Development of heterogeneous multisensor data fusion system to improve evaluation of concrete structures

Abstract

Multisensor data fusion is an emerging technology applied in various engineering applications. It provides significant advantages over single-source data. The use of multiple types of sensors plays an important role in achieving reasonable accuracy and precision. A novel integrated heterogeneous multisensor data fusion approach in structural health monitoring is proposed. The study concerns to find a simple and affordable monitoring strategy for alkali-aggregate reaction (AAR), which is one of the root causes for structural deterioration in concrete.

A standard method to accelerate AAR expansion is employed on four samples, which are prepared with different levels of alkali concentrations. Different sensor systems are used at surface and internal levels. Acoustic sensor system, electromechanical system, and optical systems are employed to obtain surface level damage. The internal level of damage is obtained by embedded sensors within the structure. Features extracted from heterogeneous sensors are fed to decentralised Kalman filter. The fused global estimates and individual source estimates are fed to artificial neural network (ANN), which characterise and quantify the level of damage. The research is focused on establishing correlation among surface damage level, internal damage level, and the amount of gel concentration in the structure. To emphasise the expected improved accuracy using data fusion, evaluations are done on efficiency and accuracy of single-source data system comparing with the fused heterogeneous data.

Keywords:

• multisensor data fusion
• structural health monitoring
• concrete
• alkali-aggregate reaction
• artificial neural network
• decentralised Kalman filter