Development of machine learning models for material classification and prediction of mechanical properties of FDM 3D printing outputs DOI
Suhyun Kim, Ji-Hye Park, Ji Young Park

et al.

Journal of Mechanical Science and Technology, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 31, 2025

Language: Английский

Evaluating enhanced predictive modeling of foam concrete compressive strength using artificial intelligence algorithms DOI
Mohamed Abdellatief, Leong Sing Wong,

Norashidah Md Din

et al.

Materials Today Communications, Journal Year: 2024, Volume and Issue: 40, P. 110022 - 110022

Published: Aug. 1, 2024

Language: Английский

Citations

28
Applications of artificial intelligence/machine learning to high-performance composites DOI
Yifeng Wang, Wang Kan, Chuck Zhang

et al.

Composites Part B Engineering, Journal Year: 2024, Volume and Issue: 285, P. 111740 - 111740

Published: July 23, 2024

Language: Английский

Citations

23
Advancements of machine learning techniques in fiber-filled polymer composites: a review DOI

R. Alagulakshmi,

R. Ramalakshmi, V. Arumugaprabu

et al.

Polymer Bulletin, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 9, 2025

Language: Английский

Citations

2
Transformers in Material Science: Roles, Challenges, and Future Scope DOI

Nitin Rane

SSRN Electronic Journal, Journal Year: 2023, Volume and Issue: unknown

Published: Jan. 1, 2023

This study explores the diverse applications, challenges, and future prospects of employing vision transformers in various material science domains, including biomaterials, ceramic materials, composite energy magnetic electronics photonic materials synthesis, polymers, nanomaterials. In realm application has significantly improved our understanding biological interactions, leading to development innovative medical implants drug delivery systems. these have revolutionized design production processes, ensuring higher durability efficiency. Likewise, they enabled creation lightweight yet robust structures, transforming industries from aerospace automotive. Energy research greatly benefited transformers, facilitating discovery novel for storage conversion. Additionally, been transformed by their ability analyze intricate patterns, aiding advanced data technologies. accelerated evolution compact high-performance devices. Integrating poses challenges managing vast datasets, model interpretability, addressing ethical concerns related privacy bias. As continue advance, nanomaterials is anticipated yield groundbreaking discoveries. highlights way forward, underscoring importance collaborative efforts between computer scientists researchers unlock full potential reshaping landscape science.

Language: Английский

Citations

27
A comprehensive review on fillers and mechanical properties of 3D printed polymer composites DOI

Nishtha Arora,

Sachin Dua,

Vivek Kumar Singh

et al.

Materials Today Communications, Journal Year: 2024, Volume and Issue: 40, P. 109617 - 109617

Published: June 21, 2024

Language: Английский

Citations

12
Machine learning approach to evaluating impact behavior in fabric-laminated composite materials DOI Creative Commons
Shivashankar Hiremath, Yu Zhang, Lu Zhang

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: 23, P. 102576 - 102576

Published: July 17, 2024

Fabric-layered composites play a crucial role in safety and surveillance applications, making it imperative to accurately predict their impact behavior. This research focuses on creating machine-learning model the behavior of fabric-stacked composites, specifically carbon Kevlar fabrics. Low-velocity tests were performed with varying parameters, energy laminate thickness information used train models properties such as force, displacement, absorbed energy. It was observed that force increased by 118.5 % carbon-laminated fibers 175.8 Kevlar-laminated fibers, while hybrid layer showed 101.4 increase upon from 16J. Displacement can affect stability layered structure; thus, similar stacking sequence is less stable than laminated structure. In terms energy, layers increase, fiber absorbs 4.8 times more structures absorb 3 at higher Furthermore, four machine learning investigate identical mixed-layered composites. The displacement predicted accuracy using polynomial regression model, achieving 80 89 accuracy, respectively. support vector approximately 96 accuracy. continuing, experimental results closely matched predictions made other utilized this study. Additionally, importance distinctive features influence performance learning-based interpreted transposed dependency plots. Various failure modes fabric also identified, providing insights enhance stacked materials.

Language: Английский

Citations

12
Rethinking materials simulations: Blending direct numerical simulations with neural operators DOI Creative Commons
Vivek Oommen, Khemraj Shukla, Saaketh Desai

et al.

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

Published: July 4, 2024

Abstract Materials simulations based on direct numerical solvers are accurate but computationally expensive for predicting materials evolution across length- and time-scales, due to the complexity of underlying equations, nature multiscale spatiotemporal interactions, need reach long-time integration. We develop a method that blends with neural operators accelerate such simulations. This methodology is integration community solver U-Net operator, enhanced by temporal-conditioning mechanism enable extrapolation efficient time-to-solution predictions dynamics. demonstrate effectiveness this hybrid framework microstructure via phase-field method. Such exhibit high spatial gradients co-evolution different material phases simultaneous slow fast establish coupled large speed-up compared DNS depending strategy utilized. generalizable broad range simulations, from solid mechanics fluid dynamics, geophysics, climate, more.

Language: Английский

Citations

10
Identification of Lighting Strike Damage and Prediction of Residual Strength of Carbon Fiber-Reinforced Polymer Laminates Using a Machine Learning Approach DOI Open Access

Ruochen Dong,

Yin Fan, J. J. Bian

et al.

Polymers, Journal Year: 2025, Volume and Issue: 17(2), P. 180 - 180

Published: Jan. 13, 2025

Due to the complex and uncertain physics of lightning strike on carbon fiber-reinforced polymer (CFRP) laminates, conventional numerical simulation methods for assessing residual strength lightning-damaged CFRP laminates are highly time-consuming far from pretty. To overcome these challenges, this study proposes a new prediction method based machine learning. A diverse dataset is acquired augmented photographs damage areas, C-scan images, mechanical performance data, layup details, current parameters. Original preprocessed with Sobel operator edge enhancement, fed into UNet neural network using four channels detect damaged areas. These identified along parameters inputs predicting depth in laminates. its close relation strength, then used estimate The effectiveness confirmed, mean Intersection over Union (mIoU) achieving 93% identification, Mean Absolute Error (MAE) reducing 5.4% prediction, Relative (MRE) 7.6% respectively.

Language: Английский

Citations

1
Classification of a nanocomposite using a combination between Recurrent Neural Network based on Transformer and Bayesian Network for testing the conductivity property DOI

Wejden Gazehi,

Rania Loukil, Mongi Besbes

et al.

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: 270, P. 126518 - 126518

Published: Jan. 15, 2025

Language: Английский

Citations

1
Experimental and computational approaches to optimizing the development of NFs reinforced polymer composite: A review of optimization strategies DOI
Olajesu Favor Olanrewaju, Justus Uchenna Anaele, Sodiq Abiodun Kareem

et al.

Sustainable materials and technologies, Journal Year: 2025, Volume and Issue: unknown, P. e01259 - e01259

Published: Jan. 1, 2025

Language: Английский

Citations

1