Optimizing of Carbon Nanotubes Growth Parameters on Substrate by Neural Network Utilizing in Fields Emission Display Synthesized with Thermal Chemical Vapor Deposition

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.