Crack detection in a framed structure using PCA-compressed piezoelectric signatures

In order to overcome the current problems of the transmission and storage of the measured data in the structural health monitoring system, it was necessary to put forward the compression sensing method to the neural network system and electro-mechanical impedance (EMI) technology. The finite element EMI model was first established for a framed structure and the conductance data were accordingly obtained for various crack severities. The compressed data by compression sensing theory were used to depict the structural damages instead of the raw ones, and were further investigated using the principal component analysis (PCA). The obtained principal components (PCs) were then used to be the input parameters of the BP artificial neural network (ANN). Results showed that the transmission bandwidth and storage space of the EMI data were only 16% of the original ones using the compression perception theory. The neural network system could detect the existence of cracks and could further classify the crack severities quantitatively using the principal components of the compressed conductance.