Multi-Response Optimization of Burnishing Variables for Minimizing Environmental Impacts

Abstract

The purpose of this investigation is to optimize minimum quantity lubrication (MQL) variables, including the nozzle diameter (D), inclined angle (A), air pressure (P), oil quantity (F), and spraying distance (S) for decreasing the energy consumption in the burnishing time (EB) and particulate matter index (PI) of the interior burnishing process. The optimal adaptive neuro-based-fuzzy inference system (ANFIS) models of the performance measures were proposed in terms of the MQL variables with the aid of the Taguchi method. The non-dominated sorting genetic algorithm based on the grid partitioning (NSGA-G) and TOPSI were employed to produce feasible solutions and determine the best optimal point. The obtained results indicated that the optimal values of the D, A, P, F, and S are 1.0 mm, 35 deg., 3 Bar, 70 ml/h, and 10 mm, respectively, while the EB and PI are decreased by 8.0% and 15.7% at the optimal solution. The optimal ANFIS models were trustworthy and ensure accurate predictions. The optimization technique comprising the ANFIS, NSGA-G, and TOPSIS could be extensively utilized to determine the optimal outcomes instead of the trial-error and/or human experience. The outcomes could help to decrease environmental impacts in the practical burnishing process.

Keywords

• ANFIS
• burnishing process
• energy savings
• genetic algorithm
• particulate matter index