Tensile strength of basalt from a neural network

摘要

In this paper, a new neural network (NN) based formula is proposed for the determination of tensile strength of basalt in terms of ultrasonic pulse velocity, dry density and water absorption parameters. The data used in training and testing NN are obtained from an extensive experimental work carried out on 86 samples that were cored from basalt blocks collected from the southeast of Turkey. The NN-based results were compared with the experimental results and the proposed NN-based formula was found to be practical in predicting the tensile strength of basalt.