Random vibration analysis with radial basis function neural networks

Abstract Random vibrations occur in many engineering systems including buildings subject to earthquake excitation, vehicles traveling on a rough road and off-shore platform random waves. Analysis of for linear has been well studied. For nonlinear systems, particularly multi-degree-of-freedom however, there are still challenges analyzing the probability distribution transient responses system. Monte Carlo simulation was considered only viable method this task. In paper, We propose construct semi-analytical solutions by using radial basis function neural networks. The activation functions consist normalized Gaussian density functions. Two examples presented show effectiveness proposed solution method. distributions response moments these presented, which have not reported literature before.