In this study, the effects of cutting parameters on surface roughness and tool wear during the turning of A357/SiC metal matrix composite material fabricated by incorporating5% SiC particles into theA357 alloy were systematically investigated. Experimental studies were carried out using a full factorial experimental design approach, taking into account the feed rate, cutting speed and depth of cut parameters. Analysis of Variance (ANOVA) results revealed that feed rate was the most dominant parameter affecting surface roughness, contributing 87.73%, while depth of cut contributed 2.76%. For tool wear, cutting speed was the most influential factor (41.95%), followed by feed rate (34.98%) and depth of cut (14.33%). Based on these statistically significant effects, Genetic Expression Programming (GEP) models were developed to mathematically formulate and predict the relationships between the turning parameters and the machining responses. The developed GEP models exhibited high statistical accuracy, with R 2 values of 0.988 for surface roughness and 0.978 for tool wear during the training phase. Validation experiments further confirmed the robustness of the models, yielding maximum prediction errors of 2.51% for surface roughness and 2.21% for tool wear. These quantitative results demonstrate that the GEP approach provides a robust and objective tool for optimizing the machining of A357/SiC metal matrix composites.
KILICKAP et al. (Wed,) studied this question.