Date of Award
Master of Science
Early and accurate prediction of the compressive strength of concrete is important in the construction industry. Modeling the compressive strength of concrete to obtain a balance and equality between prediction accuracy, time and uncertainty of the prediction is a very difficult task due to the highly nonlinear nature of concrete. For structural engineering purposes, the 28- day compressive strength is the most relevant parameter. In this study, an attempt has been made to predict the 28-day compressive strength of concrete using Relevance Vector Machine (RVM). An RVM belongs to the class of sparse kernel classifiers, which are powerful tools in classification and regression. It has a model of identical functional form to the popular and state-of-the-art `Support Vector Machine (SVM)'. The benefits of using RVM include automatic estimation of nuisance parameters, probabilistic prediction and the ability to model complex data with little information. A total of 425 different data of high performance mix designs were collected from the University of California, Irvine repository. The data used to predict the compressive strength consisted of nine components. The RVM model was trained and tested using 395 and 30 data sets respectively. The model's performance was assessed at the end of the training and testing period using four performance measures; coefficient of determination, root-mean-square error, percentage of relevance vectors and residual plots. All the performance measures confirmed the accuracy of the model. The results of the study suggested that RVM is an effective tool for predicting the 28- day compressive strength of concrete from its mix ingredients.
This thesis is only available for download to the SIUC community. Others should
contact the interlibrary loan department of your local library.