Vibration prediction in drilling processes with HSS and carbide drill bit by means of artificial neural networks

摘要

Vibrations occur in the cutting tool during machining. These vibrations adversely affect cutting tool's life span, the measurement accuracy of the workpiece and the surface quality. In order to minimize these effects, an experimental study is conducted and the vibrations generated during the process are measured. The effects of these vibrations on the cutting tool and material are investigated. Drilling tests (total of 1304 experiments) are performed experimentally and modeled with artificial neural networks (ANN). Firstly, the hole drilling operation is applied to C2080 (AISI D3) cold work tool steel workpiece with high-speed steel and carbide cutting tools at cutting speeds of 15, 20, 25 and 30 m/min and at feed rates of 0.06, 0.08, 0.1 and 0.12 mm/(rev) and the vibrations in the x, y and z axes are measured. An experimental setup for vibration measurement is prepared so that the technical equipment works in harmony with each other. Secondly, input and output parameters are determined by classifying the data obtained in the experimental work, then a new ANN model is developed, and the results are compared with the experimental data. The aim of the study is to ensure the simulation of the vibrations that may occur during hole drilling processes via a model. In this context, high-reliability ANN model has been developed with a 4 input (cutting speeds, feed rates, cutting tool type and time) and 3 output (x, y, and z vibration values).