Concrete performance prediction using boosting smooth transition regression trees (BooST)

摘要

The compressive strength of concrete structure is always inuenced by the composition of varied materials, castingprocess, and curing period, etc. Among these variables, an optimal mix of different materials will achieve betterstructural compressive strength. Thus, understanding the non-linearity of concrete and its variables is paramountfor improving and predicting the performance of concrete structures. Due to the expensive and time-consuminglaboratory analysis, the use of post-processing and data analysis provides an excellent opportunity to exploreand predict optimal models for concrete compressive strength performance. However, given the inadequacy oftraditional regression models and other analytic techniques in modeling non-linear regression problems, thereis still a need to achieve a better predictive model with minimal errors as well as the capability to estimatepartial effects of characteristics on response variables. In this study, a predictive analysis was carried out toinvestigate the performance of concrete compressive strength at 28 days with a new machine learning modelcalled boosting smooth transition regression trees (BooST). It is observed from the experimental results thatthe BooST model provides a better prediction accuracy in comparison with the state-of-the-art techniques usedfor concrete compressive strength prediction. Thus, there is a great potential to apply the BooST model forpredicting the compressive strength of concrete in practice.