feature engineering and large datasets, predict material properties for quality fabrication and practical applications. By training on available data, researchers save time and effort in experimentation. ML algorithms optimize and discover functional materials in thermoel

FAQs

Why is machine learning considered useful for designing fire-retardant polymer composites?

Machine learning can accelerate optimization by replacing traditional tedious trial-and-error approaches with faster decision-making and predictive modeling.

Which flame-retardancy features are commonly predicted in this review?

The review focuses on predicting features such as limiting oxygen index (LOI) and cone calorimetry results.

What machine learning algorithms are highlighted as practical and accurate for prediction?

Key algorithms discussed include artificial neural networks (ANN), Lasso, Ridge, L-ANN, and extreme gradient boosting (XGB).

Aug 2, 2026

Upload by River Wang