STRUCTURAL DAMAGE IDENTIFICATION METHOD BASED ON ENSEMBLE EMPIRICAL MODE DECOMPOSITION AND CONVOLUTION NEURAL NETWORK

摘要

A structural damage identification method based on ensemble empirical mode decomposition and a convolution neural network. The method comprises: selecting an acceleration response signal of a structure as an analysis object; using ensemble empirical mode decomposition technology to decompose the acceleration response signal, so as to obtain a series of intrinsic mode functions (IMFs); selecting an intrinsic mode function (IMF) containing a structural natural vibration frequency for reconstruction; and then using a one-dimensional convolution neural network to perform feature extraction and damage classification on a reconstructed signal, thereby obtaining an identification result of a structural damage position.