A statistical method for the identification of nonlinear random vibration systems is presented. The first step in the identification process is to obtain a discrete time version of a random vibration model using a local linearization approach. It is shown that the discrete time version thus obtained may be utilized in the identification of original random vibration model. The method is applied to some real ship engineering data.
Equivalent linearization method using Gaussian mixture (GM-ELM) for nonlinear random vibration analysis
