Search

Compressive strength is considered to be one of the most important mechanical properties of high‐strength concrete (HSC). In this study, three machine learning models, ELM, PSO‐ANN, and GS‐SVR were employed to predict the compressive strength of HSC using 681 data records. The five ingredients and the compressive strength of HSC were regarded as input variable features and output target, respectively. Results indicated that the GS‐SVR model showed the best performance in forecasting with the R of 0.992, MAPE of 0.016, RMSE of 1.241, MAE of 0.842, and RRMSE of 0.024, which could be an alternative candidate for strength prediction. Additionally, a sensitivity analysis was performed within the GS‐SVR model to achieve an in‐depth examination of the effect of each single input variable on the compressive strength. The sensitivity of input variables demonstrated that the water is the most sensitive parameter to the compressive strength of HSC, while the superplasticizer is less sensitive. The research of this paper can provide reference and guidance for concrete design and construction. [ABSTRACT FROM AUTHOR]

Long‐term creep compliance is one of the most important mechanical properties for evaluating the long‐term behavior of concrete structures. This paper aims to optimize machine‐learning models to predict this viscoelastic property. The most relevant dataset available in the literature is considered, cleaned, and preprocessed to optimize the outcome. The advanced XGBoost model, which is to be the most effective shallow machine‐learning model for modeling tabular datasets, is employed in this study to maximize model accuracy. Short‐term creep compliances of a given sample at typical ages are used as input features to model the long‐term creep compliance of concrete. This approach outperforms standard machine‐learning approaches that do not include short‐term creep as an input feature. Indeed, the short‐term behavior of concrete strongly influents its long‐term one. The optimized machine model presented herein is accurate and useful for practical applications. It uses input features that are easy to obtain to predict long‐term creep compliance up to several decades, which is difficult and expensive to measure. [ABSTRACT FROM AUTHOR]