Permeability and porosity of light-weight concrete with plastic waste aggregate: Experimental study and machine learning modelling

Abstract

The plastic waste has huge potential being used as the aggregate of concrete but the premise requires to have a sound understanding about the seepage mechanical properties of the light-weight concrete. In this study, initially, the physical experiment was conducted to measure the permeability and porosity of light-weight concrete with various amount of plastic waste aggregate (PWA) in different confining pressure and pore pressure. Based on the test results, a database was established. On this basis, a unique machine learning method was developed via combining the Logic Development Algorithm (LDA) with the ensemble technique of Adaptive Boosting Algorithm (BA) and Artificial Neural Network (ANN), which is the first attempt to utilize this model for estimating the permeability of PWA cement mortar. The research outcomes indicate, the corrected permeability and porosity of PWA cement mortar rises with the increase of PWA content, and the changing magnitude is more significant in high confining pressure; The corrected permeability and porosity of cement mortar with a higher content of PWA is more sensitive to the variation of confining pressure; The BA-ANN model optimised by LDA outperforms than the conventional machine learning models in terms of predictive accuracy and efficiency when assessing the permeability of PWA cement mortar; The sensitivity analysis by using the novel model reveals that confining pressure, PWA content and porosity have a relatively high impact on the permeability of PWA cement mortar, while the impact of pore pressure is relatively small. The study findings can provide guidance for the permeability and porosity design of relevant PWA concrete engineering facilities.