Intelligent hybrid approaches for ensuring better prediction of gas-assisted EDM responses

Abstract

The present research work explores the implementation of three smart hybrid predictive models based on the adaptive neuro-fuzzy inference system (ANFIS), ANFIS and genetic algorithm (GA), and ANFIS and particle swarm optimization (PSO). All such strategies have been used to determine and compare machining key elements including material removal rate (MRR) and surface roughness (SR) during the gas-assisted electrical discharge (GAEDM) process. In this study, inert gas-based EDM with a multi-hole rotating tool has been carried out. In this experimentation, pulse-on time, peak current, duty cycle, electrode rotation, and gas discharge pressure were selected as input factors. The proposed method is to upgrade ANFIS with GA and PSO techniques. The GA and PSO algorithms are used to enhance the accuracy of the ANFIS model. The models have been trained, tested, and validated with observational results. Statistical techniques were applied to assess the effectiveness of the predictive capability models established through the ANFIS, ANFIS-GA, and ANFIS-PSO techniques. The actual and predicated estimates of MRR and SR of the GAEDM, obtained by ANFIS, ANFIS-GA, and ANFIS-PSO, were observed to be as per one another. In addition, the ANFIS-PSO framework proved to be even more responsive when compared with the ANFIS and the ANFIS-GA system. In particular, the assertion of this work is that modified algorithms such as ANFIS-GA and ANFIS-PSO are an efficient and productive approach to accurate EDM response estimation.

Thermal-Dependent Ferroelectric Cochran’s Frequency and Dielectric Properties in Arsenate-Type Family of KDP Crystal

“…and [32] with the addition of four spin coupling , direct spin-spin interaction term, indirect spin -lattice interactions, phonon anharmonic interactions up to quartic, as well as extra interaction terms. The contribution of these extra interaction terms clearly found in Eq.…”

“…and 𝐽 ′ = 7𝐽 3 , but they have not studied advanced ferroelectric properties like frequency response function, polarization and permittivity. Pawan and Upadhyay [32] have also studied these crystals with the help of the PLCM model, but they have not introduced the extra interaction terms which we have considered and the proper decoupling scheme. These terms enhance the rigours results in our calculation.…”

“…Earlier Bist and, Panwar [31] used Ganguli et al [30] model and modified it (pseudospin model) by adding a few terms. Singh and Upadhyay [32] also added some other terms to the previous model [30]. We consider the model for the present work by adding all the possible interactions such as four spin coupling terms, phonon anharmonic interaction up to the fourth order, and extra spin-lattice terms in the earlier modified Hamiltonian.…”

Parameters Optimization of Electrical Discharge Machining Process Using Swarm Intelligence: A Review

“…The optimal input values (process parameters) for different desired SR were obtained, and the variation of SR and MRR were heavily dependent on discharge energy fluctuation. Singh et al [68] proposed an intelligent hybrid approach, using the PSO algorithm, to obtain a desired prediction of gas-assisted EDM (GA-EDM) performance. The results showed that the improved PSO algorithm was effective for the G-EDM performance estimation.…”