RT Journal Article
T1 A hybrid approach to the development of a multilayer neural network for wear and fatigue prediction in metal forming
A1 Belfiore, N. P.
A1 Ianniello, F.
A1 Stocchi, D.
A1 Casadei, F.
A1 Bazzoni, D.
A1 Finzi, A.
A1 Carrara, S.
A1 González, J. R.
A1 Llanos, J. M.
A1 Heikkila, I.
A1 Peñalba, F.
A1 Gómez, X.
AB In this paper an approach to surface damage prediction is proposed for the case of metal forming. The method is mainly based on three fundamental stages: (a) the detection of a feasible physical model which is able to give some important understanding of the phenomenon, although with limited generality; (b) the extensive development of an organized experimental campaign, which is necessary to tune up the developed model; and (c) the organization of an efficient and intelligent way of data collecting. The three aspects of the research work have been integrated by means of a neural network which is trained by using data coming from the real plant, from the standard tribometers, and from the reference numerical model. In this sense, the neural network is indented as hybridized. Predictions are shown to be very close to the experimental data obtained in the production plant. The method is useful for minimizing the number of experiments in the process of materials and treatment selection, and in maintenance.
SN 0301-679X
YR 2007
FD 2007-10
LK https://hdl.handle.net/11556/4399
UL https://hdl.handle.net/11556/4399
LA eng
NO Belfiore , N P , Ianniello , F , Stocchi , D , Casadei , F , Bazzoni , D , Finzi , A , Carrara , S , González , J R , Llanos , J M , Heikkila , I , Peñalba , F & Gómez , X 2007 , ' A hybrid approach to the development of a multilayer neural network for wear and fatigue prediction in metal forming ' , Tribology International , vol. 40 , no. 10-12 SPEC. ISS. , pp. 1705-1717 . https://doi.org/10.1016/j.triboint.2007.01.008
NO The authors of this paper gratefully thank the European Coal and Steel Community (ECSC) for the support of this work as part of research project number RFS-CR-03044. The work is funded in part by the Commission of the European Communities on behalf of the ECSC with a financial grant from the RFCS.
DS TECNALIA Publications
RD 28 jul 2024