Options
2008
Conference Paper
Titel
Sensor monitoring based optimisation during turning of titanium alloys
Abstract
This paper focuses on the development and application of sensor monitoring of machining processes carried out on difficult-to-machine Ti- alloy (TiAl6V4) with the aim of process optimisation. The joint research work aims to determine optimised machining process conditions based on advanced signal processing, feature extraction, and pattern recognition, with the scope to classify Acceptable / Not Acceptable process conditions. Turning tests were carried out on under diverse cutting conditions. Sensor monitoring of process conditions was performed through acceleration sensor signal detection and analysis. Decision making on process conditions acceptability was obtained through supervised expert knowledge NN pattern recognition procedures. The obtained results showed that the NN SR for Acceptable process conditions identification are always significantly higher than for Not Acceptable process conditions. By resorting to sensor fusion of the 3 cutting force components (ax + ay + az) instead of using single cutting force components (ax, ay, az), the NN SR tend to increase also for Not Acceptable process conditions identification. This emphasizes the NN capability to realize the concept of sensor fusion.