Estimation of machining responses in hard turning under dry and HPC conditions using different AI based and statistical techniques

Hard turning is garnered as a cost-effective alternative to grinding; however, the process is marred with reliability and predictability issues. Surface roughness, cutting temperature, and cutting force are three essential elements affecting hard turning reliability. The current endeavor analyzes the machinability features of hardened medium carbon steel by measuring the performance of surface roughness, cutting temperature, and cutting force of the steel under high-pressure and dry cutting conditions using Coated carbide. An artificial neural network (ANN), response surface methodology (RSM) and adaptive neuro-fuzzy interference system (ANFIS) are utilized to model responses under two different scenarios. With aP-value less than 0.05, all parameters had a statistically significant effect on the output responses under dry and HPC circumstances, and the model projected values closely matched the experimental values under both situations. Several statistics show that the three output responses are effectively represented by all modeling approaches, including correlation (R), determination (R-2), mean square error (MSE), root mean square error (RMSE), and mean absolute percentage error (MAPE). As demonstrated by the correlation coefficient factor, ANFIS has a high predictive value; this indicates that the predicted response and experimental outputs have a significant consistency.