THE RELIABILITY OF TOOL LIFE PREDICTION MODEL IN END MILLING

This paper describes the tool life prediction model when end milling AISI H13 tool steel using P10 TiN coated carbide tool. The development of the model utilizes the data set from the Taguchi method design of experiment with L18(2 1 x3 7 ) orthogonal array. The effects of cutting speed, feed rate and depth of cut on tool life of P10 are discussed. A prediction model for speed within the region of 224 m/min to 355 m/min, feed rate of 0.1 mm/tooth to 0.25 mm/tooth, and depth of cut of 0.3 mm to 0.8 mm are presented. The adequacy of the predicted model after performing multiple regression analysis give 95% confidence interval with coefficient of multiple determination (R 2 ) of 0.845. Whereas from average percentage deviation (φ ) calculated, it shows that the accuracy of the predicted model is only 23%. This shows that the accuracy of the predicted model could not depend solely on the analysis performed using SPSS alone. Other methods to check the model accuracy such as average percentage deviation (φ ) are also important.