Challenges of Data Acquisition and Analysis for Characteristics-Driven and Metrology-Based Optimization of Milling Process Development

Abstract:

The research and practical use of data and data-mining in production environment is still at an early stage. Although almost every manufacturing company collects a lot of process and product related data they often do neither use nor deploy this data in order to optimize or even analyze their production processes. The acquisition of process data brings several advantages. On the one hand the implicit knowledge is permanently stored and on the other hand it is possible to learn from previous process failures. The acquired knowledge could then be applied to all future production tasks. Although many research activities can be observed since the late 90s, none of them managed the transfer to practical usage. In order to encourage the practical transfer of data-mining in production environment this paper presents a metrology-based test set-up and therewith arising challenges when consistently acquiring and processing inhomogeneous process, product and machine data. For the experimental set-up, on-machine metrology systems were developed and integrated into a 5-axis milling machine to gain much significant data.

• Periodical: Applied Mechanics and Materials (Volume 704)
• Pages: 233-238
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.704.233
• Online since: December 2014
• Authors: Laura Niendorf*, Markus Grosse Boeckmann, Robert Schmitt
• Keywords: Data-Mining, On-Machine Metrology, Process Optimization, Production Efficiency, Production Quality

References

[1] F. Jacob and G. Strube, Why go Global? The MultinationalImperative, in Global Production, E. Abele, T Meyer, U. Naeher, G. Strube and R. Sykes, Eds. Berlin u. a: Springer, 2008, pp.2-33.

DOI: 10.1007/978-3-540-71653-2

[2] B. Denkena, O. Guemmer and C. Will, Compensation of static and dynamic tool deflections during milling process by an adaptronic spindle system, Intercut. 2nd International Conference <Innovative Cutting Processes & Smart Machining>, Oct. (2008).

[3] M. Wiercigroch and E. Budak, Sources of Nonlinearities, Chatter Generation and Suppression in Metal Cutting, Phil. Trans. The Royal Society of London A Mathematical Physical And Engineering Science, 359, pp.663-693, (2001).

DOI: 10.1098/rsta.2000.0750

[4] R. Jalili Saffar, M. R. Razfar, A. H. Salimi and M. M. Khani, Optimization of Machining Parameters to Minimize Tool Deflection in the End Milling Operation Using Genetic Algorithm, World Applied Science Journal, vol. 6, no. 1, pp.67-69, (2009).

DOI: 10.1080/10910340903586483

[5] L. Pejryd, J. Repo and T. Beno, Machine Tool Internal Encoders as Sensors for the Detection of Tool Wear, 3rd CIRP Conference on Process Machine Interactions, Procedia CIRP 4, pp.46-51, (2012).

DOI: 10.1016/j.procir.2012.10.009

[6] M. A. Elbestawi and M. Dumitrescu, "Tool condition monitoring in machining – neural networks, IFIP Internation Federation for Information Processing, vol. 220, Information Technology for Balanced Manufacturing Systems; ed. W. Shen, Boston: Springer, 2006, pp.5-16.

DOI: 10.1007/978-0-387-36594-7_2

[7] F. Salvatore, S. Saad and H. Hamdi, Modeling and simulation of tool wear during the cutting process, in 14th Conference on Modeling of Machining Operations (CIRP CMMO), Procedia CIRP 8, pp.305-310, (2013).

DOI: 10.1016/j.procir.2013.06.107

[8] A. Attanasio, E. Ceretti and C. Giardini, Analytical Models for Tool Wear Prediction during AISI 1045 Turning Operations, in 14th Conference on Modeling of Machining Operations (CIRP CMMO), Procedia CIRP 8, pp.218-223, (2013).

DOI: 10.1016/j.procir.2013.06.092

[9] A. M. Khorasani, M. R. S. Yazdi and M. S. Safizadeh, Tool Life Prediction in Face Milling Machining of 7075 Al by Using Artificial Neural Networks, in IACSIT International Journal of Engineering and Technology, vol. 3, no. 1, pp.30-35, February (2013).

DOI: 10.7763/ijet.2011.v3.196