AUTHORS: Badea Lepadatescu
Download as PDF
ABSTRACT: The work reported describes application of artificial neural networks (ANN) for the purpose of deriving a complex nonlinear relationship among several factors that influence the roughness of part surfaces obtained through superfinishing process according with different process parameters. The relationship is necessary to optimize the process parameters and predict the optimum values to obtain the roughness surfaces that are needed for the part manufactured. A feed forward two-layers ANN is designed and trained using experimental data. The model is tested for generalization and simulated in MATLABTM environment. The results are used to determine the best process parameters that must be used to have a high surface finish according with the technical requirements.
KEYWORDS: Surface finish, Reliability, Wear, Cost-performance, Two-Layer ANN, Back propagation, MATLABTM Simulation
REFERENCES:
[1] Yordanova S., Assenov V. and Z. Nedic. Application of Artificial Neural Networks for Linearising Control of а Non-Linear Plant, Proceedings of the 3rd Japan-Australia-New Zealand Joint Seminar JANZS’2004, Auckland, New Zealand, Jan. 22-23, 2004, pp.165-171.
[2] Yordanova S. and R. Tzeneva. Application of Neural Networks for Analysis in Bolted Busbar Connections of New Design, Proc. of the XLIII Int. Sc. IEEE conf. on Information, Communication and Energy Systems and Technologies ICEST’08, Ra Fs V Experiment No Serbia, Niš, 25-27 June, 2008, ISBN 978-86- 85195-61-7, pp. 666-669.
[3] Wasserman P.D. Neural Computing. Theory and Practice. ANZA Research, Inc. Van Nosrand Reinold, N.Y., 1992.
[4] Demuth H., M. Beale. Neural Network Toolbox for Use with MATLAB. Users Guide. The Mathworks Inc., 1993.
[5] Yordanova S., A. Todorov. Investigation on Some Applications of Neural Networks in Control of Plants with Variable Parameters. –In: Problems of engineering cybernetics and robotics, No47, BAS, 1998, pages 59-68.
[6] Yordanova S. Investigations on Neural Networks Flowrate Control. Proceedings of the WSES/MIUE/HNA Int. Conf. “Mathematics & Computers in Mechanical Engineering ’99” (session Computer Aided Metrology), Florida Keys, 25-29 July, 1999, 71-74. ISBN: 960-8052- 04-1.
[7] Haykin S., Neural Networks: A comprehensive foundation. 2nd Edition, Prentice Hall, 1999. ISBN 0132733501.
[8] Farago, F. T., Abrasive Methods Engineering, Vol.1, 1976, New York: Industrial Press.
[9] Borokowski, J., and A. Szymanski., Uses of Abrasives and Abrasive Tools. Chichester, Eng,: Ellis Horwood, 1992.
[10] King, R. I., and R.S. Hahn., Handbook of Modern grinding Technology. New York: Chapman and hall/Methuen. 1987.
[11] McKee, R.L., Machining with Abrasives. New York: Van Nostrad Reihold, 1982.
[12] Lepadatescu, B, Dumitrascu, A.E., Enescu, I., Nedelcu, A. – Research regarding the improvment of workpieces surface finish by machining through superfinishing process. In : Proceedings of the 4th International Conference on Manufacturing Engineering Quality and Production Systems, Barcelona, Spania, 15-17 Septembrie 2011., pag 190-195, ISBN: 978-1-61804-031-2.
[13] Lepadatescu, B., Fota, A., Nedelcu, A., Buzatu, C., Dumitrascu, A.E., Enescu, I. – Flexible Superfinishing Modules used in SME (Small and medium Enterprises). In: Proceedings of the 8th WSEAS International Conference on SIGNAL PROCESSING, ROBOTICS and AUTOMATION (ISPRA’09), Cambridge, UK, February 21-23, 2009; pag.86-90, ISSN: 1790-5109, ISBN: 978- 960-474-051-2.