Abstract Anomalies which occur during the manufacturing process of jet-engine disks can severely degrade cyclic life of highly stressed aero engine components. Thus monitoring of manufacturing processes has already proven its effectiveness for high volume production, its application has failed so far in jet-engine manufacturing. Reasons for this are the small lot sizes; the large scatter in material properties the low machinability and the requirement to consider the surface and subsurface properties created by manufacturing. This exceeds the capabilities of existing monitoring systems. The paper describes a new approach in real-time monitoring for drilling boltholes in Inconel718. By extracting and processing controller data with non-linear algorithms, it can be demonstrated that this data contains sufficient information content about the chip-making process to control tool wear and surface quality of the machined part. In an experimental setup, proven to comply with production quality standards in drilling Inconel718 in means of tool wear and surface roughness, process data origination from the NC of a Sinumeric 840D, collected by an OPC-Server (OLE for Process Control, OLE – Object linking and embedding) had been processed. For the recognition of the relevant machining cycles and the correlation of the data to tool wear and surface roughness suitable algorithms have been developed. The results indicate that OPC-data may be suitable for monitoring the tool and surface conditions created in holes in a diameter size around 7,5 mm, machined by solid carbide drills and face cutting reamers in Inconel718 workpieces.
[1]
C. Sanjay,et al.
Modeling of tool wear in drilling by statistical analysis and artificial neural network
,
2005
.
[2]
Yusuf Altintas,et al.
Prediction of Cutting Forces and Tool Breakage in Milling from Feed Drive Current Measurements
,
1992
.
[3]
Krzysztof Jemielniak,et al.
Advanced monitoring of machining operations
,
2010
.
[4]
Issam Abu-Mahfouz,et al.
Drilling wear detection and classification using vibration signals and artificial neural network
,
2003
.
[5]
Hans-Jochen Bartsch.
Taschenbuch Mathematischer Formeln
,
1982
.
[6]
Eckhardt Schneider,et al.
Tool Wear Monitoring at Turning and Drilling
,
1994
.