Optimization of wire spark erosion machining of Grade 9 titanium alloy (Grade 9) using a hybrid learning algorithm

Manufacturing has grown challenging because of the increased usage of harder materials, such as titanium alloys, in many industries, such as aerospace, automobiles, and marine. Conventional material removal procedures are not suitable for these tough materials due to their increased hardness and slow machinability. Wire Electrical discharge machining (WEDM) is a modern approach for material removal, particularly for harder materials, such as titanium alloys, nickel alloys, hard particle reinforced metal matrix composites, etc. The research design was performed by deeming the independent factors, such as duration of pulse and applied current. The removal rate of material, surface roughness of the machined region, dimensional deviation, and tolerance errors in form/orientation are considered performance metrics. Taguchi’s approach was engaged to assess the process variables, and the importance of the process factors was established using analysis of variance approach. The purpose of this research is to create an AI based decision making tool, which can be utilized to anticipate the various parameters that impact the WEDM material removal process. The discoveries of the present exploration allowing the manufacturers to make better-informed decisions with a developed model’s capability by demonstrating that the model’s predicted values were in close confirmation to the actual values.