Shiraz University Iranian Journal of Materials Forming 2383-0042 4 2 2017 10 01 A SVM model to predict the hot deformation flow curves of AZ91 magnesium alloy 15 24 4289 10.22099/ijmf.2017.22296.1062 EN M. Rakhshkhorshid Department of Mechanical Engineering, Birjand University of Technology, POBOX 97175-569, Birjand, Iran N. Mollayi Department of Computer Engineering and Information Technology, Birjand University of Technology, POBOX 97175-569, Birjand, Iran A.R. Maldar No affiliation Journal Article 2016 08 07 Abstract<br /> In this work, a support vector machine (SVM) model was developed to predict the hot deformation flow<br /> curves of AZ91 magnesium alloy. The experimental stress-strain curves, obtained from hot compression<br /> testing at different deformation conditions, were sampled. Consequently, a data base with the input<br /> variables of the deformation temperature, strain rate and strain and the output variable of flow stress was<br /> prepared. To develop the support vector machine (SVM) model, the overall data was divided into two<br /> subsets of training and testing (randomly selected). Root mean square error (RMSE) criterion was used to<br /> evaluate the prediction performance of the developed model. The low RMSE value calculated for the<br /> developed model showed the robustness of it to predict the hot deformation flow curves of tested alloy. Also, the performance of the SVM model was compared with the performance of some previously used constitutive equations. The overall results showed the better performance of the SVM model over them. https://ijmf.shirazu.ac.ir/article_4289_23c532634dfeca200b5f9812c89b638f.pdf