Data driven performance prediction of titanium-based matrix composites DOI Creative Commons
Xiaoling Wu, Yunfeng Zhou, Jinxian Zhang

et al.

Alexandria Engineering Journal, Journal Year: 2023, Volume and Issue: 85, P. 300 - 306

Published: Nov. 23, 2023

Titanium matrix composites (TMCs) offer superior specific mechanical properties compared to monolithic alloys. However, the complex interdependent effects of composition and processing on resulting microstructure make experimental determination optimal TMC formulations challenging. This work explored a materials informatics approach integrating machine learning (ML) modeling with targeted fabrication characterization for accelerated data-driven design TMCs. A dataset 368 data points composition, method various TMCs was compiled from literature. Five ML regression algorithms were implemented predict density, hardness strength composition-processing features. Among models, random forest achieved highest accuracy R2 scores above 0.93 low errors. Fabrication Ti-6Al-4 V/SiC using ML-guided parameters showed excellent agreement between predicted experimentally measured properties. The models outperformed conventional empirical predictions by structure-property linkages data. integrated computational-experimental framework can guide rapid identification property-optimized reducing trial-and-error. Further should focus physics-based feature engineering active learning. demonstrated here shows promise accelerating development high-performance

Language: Английский

Data driven performance prediction of titanium-based matrix composites DOI Creative Commons
Xiaoling Wu, Yunfeng Zhou, Jinxian Zhang

et al.

Alexandria Engineering Journal, Journal Year: 2023, Volume and Issue: 85, P. 300 - 306

Published: Nov. 23, 2023

Titanium matrix composites (TMCs) offer superior specific mechanical properties compared to monolithic alloys. However, the complex interdependent effects of composition and processing on resulting microstructure make experimental determination optimal TMC formulations challenging. This work explored a materials informatics approach integrating machine learning (ML) modeling with targeted fabrication characterization for accelerated data-driven design TMCs. A dataset 368 data points composition, method various TMCs was compiled from literature. Five ML regression algorithms were implemented predict density, hardness strength composition-processing features. Among models, random forest achieved highest accuracy R2 scores above 0.93 low errors. Fabrication Ti-6Al-4 V/SiC using ML-guided parameters showed excellent agreement between predicted experimentally measured properties. The models outperformed conventional empirical predictions by structure-property linkages data. integrated computational-experimental framework can guide rapid identification property-optimized reducing trial-and-error. Further should focus physics-based feature engineering active learning. demonstrated here shows promise accelerating development high-performance

Language: Английский

Citations

0