Experimental Investigation and Multi-Response Optimization of Turning Parameters for AISI 1050 Steel on CNC Machine Using Taguchi-Based GRA and GA

Abstract

The Machining Industry Is Challenged By Achieving The Required Surface Finish, Longer Tool Life, And Good Productivity. Major Challenges Of Turning Of Aisi 1050 Steel Are To Get Good Surface Finish, Less Tool Wear And Good Material Removal Rate Due To Improper Selection Of Cutting Parameters And Optimization Techniques. To Address Those Problems, The Current Research Utilized A Multi-Objective Optimization Method In Identifying Optimal Parameter Settings. Regression Equations Were Formed To Predict The Influence Of Cutting Parameters On Output Response Parameters, I.E., Material Removal Rate, Tool Flank Wear, And Roughness On The Work piece Surface. To Validate The Developed Model As A True Representation Of Relationships Among Variables, Analysis Of Variance (Anova) Test Was Conducted. Experiments Were Conducted On A Cnc Machine Using Aisi 1050 Steel. The Results Indicated That Feed Rate Contributes 91.83% Variation In Surface Roughness And Thus Ranked As The Most Influential Parameter Among Those Parameters. The Minimum Recorded 0.67??M Value For Surface Roughness Occurred At Maximum Cutting Speed, Lowest Feed Rate, And Maximum Depth Of Cut While Maximum 2??M For Surface Roughness Occurred At Moderate Cutting Speed, Maximum Feed Rate, And Minimum Depth Of Cut. Maximum Influence On Material Removal Rate Was Due To Depth Of Cut And Accounted For 84.68%, And Followed By Feed Rate And Cutting Speed At 10.16% And 3.51%, Respectively. Least Tool Wears Occurred At Lower Cutting Settings And Maximum Tool Wear At Higher Cutting Settings. Maximum Flank Tool Wear Of 154 ??M Occurred At Maximum Cutting Speed, Maximum Feed Rate, And An Intermediate Level Depth. Minimum Flank Tool Wear Of 54.85 ??M Was Achieved At Minimum Cutting Parameters. An Optimal Solution To A Complex Problem With Numerous Objectives Was Conducted Using Gra And Genetic Algorithm Techniques In Matlab R2022b. Based On That, Optimal Pareto Values Were Generated Using Genetic Algorithm.