Abstract
Standard development process involves several CAD and CAE analysis in order to determine parameter values satisfying technical product specifications. In case of nonlinear static behaviour of the system, the computational time may quickly increase depending on model complexity, load cases and cycles of analysis. A new technique, based on Neural Networks, is introduced to analyse virtual models. As example, the methodology is applied to adjust design parameters of an exhaust system, showing same accuracy range than FEA, but strongly reducing the simulation time.
Keywords: Exhaust system, Neural network, Genetic algorithm, Nonlinear static system