Optimization of wire EDM parameters using teaching learning based algorithm during machining of maraging steel 300. (2018)

• Record Type: Journal Article
• Authors: Sen, Ruma; Choudhuri, Bikash; Barma, John Deb; Chakraborti, Prasun
• Is Part Of: Materials today. Volume 5:Number 2(2018)Part 2
• Page Start: 7541
• Page End: 7551
• Publication Date: 2018
• Subjects: WEDM -- Maraging steel 300 -- BPNN -- Fuzzy -- TLBO; Materials science -- Congresses -- Periodicals; 620.1
• DOI: 10.1016/j.matpr.2017.11.426
• Languages: English
• ISSNs: 2214-7853

Abstract

Abstract: Maraging steel possesses high strength and resistance to oxidation and corrosion. Machining of Maraging steel has an inherent problem with the conventional manufacturing process. The wire electrical discharge machining has been used as an alternative of conventional methods. It is controlled by various machining variables. It is essential to arrange them in a judicious manner. Neural network models are established to predict cutting speed, surface roughness and wire consumption for effective modeling. Fuzzy logic is incorporated here for converting the multi objective problem into a single objective one. Further parametric optimizations have been done based on both teaching learning based optimization and genetic algorithm technique. Confirmation tests verified that teaching learning based optimization is the more appropriate method.