Crack Fault Diagnosis Based on MEP Based Neural Network

Abstract

The Multi Expression Programming (MEP) and Neural Network (NN) is applied to the crack fault diagnosis of structure. The inherent frequency and the position of the crack obtained by ANSYS are used as parameters of the neural network. This approach employs MEP to evolve the architecture and the parameters encoded in the NN. This framework allows input variables selection, over-layer connections for the various nodes involved. It is showed that the proposed method is feasible to diagnose the crack fault of structure.