Abstract
We describe a device which uses a neural network to generate part-programs for milling, drilling and similar operations on machining centres, on the basis of 2D, 2.5D or 3D geometric models of prismatic parts, without operator intervention. The neural network consists of networks for prediction of milling strategy, for prediction of surface quality and for the optimisation of technological parameters in milling. We introduce the surface complexity index (SCI) for identifying surfaces which are very difficult to machine. The SCI takes the surface roughness and machining strategy into account. Teaching and testing of the NN is described. The device, which can be retrofitted to a CNC controller, can be trained from a set of typical parts and will then generate new NC part-programs. A case study of a tool used in the automotive supplier industry shows how a milling strategy is proposed, according to set constraints.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Balic, J. and Brezocnik, M.: A model of intelligent CAD/CAM interface in CIM, in: Proc. of the 13th Internat. Conf. on Production Research, Jerusalem, Israel, Freund Publishing House, London, 1995, pp. 29–31.
Balic, J. and Korosec, M.: Intelligent tool path generation for milling of free surfaces using neural networks, Internat. J. Mach. Tools Manufacture 10 (2002), 1171–1179.
Brezocnik, M., Pahole, I., and Balic, J.: Feature recognition from boundary model of a part (intelligent CAD-CAP interface), in: Proc. of Internat. Conf. on Design to Manufacture in Modern Industry, Bled, Slovenia, Maribor, Faculty of Mechanical Engineering, 1995, pp. 395–404.
Chang, W.-R.: Neural information processing approach to improvements of productivity and accuracy of CNC turning process, PhD Work, University of Texas, Austin, 1993, DAI-B 54/12, June 1994, p. 6415.
Chang, I., Deng, J., and Chan, S.: A next generation machining system based on NC feature unit and real-time tool path generation, Internat. J. Adv. Manufacturing Technol. 16 (2000), 889–901.
Dongmok, S.: Adaptive neural network control with inverse model: Application to the control of turning process (artificial intelligence), PhD Work, Pennsylvania State University, 1995, DAI-b 57/01, July 1996, p. 610.
EDS Unigraphics: Modeling, Manufacturing User Manua l, Vols. 1, 2, V13, EDS, 1998.
HyperMill, Geometry-oriented CAM solution, OPEN MIND Technologies AG, Germany, 2003.
Kadono, M.: Tool path data generation apparatus for NC machine tool and numerical controller provided with it, Patent Nr. US2001/0000805 A1, 2001.
Kamioka, T. and Mochizuki, H.: Learning promotion method on tool and learning promotion type machine, Patent JP2001034155, 2001.
Kato, K. and Momochi, T.: Numerical controller for machining tool with learning function — combines learning program with entered program to produce resulting process, Patent DE4011591 (JP19890098177), 1989.
Korosec, M., Balic, J., and Kopac, J.: Neural network based manufacturability evaluating of free form machining, Internat. J. Mach. Tools Manufacture (2004), to appear.
Li, H.: Intelligent rough machining of sculptured parts, University of Victoria, Canada, 1997.
Liu, Y. and Wang, C.: Neural network adaptive control and optimisation in the milling process, Internat. J. Adv. Manufacturing Technol. 15 (1999), 791–795.
Mahadevan, B.: Automatic 5–axis NC tool-path generation, Massachusetts Institute of Technology, 2001, DAI-B 63/02, August 2002, p. 980.
Melik, D.: Modeling and estimation by structured neural networks for CNC machine tools, University of Wisconsin, Madison, 2000.
Nemoto, K., Kyoichi, M., Yamaguchi, M., Sugimoto, H., and Hasegawa, H.: NC data generation device and its method, Patent JP11242510, 1999.
Neural network application, aiNet V1.25, Celje, Slovenia, 1997.
NeuroShell predictor, Ward systems group, Frederick, MD, 2000.
NeuroSolutions for Excel, custom solution wizard, Neuro Dimension, Gainesville, 2000.
Parametric Technology and Corporation, Pro/MFG&Pro/NC-CHECK, User's guide release 2000i, 2000.
Shunmugam, M. S., Puneti, M., and Bhaskara Reddy, S. V.: A method of preliminary planning for rotational components with C-axis features using genetic algorithm, Computers Industry (2004), in press.
Valenti, M.: Machine tools get smarter, Mech. Engrg. 117(11) (1995).
Waldenmaier, P., Wirth, H., and Monz, J.: Dialogue orientated programming system for a CNC machine tool, Patent EP0726509A1, 1996.
Weck, M.: Werkzeugmaschinen Fertigungssystem, Springer, Berlin, 1998.
Xiao, N.-F. and Saeid, N.: Visual feedback control of a robot in an unknown environment (learning control using neural networks), Internat. J. Adv. Manufacturing Technol.
Zelinski, P.: Choosing a Retrofit CNC, Modern Machine Shop, Gardner Publications, Cincinnati, OH, USA, 1998.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Balic, J. Neural-Network-Based Numerical Control for Milling Machine. Journal of Intelligent and Robotic Systems 40, 343–358 (2004). https://doi.org/10.1023/B:JINT.0000042183.02570.7f
Issue Date:
DOI: https://doi.org/10.1023/B:JINT.0000042183.02570.7f