Configuration feature extraction and mechanical properties prediction of particle reinforced metal matrix composites

Abstract

Improving the strength-toughness matching properties has become a key issue in metal matrix composites, which can be achieved by some specific designs of composite configurations (i.e. spatial distribution of reinforced particles). To better interpret the composite configuration effect on mechanical properties, it is necessary to develop comprehensive feature descriptors for composite configurations. In this work, topological data analysis and particle clustering parameter are applied to extract feature descriptors for composite configurations of SiCp/Al composites, which are effective to distinguish different types of composite configurations. In addition, based on the dataset constructed by finite element analysis, machine learning algorithms are applied to predict the composite configurations-mechanical properties of SiCp/Al composites. Then, particle swarm optimization is used to search the composite configurations with extreme mechanical properties predicted by machine learning model. The results of this work indicate that the composite configurations with larger particle clustering parameter and persistent entropy will yield better strength-toughness matching.