Neural network based selection of optimal tool - path in free form surface machining

• Autorzy: Korosec M. , Kopaz J.
• Języki publikacji: EN

Abstrakty

EN

The purpose of the presented paper is to show how with the help of artificial Neural Network (NN) the prediction of milling tool-path strategies could be performed in order to determine which milling tool - path strategies or their sequences will yield the best results (i.e. the most appropriate ones) of free form surface machining, in accordance with a selected technological aim. Usually, the machining task could be completed successfully using different tool-path strategies or their sequences. They can all perform the machining task according to the demands but always only one of the all possible applied strategies is optimal in terms of the desired technological goal (surface quality in most cases). In the presented paper, the best possible surface quality of a machined surface was taken as the primary technological aim. Configuration of the applied Neural Network is presented and the whole procedure of determining the optimal tool-path sequence is shown through an example of a light switch mould. Verification of the machined surface quality, in relation to the average mean roughness Ra is also being performed and compared with the NN predicted results.

Słowa kluczowe

EN

(NN) Neural Network; CAD/CAM system; CAPP; Intelligent CAM (ICAM); milling strategy

• Wydawca: Łukasiewicz Industrial Research Institute for Automation and Measurements PIAP
• Czasopismo: Journal of Automation Mobile Robotics and Intelligent Systems
• Rocznik: 2007
• Tom: Vol. 1, No. 4
• Strony: 41--50
• Opis fizyczny: Bibliogr. 28 poz., rys.

Twórcy

autor

Korosec M.

autor

Kopaz J.

• University of Ljubljana, Faculty of Mechanical Engineering Askerceva 6, 1000 Ljubljana; Slovenia,

Bibliografia

• [1] A.C. Lin, S.Y. Lin and. S.B. Cheng, “Extraction of manufacturing features from a feature-based design model”, Int. J. Prod. Res., vol. 35, 1997, no. 12, pp. 3249-3288.
• [2] G.A. Stark, K.S. Moon, “Modeling surface texture in the peripheral milling process using Neural network”, Journal of Manufacturing science and Engineering, ASME, ISSN 1087-1357, May 1999.
• [3] S.H. Suh, Y.S. Shin, “Neural network modeling for tool path planning of the rough cut in complex pocket milling”, Journal of Manufacturing Systems, ISSN 0278-6125, 1996, pp. 295-304.
• [4] J. Balic, A. Nestler, G. Schulz, “Prediction and optimization of cutting conditions using neural networks and genetic algorithm”, Journal of Mechanical Engineering, Association of Mechanical Engineers and Technicians of Slovenia, ISSN 0039-2480, 1999, pp. 192-203.
• [5] Y.M. Liu, C.J. Wang, “Neural network based adaptive control and optimisation in the milling process”, International Journal of Advanced Manufacturing Technology, ISSN 0268-3768, vol. 14, no. 11, 1999, pp. 791-795,
• [6] M. Korosec , “Optimization of free form surface machining, using neural networks”, Doctor thesis, 2003, University of Maribor, Faculty of technical engineering.
• [7] Sankha Deb, Kalyan Ghosh; S. Paul, “A neural network based methodology for machining operations selection in Computer-Aided Process Planning for rotationally symmetrical parts”, Journal of Intelligent Manufacturing, vol. 17, no. 5, October 2006 , pp. 557-569 (13).
• [8] M. Brezocnik, I. Pahole, J. Balic, “Feature recognition from boundary model of a part” (intelligent CAD-CAP interface), in: Proc. International Conference Design to Manufacture in Modern Industry, Bled, Slovenia, 29th-30th May 1995, pp. 395-404.
• [9] J. Dong and S. Vijayan, “Feature extraction with the consideration of manufacturing processes”, Int. J. Prod. Res., vol. 35, no. 8, 1997, pp. 2135-2155.
• [10] T.N. Wong and Wong K.N., “Feature-based design by volumetric machining features”, Int. J. Prod. Res., vol. 36, no. 10, 1998, pp. 2839-2862.
• [11] K. A. Aldakhilallah and R. Ramesh, “Recognition of minimal feature covers of prismatic objects: A prelude to automated process planning”, Int. J. Prod. Res., vol. 35, no. 3, 1997, pp. 635-650.
• [12] C. Bishop, Neural networks for pattern recognition, Oxford Press, 1995.
• [13] I. Grabec, “Optimization of kernel-type density estimator by the principle ofmaximal self-consistency”,Neural Parallel & Scientific Computations, no. 1, 1993, pp. 83-92.
• [14] S. G. Wang, Y. L. Hsu , “One-pass milling machining parameter optimization to achieve mirror surface roughness”. In: Proceedings of the I MECHE Part B Journal of Engineering Manufacture, vol. 219, no. 1, 2005, pp. 177-181(5) .
• [15] J. Wang, “Multiple-objective optimisation of machining operations based on neural networks”, The Int. J. of Advanced manufacturing technology, Springer London, vol. 8, no. 4, July 1993, pp. 235-243.
• [16] C.K. Mok and F.S.Y. Wong, “Automatic feature recognition for plastic injection moulded part design”, The International Journal of Advanced Manufacturing Technology, Springer: London, vol.34, no. 5-6, September 2007, pp. 1058-1070.
• [17] G. Jung Hyun Han, Inho Han, Eunseok Lee, Juneho Yi, “Manufacturing feature recognition toward integration with process planning systems”, Man and Cybernetics. Part B, IEEE Transactions on, vol. 31, issue 3, June 2001, pp. 373 – 380.
• [18] Helen L. Locket, Marin D. Guenov, “Graph based feature recognition for injection moulding based on a mid-surface approach”, Computer –Aided Design, vol. 37, issue 2, 2005, pp. 251-262.
• [19] I. Grabec, “Self-Organization of Neurons Described by the Maximum Entropy Principle”, Biol.Cybern., no. 63, 1990a, pp. 403-409.
• [20] I. Grabec, “Modeling of Natural Phenomena by a Self-Organizing System”, Proc. of the ECPD NEURO COMPUTING, vol. 1, no. 1, 1990b, pp. 142-150.
• [21] D. F. Specht, Probabilistic Neural Networks for Classification, Mapping or Associative Memory, ICNN-88, Conference Proc., 1988, pp.525-532.
• [22] C. Principe, R. Euliano, Neural and adaptive systems, John Wiley&Sons, 2000.
• [23] T. Kohonen et al., “Statistical Pattern Recognition with Neural Networks: Benchmark Studies”. In: Proceedings of the 2nd Annual IEEE International Conference on Neural Networks, 1988, vol. 1.
• [24] J. Guh et al., “Predicting equilibrated postdialysis BUN an artificial neural network in high-efficiency hemodialysis”, Am. J. Kidney Dis , no. 31 (4), April 1998, pp. 638-46.
• [25] S. Prabhu, “Automatic extraction of manufacturable features from CADD models using syntactic pattern recognition techniques”, International Journal of Production Research, vol. 37, issue 6, 1999, pp. 1259-1281.
• [26] Neural Ware, Inc., Neural Computing Manual, Wiley, 1991.
• [27] T.C. Li, Y.S. Tarng, M.C. Chen, “A self-organising Neural network for chatter identification in milling”,International Journal of Computer Applications in Technology, ISSN 0952-8091, vol.9, no.5-6, 1996, pp. 239-248.
• [28] M. Korosec, J. Balic, J. Kopac, “Neural network based manufacturability evaluation of free form machining”, I. Journal of Machine Tools & Manufacture, no.45, 2005, pp. 13-20.