Combining fuzzy RES with GA for predicting wear performance of circular diamond saw in hard rock cutting process

Predicting the wear performance of circular diamond saw in the process of sawing hard dimensional stone is an important step in reducing production costs in the stone sawing industry. In the present research work, the effective parameters on circular diamond saw wear are defined, and then the weight of each parameter is determined through adopting a fuzzy rock engineering system (Fuzzy RES) based on defining an accurate Gaussian pattern in fuzzy logic with analogous weighting. After this step, genetic algorithm (GA) is used to determine the levels of the four major variables and the amounts of the saw wear (output parameter) in the classification operation based on the fixed, dissimilar, and logarithmic spanning methods. Finally, a mathematical relationship is suggested for evaluation of the accuracy of the proposed models. The main contribution of our method is the novelty of combination of these methods in fuzzy RES. Before this work, all Fuzzy RESs only use simple membership functions and uniform spanning. Using GA for spanning and normal distribution as membership function based upon our latest work is the first work in fuzzy RES. To verify the selected proposed model, rock mechanics tests are conducted on nine hard stone samples, and the diamond saw wear is measured and compared with the proposed model. According to the results obtained, the proposed model exhibits acceptable capabilities in predicting the circular diamond saw wear.