Akademik Veri Yönetim Sistemi
PAMUKKALE UNIVERSITY JOURNAL OF ENGINEERING SCIENCES-PAMUKKALE UNIVERSITESI MUHENDISLIK BILIMLERI DERGISI, sa.3, ss.387-395, 2007 (ESCI)
In this study, testing and training data sets of Artificial Neural Networks(ANNs) models have been produced by employing analytical design calculations of cylindrical spur gears. In the input layer, the constraints and requirement values of cylindrical spur gears are used while at the output layer the modules (e.g. the bending and contact stress) and the number of tooths are used. These data have been presented to train a multi layered, single directed, hierarchically connected ANNs using Scaled Conjugate Gradient (SCG) and Levenberg-Marquardt (LM) Back Propagation algorithms with the logistic sigmoid transfer function. The outcomes demonstrated that, the ANN based model have been very successful and the testing data produced very low level of errors. It has been shown that, the ANN based mechanism may be used in the design of cylindrical spur gears instead of analytical calculations.