Research on Structural Damage Identification of Truss Structure Based on EMD and Neural Network

Abstract In this paper, a method was proposed for damage detection of truss structures under natural excitation based on the combination of radial-basis function neural network and empirical mode decomposition (EMD). Firstly, EMD method was applied to decomposing the vibration response data of the rod end node into a series of IMFs (Intrinsic Mode Functions). For the structure’s original response data, after using the EMD to decompose it, the damage information and other useful contents will be distributed into various IMFs. Using neural network’s excellent feature of linear mapping, IMFs are put as an input into the neural network, and the output was compared with the ideal output, which reveals the damage status of the structure. In this paper, experimental analysis and numerical simulation were used to detect the damage conditions of single-damage condition and two different rods in the same truss structure. Good recognition results were obtained.