Prediction of fracture characteristics of high strength and ultra high strength concrete beams based on relevance vector machine

Abstract

This paper examines the applicability of relevance vector machine-based regression to predict fracture characteristics and failure load ( Pmax) of high strength and ultra high strength concrete beams. Fracture characteristics include fracture energy ( GF), critical stress intensity factor ( KIC) and critical crack tip opening displacement. Characterization of mix and testing of beams of high strength and ultra high strength concrete have been described briefly. The procedure to compute GF , KIC and CTODC has been outlined. Relevance vector machine is a machine learning technique that uses Bayesian inference to obtain parsimonious solutions for regression and classification. The relevance vector machine has an identical functional form to the support vector machine, but provides probabilistic classification and regression. Relevance vector machine is based on a Bayesian formulation of a linear model with an appropriate prior that results in a sparse representation. Four relevance vector machine models have been developed using MATLAB software for training and prediction of Pmax, KIC, GF and CTODC. Relevance vector machine models have been trained with about 70% of the total 87 datasets and tested with about 30% of the total datasets. It is observed that the predicted values from the relevance vector machine models are in good agreement with those of the experimental values.