TY - JOUR AU - De La Salle University, AU - Andres Winston C. Oreta, PY - 2021/02/28 Y2 - 2024/03/29 TI - BOND STRENGTH PREDICTION MODEL OF CORRODED REINFORCEMENT IN CONCRETE USING NEURAL NETWORK JF - GEOMATE Journal JA - INTERNATIONAL JOURNAL OF GEOMATE VL - 16 IS - 54 SE - Articles DO - UR - https://geomatejournal.com/geomate/article/view/2627 SP - 55-61 AB - <p>The expansion of corrosion products in the steel-concrete interface offers radial tensile stress <br>resulting in the development of cracks in reinforced concrete structures. This corrosion-induced crack promotes <br>bond reduction involving intricate non-linear interactions. To deeply understand the underlying mechanisms in the <br>bond strength of corroded rebars in concrete, a novel bond prediction model using artificial neural network (ANN) <br>was developed. Accelerated corrosion was performed to 108 cube samples using 500 µA/cm2 current density. Steel <br>bond strength after 35 and 70 days impressed corrosion exposure of concrete cube samples was measured using a <br>single pull out test. The compressive strength, tensile strength, rebar diameter, embedment length, concrete cover, <br>ultrasonic pulse velocity (UPV), crack severity, and corrosion level were the predictors in the ANN bond model. <br>Among all the bond strength models considered in this study, the proposed neural network model provided the <br>most desirable bond estimates in good agreement with experimental results. The ANN model further showed <br>superior prediction performance against the derived regression model.</p> ER -