skip to main content

Title: Advancing flame retardant prediction: A self-enforcing machine learning approach for small datasets

Improving the fireproof performance of polymers is crucial for ensuring human safety and enabling future space colonization. However, the complexity of the mechanisms for flame retardant and the need for customized material design pose significant challenges. To address these issues, we propose a machine learning (ML) framework based on substructure fingerprinting and self-enforcing deep neural networks (SDNN) to predict the fireproof performance of flame-retardant epoxy resins. Our model is based on a comprehensive understanding of the physical mechanisms of materials and can predict fireproof performance and eliminate the needs for properties descriptors, making it more convenient than previous ML models. With a dataset of only 163 samples, our SDNN models show an average prediction error of 3% for the limited oxygen index (LOI). They also provide satisfactory predictions for the peak of heat release rate PHR and total heat release (THR), with coefficient of determination (R2) values of 0.87 and 0.85, respectively, and average prediction errors less than 17%. Our model outperforms the support vector model SVM for all three indices, making it a state-of-the-art study in the field of flame retardancy. We believe that our framework will be a valuable tool for the design and virtual screening of flame retardants and will contribute to the development of safer and more efficient polymer materials.

more » « less
Award ID(s):
Author(s) / Creator(s):
; ; ; ; ;
Publisher / Repository:
Date Published:
Journal Name:
Applied Physics Letters
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    In this paper, Salen‐Ni basis polyphosphazene microsphere (Salen‐PZN‐Ni), boric acid (BA), and 3‐aminopropyltriethoxysilane (KH‐550) were used as raw materials to prepare a new flame retardant Salen‐PZN‐Ni@BA@KH‐550 by surface modification. The thermal and flame retardant properties of epoxy resin (EP) composites were studied. The introduction of Salen‐PZN‐Ni@BA@KH‐550 refined the thermal stability of EP composites, as well as the amount of carbon residue at 800°C. At 5 wt% of Salen‐PZN‐Ni@BA@KH‐550, the limiting oxygen index (LOI) of EP composites is increased from 25.4% to 30.5% and UL‐94 has been achieved with a V‐1 rating. Meanwhile, the mechanical properties of Salen‐PZN‐Ni@BA@KH‐550/EP composites were also improved. In addition, the good char formation ability of Salen‐PZN‐Ni@BA@KH‐550 caused the reduction of peak heat release rate, total heat release rate, maximum average heat release rate and total smoke generation of the EP composites. All these results indicate that Salen‐PZN‐Ni@BA@KH‐550/EP composites have a wider range of applications.

    more » « less

    A series of 16‐layer polypropylene/flame retardant (PP/FR) film/foam composite structures were produced by microlayer coextrusion. A highly branched PP was used in the foam layers to increase strain hardening and cell stability, while the PP used in the film layers was a high shear viscosity grade to confine bubble growth. In addition to improved tensile properties, the PP/FR composite film/foams exhibited five times the compression modulus of PP/FR composite foams at each FR loading level. The thermal stabilities of the composites were investigated, exhibiting three step decompositions. The FR particles were effective in decreasing flammability by forming intumescent char. The PP/FR‐film/foam‐20 showed self‐extinguishing behavior in a modified vertical burn test, while the PP/FR‐foam‐20 sample continued to burn. Cone calorimetry demonstrated that PP/FR film/foams had lower heat release than PP/FR foams due to the unique alternating film/foam structure of PP/FR film/foams. Scanning electron microscopy imaging of the residual chars from fire testing that the PP/FR composite film/foams showed a more continuous protective char surface when compared with PP/FR composite foams at each FR concentration. The combined data indicate that the formation of a surface film on top of a foam ensures a robust intumescent fire protective barrier for partly foamed materials and shows a new way toward lightweight materials with improved fire safety performance. © 2019 Wiley Periodicals, Inc. J. Appl. Polym. Sci.2020,137, 48552.

    more » « less
  3. Abstract

    Fire retardant coatings have been proven effective at reducing the heat release rate (HRR) of structural materials during burning; yet effective methods for increasing the ignition temperature and delay time prior to burning are rarely reported. Herein, a strong, fire‐resistant wood structural material is developed by combining a densification treatment with an anisotropic thermally conductive flame‐retardant coating of hexagonal boron nitride (h‐BN) nanosheets to produce BN‐densified wood. The thermal management properties created by the BN coating provide fast, in‐plane thermal diffusion, slowing the conduction of heat through the densified wood, which improves the material's ignition properties. Compared with densified wood without the BN coating, a 41 °C enhancement in ignition temperature (Tig), a twofold increase in ignition delay time (tig), and a 25% decrease in the maximum HRR of BN‐densified wood can be achieved. As a proof of concept for scalability, the pieces of the BN‐densified wood are fabricated with a length larger than 25 cm, width greater than 15 cm, and thickness more than 7 mm. The improved thermal management, fire resistance, mechanical strength, and scalable production of BN‐densified wood position it as a promising structural material for safe and energy‐efficient buildings.

    more » « less
  4. Abstract

    Graph analytics shows promise for solving challenging problems on relational data. However, memory constraints arise from the large size of graphs and the high complexity of algorithms. Data prefetching is a crucial technique to hide memory access latency by predicting and fetching data into the memory cache beforehand. Traditional prefetchers struggle with fixed rules in adapting to complex memory access patterns in graph analytics. Machine learning (ML) algorithms, particularly long short-term memory (LSTM) models, excel in memory access prediction. However, they encounter challenges such as difficulty in learning interleaved access patterns and high storage costs when predicting in large memory address space. In addition, there remains a gap between designing a high-performance ML-based memory access predictor and developing an effective ML-based prefetcher for an existing memory system. In this work, we propose a novel Attention-based prefetching framework to accelerate graph analytics applications. To achieve high-performance memory access prediction, we propose A2P, a novel Attention-based memory Access Predictor for graph analytics. We use the multi-head self-attention mechanism to extract features from memory traces. We design a novelbitmap labelingmethod to collect future deltas within a spatial range, making interleaved patterns easier to learn. We introduce a novelsuper pageconcept, allowing the model to surpass physical page constraints. To integrate A2P into a memory system, we design a three-module prefetching framework composed of an existing memory hierarchy, a prefetch controller, and the predictor A2P. In addition, we propose a hybrid design to combine A2P and existing hardware prefetchers for higher prefetching performance. We evaluate A2P and the prefetching framework using the widely used GAP benchmark. Prediction experiments show that for the top three predictions, A2P outperforms the widely used state-of-the-art LSTM-based model by 23.1% w.r.t. Precision, 21.2% w.r.t. Recall, and 10.4% w.r.t. Coverage. Prefetching experiments show that A2P provides 18.4% IPC Improvement on average, outperforming state-of-the-art prefetchers BO by 17.2%, ISB by 15.0%, and Delta-LSTM by 10.9%. The hybrid prefetcher combining A2P and ISB achieves 21.7% IPC Improvement, outperforming the hybrid of BO and ISB by 16.3%.

    more » « less
  5. Abstract Modern machine learning (ML) and deep learning (DL) techniques using high-dimensional data representations have helped accelerate the materials discovery process by efficiently detecting hidden patterns in existing datasets and linking input representations to output properties for a better understanding of the scientific phenomenon. While a deep neural network comprised of fully connected layers has been widely used for materials property prediction, simply creating a deeper model with a large number of layers often faces with vanishing gradient problem, causing a degradation in the performance, thereby limiting usage. In this paper, we study and propose architectural principles to address the question of improving the performance of model training and inference under fixed parametric constraints. Here, we present a general deep-learning framework based on branched residual learning (BRNet) with fully connected layers that can work with any numerical vector-based representation as input to build accurate models to predict materials properties. We perform model training for materials properties using numerical vectors representing different composition-based attributes of the respective materials and compare the performance of the proposed models against traditional ML and existing DL architectures. We find that the proposed models are significantly more accurate than the ML/DL models for all data sizes by using different composition-based attributes as input. Further, branched learning requires fewer parameters and results in faster model training due to better convergence during the training phase than existing neural networks, thereby efficiently building accurate models for predicting materials properties. 
    more » « less