Machine-learning-assisted multiscale modeling strategy for predicting mechanical properties of carbon fiber reinforced polymers

Composites Science and Technology, Journal Year: 2024, Volume and Issue: 248, P. 110455 - 110455

Published: Jan. 18, 2024

Language: Английский

---

Machine Learning-Assisted Design of Advanced Polymeric Materials

Accounts of Materials Research, Journal Year: 2024, Volume and Issue: 5(5), P. 571 - 584

Published: April 16, 2024

ConspectusPolymeric material research is encountering a new paradigm driven by machine learning (ML) and big data. The ML-assisted design has proven to be successful approach for designing novel high-performance polymeric materials. This goal mainly achieved through the following procedure: structure representation database construction, establishment of ML-based property prediction model, virtual high-throughput screening. key this lies in training ML models that delineate structure–property relationships based on available polymer data (e.g., structure, component, data), enabling screening promising polymers satisfy targeted requirements. However, relative scarcity high-quality complex multiscale pose challenges method, such as modeling challenges.In Account, we summarize state-of-the-art advancements concerning Regarding digital representations are predominant methods cheminformatics along with some newly developed integrate characteristics. When establishing choosing optimizing attain high-precision predictions across vast chemical space. Advanced algorithms, transfer multitask learning, have been utilized address challenges. During process, defining combining genes, candidates generated, subsequently, their properties predicted screened using models. Finally, identified verified computer simulations experiments.We provide an overview our recent efforts toward developing approaches discovering advanced materials emphasize intricate nature structural design. To well describe structures polymers, methods, fingerprint cross-linking descriptors, were developed. Moreover, multifidelity method was proposed leverage multisource isomerous from experiments simulations. Additionally, graph neural networks Bayesian optimization applied predicting compositions.Finally, identify current point out development directions emerging field. It highly desirable establish materials, particularly when constructing large language. Through seek stimulate further interest foster active collaborations realizing innovation

Language: Английский

---

Machine Learning Approaches in Polymer Science: Progress and Fundamental for a New Paradigm

SmartMat, Journal Year: 2025, Volume and Issue: 6(1)

Published: Jan. 9, 2025

ABSTRACT Machine learning (ML), material genome, and big data approaches are highly overlapped in their strategies, algorithms, models. They can target various definitions, distributions, correlations of concerned physical parameters given polymer systems, have expanding applications as a new paradigm indispensable to conventional ones. Their inherent advantages building quantitative multivariate largely enhanced the capability scientific understanding discoveries, thus facilitating mechanism exploration, prediction, high‐throughput screening, optimization, rational inverse designs. This article summarizes representative progress recent two decades focusing on design, preparation, application, sustainable development materials based exploration key composition–process–structure–property–performance relationship. The integration both data‐driven insights through ML deepen fundamental discover novel is categorically presented. Despite construction application robust models, strategies algorithms deal with variant tasks science still rapid growth. challenges prospects then We believe that innovation will thrive along approaches, from efficient design applications.

Language: Английский

---

Polymer Informatics at Scale with Multitask Graph Neural Networks

Chemistry of Materials, Journal Year: 2023, Volume and Issue: 35(4), P. 1560 - 1567

Published: Feb. 15, 2023

Artificial intelligence-based methods are becoming increasingly effective at screening libraries of polymers down to a selection that is manageable for experimental inquiry. The vast majority presently adopted approaches polymer rely on handcrafted chemostructural features extracted from repeat units-a burdensome task as libraries, which approximate the chemical search space, progressively grow over time. Here, we demonstrate directly "machine learning" important unit cheap and viable alternative extracting expensive by hand. Our approach-based graph neural networks, multitask learning, other advanced deep learning techniques-speeds up feature extraction 1-2 orders magnitude relative without compromising model accuracy variety property prediction tasks. We anticipate our approach, unlocks truly massive scale, will enable more sophisticated large scale technologies in field informatics.

Language: Английский

---

Ultrastrong and High‐Tough Thermoset Epoxy Resins from Hyperbranched Topological Structure and Subnanoscaled Free Volume

Advanced Materials, Journal Year: 2023, Volume and Issue: 36(9)

Published: Oct. 28, 2023

The strength and toughness of thermoset epoxy resins are generally mutually exclusive, as the high performance rapid recyclability. Experimentally determined mechanical values usually much lower than their theoretical values. preparation with modulus, toughness, ultrastrong strength, highly efficient recyclability is still a challenge. Here, novel hyperbranched (Bn, n = 6, 12, 24) imide structures by thiol-ene click reaction. Bn shows an excellent comprehensive function in simultaneously improving low-temperature resistance, degradability diglycidyl ether bisphenol-A (DGEBA). All properties first increase then decrease minimization free volume properties. improvement attributable to uniform molecular holes or mixture linear topological structures. precise measurement controllability discovered, well structure degradation crosslinked resins. two conflicts successfully resolved between during service efficiency degradation. These findings provide route for designing ultrastrong, tough, recyclable

Language: Английский

---

A Model Ensemble Approach Enables Data-Driven Property Prediction for Chemically Deconstructable Thermosets in the Low-Data Regime

ACS Central Science, Journal Year: 2023, Volume and Issue: 9(9), P. 1810 - 1819

Published: Sept. 14, 2023

Thermosets present sustainability challenges that could potentially be addressed through the design of deconstructable variants with tunable properties; however, combinatorial space possible thermoset molecular building blocks (e.g., monomers, cross-linkers, and additives) manufacturing conditions is vast, predictive knowledge for how combinations these components translate to bulk properties lacking. Data science overcome problems, but computational methods are difficult apply multicomponent, amorphous, statistical copolymer materials which little data exist. Here, leveraging a set 101 examples, we introduce closed-loop experimental, machine learning (ML), virtual screening strategy enable predictions glass transition temperature (Tg) polydicyclopentadiene (pDCPD) thermosets containing cleavable bifunctional silyl ether (BSE) comonomers and/or cross-linkers varied compositions loadings. Molecular features formulation variables used as model inputs, uncertainty quantified ensembling, together heavy regularization helps avoid overfitting ultimately achieves within <15 °C compositionally diverse BSEs. This work offers path predicting based on their blocks, may accelerate discovery promising plastics, rubbers, composites improved functionality controlled deconstructability.

Language: Английский

---

Heat-Resistant Polymer Discovery by Utilizing Interpretable Graph Neural Network with Small Data

Macromolecules, Journal Year: 2024, Volume and Issue: 57(8), P. 3515 - 3528

Published: April 12, 2024

Polymers with exceptional heat resistance are critically valuable in numerous domains, particularly as essential components of flexible organic light-emitting diodes. Among these, polyimides (PIs) demonstrate significant potential substrate candidates for these next-generation displays due to their robustness. However, traditional Edisonian approaches struggle navigate the vast chemical space PIs and also pose challenges small data, which constrains learnable machine learning (ML). In this study, we propose a chemical-knowledge-based strategy facilitate design high glass transition temperature (Tg) utilizing an atom-wise graph neural network data. Inspired by intuition, our leverages available data on same property (i.e., Tg) from other polymers, is beneficial expanding used ML. The trained ML model achieves impressive performance predicting Tg polymers. We have investigated impact encompassed sets models. Through interpretability analysis, it has been demonstrated that learned more accurate knowledge. Utilizing model, 89 were rapidly discovered over 106 candidates, experimental validation confirmed most promising PIs, found possess exceeding 405 °C even 450 °C. These results, along accelerate discovery polymer materials display devices.

Language: Английский

---

Nacre-inspired hierarchical framework enables tough and impact-monitoring epoxy nanocomposites

Composites Part B Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 111246 - 111246

Published: Jan. 1, 2024

Language: Английский

---

Microscopic Mechanisms of Self-Healing in Polymers Revealed by Molecular Simulations and Machine Learning

Macromolecules, Journal Year: 2024, Volume and Issue: 57(7), P. 3258 - 3270

Published: March 22, 2024

At present, there is still a lack of in-depth research into the relationship between structural changes during healing process and self-healing efficiency polymers. In current work, molecular dynamics (MD) simulations machine learning methods were applied to investigate microscopic mechanisms in Based on MD simulations, it was found that chain segments entire chains diffuse crack region healing, together with reformation reversible interactions. Segment diffusion closely related reconstruction interactions, can lead interpenetration chains. methods, demonstrated (the chains) plays most crucial role influencing Furthermore, based Random Forest method, quantitative be established.

Language: Английский

---

Intelligent Biomaterialomics: Molecular Design, Manufacturing, and Biomedical Applications

Advanced Materials, Journal Year: 2023, Volume and Issue: 36(22)

Published: July 25, 2023

Abstract Materialomics integrates experiment, theory, and computation in a high‐throughput manner, has changed the paradigm for research development of new functional materials. Recently, with rapid characterization machine‐learning technologies, establishment biomaterialomics that tackles complex physiological behaviors become accessible. Breakthroughs clinical translation nanoparticle‐based therapeutics vaccines have been observed. Herein, recent advances biomaterials, including polymers, lipid‐like materials, peptides/proteins, discovered through screening or machine learning‐assisted methods, are summarized. The molecular design structure‐diversified libraries; characterization, screening, preparation; and, their applications drug delivery discussed detail. Furthermore, prospects main challenges future highlighted.

Language: Английский

---