This article proposes a novel dynamic response reconstruction approach for structural health monitoring using densely connected convolutional networks. Skip connection and dense block techniques are carefully applied in the designed network architecture, which greatly facilitates the information flow, and increases the training efficiency and accuracy of feature extraction and propagation with fewer parameters in the network. Sub-pixel shuffling and dropout techniques are used in the designed network and applied to reduce the computational demand and improve training efficiency. The network is trained in a supervised manner, where the input and output are the measurements of the available channels at response available locations and desired channels at response unavailable locations. The proposed densely connected convolutional networks automatically extract the high-level features of the input data and construct the complicated nonlinear relationship between the responses of available and desired locations. Experimental studies are conducted using the measured acceleration responses from Guangzhou New Television Tower to investigate the effects of the locations of available responses, the numbers of available and unavailable channels, and measurement noise. The results demonstrate that the proposed approach can accurately reconstruct the responses in both time and frequency domains with strong noise immunity. The reconstructed response is further used for modal identification to demonstrate the usability and accuracy of the reconstructed responses. The applicability of the proposed approach for structural health monitoring is further proved by the highly consistent modal parameters identified from the reconstructed and true responses.

This article proposes a deep sparse autoencoder framework for structural damage identification. This framework can be employed to obtain the optimal solutions for some pattern recognition problems with highly nonlinear nature, such as learning a mapping between the vibration characteristics and structural damage. Three main components are defined in the proposed framework, namely, the pre-processing component with a data whitening process, the sparse dimensionality reduction component where the dimensionality of the original input vector is reduced while preserving the required necessary information, and the relationship learning component where the mapping between the compressed dimensional feature and the stiffness reduction parameters of the structure is built. The proposed framework utilizes the sparse autoencoders based deep neural network structure to enhance the capability and performance of the dimensionality reduction and relationship learning components with a pre-training scheme. In the final stage of training, both components are jointly optimized to fine-tune the network towards achieving a better accuracy in structural damage identification. Since structural damages usually occur only at a small number of elements that exhibit stiffness reduction out of the large total number of elements in the entire structure, sparse regularization is adopted in this framework. Numerical studies on a steel frame structure are conducted to investigate the accuracy and robustness of the proposed framework in structural damage identification, taking into consideration the effects of noise in the measurement data and uncertainties in the finite element modelling. Experimental studies on a prestressed concrete bridge in the laboratory are conducted to further validate the performance of using the proposed framework for structural damage identification.