Date of Award
Master of Science
Strength of concrete is the major parameter in the design of structures and is represented by the 28-day compressive strength of concrete. Many earlier studies proved that the compressive strength of concrete is not only related to w/c ratio but also rely on proportion of other constituent materials. Application of recently developed new generation admixtures for the production of high performance concrete, has made the concrete strength prediction complex and highly nonlinear challenging the research engineers and data scientists. Development of early accurate prediction model for concrete strength provides the mix designer a tentative idea to proportionate the mix ingredients accordingly reducing the number of trial mixes ultimately saving a lot of cost and time associated with it. In this study, we have proposed SVM regression tool to create the model for the prediction of concrete strength. Support vector machine (SVM) is a supervised machine learning technique based on statistical learning theory developed by Vapnik in 1995. SVM employs a kernel function to transform the data into high dimensional feature space and linear modeling is performed in the feature space to overcome the complexity related to highly nonlinear datasets. A dataset containing 425 observations of high performance concrete mix design with nine attribute variables from University of California, Irvine Repository are considered for this study. 395 datasets were used to train the model and 30 samples were taken as a test set by random sub sampling to test the model. Five-fold cross-validation technique was used to select the parameters of SVM. The metaparameter values ε = 0.001, C = 29.47 and γ = 10 are selected for creating the model. The model performance measures correlation coefficient (R), root mean square error (RMSE) values and residual plots suggest that the proposed SVM model is competent enough to predict the strength of concrete. The performance measures of proposed SVM model was compared with RVM model.
This thesis is only available for download to the SIUC community. Current SIUC affiliates may also access this paper off campus by searching Dissertations & Theses @ Southern Illinois University Carbondale from ProQuest. Others should contact the interlibrary loan department of your local library or contact ProQuest's Dissertation Express service.