Comparison of ANN and RSM modeling approaches for WEDM process optimization

Abstract

In this paper, an effective process optimization approach based on artificial neural networks with a back propagation algorithm and response surface methodology including central composite design is presented for the modeling and prediction of surface roughness in the wire electrical discharge machining process. In the development of predictive models, cutting parameters of pulse duration, open circuit voltage, wire speed and dielectric flushing are considered as model variables. After experiments are carried out, the analysis of variance is implemented to identify the contribution of uncontrollable process parameters effecting surface roughness. Then, a comparative analysis of the proposed approaches is carried out to determine the most efficient one. The performance of the developed artificial neural networks and response surface methodology predictive models is tested for prediction accuracy in terms of the coefficient of determination and root mean square error metrics. The results indicate that an artificial neural networks model provides more accurate prediction than the response surface methodology model.

Analysis and Optimization of Process Parameters in Wire Electrical Discharge Machining Based on RSM: A Case Study

“…In cutting operation, WEDM primarily employed either for trim cut [25][26][27] or rough cut [28,29]. To the best knowledge of authors, this technique can be successfully employed for machining of steel and steel alloys [30][31][32][33] aluminum and aluminum alloys, titanium and its alloys [27,34] super alloys [35,36] metal matrix composites [37,38] green compact manufactured by powder metallurgy [39]. Investigations into the influences of machining input parameters on the performance of WEDM have been widely reported [25,[40][41][42].…”

Surface Quality Control of p-type Silicon Chip during Edge Insulation with Wire Electric Dischaarge Machining

“…Their results indicated that just one processing run was effective for achieving the desired surface roughness, and multiple processing runs adversely affected the specimen's accuracy. In 2021, Sagbas et al (13) developed a neural network model to predict the surface roughness of WEDM-processed specimens. Their results indicated that open-circuit voltage and feed rate were the main parameters affecting the surface quality of the specimens.…”