Four groups of non-traditional and natural pozzolan (NNP) based (aluminosilicate-based) materials, calcined clays, ground bottom ashes, volcanic ashes, and fluidized bed combustion ashes, were alkali activated using a hybrid solution of sodium silicate and sodium hydroxide. The microhardness and reduced modulus of the phases present in eleven alkali-activated pastes were measured using nanoindentation. At least 800 data points were collected from 28-day old ambiently cured paste samples. Unsupervised machine learning techniques i.e., k-means clustering and Gaussian mixture modeling (GMM) were used for the classification of the micromechanical properties supplemented by scanning electron microscopy (SEM) and energy dispersive X-ray spectroscopy (EDS). The clustering of micromechanical and EDS data revealed five distinct phases in these hardened pastes. The alkali-activated gels identified had reduced modulus values ranging from 12 to 34 GPa. The remnant phases were partly reacted grains and unreacted minerals exhibiting reduced modulus values ranging from 35 to 105 GPa. Micromechanical property contour plots and SEM image pixel count plots were used to validate the phase assemblage. Additionally, the identification capabilities and advantages of the method are assessed by direct comparison with experimental results for different alkali-activated gels.
Read full abstract