Health Monitoring For Composite Structure Based On Computational Mechanics And Neural Network

Firstly, a comprehensive discussion about neural network and its improved algorithm were presented in this paper, and a program of BP neural network was finished. Secondly, two carbon fiber reinforced composite beams were fabricated, and their modal frequencies were measured by an experiment method. Thirdly, delaminations were modeled by pairs of nodes with the same coordinates but different node numbers, while the modal frequencies of these beams with different delamination location and size were computed by an EAS piezoelectric solid element. Moreover, a novel method combining computational mechanics and neural network was demonstrated for composite health monitoring; The first five flexure modal frequencies obtained by FEM were modified by a primary revising approach and were used to train the neural network. Finally, the first five flexure experimental modal frequencies were input to the neural network to predict the demalination location and extent.