期刊名：Journal of Composites Science

期刊主页：https://www.mdpi.com/journal/jcs

本文梳理了近期发表在 J. Compos. Sci.的复合材料与人工智能交叉领域的前沿研究文献，重点聚焦于人工智能设计优化、先进数值模拟与多尺度分析、以及结构力学行为与损伤评估三个维度。相关工作涵盖了机器学习在复合材料微观性能预测、铺层优化及损伤识别中的广泛应用，从分子动力学到有限元的多尺度数值建模研究，以及针对低速冲击、疲劳失效和螺栓连接的结构力学行为分析与试验验证，并对特定复合体系及损伤识别方法的综合研究进行了系统总结。

1. The Effects of Fiber Concentration, Orientation, and Aspect Ratio on the Frontal Polymerization of Short Carbon-Fiber-Reinforced Composites: A Numerical Study

纤维浓度、取向和长径比对短碳纤维增强复合材料前沿聚合的影响：数值研究

https://www.mdpi.com/2504-477X/9/6/307

Shams, A.T.; Papon, E.A.; Haque, A. The Effects of Fiber Concentration, Orientation, and Aspect Ratio on the Frontal Polymerization of Short Carbon-Fiber-Reinforced Composites: A Numerical Study. J. Compos. Sci. 2025, 9, 307.

2. Damage Mechanism Characterization of Glass Fiber-Reinforced Polymer Composites: A Study Using Acoustic Emission Technique and Unsupervised Machine Learning Algorithms

玻璃纤维增强聚合物复合材料损伤机理表征：基于声发射技术和无监督机器学习算法的研究

https://www.mdpi.com/2504-477X/9/8/426

Palacios Moreno, J.; Nazaripoor, H.; Mertiny, P. Damage Mechanism Characterization of Glass Fiber-Reinforced Polymer Composites: A Study Using Acoustic Emission Technique and Unsupervised Machine Learning Algorithms. J. Compos. Sci. 2025, 9, 426.

3. Development of Structural Model of Fiber Metal Laminate Subjected to Low-Velocity Impact and Validation by Tests

低速冲击作用下纤维金属层合板结构模型的建立及试验验证

https://www.mdpi.com/2504-477X/9/7/322

Cetinkaya, B.; Yilmaz, E.; Özkol, I.; Sen, I.; Saracyakupoglu, T. Development of Structural Model of Fiber Metal Laminate Subjected to Low-Velocity Impact and Validation by Tests. J. Compos. Sci. 2025, 9, 322.

4. An Exact 3D Shell Model for Free Vibration Analysis of Magneto-Electro-Elastic Composite Structures

用于磁电弹性复合材料结构自由振动分析的精确三维壳体模型

https://www.mdpi.com/2504-477X/9/8/399

Brischetto, S.; Cesare, D.; Mondino, T. An Exact 3D Shell Model for Free Vibration Analysis of Magneto-Electro-Elastic Composite Structures. J. Compos. Sci. 2025, 9, 399.

5. Comprehensive Experimental Optimization and Image-Driven Machine Learning Prediction of Tribological Performance in MWCNT-Reinforced Bio-Based Epoxy Nanocomposites

基于图像驱动机器学习的MWCNT增强生物基环氧纳米复合材料摩擦学性能综合实验优化

https://www.mdpi.com/2504-477X/9/8/385

Hiremath, P.; Heckadka, S.S.; Anne, G.; Ghadai, R.K.; Deepak, G.D.; Shivamurthy, R.C. Comprehensive Experimental Optimization and Image-Driven Machine Learning Prediction of Tribological Performance in MWCNT-Reinforced Bio-Based Epoxy Nanocomposites. J. Compos. Sci. 2025, 9, 385.

6. Artificial Intelligence in the Design and Optimization of Laminated FRP Composites: A Review of Methodologies and Applications

人工智能在层合FRP复合材料设计与优化中的应用：方法论与应用综述

https://www.mdpi.com/2504-477X/9/12/654

Elsisi, A.; Abdel-Monsef, S.; Salim, H. Artificial Intelligence in the Design and Optimization of Laminated FRP Composites: A Review of Methodologies and Applications. J. Compos. Sci. 2025, 9, 654.

7. Numerical Study on the Performance and Failure Modes of Bolted Connections in Pultruded-Fibre-Reinforced Polymer (PFRP) Profiles

拉挤成型纤维增强聚合物（PFRP）型材螺栓连接性能及失效模式的数值研究

https://www.mdpi.com/2504-477X/9/9/492

Rahman, A.; Boem, I.; Gattesco, N. Numerical Study on the Performance and Failure Modes of Bolted Connections in Pultruded-Fibre-Reinforced Polymer (PFRP) Profiles. J. Compos. Sci. 2025, 9, 492.

8. Design and Analysis of Natural Fiber-Reinforced Jute Woven Composite RVEs Using Numerical and Statistical Methods

利用数值和统计方法设计与分析天然纤维增强黄麻编织复合材料代表性体积单元

http://www.mdpi.com/2504-477X/9/6/283

Sultana, J.; Varga, G. Design and Analysis of Natural Fiber-Reinforced Jute Woven Composite RVEs Using Numerical and Statistical Methods. J. Compos. Sci. 2025, 9, 283.

9. Uncertainty-Based Design: Finite Element and Explainable Machine Learning Modeling of Carbon–Carbon Composites for Ultra-High Temperature Solar Receivers

基于不确定性的设计：用于超高温太阳能接收器的碳-碳复合材料的有限元和可解释机器学习建模

https://www.mdpi.com/2504-477X/9/3/100

Daghigh, V.; Daghigh, H.; Keller, M.W. Uncertainty-Based Design: Finite Element and Explainable Machine Learning Modeling of Carbon–Carbon Composites for Ultra-High Temperature Solar Receivers. J. Compos. Sci. 2025, 9, 100.

10. Micro-Scale Numerical Simulation for Residual Strength of CFRP After Cyclic Tensile or Out-of-Plane Shear Loadings Fatigue

CFRP在循环拉伸或面外剪切载荷疲劳后残余强度的微观尺度数值模拟

http://www.mdpi.com/2504-477X/9/1/28

Sekino, T.; Kudo, N.; Koyanagi, J. Micro-Scale Numerical Simulation for Residual Strength of CFRP After Cyclic Tensile or Out-of-Plane Shear Loadings Fatigue. J. Compos. Sci. 2025, 9, 28.

11. An Overview of Damage Identification in Composite Structures—From Computational Methods to Machine Learning

复合材料结构损伤识别概述——从计算方法到机器学习

http://www.mdpi.com/2504-477X/9/12/683

Dubey, A.; Shakoor, M.; Vasiukov, D.; Khoury, B.; Deléglise Lagardère, M.; Chaki, S. An Overview of Damage Identification in Composite Structures—From Computational Methods to Machine Learning. J. Compos. Sci. 2025, 9, 683.

12. Deep Artificial Neural Network Modeling of the Ablation Performance of Ceramic Matrix Composites in the Hydrogen Torch Test

基于深度人工神经网络的陶瓷基复合材料在氢气炬试验中的烧蚀性能建模

https://www.mdpi.com/2504-477X/9/5/239

Deb, J.B.; Varela, C.; Faysal, F.; Wang, Y.; Maiti, C.; Gou, J. Deep Artificial Neural Network Modeling of the Ablation Performance of Ceramic Matrix Composites in the Hydrogen Torch Test. J. Compos. Sci. 2025, 9, 239.

13. Voxel-Based Finite Element Investigation of Micromechanics Models for Stiffness Prediction of Cross-Ply Laminates

基于体素的有限元方法研究交叉层合板刚度预测的微观力学模型

http://www.mdpi.com/2504-477X/9/6/288

Forooghi, D.; Luo, Y. Voxel-Based Finite Element Investigation of Micromechanics Models for Stiffness Prediction of Cross-Ply Laminates. J. Compos. Sci. 2025, 9, 288.

14. Comprehensive Overview on the Computational, Experimental, Numerical, and Theoretical Assessments of Silica Aerogel Composites

二氧化硅气凝胶复合材料的计算、实验、数值和理论评估的综合概述

http://www.mdpi.com/2504-477X/9/6/306

Kunte, A.A.; Khandelwal, S.; Patil, S.P. Comprehensive Overview on the Computational, Experimental, Numerical, and Theoretical Assessments of Silica Aerogel Composites. J. Compos. Sci. 2025, 9, 306.

15. Prediction of Mechanical and Fracture Properties of Lightweight Polyurethane Composites Using Machine Learning Methods

利用机器学习方法预测轻质聚氨酯复合材料的力学性能和断裂性能

http://www.mdpi.com/2504-477X/9/6/271

Narkhede, N.N.; Chalivendra, V. Prediction of Mechanical and Fracture Properties of Lightweight Polyurethane Composites Using Machine Learning Methods. J. Compos. Sci. 2025, 9, 271.

16. Analysis and Numerical Simulation of the Behavior of Composite Materials with Natural Fibers Under Quasi-Static Frictional Contact

准静态摩擦接触下天然纤维复合材料行为的分析与数值模拟

https://www.mdpi.com/2504-477X/9/7/338

Apsan, M.R.; Mitu, A.M.; Pop, N.; Sireteanu, T.; Maxim, V.M.; Musat, A. Analysis and Numerical Simulation of the Behavior of Composite Materials with Natural Fibers Under Quasi-Static Frictional Contact. J. Compos. Sci. 2025, 9, 338.

17. The Silylation Effect of C/SiC Nanofillers on Mechanical Properties of Cellulose Nanocomposite: Insights from Molecular Dynamics Simulations

C/SiC纳米填料的硅烷化效应对纤维素纳米复合材料力学性能的影响：来自分子动力学模拟的启示

http://www.mdpi.com/2504-477X/9/6/284

Al-Maharma, A.Y.; Markert, B.; Bamer, F. The Silylation Effect of C/SiC Nanofillers on Mechanical Properties of Cellulose Nanocomposite: Insights from Molecular Dynamics Simulations. J. Compos. Sci. 2025, 9, 284.

18. Leveraging Machine Learning (ML) to Enhance the Structural Properties of a Novel Alkali Activated Bio-Composite

利用机器学习（ML）增强新型碱活化生物复合材料的结构性能

https://www.mdpi.com/2504-477X/9/9/464

Mahamat, A.A.; Boukar, M.M.; Obianyo, I.I.; Nshimiyimana, P.; Ngayakamo, B.; Leklou, N.; Bih, N.L. Leveraging Machine Learning (ML) to Enhance the Structural Properties of a Novel Alkali Activated Bio-Composite. J. Compos. Sci. 2025, 9, 464.

期刊介绍

主编：Dr. Francesco Tornabene

Journal of Composites Science (ISSN 2504-477X) 是一个国际开源期刊，致力于发表复合材料领域的前沿研究，涵盖纤维增强复合材料、纳米复合材料、生物医学复合材料及能源复合材料等多个方向，并重点关注材料的建模、制造工艺与性能表征。目前，期刊已被 ESCI (Web of Science) 与 Scopus 等权威数据库收录，位于 JCR 材料科学-复合材料领域的 Q2 分区，CiteScore 工程综合领域的 Q1 分区。期刊旨在为复合材料研究者构建一个展示创新成果、促进国际学术交流的高效平台。

2025 Impact Factor：4.6

2025 CiteScore：6.7

Time to First Decision：13.9 Days

Acceptance to Publication：4.5 Days