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

Machine-learning potentials for nanoscale simulations of tensile deformation and fracture in ceramics DOI Creative Commons
Shuyao Lin, Luis Casillas‐Trujillo, Ferenc Tasnádi

et al.

npj Computational Materials, Journal Year: 2024, Volume and Issue: 10(1)

Published: April 2, 2024

Language: Английский

Citations

9
Machine Learning Speeds Up the Discovery of Efficient Porphyrinoid Electrocatalysts for Ammonia Synthesis DOI Creative Commons
Wenfeng Hu, Bingyi Song, Li‐Ming Yang

et al.

Energy & environment materials, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 5, 2025

Two‐dimensional transition metal porphyrinoid materials (2DTMPoidMats), due to their unique electronic structure and tunable active sites, have the potential enhance interactions with nitrogen molecules promote protonation process, making them promising electrochemical reduction reaction (eNRR) electrocatalysts. Experimentally screening a large number of catalysts for eNRR catalytic performance would consume considerable time economic resources. First‐principles calculations machine learning (ML) algorithms could greatly improve efficiency catalyst screening. Using this approach, we selected 86 candidates capable catalyzing from 1290 types 2DTMPoidMats, verified results density functional theory (DFT) computations. Analysis full pathway shows that MoPp‐meso‐F‐β‐Py, MoPp‐β‐Cl‐meso‐Diyne, MoPp‐meso‐Ethinyl, WPp‐β‐Pz exhibit best onset −0.22, −0.19, −0.23, −0.35 V, respectively. This work provides valuable insights into efficient design promotes application ML algorithmic models in field catalysis.

Language: Английский

Citations

1
Design and optimization of a mechanical metamaterial featuring dual tunability in auxeticity and bandgap modulation DOI
Jiayi Hu, Zhi Gong, Yuanlong Li

et al.

Composite Structures, Journal Year: 2025, Volume and Issue: unknown, P. 119050 - 119050

Published: March 1, 2025

Language: Английский

Citations

1
Prediction of thermal conductivity in multi-component magnesium alloys based on machine learning and multiscale computation DOI Open Access

Junwei Chen,

Yixin Zhang,

Jun Luan

et al.

Journal of Materials Informatics, Journal Year: 2025, Volume and Issue: 5(2)

Published: March 13, 2025

Magnesium (Mg) alloys have attracted considerable attention as next-generation lightweight thermal conducting materials. However, their conductivity decreases significantly with increasing alloying content. Current methods for predicting of Mg primarily rely on computationally intensive first-principles calculations or semi-empirical models limited accuracy. This study presents a novel machine learning approach coupled multiscale computation in multi-component alloys. A comprehensive database 1,139 measurements from as-cast was systematically compiled. feature set incorporating elemental characteristics, thermodynamic properties, and electronic structure parameters constructed. Key features, including atomic radius differences, enthalpy, cohesive energy, the ratio to relaxation time, were identified through sequential forward floating selection (SFFS). The XGBoost algorithm demonstrated superior performance, achieving mean absolute percentage error (MAPE) 2.16% low-component ternary simpler alloy systems. Through L1 L2 regularization optimization, model’s extrapolation capability quaternary higher-order systems enhanced, reducing prediction 13.60%. research provides new insights theoretical guidance accelerating development high

Language: Английский

Citations

1
Machine learning insights into CaCO3 phase transitions: Synthesis and phase prediction DOI
Yanqi Huang, Bart De Spiegeleer, Bogdan V. Parakhonskiy

et al.

Ceramics International, Journal Year: 2024, Volume and Issue: 50(13), P. 23284 - 23295

Published: April 5, 2024

Language: Английский

Citations

8
Illustrating an Effective Workflow for Accelerated Materials Discovery DOI
Mrinalini Mulukutla,

A. Nicole Person,

Sven Voigt

et al.

Integrating materials and manufacturing innovation, Journal Year: 2024, Volume and Issue: 13(2), P. 453 - 473

Published: June 1, 2024

Language: Английский

Citations

7
New Directions for Thermoelectrics: A Roadmap from High‐Throughput Materials Discovery to Advanced Device Manufacturing DOI Creative Commons

Kaidong Song,

A. N. M. Tanvir, Md Omarsany Bappy

et al.

Small Science, Journal Year: 2024, Volume and Issue: unknown

Published: April 4, 2024

Thermoelectric materials, which can convert waste heat into electricity or act as solid‐state Peltier coolers, are emerging key technologies to address global energy shortages and environmental sustainability. However, discovering materials with high thermoelectric conversion efficiency is a complex slow process. The field of high‐throughput material discovery demonstrates its potential accelerate the development new combining low cost. synergistic integration processing characterization techniques machine learning algorithms form an efficient closed‐loop process generate analyze broad datasets discover unprecedented performances. Meanwhile, recent advanced manufacturing methods provides exciting opportunities realize scalable, low‐cost, energy‐efficient fabrication devices. This review overview advances in using methods, including processing, characterization, screening. Advanced devices also introduced impacts power generation cooling. In end, this article discusses future research prospects directions.

Language: Английский

Citations

6
Structure genome based machine learning method for woven lattice structures DOI

Chundi Zhang,

Ben Wang, Hengyi Zhu

et al.

International Journal of Mechanical Sciences, Journal Year: 2023, Volume and Issue: 245, P. 108134 - 108134

Published: Jan. 9, 2023

Language: Английский

Citations

15
Customizable anisotropic microlattices for additive manufacturing: Machine learning accelerated design, mechanical properties and structural-property relationships DOI
Xinwei Li, Pan Wang, Miao Zhao

et al.

Additive manufacturing, Journal Year: 2024, Volume and Issue: 89, P. 104248 - 104248

Published: June 1, 2024

Language: Английский

Citations

5
Exploring the Future of Polyhydroxyalkanoate Composites with Organic Fillers: A Review of Challenges and Opportunities DOI Open Access
Abhishek Thakur, Marta Musioł, Khadar Duale

et al.

Polymers, Journal Year: 2024, Volume and Issue: 16(13), P. 1768 - 1768

Published: June 22, 2024

Biopolymers from renewable materials are promising alternatives to the traditional petroleum-based plastics used today, although they face limitations in terms of performance and processability. Natural fillers have been identified as a strategic route create sustainable composites, natural form waste by-products received particular attention. Consequently, primary focus this article is offer broad overview recent breakthroughs environmentally friendly Polhydroxyalkanoate (PHA) polymers their composites. PHAs aliphatic polyesters obtained by bacterial fermentation sugars fatty acids considered play key role addressing sustainability challenges replace various industrial sectors. Moreover, examines potential biodegradable polymer with specific emphasis on composite materials, current trends, future market prospects. Increased environmental concerns driving discussions importance integrating our daily use, emphasizing need for clear frameworks economic incentives support use these materials. Finally, it highlights indispensable ongoing research development efforts address sector, reflecting growing interest across all industries.

Language: Английский

Citations

5