Compressive strength of tungsten mine waste- and metakaolinbased geopolymers

摘要

Neuro-fuzzy approach has been successfully applied to a wide range of civil engineering problems so far. However, this is limited forgeopolymeric specimens. In the present study, compressive strength of different types of geopolymers has been modeled by adaptive neuro-fuzzyinterfacial systems (ANFIS). The model was constructed by 395 experimental data collected from the literature and divided into 80% and 20% fortraining and testing phases, respectively. Curing time, Ca(OH)2 content, NaOH concentration, mold type, aluminosilicate source and H2O/Na2Omolar ratio were independent input parameters in the proposed model. Absolute fraction of variance, absolute percentage error and root meansquare error of 0.94, 11.52 and 14.48, respectively in training phase and 0.92, 15.89 and 23.69, respectively in testing phase of the model wereachieved showing the relatively high accuracy of the proposed ANFIS model. By the obtained results, a comparative study was performed toshow the interaction of some selected factors on the compressive strength of the considered geopolymers. The discussions findings were inaccordance to the experimental studies and those results presented in the literature.