A NOVEL HYBRIDIZATION OF SEAGULL ALGORITHM AND COMBINED COMPROMISE SOLUTION (SOA–CoCoSo) IN DRILLING INVESTIGATION OF CARBON NANO-ONION-MODIFIED POLYMER COMPOSITES FOR STRUCTURAL APPLICATION

Abstract

Carbon nanomaterial (CNM)-reinforced polymer composite is broadly employed in emergent industrial needs due to advanced mechanical properties. In this research paper, a comparatively innovative integrated approach (SOA–CoCoSo) is proposed by using Principal Component Analysis (PCA)-based Combined Compromise Solution (CoCoSo) and Seagull Optimization Algorithm (SOA). This modified module is used in the drilling operation of zero-dimensional (0D) carbon nano-onion (CNO)-reinforced polymer (epoxy) composite. The desired machining performances, namely, surface roughness ([Formula: see text]), thrust force (Th), and Torque (Tr), are optimized to improve the quality and productivity concerns. The control of process constraints, i.e. the wt.% of nanomaterial ([Formula: see text]), spindle speed ([Formula: see text]), and feed rate ([Formula: see text]), was performed to achieve the desired objective value. The drilling experimentation was executed at three different levels of Box–Behnken Design (BBD). The objective function of PCA–CoCoSo was fed as input into the SOA. To acquire a better work efficiency, higher spindle speed, lower feed rate, and incremental wt.% of nanomaterial reinforcement are considered. The results demonstrated that the wt.% of CNO reinforcement and feed rate are the most influential factors for optimal machining performance results. The optimal constraints condition from the SOA–CoCoSo hybrid module is found at a combination of lower level of CNO wt.% (0.5[Formula: see text]wt.%) and feed rate (61[Formula: see text]mm/min) and high value of spindle speed (1500[Formula: see text]rpm). Also, the hybrid SOA–CoCoSo module shows a lesser amount of error percentage than the usual PCA–CoCoSo. The experiments were performed to confirm the feasibility of the suggested hybrid module for optimizing the varying machining parameters. The results indicated that the hybrid method is more efficient than the conventional method.