Prediction of interface yield stress and plastic viscosity of fresh concrete using a hybrid machine learning approach

摘要: Abstract The interface yield stress and the plastic viscosity of concrete mixes critically influence their pumpability. This study constructs verifies a data-driven method for predicting these two important parameters. proposed is hybridization Least Squares Support Vector Machine (LSSVM) Particle Swarm Optimization (PSO). LSSVM employed to infer mapping function between mix’s parameters influencing factors. Moreover, in order overcome challenging task fine-tuning model hyper-parameters, PSO algorithm, swarm intelligence based metaheuristic, utilized optimize prediction model. A data set including 142 experimental tests has been collected this construct verify hybrid method. Experimental results supported by Wilcoxon signed-rank test point out that (with coefficients determination = 0.71 0.77 predictions, respectively) can deliver predictive superior those benchmark models. Hence, be promising alternative assist engineers structure construction.