Mechanical performances and processing-property modeling for Al0.3CoCrFeNiMn high-entropy alloy

Mechanical performances have a strong correlation with processing technology for Al0.3CoCrFeNiMn high-entropy alloy. Thus, the current study adopts solution treatment, cold rolling and annealing to investigate their corresponding microstructure and mechanical properties, and the models of backpropagation artificial neural network are established by using collected data set. The results indicate that twinning induced plasticity contributes to the synergized strength and plasticity, and excellent phase stability is found in both solid solution and cold rolling conditions. The neural network structures of 3-1-1, 3-3-1 and 3-3-1 are built for elongation, yield and tensile strength, respectively, the average accuracy of which is up to 93.4% providing an outstanding agreement between predicted and experimental results. According to coefficients matrix measuring the importance of a parameter, the order of significant factors is reduction rate, annealing temperature and solutionizing temperature. (C) 2022 Published by Elsevier B.V.

Automated summary

The mechanical performances of Al0.3CoCrFeNiMn high-entropy alloy are strongly influenced by processing technology. This study investigates the microstructure and mechanical properties of the alloy after solution treatment, cold rolling, and annealing, and utilizes backpropagation artificial neural network models to predict its properties. The results demonstrate that twinning induced plasticity contributes to the strength and plasticity of the alloy, while excellent phase stability is observed in both solid solution and cold rolling conditions. The neural network models achieve an average accuracy of 93.4% in predicting elongation, yield, and tensile strength, showing a remarkable agreement with experimental results. The importance of parameters is assessed, with reduction rate, annealing temperature, and solutionizing temperature identified as significant factors.