Application of machine learning in polyimide structure design and property regulation DOI Creative Commons

Wenjia Huo,

Haiyue Wang, Liying Guo

et al.

High Performance Polymers, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 8, 2025

Polyimide (PI) is widely used in modern industry due to its excellent properties. Its synthesis methods and property research have significantly progressed. However, the design regulation of PI structures through traditional technologies are slow expensive, which make it difficult meet practical demand materials. With rapid development high-throughput computing data-driven technology, machine learning (ML) has become an important method for exploring new Data-driven ML envisaged as a decisive enabler PIs discovery. This paper first introduces basic workflow common algorithms ML. Secondly, applications material properties prediction, assisting computational simulation inverse desired reviewed. Finally, we discuss main challenges possible solutions research.

Language: Английский

From prediction to design: Recent advances in machine learning for the study of 2D materials DOI Open Access
Hua He, Yuhua Wang,

Yajuan Qi

et al.

Nano Energy, Journal Year: 2023, Volume and Issue: 118, P. 108965 - 108965

Published: Oct. 4, 2023

Language: Английский

Citations

46
Application of Machine Learning in Material Synthesis and Property Prediction DOI Open Access
Guannan Huang, Yani Guo, Ye Chen

et al.

Materials, Journal Year: 2023, Volume and Issue: 16(17), P. 5977 - 5977

Published: Aug. 31, 2023

Material innovation plays a very important role in technological progress and industrial development. Traditional experimental exploration numerical simulation often require considerable time resources. A new approach is urgently needed to accelerate the discovery of materials. Machine learning can greatly reduce computational costs, shorten development cycle, improve accuracy. It has become one most promising research approaches process novel material screening property prediction. In recent years, machine been widely used many fields research, such as superconductivity, thermoelectrics, photovoltaics, catalysis, high-entropy alloys. this review, basic principles are briefly outlined. Several commonly algorithms models their primary applications then introduced. The predicting properties guiding synthesis discussed. Finally, future outlook on materials science field presented.

Language: Английский

Citations

45
Recent Advances in High‐Entropy Layered Oxide Cathode Materials for Alkali Metal‐Ion Batteries DOI
Liping Duan, Yingna Zhang,

Haowei Tang

et al.

Advanced Materials, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 29, 2024

Abstract Since the electrochemical de/intercalation behavior is first detected in 1980, layered oxides have become most promising cathode material for alkali metal‐ion batteries (Li + /Na /K ; AMIBs) owing to their facile synthesis and excellent theoretical capacities. However, inherent drawbacks of unstable structural evolution sluggish diffusion kinetics deteriorate performance, limiting further large‐scale applications. To solve these issues, novel strategy high entropy has been widely applied oxide cathodes AMIBs recent years. Through multielement synergy stabilization effects, high‐entropy (HELOs) can achieve adjustable activity enhanced stability. Herein, basic concepts, design principles, methods HELO are introduced systematically. Notably, it explores detail improvements on limitations oxides, highlighting latest advances materials field AMIBs. In addition, introduces advanced characterization calculations HELOs proposes potential future research directions optimization strategies, providing inspiration researchers develop areas energy storage conversion.

Language: Английский

Citations

34
High‐Entropy Oxides for Rechargeable Batteries DOI

Biao Ran,

Huanxin Li, Ruiqi Cheng

et al.

Advanced Science, Journal Year: 2024, Volume and Issue: 11(25)

Published: April 22, 2024

Abstract High‐entropy oxides (HEOs) have garnered significant attention within the realm of rechargeable batteries owing to their distinctive advantages, which encompass diverse structural attributes, customizable compositions, entropy‐driven stabilization effects, and remarkable superionic conductivity. Despite brilliance HEOs in energy conversion storage applications, there is still lacking a comprehensive review for both entry‐level experienced researchers, succinctly encapsulates present status challenges inherent HEOs, spanning features, intrinsic properties, prevalent synthetic methodologies, diversified applications batteries. Within this review, endeavor distill characteristics, ionic conductivity, entropy explore practical (lithium‐ion, sodium‐ion, lithium‐sulfur batteries), including anode cathode materials, electrolytes, electrocatalysts. The seeks furnish an overview evolving landscape HEOs‐based cell component shedding light on progress made hurdles encountered, as well serving guidance compositions design optimization strategy enhance reversible stability, electrical electrochemical performance conversion.

Language: Английский

Citations

27
High‐temperature ablation resistance prediction of ceramic coatings using machine learning DOI
Jia Sun, Zhixiang Zhang, Yujia Zhang

et al.

Journal of the American Ceramic Society, Journal Year: 2024, Volume and Issue: 108(1)

Published: Sept. 20, 2024

Abstract Surface ablation temperature and linear rate are two crucial indicators for ceramic coatings under ultrahigh temperatures service, yet the results collection of such in process is difficult due to long‐period material preparation high‐cost test. In this work, four kinds machine learning models applied predict above indicators. The Random Forest (RF) model exhibits a high accuracy 87% predicting surface temperature, while low 60% rate. To optimize model, novel features constructed based on original by sum importance weights model. Thereafter, newly increases significantly, optimized RF improved 11%, exceeding 70% accuracy. By validation with available data experiments, demonstrates precise predictions target variables.

Language: Английский

Citations

26
A comprehensive review of covalent organic frameworks (COFs) and their derivatives in environmental pollution control DOI Creative Commons
Shengbo Ge,

Kexin Wei,

Wanxi Peng

et al.

Chemical Society Reviews, Journal Year: 2024, Volume and Issue: unknown

Published: Jan. 1, 2024

Covalent organic frameworks (COFs) have gained considerable attention due to their design possibilities as the molecular building blocks that can stack in an atomically precise spatial arrangement.

Language: Английский

Citations

25
AI in single-atom catalysts: a review of design and applications DOI Open Access

Qijun Yu,

Ninggui Ma,

Chihon Leung

et al.

Journal of Materials Informatics, Journal Year: 2025, Volume and Issue: 5(1)

Published: Feb. 12, 2025

Single-atom catalysts (SACs) have emerged as a research frontier in catalytic materials, distinguished by their unique atom-level dispersion, which significantly enhances activity, selectivity, and stability. SACs demonstrate substantial promise electrocatalysis applications, such fuel cells, CO2 reduction, hydrogen production, due to ability maximize utilization of active sites. However, the development efficient stable involves intricate design screening processes. In this work, artificial intelligence (AI), particularly machine learning (ML) neural networks (NNs), offers powerful tools for accelerating discovery optimization SACs. This review systematically discusses application AI technologies through four key stages: (1) Density functional theory (DFT) ab initio molecular dynamics (AIMD) simulations: DFT AIMD are used investigate mechanisms, with high-throughput applications expanding accessible datasets; (2) Regression models: ML regression models identify features that influence performance, streamlining selection promising materials; (3) NNs: NNs expedite known structural models, facilitating rapid assessment potential; (4) Generative adversarial (GANs): GANs enable prediction novel high-performance tailored specific requirements. work provides comprehensive overview current status insights recommendations future advancements field.

Language: Английский

Citations

2
X-ray Diffraction Data Analysis by Machine Learning Methods—A Review DOI Creative Commons
Vasile-Adrian Surdu, Romuald Győrgy

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(17), P. 9992 - 9992

Published: Sept. 4, 2023

X-ray diffraction (XRD) is a proven, powerful technique for determining the phase composition, structure, and microstructural features of crystalline materials. The use machine learning (ML) techniques applied to materials research has increased significantly over last decade. This review presents survey scientific literature on applications ML XRD data analysis. Publications suitable inclusion in this were identified using “machine diffraction” search term, keeping only English-language publications which was employed analyze specifically. selected covered wide range applications, including classification identification, lattice quantitative analyses, detection defects substituents, as well material characterization. Current trends field suggest that future efforts pertaining application analysis will address shortcomings approaches related quality availability, interpretability results model generalizability robustness. Additionally, likely incorporate more domain knowledge physical constraints, integrate with quantum methods, apply like real-time high-throughput screening accelerate discovery tailored novel

Language: Английский

Citations

35
Inverse design of 3D cellular materials with physics-guided machine learning DOI Creative Commons

Mohammad Abu-Mualla,

Jida Huang

Materials & Design, Journal Year: 2023, Volume and Issue: 232, P. 112103 - 112103

Published: July 4, 2023

This paper investigates the feasibility of data-driven methods in automating engineering design process, specifically studying inverse cellular mechanical metamaterials. Traditional designing materials typically rely on trial and error or iterative optimization, which often leads to limited productivity high computational costs. While approaches have been explored for materials, many these lack robustness fail consider manufacturability generated structures. study aims develop an efficient methodology that accurately generates metamaterial while ensuring predicted To achieve this, we created a comprehensive dataset spans broad range properties by applying rotations cubic structures synthesized from nine symmetries materials. We then employ physics-guided neural network (PGNN) consisting dual networks: generator network, serves as tool, forward acts simulator. The goal is match desired anisotropic stiffness components with unit-cell parameters. results our model are analyzed using three distinct datasets demonstrate efficiency prediction accuracy compared conventional methods.

Language: Английский

Citations

29
State-of-art review on the process-structure-properties-performance linkage in wire arc additive manufacturing DOI Creative Commons
Han Zhang, Runsheng Li, Junjiang Liu

et al.

Virtual and Physical Prototyping, Journal Year: 2024, Volume and Issue: 19(1)

Published: Sept. 5, 2024

Language: Английский

Citations

10