As the cutting stone is a wear process, performing this process with diamond pieces' aid can be considered the wear of stone particles bypassing diamond grains on its surface. To better understand this process as well as the conditions governing the cutting diamond grain, it is necessary to be familiar with the cutting mechanism along with affecting parameters. In this case, forecasting the quantity of bead consumption is crucial for calculating manufacturing costs and mapping out the locations of the construction stone mines. In order to calculate the consumption of diamond cutting wire beads, this article used data collected from carbonate and granite stones. To do so, two methods, namely support vector regression (SVR) and genetic algorithm + Multilayer perceptron (GA-MLP), were chosen using MATLAB software toolboxes to estimate the bead wear. In each of above algorithms, a low-pass smoothing filter called Savitzky-Golay was used on the data. For this purpose, three rock properties, including uniaxial compressive strength (UCS), Schmiazek abrasivity factor (SFa), and Young's modulus (YM), were employed as the model's input. Then, twelve models were constructed, and the bead wear was estimated as well. At last, the accuracy of above models was assessed using the coefficient of determination (\({R}^{2}\)), mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and variance account for (VAF). According to obtained results, it can be concluded that SVR approach and the Savitzky-Golay filter with Polynomial Kernel could better estimate the wear rate of diamond cutting wire bead.
