سجاد نصیری خلیل آباد

Regarding to extraordinary significance and application of carbon nanotubes in different industries, producing methods and effective parameters could alternate the diverse carbon nanotubes properties. In this study for the first time, the influential parameters (with economic and industry concept) manipulating the properties of multi-wall carbon nanotubes are investigated by neural network grown by thermal chemical vapor deposition. The six growth parameters which were catalyst thickness, pressure of acetylene gas, temperature and time of pre-treatment and growth were used as input data for the determination of the CNT’s diameter and length. Experimental evaluation showed near coalescence relation between simulation data and operating outcomes. The error level for diameter and length was 5.5% and 7.8%, respectively. Measuring of field emission property demonstrated ideal current density at 5-8 applied voltage. Consequently, using of the network model for determining of diameter and length of carbon nanotubes could decrease the test repetitions in an appropriate matter.

In this study a feed forward back propagation artificial neural network (ANN) model was established to predict Vickers microhardness in aluminum-alumina nanocomposites which have been synthesized by mechanical alloying and hot pressing. Volume percent of reinforcement، size of nanoparticles، force in microhardness test; and mechanical alloying parameters، such as time، ball to powder ratio (BPR) and speed of ball mill were used as the inputs and Vickers microhardness as the output of the model. Effective parameters in training such as learning rate، hidden layers and number of neurons، were determined by trail and error due to amount and percentage of errors. Regression analysis in train، validation and test stages; and mean squared error were used to verify the performance of neural network. Average error of predicted results was 2. 67% or 2. 25 Vickers. Also mean squared error for validation data was 7. 76. As can be expected، ANN methods reduce the expenses of experimental investigations، by predicting the optimum parameters.