▎ 摘 要
NOVELTY - The method involves fixing five to seven hidden layers with each hidden layer having minimum 20 nodes and maximum 30 nodes for quick convergence of DNN with expected generalization. The proper filter function is utilized in predicting the material properties with good accuracy. The strain hardening and deformation effects in GNPs reinforced AMCs preforms are evaluated as given minimum and maximum value to design the mechanical parts of Automotive and aircraft industries. USE - Effective analysis method for impact of graphene nano tubes (GNPs) reinforced extruded and non-extruded aluminum matrix composites (AMCs) in automotive and aircraft industries using computational intelligence. ADVANTAGE - The prediction accuracy is improved. The analysis of various parameters related to the GNPs reinforced extruded and non-extruded AMCs are improved. The generalization of learning models in predicting the deformations and strain hardening properties of GNPs is improved. DESCRIPTION OF DRAWING(S) - The drawing shows a schematic view illustrating the effective analysis method for impact of graphene nano tubes reinforced extruded and non-extruded aluminum matrix composites.