Review of Bridge Structural Health Monitoring Aided by Big Data and Artificial Intelligence: From Condition Assessment to Damage Detection

Abstract

Structural health monitoring (SHM) techniques have been widely used in long-span bridges. However, due to limitations of computational ability and data analysis methods, the knowledge in massive SHM data is not well interpreted. Big data (BD) and artificial intelligence (AI) techniques are seen as promising ways to address the data interpretation problem. This paper aims to clarify the scope of BD and AI techniques on what and how regarding bridge SHM. The BD and AI techniques are summarized, and the requirements of bridge SHM for new techniques are generalized. Applications of BD and AI techniques in bridge SHM are reviewed, respectively. BD techniques can be divided into two categories, namely computing techniques and data analysis methods. The computing techniques are employed in SHM to build a BD-oriented SHM framework and to address computing problems, while the data analysis methods are introduced under a pipeline of BD analysis, application scenarios of BD techniques in bridge SHM are proposed in each step of this pipeline. The state of the art of deep learning in SHM is introduced to represent AI applications, which are concerned with processing unstructured data for visual inspection and time series for structural damage detection. Finally, the upper limit, challenges, and future trends are discussed. As a review, the paper offers meaningful perspectives and suggestions for employing BD and AI techniques in the field of bridge SHM.