Soft computing models for assessing bond performance of reinforcing bars in concrete at high temperatures

Abstract The bond between steel and concrete in reinforced concrete structures is a multifaceted and intricate phenomenon that plays a vital role in the design and overall performance of such structures. It refers to the adhesion and mechanical interlock between the steel reinforcement bars and the surrounding concrete matrix. Under elevated temperatures, the bond is more complex under higher temperatures, yet having an accurate estimate is an important factor in design. Therefore, this paper focuses on using data-driven models to explore the performance of the concrete-steel bond under high temperatures using a Gene Expression Programming (GEP) soft computing model. The GEP models are developed to simulate the bond performance in order to understand the effect of high temperatures on the concrete-steel bond. The results were compared to the multi-objective evolutionary polynomial regression analysis (MOGA-EPR) models for different input variables. The new model would help the designers with strength predictions of the bond in fire. The dataset used for the model was obtained from experiments conducted in a laboratory setting that gathered a 316-point database to investigate concrete bond strength at a range of temperatures and with different fibre contents. This study also investigates the impact of the different variables on the equation using sensitivity analysis. The results show that the GEP models are able to predict bond performance with different input variables accurately. This study provides a useful tool for engineers to better understand the concrete-steel bond behaviour under high temperatures and predict concrete-steel bond performance under high temperatures.