Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Machining process acceptability for high performance materials by multilple sensor monitoring

: Teti, R.; Segreto, T.; Neugebauer, Reimund

Neugebauer, Reimund ; Fraunhofer-Institut für Werkzeugmaschinen und Umformtechnik -IWU-, Chemnitz:
Sustainable production for resource efficiency and ecomobility : Manufacturing Colloquium, September 29-30, 2010 Chemnitz; ICMC 2010
Zwickau: Verlag Wissenschaftliche Scripten, 2010 (Berichte aus dem IWU 54)
ISBN: 978-3-942267-04-5
International Chemnitz Manufacturing Colloquium <2010, Chemnitz>
Conference Paper
Fraunhofer IWU ()
Drehen; Kaltverfestigung; Kolkverschleiß; Kraftsensor; neuronales Netzwerk; Nickeltitanlegierung; Pseudoelastizität; Schnittgeschwindigkeit; Sensorfusion; Sensortechnik; Signalaufbereitung; Signalauswertung; Signalerkennung; Spanbarkeit; Spanform; Störsignal; Verfahrensauswahl; Verfahrensbedingung; Vibrationssensor; Vorschubgeschwindigkeit

The principal roadblocks to the industrial implementation of NiTi alloy products are given by the difficulties in their manufacturing processes. Very high deformation at failure, severe strain hardening and unique pseudoelastic behaviour make NiTi alloy machining properties quite complex, yielding problems in material processing and workpiece quality. Following the call for a deeper insight into the machinability of NiTi alloys, a collaborative research work was carried out by two Laboratories: the Machining Technology Laboratory at the Fraunhofer Institute for Machine Tools and Forming Technology (IWU), Chemnitz, Germany, and the Laboratory for Advanced Production Technology (LAPT) at the Department of Materials and Production Engineering, University of Naples Federico II, Italy. The joint research activities comprised cutting force and acceleration sensor monitoring during turning of NiTi alloy under different cutting conditions. The main scope was to correlate sensorial data and process acceptability for machinability assessment through a supervised expert knowledge based neural network paradigm. In this paper, a particular focus is dedicated to sensor fusion of signal data for the integration of information generated by sensors of different nature in order to better and more robustly characterize NiTi alloy machining process conditions.