Application of advanced algorithms for enhancement in machining performance of Inconel 718

摘要

Inconel 718 is the most promising nickel-based alloy finding wide usage in engineering applications because of its good mechanical properties. However, this alloy is difficult to machine and results in poor surface quality after machining. Optimization of parameters is essential for improving machining performance of this costly and hard to cut material. The research discusses estimation of optimum parameters using teaching-learning based optimization (TLBO) and compares them to those obtained by genetic algorithm (GA) in turning of Inconel 718. The parameters cutting speed, feed rate and depth of cut are selected as independent variables. The experiments are designed using central composite design of response surface methodology for the modelling of turning process. Surface roughness, tool flank wear and cutting temperature are selected as response parameters for minimization. The adequacy of modified models developed by response surface methodology are tested and then utilized for formulation of multi-objective optimization function. The function is solved by GA and TLBO. After comparing optimization results, the best algorithm is used for confirmation test. Convergence of TLBO algorithm is much faster as compared to GA even though there is very little difference in the optimum values of parameters.