Prediction of Surface Roughness in Turning Using Adaptive Neuro-Fuzzy Inference System

Due to the extensive use of highly automated machine tools in the industry, manufacturing requires reliable models for the prediction of output performance of machining processes. The prediction of surface roughness plays a very important role in the manufacturing industry. The present work deals with the development of surface roughness prediction model for machining of aluminum alloys, using adaptive neuro-fuzzy inference system (ANFIS). The experimentation has been carried out on CNC turning machine with carbide cutting tool for machining aluminum alloys covering a wide range of machining conditions. The ANFIS model has been developed in terms of machining parameters for the prediction of surface roughness using train data. The Experimental validation runs were conducted for validating the model. To judge the accuracy and ability of the model percentage deviation and average percentage deviation has been used. The Response Surface Methodology (RSM) is also applied to model the same data. The ANFIS results are compared with the RSM results. Comparison results showed that the ANFIS results are superior to the RSM results