Optimization and ANFIS Predictive Modeling of Wire Electrical Discharge Machining for Invar 36 Material

Wire Electrical Discharge Machining (WEDM) is a highly accurate machining approach that is well-known for its capability to create intricate forms in materials with high levels of hardness and intricate geometries. Invar 36, a nickel-iron alloy, is extensively utilized in industries that demand exceptional dimensional stability across a wide temperature range. The objective of this exploration is for optimizing the WEDM parameters of Invar 36 material. Additionally, a predictive model called Adaptive Neuro-Fuzzy Inference System (ANFIS) will be developed to forecast the machining performance. The study involved conducting experimental trials to analyze the influence of crucial factors in WEDM. These parameters included pulse-on time (Ton), pulse-off time (Toff), and current. The objective was to examine their influence on key performance indicators such as material removal rate (MRR), surface roughness (Ra). The methodology of Design of Experiments (DOE) enabled a systematic exploration of parameters. A predictive model using ANFIS was created to forecast machining performance by utilizing input parameters. The model was trained using empirical data to accurately capture the intricate correlations between process variables and output responses. The outcomes clearly demonstrated that the ANFIS predictive model was highly effective in accurately predicting machining performance for WEDM of Invar 36 material. The model offers valuable insights on the ideal parameter configurations to maximize machining efficiency and surface quality. This study enhances the comprehension of WEDM for Invar 36 material and provides a useful tool for optimizing the process. Manufacturers can improve machining productivity and quality in precision engineering applications by utilizing the ANFIS predictive model, thereby promoting the wider use of WEDM technology.