Prediction on Material Removal Rate in Electrical Discharge Machining Based Upon Adaptive Neuro-Fuzzy Inference System
暂无分享,去创建一个
The Material Removal Rate (MRR) is very influencer factor in electrical discharge machining (EDM). In this work, the effect of EDM parameters such as current (10, 20 & 30A), pulse on time (50, 60 & 70 µs) and pulse off time (35, 45 & 55 µs) on MRR in stainless steel alloy 304 (ASTM A 240) was studied. All experiments are achieved based on design of experiments methodology by adapting L9 orthogonal array. From this work, it is observed that variant sets of EDM process parameters are needed to obtain higher MRR for stainless steel alloy 304. Adaptive neuro-fuzzy inference system (ANFIS) has been used to generate drawing relation between input parameters and output response. The results specifies that the designed adaptive neuro-fuzzy inference system model provides minimum error in MRR predicted values as 0.0927 at 20 epochs. This results indicates that this model can be used to predict the MRR responses effectively.
[1] Ahmed A. D. Sarhan,et al. Improve wire EDM performance at different machining parameters - ANFIS modeling , 2015 .
[2] M. F. MADIGAN. Machine Tools , 1969, Nature.
[3] Gary Wise. Electrical Discharge Machining (EDM) , 1972 .
[4] 著者名なし. プロテク (PROduction TECHnology) 研究会 , 1992 .
[5] Gary F. Benedict,et al. Electrical Discharge Machining (EDM) , 2017 .