Taguchi-Based Grey Optimization of Wire Electrical Discharge Machining Parameters for Invar 36 Material used in Automotive Valves

Wire Electrical Discharge Machining (WEDM) is a commonly employed technique for shaping conductive materials such as SAE 1010 steel, providing highly accurate machining capabilities. This low-carbon steel has excellent formability, weldability, and machinability, making it useful in many contexts including bolts, nuts, valves and cold headed fasteners. The objective of this study is to improve the efficiency and precision of the Wire Electrical Discharge Machining (WEDM) process for SAE 1010 material. This will be achieved by creating a predictive model using an Adaptive Neuro-Fuzzy Inference System (ANFIS). The study investigates the influence of WEDM parameters, specifically pulse-on time, pulse-off time, and discharge current, on important machining outcomes such as surface roughness (Ra), material removal rate (MRR). The experimentation has been planned and conduced as per Taguchi L9 orthogonal array design. The ANFIS predictive model is constructed by utilizing the obtained information set, which integrates the learning capacities of neural networks with the comprehensibility of fuzzy logic systems. The model has undergone training and optimization to effectively forecast machining responses using input parameters, thereby offering valuable insights into process behavior. The ANFIS predictive model's performance is assessed using statistical analysis and compared to experimental results. The model that was created shows its ability to accurately forecast machining outcomes and capture intricate process dynamics, making it easier to determine the best parameter configurations for enhanced WEDM performance. The proposed Adaptive Neuro-Fuzzy Inference System (ANFIS) predictive model provides a methodical approach to optimize parameters for Wire Electrical Discharge Machining (WEDM). This allows manufacturers to improve productivity and quality in machining operations on SAE 1010 material. This study enhances the comprehension of WEDM processes and offers a useful tool for optimizing processes in high-precision manufacturing applications.