Artificial Neural Network assisted Sensor Fusion model for predicting surface roughness during hard turning with minimal cutting fluid application and its comparison with Regression Model

Surface roughness is a factor of great importance in the evaluation of cutting performance and it plays an important role in manufacturing processes. Performance parameters such as cutting force, cutting temperature, vibration etc. can be used to predict surface roughness. It is expected that more accurate prediction would be possible if these factors are considered collectively with cutting parameters since each of these factors predict surface roughness in their own characteristic fashion. In this present work, an attempt was made to fuse cutting temperature along with cutting parameters to predict surface roughness during turning of H13 tool steel having a hardness of 45 HRC. A regression model and an artificial neural network model with sensor fusion were developed and their ability to predict surface roughness (Ra) was analyzed. The fusion model developed based on the artificial neural network was found to be superior to the regression model.