Atıf İçin Kopyala
Yildirim A., Akay A. A., Gülasik H., Çöker D., Gürses E., Kayran A.
Journal of Pressure Vessel Technology, Transactions of the ASME, cilt.141, 2019 (SCI-Expanded)
Özet
Finite element analysis (FEA) of bolted flange connections is the common methodology
for the analysis of bolted flange connections. However, it requires high computational
power for model preparation and nonlinear analysis due to contact definitions used
between the mating parts. Design of an optimum bolted flange connection requires many
costly finite element analyses to be performed to decide on the optimum bolt
configuration and minimum flange and casing thicknesses. In this study, very fast
responding and accurate artificial neural network-based bolted flange design tool is
developed. Artificial neural network is established using the database which is generated
by the results of more than 10,000 nonlinear finite element analyses of the bolted flange
connection of a typical aircraft engine. The FEA database is created by taking permuta-
tions of the parametric geometric design variables of the bolted flange connection and
input load parameters. In order to decrease the number of FEA points, the significance of
each design variable is evaluated by performing a parameter correlation study before-
hand, and the number of design points between the lower and upper and bounds of the
design variables is decided accordingly. The prediction of the artificial neural network
based design tool is then compared with the FEA results. The results show excellent
agreement between the artificial neural network-based design tool and the nonlinear
FEA results within the training limits of the artificial neural network.