Search

Abstract: A numerical study of the crushing of thin-walled circular aluminum tubes has been carried out to investigate their behaviors under axial impact loading. These kinds of tubes are usually used in automobile and train structures to absorb the impact energy. A Multi-Objective Optimization of circular aluminum tubes undergoing axial compressive loading for vehicle crash energy absorption is performed for five crushing parameters using the weighted summation method. To improve the accuracy of the optimization process, artificial neural networks are used to reproduce the behavior of the crushing parameters in crush dynamics conditions. An explicit finite element method (FEM) is used to model and analyzed the behavior. A series of aluminum cylindrical tubes are simulated under axial impact condition for the experimental validation of the numerical solutions. A finite element code, capable of evaluating parameters crush, is prepared of which the outputs are used for training and testing the developed neural networks. In order to find the optimal solution, a genetic algorithm is implemented. With the purpose of illustrating optimum dimensional ratios, numerical results are presented for thin-walled circular aluminum AA6060-T5 and AA6060-T4 tubes. Multi-Objective Optimization of circular aluminum tubes has been performed in the basis of different priorities to create the ability for designer to select the optimum dimension ratio. Also, crush parameters of two aluminum alloys has been compared. [Copyright &y& Elsevier]

• Effect of key parameters on LIDM hematite beneficiation was determined. • Evolving MLPs' architecture was successfully optimized by PSO. • DOE-RSM and PSO-MLP neural network, successfully modelled LIDM separation. • PSO-MLP model out-performed DOE model in predicting product Fe content and SE. • Optimization of the operating parameters led to the product Fe = 60.1% and SE = 36.1% The low intensity dry magnetic beneficiation of hematite was studied in this study, and the effect of field intensity (FI: 800–2000 G), drum speed (DS: 25–75 rpm), separating gate position (SG: 55–83°), and mean particle size (PS: 0.5–1.18 mm) on the products' Fe content and system separation efficiency were determined. A new hybrid particle swarm optimization enhanced multilayer perceptron (PSO-MLP) neural network and design of experiment have been employed to model and predict such a beneficiation result. Based on the CCD-RSM response surfaces, the effectiveness of variables on both evaluation criteria was determined to be DS > FI > SG. The mutual interaction between DS-SG was a common interaction for both responses, while FI-DS interaction was found to be significant only for separation efficiency. Compared to the desired levels of the statistical evaluators, the trained PSO-MLP outperformed the CCD-RSM model in predicting the hematite beneficiation results. Product Fe grade of 60.1% and corresponding SE of 36.1% was achieved for FI = 1200 G, DS = 75 rpm, SG = 83°, and PS = 0.5 mm, concluded from optimizing the parameters. [ABSTRACT FROM AUTHOR]