K.K., Pathak and Ajay Kumar , Kaviti and M.S., Hora (2010) The application of neural networks in the preform design of the upsetting process. Journal of Materials Science Letters, 62. pp. 55-59. ISSN 1047-4838

PDF - Published Version Restricted to Registered users only Download (2897Kb) | Request a copy

Abstract

Design of the optimum preform for near net shape manufacturing is a crucial step in upsetting process design. In this study, artificial neural networks (ANN) are used to consider different interfacial friction conditions between the top and bottom die and billet interface. Two back propagation neural networks are trained based on finite element analysis results considering ten interfacial friction conditions and varying geometrical and processing parameters, to predict the optimum preform for high strength (HS) steel and commercial aluminum. Neural network predictions were verified for three new problems of both HS steel and commercial aluminum and observed that these are in close match with their simulation counterparts. It was further Experimentally verified with two commercial aluminum specimens and observed that the preform values predicted by ANN are in good agreement with experimental results.

Item Type:	Article
Subjects:	Material/Component Development, Processing and Characterization
Divisions:	UNSPECIFIED
Depositing User:	Mr. B.K. Prasad
Date Deposited:	19 Nov 2013 07:32
Last Modified:	19 Nov 2013 07:32
URI:	http://ampri.csircentral.net/id/eprint/816

Actions (login required)

View Item