Multi-Objective Optimization of the Process Parameters in Electric Discharge Machining of 316L Porous Stainless Steel Using Metaheuristic Techniques

Abstract

Electric discharge machining is an essential modern manufacturing process employed to machine porous sintered metals. The sintered 316L porous stainless steel (PSS) components are widely used in diverse engineering domains, as interconnected pores are present. The PSS material has excellent lightweight and damping properties and superior mechanical and metallurgical properties. However, conventional machining techniques are not suitable for porous metals machining. Such techniques tend to block the micro-pores, resulting in a decrease in porous materials’ breathability. Thus, the EDM process is an effective technique for porous metal machining. The input process parameters selected in this study are peak current (Ip), pulse on time (Ton), voltage (V), flushing pressure (fp), and porosity. The response parameters selected are material removal rate (MRR) and tool wear rate (TWR). The present work aims to obtain optimum machining process parameters in the EDM of porous sintered SS316L using two meta-heuristic optimization techniques, i.e., Teaching Learning-Based Optimization (TLBO) and Particle Swarm Optimization (PSO) algorithms, to maximize the MRR and minimize the TWR values. In the case of PSS having a 12.60% porosity value, PSO and TLBO algorithms give same optimum machining parameters. However, for PSS having an 18.85% porosity value, the PSO algorithm improves by about 5.25% in MRR and by 5.63% in TWR over the TLBO. In the case of PSS having a 31.11% porosity value, the PSO algorithm improves about 3.73% in MRR and 6.46% in TWR over the TLBO. The PSO algorithm is found to be consistent and to converge more quickly, taking minimal computational time and effort compared to the TLBO algorithm. The present study’s findings contribute valuable information in regulating the EDM performance in machining porous SS316L.

Multi-Objective Optimization of Process Parameters during Micro-Milling of Nickel-Based Alloy Inconel 718 Using Taguchi-Grey Relation Integrated Approach

“…Table 4 analysis reveals that individual output responses optimize at different input variable levels. Due to this particular situation, it is necessary to conduct multi-objective optimization to collectively optimize the manufacturing output [ 53 , 54 , 55 , 56 ].…”

Design of experiments integrated with neural networks for optimization and predictive modelling of electrode wear of novel Ti-6Al-4V-SiCp composites during die sinking electric discharge machining

“…This intensified thermal effect contributes to the gradual increase in wear rate observed. Additionally, higher discharge currents can lead to more frequent and intense electrical discharges between the electrode and the workpiece, causing greater mechanical erosion and material displacement, further contributing to wear [39]. However, unlike Brass and Copper electrodes, Ti-6Al-4V-SiCp electrodes possess unique properties such as the presence of the Ti 3 SiC 2 phase, which enhances their high-temperature resistance.…”

Unified supervised learning and optimization technique for wire electrical discharge machining of various grades of alloys: stochastic algorithm combined neural network approach

“…14 A regression model using desirability function analysis (DFA) was also used to optimize the MRR of Ti64 alloy, and it was observed that the applied current (I) and P off are the main variables affecting MRR during the WEDM process. 15 Stainless steel alloys are also studied by many researchers and different optimization techniques like Taguchi signal-to-noise analysis, 16 GA, 17 DFA, 18 PSO 19 , and others are used for performance optimization during the WEDM process. The Taguchi signalto-noise analysis was used to optimize the WEDM of a 316 stainless steel-clad surface.…”

“…Stainless steel alloys are also studied by many researchers and different optimization techniques like Taguchi signal-to-noise analysis, 16 GA, 17 DFA, 18 PSO 19 , and others are used for performance optimization during the WEDM process. The Taguchi signal-to-noise analysis was used to optimize the WEDM of a 316 stainless steel-clad surface.…”

“…The study also shows that the P on and SV have a stronger impact on MRR than the other variables. 19 Majumder 20 used a hybrid approach while optimizing the parameters of the 316LN alloy using a multi-objective PSO with fuzzy logic. In this hybrid approach, the PSO served as the primary tool for parameter prediction and optimization while fuzzy was used as the fitness function.…”