作者: Mohammad Hasan Shojaeefard , Mostafa Akbari , Parviz Asadi
DOI: 10.1007/S12541-014-0600-X
关键词: Friction stir welding 、 Structural engineering 、 Artificial neural network 、 Finite element method 、 Traverse 、 Multi-objective optimization 、 Ideal solution 、 Rotational speed 、 Engineering 、 Welding
摘要: In this study the inuence of rotational and traverse speed on friction stir welding AA5083 aluminum alloy has been investigated. For purpose a thermo-mechanically coupled, 3D FEM analysis was used to effect force, peak temperature HAZ width. Then, an Articial Neural Network (ANN) model employed understand correlation between parameters (rotational speed) temperature, width force values in weld zone. Performance ANN found excellent can be predict force. Furthermore, order find optimum speed, multi-objective optimization obtain Pareto front. Finally, Technique for Order Preference by Similarity Ideal Solution (TOPSIS) best compromised solution.