Prediction and analysis of multiple quality characteristics in drilling under minimum quantity lubrication

Abstract

The need for environmental technology of machining is intensifying and is a tough challenge for manufacturing industries. This article investigates the performance of the minimum quantity lubrication in drilling of 6063-T6 aluminum. The experiments were conducted in dry and conventional wet machining and the results compared. Spindle speed, feed rate and point angle are the three parameters considered in this study. High speed steel drilling tools were used and an L8 orthogonal array was chosen for the experimental design. The quality characteristics of dimensional deviation of hole diameter, height of burrs, hole taper, chip thickness, tool wear, cutting power and surface roughness were measured and compared to evaluate the performance of the drilling in minimum quantity lubrication condition. The results presented that the drilling performance has improved in minimum quantity lubrication and demonstrates its capacity as an alternative for dry and wet machining. This article also proposes a feed forward artificial neural network model with a back propagation algorithm to predict the quality characteristics surface roughness and tool wear with chip thickness inputs and cutting power in addition to cutting parameters. The prediction results demonstrated the accuracy of the proposed artificial neural network (ANN) model.