Participant: Gerardo Beruvides
Conference: IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2014), November 10-12, 2014, Limassol, Cyprus.
Summary: This paper presents the modeling of thrust force and perpendicular vibrations in microdrilling processes of five commonly used alloys (titanium-based, tungsten-based, aluminum-based and invar). The process was carried out by peck drilling and the influence of five parameters (drill diameter, cutting speed, feed rate, one-step feed length and total drilling length) on the behavior of the thrust force was considered. Some important mechanical and thermal properties of the workpiece material were also considered in the model. Two different models were developed: the first one based on artificial neural networks and the second one based on fuzzy inference systems. Outcomes of both approaches were compared to each other and to a multiple regression model. The neural model shows not only a better goodness-of-fit but also a higher generalization capability.