Abstract
This article highlights a hybrid methodology of Grey theory and the Ant Lion Optimizer algorithm (Grey-ALO). The proposed module aggregated the multiple responses such as Cutting force (Fc) and Surface roughness (SRa) into a single objective function. The effect of varying constraints, namely, nano-filler content (CNO Wt.%), cutting speed (S), feed (F) and depth of Cut (D), is examined using Taguchi experimental design. The optimal condition from the Grey-ALO hybrid module are found as W3-S3-F1-D1, i.e., 1.5 wt.% CNO, Spindle Speed at 1500 rpm, Feed at 50 mm/min, and 1 mm of cutting depth. The validation test reveals that the overall assessment values significantly improved from 0.9136 to 0.9156, which indicates the improved prediction performance of ALO with 0.2189% error. The finding confirms that the feed rate and weight% of CNOs are the highly influencing factor for Milling performances. It can be recommended to the manufacturing sector for quality and production control.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have