Structural health monitoring by using a sparse coding-based deep learning algorithm with wireless sensor networks

Structural health monitoring has received remarkable attention due to the arising structural safety problems. Most of these structural health problems are accumulative damages such as slight changes in structural deformations which are very hard to be detected. In addition, the complexity of real structure and environmental noises make structural health monitoring more difficult. Existing methods largely use various types of sensors to collect useful parameters and then train a machine learning model to diagnose damage level and location, in which a large amount of training data are needed for the model training, while the labeled data are rare in the real world. To overcome this problem, sparse coding is employed in this paper to achieve structural health monitoring of a bridge equipped with a wireless sensor network, so that a large amount of unlabeled examples can be used to train a feature extractor based on the sparse coding algorithm. Features learned from sparse coding are then used to train a neural network classifier to distinguish different statuses of the bridge. Experimental results show the sparse coding-based deep learning algorithm achieves higher accuracy for structural health monitoring under the same level of environmental noises, compared with some existing methods.