A Framework of Structural Damage Detection for Civil Structures Using Fast Fourier Transform and Deep Convolutional Neural Networks

In the field of structural health monitoring (SHM), vibration-based damage detection is an important technology to ensure safety civil structures. By taking advantage deep learning, this study introduces a data-driven method that combines convolutional neural networks (DCNN) and fast Fourier transform (FFT). method, vibration data are fed into FFT acquire frequency information reflecting conditions. Then, DCNN utilized automatically extract features from identify To verify effectiveness proposed FFT-DCNN carried out on three-story building structure ASCE benchmark. The experimental result shows achieves high accuracy, compared with classic machine-learning algorithms such as support vector machine (SVM), random forest (RF), K-Nearest Neighbor (KNN), eXtreme Gradient boosting (xgboost).