Optimization of mechanical properties of PP/EPDM/ clay nanocomposite fabricated by friction stir processing with response surface methodology and neural networks.

In this article, effects of friction stir processing parameters such as tool rotational speed, traverse speed, shoulder temperature, and number of passes on tensile modulus and impact strength of polypropylene/ethylene-propylene diene monomer/clay nanocomposite has been investigated. The Box-Behnken design with four factors at three levels was used for design of experiments. The response surface methodology was employed to develop models capable of predicting the effect of input variable on responses. A multi-layer artificial neural network with back propagation algorithm and 4 - 8 - 10 - 2 topology was also selected for modeling. A set of data on friction stir parameters and experimental results of the mechanical properties were used to train and test the artificial neural network. POLYM. COMPOS., 38:E421-E432, 2017. © 2016 Society of Plastics Engineers [ABSTRACT FROM AUTHOR]