Multilayer feedforward networks are universal approximators
Neural Networks
Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
Fuzzy and Neural Approaches in Engineering
Fuzzy and Neural Approaches in Engineering
A general regression neural network
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
A comprehensive laboratory work relating impact damping phenomenon of a flexible beam was carried out by Butt and Akl [Butt AS, Akl FA. Experimental analysis of impact-damped flexible beams. J Eng Mech ASCE 1997;123(4):376-83] to investigate the relation between system's modal damping ratio (@z) and system parameters, namely gap (c,mm), mass (m,kg), modal amplitude (@F"d), frequency (f,Hz), and peak value of the imaginary part of the frequency response functions (F"I). Using a multiple nonlinear regression technique (MNLR), they established a relation between these system parameters and the resulting damping ratio, based on 60 steady-state vibration tests of a flexible beam. In current work, three different artificial neural network approaches (ANNs), namely FFBP (Feed-Forward Back Propagation), RBNN (Radial Basis Function Based Neural Network), and GRNN (Generalized Regression Neural Networks), for estimating modal damping ratio (@z) were developed using the data collected by Butt and Akl (1997) and compared with MNLR. The results showed that the RBNN produced slightly better estimations than those of the FFBP and was significantly superior to the MNLR and GRNN.