A Study of Factors Affecting GPR Signal Amplitudes in Reinforced Structures Using Deep Belief Networks

The applications of the deep belief network (DBN) for addressing practical engineering issues have recently emerged all over world thanks to its accuracy and availability data. In this paper, a predictive model using DBN was employed investigate factors that affect ground-penetrating radar (GPR) signals from rebar embedded in concrete structures. Four variables, namely temperature, relative humidity, chloride contamination level, surface corrosion condition were used as inputs investigation. Comprehensive data acquired previously published documents establish proposed model. It shown temperature level variables generated significant effects on GPR amplitude signal rebar. contrast, humidity parameters found yield minimal influence output can be predict four with high accuracy. Specifically, coefficient determination (R2) 0.9634 0.9681 testing dataset entire database, respectively.