Bond strength prediction of concrete-encased steel structures using hybrid machine learning method

Abstract

The mechanical behavior of concrete-encased steel (CES) structures is crucially linked to the bond strength between steel section and concrete which should be predicted with ease and accuracy. In this paper, an efficient and robust soft computing strategy was proposed, where the artificial neural networks (ANN) are hybridized with genetic algorithm (GA) or particle swarm optimization (PSO) to predict the bond strength in CES structures. Seven features were extracted from push-out tests in the available literature, and a database containing 191 records was established for model training and testing. Then, the performance of three machine learning models ANN, GA-ANN, and PSO-ANN was thoroughly compared. The results showed that the developed GA-ANN and PSO-ANN models exhibit superior performance to both conventional ANN model and existing empirical equations. The PSO-ANN outperforms the GA-ANN in terms of convergence speed and prediction error owing to its unique information-sharing mechanism. Further, sensitivity analysis of main contributing factors was conducted on PSO-ANN model. It is quantitatively confirmed that the relative concrete cover has the most significant effect on bond strength while the influence of relative bonded length is relatively minimal. Eventually, an explicit formula was directly derived from the PSO-ANN model and a practical tool with a graphical user interface was created for design practice. The outcome of this study could be employed to intelligently estimate the bond strength in CES without costly and time-consuming tests.