Predicting elastic modulus degradation of alkali silica reaction affected concrete using soft computing techniques: A comparative study

Alkali silica reaction (ASR) is a harmful distress mechanism which results in expansion and reduction of mechanical properties concrete. The latter may cause loss serviceability load carrying capacity affected concrete structures. Influences ASR on are known to be complex nature, for the traditional empirical curve-fitting approaches insufficient provide adequate models capture such complexity. Recent advancement soft computing (SC) offers new tool tackling complexity Most previous experimental studies agreed that as result ASR, elastic modulus suffers significant compared with other compressive tensile strength In this study, an investigation has been conducted, utilising different SC quantify ASR-induced degradation unrestrained Five techniques, namely support vector machine (SVM), artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), M5P model genetic expression programming (GEP), investigated comparatively research. models, basis developed tested using comprehensive dataset collected from existing publications. order demonstrate superiorities proposed several same dataset. comparative show outperform wide range evaluation indices, indicates promising applications approach.