Kinetic model of a newly-isolated Lysinibacillus sp. strain YL and elastic properties of its biogenic CaCO3 towards biocement application

Investigating the effects of superplasticizer and recycled plastics on the compressive strength of cementitious composites using neural networks

The potential application of neural network (NN) models to estimate the compressive strength (C S ) of cementitious composites under a variety of experimental settings and cement mixes was investigated. The data were extensively collected from previous literature, and the bootstrap resampling tests were applied to estimate the statistics of the parameter correlations. We find that the NN model that involves the coarse and fine natural aggregates (C A and F A ), superplasticizer (S P ) and recycled plastics (R P ) as the features can accurately predict the C S (R2 ∼ 0.9), without the need to specify the type of S P and the structure of R P in advance. The developed NN model holds promise for revealing the global dependency of C S on these parameters. It suggested that increasing 100 kg/m3 of C A could increase C S by ∼4 MPa, but the usage of C A more than 700 kg/m3 could negatively affect C S . How the C S varying with F A is apparently nonlinear. Within the optimum limit, adding 1 kg/m3 of S P could enhance the C S by ∼2 MPa. Contrarily, additional 1 kg/m3 of R P results in a decrease of ∼0.2 MPa of C S . The mixture-type independent models developed here would broaden our understanding of the global influential-sensitivity among these variables and help save cost and time in the industrial applications.