Convolutional Neural Networks for Structural Damage Identification in Assembled Buildings

This paper investigates the migration learning AlexNet-based algorithm for recognition of assembly building structures and based on an improved algorithm, gives analysis results. The structure AlexNet convolutional neural network is introduced basic principles are analysed. optimal model ceiling damage task was obtained through parameter adjustment, with a test accuracy 96.6%. maximum improvement in about 4%, 82.6% 79.7% beam column infill wall respectively.