Application of artificial intelligence and numerical method to improve the natural oscillation of the sport mountain bike tires

Abstract

This research gravitates toward the acceleration in the computation process required for analyzing the temporal stability of the graphene-platelets enriched nanocomposite sport bike tire (GPLEN-SBT) through the perspective of soft-computation-based methods, for the first time. In this regard, a genetic algorithm empowered multi-layered neural network (GAEMLNN) with optimum topology is trained by stability information of the GPLEN-SBT determined by applying differential quadrature approach (DQA) to the governing equations established in the platform of the extended higher-order shear deformation theory. The SBT is modeled as a nanocomposite toroidal shell of revolution enriched by nanosized particles of graphene across its transversal direction. Effects of the number of neurons in addition to the size of the agents’ population are examined to find the optimum topology required for constructing the most accurate GAEMLNN for the least computational cost. The efficiency of the solution is verified through comparison with the published studies. As an empirical finding, it is revealed that the net difference between the outer pressure and inner pressure of the tire plays the most considerable role in the temporal stability of the GPLEN-SBT.