Prediction of displacement in Reinforced concrete based on artificial neural networks using sensors
Arvindan Sivasuriyan, D. S. Vijayan
Abstract
Although structural health monitoring (SHM) is widely used in civil engineering, researchers are working to enhance its accuracy. In previous laboratory experiments, four types of sensors, namely force resisting sensor (FSR), piezoelectric sensor (PZS), microelectromechanical system (MEMS) accelerometer sensor, and flex sensor (FLS), were employed to predict load-displacement in Reinforced Concrete (RC) beams subject to monotonic two-point loading. Static loading was performed in the laboratory. The results demonstrated that MEMS sensors outperformed the other three sensors. Consequently, only MEMS sensors were used in the ANN model to predict the error percentage. This study compared the static results of previous experiments to those obtained from an Artificial Neural Network (ANN) model that used the beam's position and load as input parameters to predict displacement. The results revealed that the non-linear ANN model produced positive outcomes. Therefore, SHM is likely to utilize MEMS sensors in various civil engineering applications.