S F Masri et al 1992 Smart Mater. Struct. 1 45 doi:10.1088/0964-1726/1/1/007
S F Masri, A G Chassiakos and T K Caughey
Show affiliationsExplores the potential of using parallel distributed processing (neural network) approaches to identify the internal forces of structure-unknown non-linear dynamic systems typically encountered in the field of applied mechanics. The relevant characteristics of neural networks, such as the processing elements, network topology, and learning algorithms, are discussed in the context of system identification. The analogy of the neural network procedure to a qualitatively similar non-parametric identification approach, which was previously developed by the authors for handling arbitrary non-linear systems, is discussed. The utility of the neural network approach is demonstrated by application to several illustrative problems.
07.05.Mh Neural networks, fuzzy logic, artificial intelligence
Issue 1 (March 1992)
S F Masri et al 1992 Smart Mater. Struct. 1 45
L Robertsson et al 2001 Metrologia 38 567
P Ellicott and D J Toms 1989 Class. Quantum Grav. 6 1033
S D Odintsov and I L Shapiro 1992 Class. Quantum Grav. 9 873
A ten Bosch and K H Bennemann 1975 J. Phys. F: Met. Phys. 5 1333
D Griffiths 1970 J. Phys. E: Sci. Instrum. 3 243
Winfried K Hensinger et al 2003 J. Opt. B: Quantum Semiclass. Opt. 5 R83
D Rayner 1990 Class. Quantum Grav. 7 111
Maarten R Wegewijs et al 2007 New J. Phys. 9 344
Y Ohno et al 2000 Metrologia 37 583