Development of ANFIS Predictive Model for Wire Electrical Discharge Machining of Cupronickel Material

Wire Electrical Discharge Machining (WEDM) is an essential manufacturing process used to shape complex geometries in conductive materials such as cupronickel, which is valued for its corrosion resistance and electrical conductivity. The objective of this study is to improve the efficiency and precision of machining by creating a specialized predictive model using an Adaptive Neuro-Fuzzy Inference System (ANFIS) for cupronickel material. The study examines the intricate correlation between process parameters of the WEDM (Wire Electrical Discharge Machining) technique, such as pulse-on time, pulse-off time, and discharge current, and crucial machining responses, including surface roughness, material removal rate. Data is collected through systematic experimentation in order to train and validate the ANFIS predictive model. The ANFIS model utilizes the collective learning capabilities of neural networks and fuzzy logic systems to precisely forecast machining responses by considering input parameters. The ANFIS model captures the complex nonlinearities of the WEDM process, allowing for valuable insights into the best parameter settings to achieve desired machining results. The efficacy of the developed ANFIS predictive model is assessed through statistical analysis and compared with empirical findings. The model showcases its proficiency in accurately predicting machining responses, providing manufacturers with a potent instrument for optimizing processes and making decisions in cupronickel material WEDM operations. This allows manufacturers to enhance productivity and quality while simultaneously reducing production costs. This research enhances the comprehension of WEDM processes and provides practical recommendations for achieving excellent machining results in diverse industrial applications.