Modeling and optimization of cutting parameters during machining of ZrO₂ filled MMC

In the era of composites and ceramics, reinforced metal matrix composites have paved its way to many engineering fields due to its superior mechanical and thermal properties. Zirconia (ZrO₂) is one such most researched ceramics, which leads to excellent bond strength, grain refinement, and improved tribological aspects of the composite. To simplify the post mold machining of such new composites, the present work emphasizes on the prediction of cutting force for different composition of ZrO₂ in an Aluminum metal matrix composite reinforced with SiCp and Graphite. The purpose is to streamline the complex analysis of induced cutting force during turning with quantifiable machining parameters for the developed composite. The influence of two machining parameters such as depth of cut and feed rate are analyzed with an increase in ZrO₂%. For the better prediction of the cutting force, the artificial intelligence techniques like adaptive neuro-fuzzy interface system (ANFIS) backed by a heuristic genetic algorithm (GA) is employed. The comparison between the predicted model values with the experiment results is exhibited ±1% error having R-square value 0.9927. The interaction plot and soft computing model stood in equal agreement that with the rise in both depth of cut and feed rate, the cutting force value decreases. Again for an increase in ZrO₂% and feed rate, a definite increase in cutting force is observed. The effect of an increase in ZrO₂% in the composite over the machining parameter is suggested through the main effect plot, which stands in equal agreement with the GA model. (paper)