Application of Multiple Regression and Adaptive Neuro-Fuzzy Inference System for Prediction of Surface Roughness in EDM

A manufacturing system is oriented towards higher production rate, better quality and reduced cost and time to make a product. Surface roughness is an index parameter for determining the quality of a machined product and is influenced by various input process parameters. Surface roughness prediction in Electrical Discharge Machine (EDM) is being attempted with many methodologies, yet there is a need to develop robust, autonomous and accurate predictive system. This work proposes the application of hybrid intelligent technique, multiple regression and adaptive neuro-fuzzy inference system (ANFIS) for prediction of surface roughness in EDM. An experimental data set is obtained with current, pulse-on time and pulse-off time as input parameters and surface roughness as output parameter. Central composite rotatable design was used to plan the experiments. Multiple regression model is developed using the experimental data, to generate additional input-output data set. The input-output data set is used for training and validation of the proposed technique. After validation, data are forwarded for prediction of surface roughness. The proposed hybrid model for the prediction of surface roughness has very good agreement with the experimental results.