Predictive modeling of drilling machine performance for jute fiber-reinforced polymer composites using GA, TLBO, and GRA-based RSM approaches

Machining the surface of polymer composites is an inevitable task for components. Hole-making processes like milling or drilling can be conducted to analyze a range of parameters concerning the polymer composite. Specific techniques have revealed that machinability in polymers is challenging due to their high hardness. This research investigated thrust as well as surface roughness measurements on jute fiber-reinforced polymer composites utilising different drill bit diameters, studying parameter interactions via 3-D surface plots. In contrast, optimal process parameters were predicted using the Response Surface Methodology (RSM), Grey Relational Analysis (GRA), Genetic Algorithm (GA), and Teaching learning-based optimization (TLBO) curve. GRA-based RSM was instrumental in crafting optimal fitness regression models for the GA and TLBO of polymer composites reinforced with jute fibers. Both, the RSM and TLBO methods exhibited significant correspondence over experimental results. According to these outcomes, thrust force was often shown to enhance with low spindle speed, high feed rate, and small drill diameter. When spindle speed, feed, and tool diameter are reduced, surface roughness decreases. This study holds practical significance by offering a clear pathway to minimize thrust force and surface roughness during drilling operations, consequently enhancing process quality and efficiency.