Journal
MATERIALS SCIENCE AND ENGINEERING A-STRUCTURAL MATERIALS PROPERTIES MICROSTRUCTURE AND PROCESSING
Volume 658, Issue -, Pages 135-149Publisher
ELSEVIER SCIENCE SA
DOI: 10.1016/j.msea.2016.01.114
Keywords
Metal matrix composite; B4C; Artificial neural network; Thin plate spline
Ask authors/readers for more resources
This paper investigates the manufacturing of aluminium boron carbide composites using the stir casting method. Mechanical and physical properties tests to obtain hardness, ultimate tensile strength (UTS) and density are performed after solidification of specimens. The results show that hardness and tensile strength of aluminium based composite are higher than monolithic metal. Increasing the volume fraction of B4C, enhances the tensile strength and hardness of the composite; however over-loading of B4C caused particle agglomeration, rejection from molten metal and migration to slag. This phenomenon decreases the tensile strength and hardness of the aluminium based composite samples cast at 800 degrees C. For Al-15 vol% B4C samples, the ultimate tensile strength and Vickers hardness of the samples that were cast at 1000 degrees C, are the highest among all composites. To predict the mechanical properties of aluminium matrix composites, two key prediction modelling methods including Neural Network learned by Levenberg-Marquardt Algorithm (NN-LMA) and Thin Plate Spline (TPS) models are constructed based on experimental data. Although the results revealed that both mathematical models of mechanical properties of Al-B4C are reliable with a high level of accuracy, the TPS models predict the hardness and tensile strength values with less error compared to NN-LMA models. (C) 2016 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available