A clustering approach for determining the optimal process parameters in cutting

Residual stresses are normally generated in any cutting operation. However, while compressive residual stresses are sometimes suitable as they may even enhance and improve the piece life, tensile residual stresses can be very detrimental representing a negative feature for fatigue life, corrosion, strength and other functional aspects. Thus, a proper set-up of the process parameters in machining operations has a dramatic importance. Currently, optimization methodologies do not seem to be very effective for industrial needs, for which the optimal setup being a desired residual stresses profile becomes a relevant issue. On the basis of the previous considerations, this work proposes a data mining technique, which has proven to be reliable to identify the analytical relationship between residual stresses and the proper process parameters. In order to ensure the use of the developed technique in practice, it has been integrated in the user-friendly software, Predators (R).

Residual stresses are normally generated in any cutting operation. However, while compressive residual stresses are sometimes suitable as they may even enhance and improve the piece life, tensile residual stresses can be very detrimental representing a negative feature for fatigue life, corrosion, strength and other functional aspects. Thus, a proper set-up of the process parameters in machining operations has a dramatic importance. Currently, optimization methodologies do not seem to be very effective for industrial needs, for which the optimal setup being a desired residual stresses profile becomes a relevant issue. On the basis of the previous considerations, this work proposes a data mining technique, which has proven to be reliable to identify the analytical relationship between residual stresses and the proper process parameters. In order to ensure the use of the developed technique in practice, it has been integrated in the user-friendly software, Predators®.