On burr height estimation based on axial drilling force

• Autorzy: Sokołowski A.
• Języki publikacji: EN

Abstrakty

EN

Purpose: The main goal of the research is to build a model of relationship between burr height created during drilling operation and signal representing axial drilling force. Such a model can be applied in diagnostic system for on-line estimation of bur height. Design/methodology/approach: The first applied approach is based on a step by step procedure in which several statistical models were built. The second one is based on specific features of artificial intelligence methods. The artificial neural networks serve as a tool for data selection and integration while the fuzzy logic systems are applied for data integration, only. Findings: The developed algorithm for processing axial drilling force allowed constraining the noise inherent to the drilling process and emphasising the information that could be useful for building considered model. The impact of the properly conducted data selection has been emphasised. Also, importance of providing information represented with axial drilling force has revealed. Research limitations/implications: The developed models need to be checked or improved for practical implementation. Such improvement can be done by introducing other signal features or other cutting parameters as model inputs. Also, analysis of other signals that can be measured during drilling is assumed as a future work. Practical implications: The conducted research reconfirmed possibility of on-line diagnostics of bur height during drilling. Several parameters necessary for such diagnostics have been estimated. This suggests continuing the research in order to design a system that could be applied in industrial conditions. Originality/value: The proposed approach is not a typical since analytical models, FEM models or models basing only on cutting process parameters have been considered, mainly. Such models are limited to two dimensional machining, usually. Besides, application of artificial intelligence methods for data selection and integration points at novelty of the research conducted.

Słowa kluczowe

EN

machining; burr formation; drilling; diagnostics; artificial intelligence methods

PL

obróbka; powstawanie zadziorów; wiercenie; diagnostyka; metody sztucznej inteligencji

• Wydawca: International OCSCO World Press
• Czasopismo: Journal of Achievements in Materials and Manufacturing Engineering
• Rocznik: 2010
• Tom: Vol. 43, nr 2
• Strony: 734--742
• Opis fizyczny: Bibliogr. 11 poz., rys., tab., wykr.

Twórcy

autor

Sokołowski A.

• Department of Machine Technology, Faculty of Mechanical Engineering, Silesian University of Technology, ul. Konarskiego 18a, 44-100 Gliwice, Poland

Bibliografia

• [1] G.L. Chern, Analysis of burr formation and breakout in metal cutting, Ph.D. Dissertation, Department of Mechanical Engineering, University of California at Berkeley, 1993.
• [2] Consortium on Deburring and Edge Finishing (CODEF), The University of California at Berkeley (http://lma.berkeley.edu/codef/).
• [3] C.T. Lin, G.C.S. Lee, Neural-network-based fuzzy logic control and decision system, IEEE Transaction on Computers 40/12 (1991) 1320-1336.
• [4] S. Min, J. Kim, D.A. Dornfeld, Development of a drilling burr control chart for low alloy steel AISI 4118, Journal of Materials Processing Technology 113/1-3 (2001) 4-9.
• [5] D.E. Rumelhart, G.E. Hinton, R.J. Williams, Learning internal representation by error propagation, Parallel Distributing Processing, The MIT Press, 1986.
• [6] J. Stein, R. Narayanaswami, S. Ho, A. Lam, M. Babu, I. Park, A. Afzal, D. Dornfeld, Intelligent Deburring of Precision Components, Proceedings of the Symposium on Deburring and Surface Finishing, SME, 1993.
• [7] A. Sokołowski, Selected problems of designing of the machine tool and cutting process diagnostic systems, Monographs of the Silesian University of Technology, series: Mechanics no. 142, Gliwice, 2003 (in Polish).
• [8] A. Sokołowski, Application of neural networks and neuro-fuzzy logic for burr modelling, Proceedings of the 12th International DAAAM Symposium, Jena, Germany, 2001.
• [9] A. Sokołowski, J. Kosmol, Feature selection for burr height estimation, Proceedings of 5th International Conference “Monitoring and Automatic Supervision in Manufacturing”, Warszawa, Poland, 1998.
• [10] A. Sokołowski, J. Kosmol, Selected examples of cutting process monitoring and diagnostics, Journal of Materials Processing Technology 113/1-3 (2001) 322-330.
• [11] A. Sokołowski, E. Gałuszka, T. Czyszpak, Statistical and artificial intelligence based approaches to the data selection task, Proceedings of the 7th International Scientific Conference "Computer Integrated Manufacturing - Intelligent Manufacturing Systems” CIM'2005, Gliwice-Zakopane, Poland, 2005.