Hybrid taguchi glowworm optimization algorithm for optimization of cutting parameters

Abstract

Quality of machining products is generally associated with the surface roughness (Ra) and is one of the important aspects that could affect machining performance. In traditional and modern machining operations, optimization of reasonable cutting parameters is a requirement for providing better quality products. This research employs and enhanced the Glowworm Swarm Optimization (GSO) algorithm to optimize cutting parameters to obtain minimum Ra values. GSO is a new method of swarm intelligent based algorithm to search for global extremes of multi-modal optimization problems. The algorithm is employed in this study to approximate optimum cutting parameters to obtain improved values of Ra in end milling and abrasive water jet (AWJ) processes. The cutting parameters considered for end milling are cutting speed (v), feed rate (f) and depth of cut (d) whereas traverse speed (V), water jet pressure (P), standoff distance (h), abrasive grit size (D) and abrasive flow rate (m) are considered for AWJ. Following that, to improve further the Ra values, this study proposed hybridization of GSO and Taguchi method known as HTGSO. HTGSO simulation results were compared to experimental and GSO results. In AWJ machining process, HTGSO reduced the Ra value by 13% and 25% compared to those obtain from both experimental and GSO. Whilst, HTGSO is found has outperformed both experimental and GSO in end milling by decreasing the Ra value up to 25% and 40% respectively. Therefore, HTGSO produced the best Ra with the lowest values. This performance indicates HTGSO significantly improved the Ra during the machining process that lead to higher quality of machining product