Prediction of surface roughness and material removal rate in laser assisted turning of aluminium oxide using fuzzy logic

Abstract

Processing of ceramics with good surface integrity and high material removal rate is a challenging task in the manufacturing industry. Laser assisted machining (LAM) is one of the benchmark technique currently used in industry to process difficult to machine materials. In LAM, laser is used as source to heat the work piece and simultaneously remove the softened material by cutting tool without changing the material microstructure. Since many process parameters are involved in LAM, experimental investigation of processing of ceramics is expensive. So the main objective of this present work is to develop an Artificial Intelligence model to understand the process mechanics and for the prediction of surface roughness and material removal rate (MRR) during laser assisted turning of Aluminium oxide using fuzzy logic. Input parameters are assumed as triangular and Gaussian function and output parameters are assumed as trapezoidal function. It is inferred that increase in cutting speed and pulsed frequency of laser, there is an improvement in surface finish, whereas increase of feed rate results in deterioration of surface integrity. The material removal rate is directly proportional to feed, speed, depth of cut and pulsed frequency of laser. There is a better agreement between experimental and fuzzy model values. The proposed model predicts the surface roughness and MRR with prediction error of 15.76 and 7.69 % respectively.