Search

In this study machine learning models are used that forecast the compressive strength of self-compacting concrete (SCC) depending on percentage replacement of cement by supplementary cementitious material. In order to predict the mechanical property of SCC, a hybrid artificial neural network (ANN) along with metaheuristic optimization techniques and two traditional models were employed which comprised of 300 datasets. Several input factors are employed in the modelling process, including cement, the water-binder ratio, coarse aggregate, fine aggregate, fly ash (FA) and the superplasticizer. ANN hybridised with RUNge Kutta optimizer (RUN) was chosen as one of the top predictive models based on coefficient of determination ((R2 = 0.933 (in training) and R2 = 0.9203 (in testing))) findings and model validation. According to the rank analysis, the ANN-RUN surpassed other models with a score of 128. Permutation feature importance, statistical analysis, and comparisons amongst regression models are used to determine the models' efficacy. The best input parameters were selected based on person correlation and density plot. Also, the use of Taylor diagrams and accuracy matrices was also examined for the visual comprehension of the data which has shown similar results as discussed above. The results show that the suggested machine learning models attained consistent accuracy and can be used as a robust technique to predict the compressive strength of SCC.

The structural failures induced by alkali-contamination of soils are well established by earlier researchers. In the present study, the effect of alkali concentration (2 M and 4 M) and duration of curing on the unconfined compressive strength (UCS) of two types of soils (Kaolin and BC soil) were evaluated. Further, the effect of fly ash (FA) addition (10%, 15%, and 20%) on the UCS of alkali-contaminated soils was also determined. The results revealed that alkali contamination resulted in reducing UCS (by 36% and 46%), observed for kaolin and BC soil, respectively. The addition of FA has resulted in a linear increase in UCS of both soils. The optimum content was noted at 15%, attributed to the pozzolanic reaction initiated by alkali and subsequent gain of UCS with the formation of calcium (with FA addition) based hydration compounds. In addition, three attributes, i.e., FA content, curing period, and alkali concentration, have been used to develop GEP tree-based models to furnish simple prediction equations for calculating the UCS of Kaolin and BC soils. The accuracy of the developed models were initially validated using various statistical checks such as R, MAE, RMSE and RSE. For the 2nd level validation, parametric and sensitivity analyses were carried out for both soils, which yielded a comparable variation and contribution of each input conforming to the literature.