Choi, Jae-Hyuk Na, Wonjin Yu, Woong-Ryeol 2024-02-14T01:30:12Z 2024-02-14T01:30:12Z 2024-02-14 2023-03 0965-0393 https://pubs.kist.re.kr/handle/201004/148617 Significant variations in the tensile strength of unidirectional (UD) fiber-reinforced composites are frequently observed due to randomness in the fiber arrays. Herein, we propose a novel method for predicting tensile strength capable of quantifying uncertainty based on a new recurrence relation for fiber fracture propagation and a determination algorithm for the fracture sequence for random fiber arrays (RFAs). We performed finite element simulations, calculating the stress concentration factor (SCF) for UD composites with various RFAs. Then, we trained an artificial neural network with the obtained SCF data and used it to predict the SCF for composites with an arbitrary RFA. The tensile strength of UD composites was predicted over a range of values, demonstrating that accuracy was superior to conventional prediction methods. English Institute of Physics Publishing Machine learning-assisted modelling of stress concentration factor of unidirectional fiber composites for predicting their tensile strength Article 10.1088/1361-651x/acaaf8 1 Modelling and Simulation in Materials Science and Engineering, v.31, no.2 Modelling and Simulation in Materials Science and Engineering 31 2 N scie scopus 000902351200001 Materials Science, Multidisciplinary Physics, Applied Engineering & Materials Science Mechanics Homogenization ARTIFICIAL NEURAL-NETWORK MULTIPLE LINEAR-REGRESSION COMPRESSIVE STRENGTH COMPUTED-TOMOGRAPHY MECHANICAL-PROPERTIES SIMULATION FAILURE FRACTURE ARRANGEMENT POROSITY unidirectional composite tensile strength machine learning artificial neural network stress concentration factor random fiber array