Prediction of the sawing quality of Marmarit stones using the capability of artificial neural network

The sawing rate is one of the most significant and effective parameters in extracting building stones via diamond wire sawing. This parameter designates the capability of diamond wire sawing for sawing different stones; in addition, the parameter gives rise to economical considerations for quarry designers. In this study, the existent relations between stone geotechnical parameters and the sawing rate of stones via diamond wire sawing were analyzed using regression and correlation coefficient as well as the collected data from Marmarit stone quarries. Moreover, we estimated the sawing rate of Marmarit using the dimensional stone rock mass rating (DSRMR); upon comparison of the data obtained from DSRMR our pre‐collected data on quarries, we did not gain satisfactory results from DSRMR, hence we used artificial neural network (ANN). The results showed that the percentage of Silica, the coefficient of water absorption, the uniaxial compressive strength (UCS), and abrasive hardness are the proper parameters for creating the ANN. Discontinuities have the least effects possible on diamond wire sawing. Having given the training possibility of the ANN, and its ability to evaluate relations among input parameters, the ANN, which was being trained with Marmarit's traits, was an accurate network for estimating diamond wire sawing in Marmarit quarries, although it could not generalize this network for other stones such as Chini and Crystal. Copyright © 2011 John Wiley & Sons, Ltd.