Guest Editors
Prof. Qinghang Wang
Email: wangqinghang@yzu.edu.cn
Affiliation: School of Mechanical Engineering, Yangzhou University, Yangzhou, 225127, China
Homepage:
Research Interests: machine learning; Mg alloy; mechanical property; corrosion; air battery
Summary
Machine learning (ML) holds immense potential in advancing light alloys research and development. It can accelerate the discovery and optimization of new light alloy compositions by analyzing vast datasets of material properties and performance. ML models can predict mechanical properties, corrosion resistance, and formability, guiding experimental efforts more efficiently. Additionally, ML aids in understanding complex relationships between processing parameters, microstructures, and properties, enabling precise control during manufacturing. By integrating computational modeling with experimental data, it facilitates the design of high-performance light alloys tailored for specific applications. As computational power grows and data-sharing initiatives expand, ML will become increasingly vital in driving innovation, enhancing sustainability, and reducing costs in the light alloys industry.
The issue will cover a broad spectrum of machine learning-assisted light alloy design, including but not limited to screening compositional combinations of light alloys and predicting their properties; developing machine learning algorithms to investigate the complex relationships between the microstructure and macroscopic properties; constructing multi-objective optimization models to consider various performance indicators; study methods for quantifying uncertainty in machine learning models; use machine learning-based data-driven approaches to predict phase diagrams and analyze their stability under different temperature and stress conditions; combine machine learning with multi-scale modeling techniques to model light alloys from atomic to macroscopic scales; apply machine learning to optimize processing parameters.
This Special Issue invites contributions that address the following areas:
· High-throughput Material Screening and Discovery
· Microstructure-Property Relationship Modeling
· Multi-objective Performance Optimization
· Uncertainty Quantification in Material Design
· Data-driven Phase Diagram Prediction and Material Stability Analysis
· Cross-scale Material Modeling and Design
· Machine Learning-assisted Optimization of Light Alloy Processing Technologies
Keywords
High-throughput computing; Multi-objective optimization; Cross-scale material Modeling Data-driven performance prediction; Inverse design
Published Papers
Login
Register
Submit a Paper
Propose a Special lssue