Home FOR AUTHORS Kovove Materialy-Metallic Materials 2012 Metallic Materials Vol. 50 (2012), no. 1, pp.25-31

Journal info

Select Journal







Webshop Cart

Your Cart is currently empty.

Info: Your browser does not accept cookies. To put products into your cart and purchase them you need to enable cookies.

Metallic Materials Vol. 50 (2012), no. 1, pp.25-31

Title: The most accurate ANN learning algorithm for FEM prediction of mechanical performance of alloy A356
Author: M. O. SHABANI, A. MAZAHERY, M. R. RAHIMIPOUR, A. A. TOFIGH, M. RAZAVI

Abstract: In order to discover the most accurate prediction of yield stress, UTS and elongation percentage, the effects of various training algorithms on learning performance of the neural networks were investigated. Different primary and secondary dendrite arm spacings were used as inputs, and yield stress, UTS and elongation percentage were used as outputs in the training and test modules of the neural network. After the preparation of the training set, the neural network was trained using different training algorithms, hidden layers and neuron numbers in hidden layers. The test set was used to check the system accuracy of each training algorithm at the end of learning. The results show that Levenberg–Marquardt learning algorithm gave the best prediction for yield stress, UTS and elongation percentage of A356 alloy.

Keywords: FEM, ANN, training algorithms
Year: 2012, Volume: 50, Issue: 1 Page From: 25, Page To: 31
doi:10.4149/km_2012_1_25


download file



© AEPress s.r.o
Copyright notice: For any permission to reproduce, archive or otherwise use the documents in the ELiS, please contact AEP.