This article examines the capability of Least Square Support Vector Machine (LSSVM) and Relevance Vector Machine (RVM) for determination of compressive strength (fc) of self compacting concrete. The input variables of LSSVM and RVM are Cement (kg/m3)(C), Fly ash (kg/m3)(F), Water/powder (w/p), Superplasticizer dosage (%)(SP) Sand (kg/m3)(S) and Coarse Aggregate (kg/m3)(CA). The output of LSSVM and RVM is fc. The developed LSSVM and RVM give equations for prediction of fc. A comparative study has been done between the developed LSSVM, RVM and ANN models. Experiments have been conducted to verify the developed RVM and LSSVM. The developed RVM gives variance of the predicted fc. The results confirm that the developed RVM is a robust model for prediction of fc of self compacting concrete.
Risk identification and management are the two most important parts of construction project management. Better risk management can help in determining the future consequences, but identifying possible risk factors has a direct and indirect impact on the risk management process. In this paper, a risk prediction system based on a cross analytical-machine learning model was developed for construction megaprojects. A total of 63 risk factors pertaining to the cost, time, quality, and scope of the megaproject and primary data were collected from industry experts on a five-point Likert scale. The obtained sample was further processed statistically to generate a significantly large set of features to perform K-means clustering based on high-risk factor and allied sub-risk component identification. Descriptive analysis, followed by the synthetic minority over-sampling technique (SMOTE) and the Wilcoxon rank-sum test was performed to retain the most significant features pertaining to cost, time, quality, and scope. Eventually, unlike classical K-means clustering, a genetic-algorithm-based K-means clustering algorithm (GA–K-means) was applied with dual-objective functions to segment high-risk factors and allied sub-risk components. The proposed model identified different high-risk factors and sub-risk factors, which cumulatively can impact overall performance. Thus, identifying these high-risk factors and corresponding sub-risk components can help stakeholders in achieving project success.
The utilization of alternative binders at a higher volume in cement composites is an effective approach toward sustainability by reducing global carbon emissions. This article discusses about replacing cement with High-volume fly ash (HVFA) as binary blend and Ternary Blended Silica fume (TBSF) mortars and enhancing their efficiency by addition of Nanomaterial such as Graphene Oxide (GO). The main drawback in utilizing fly ash for industrial applications is its reduction in early strength due to slower reactivity. GO promotes early strength and capable of controlling the microstructure of cement composites even in high siliceous environment. Results revealed by addition of GO, 21.15%, and 24.5% of strength is enhanced for 35%, and 45% level of fly ash replacements respectively, and 23.5%, 15.4% strength increased for (95%PPC + 5% silica fume), and (90%PPC + 10% silica fume) ternary blended mixes respectively. Microstructural characterization techniques such as SEM, XRD, FTIR, and TGA showed GO promoted strength by enhancing pozzolanic reactions. Findings in this study suggests application of GO in HVFA and TBSF sustainable cement composites to improve the microstructural properties.
28 July 2021 in Innovative Infrastructure Solutions