摘要(英) |
Taiwan is a
high seismic zone since it is located at the active arc-continent
collision region between the Luzon arc of the Philippine Sea plate and
the Eurasian plate. The Chi-Chi Earthquake is the largest inland
earthquake occurred in Taiwan during this century. Due to the great
damage caused by this earthquake, more and more emphases have been put
on the earthquake resistant design of buildings. Dynamic behavior of
buildings under earthquakes should be considered in the process of
design. In order to realize the dynamic behavior of structural systems
subjected to earthquakes, we can determine dynamic models and parameters
through various system identification techniques. In this study, it is
intended to develop new identification techniques by combining the
advantages of both neural network (NN) and genetic algorithm
(GA). Firstly, the time history of the ground acceleration and
the system parameters of a variety of SDOF systems are used as the input
data of neural network, and the time history of the relative
acceleration of the respective SDOF systems as the neural network
outputs. After the training of the neural network, the network topology
used to evaluate the time history of the relative acceleration of the
SDOF systems will be captured. This network topology is then employed to
replace the procedure for solving the governing (differential) equation
when GA is used to identify the system parameters. Furthermore, this
topology is used in the identification of the MDOF system subjected to
the single input by mode superposition technique. On the other
hand, the starting weights of NN are randomly selected and the
optimization algorithm used in the training of NN may get stuck in the
local minimal. GA is a search method based on natural selection and
genetics and is different from conventional optimization methods in
several ways. The GA is a parallel and global search technique that
searches multiple points, so it is more likely to obtain a global
solution. In this regard, a new algorithm of combining GA and NN is
proposed here. The GA is employed to search for the starting
weights and the NN is used to obtain the network topology. Through the
iterative process of selection, reproduction, cross over and mutation,
the optimal weight can then be obtained. This proposed algorithm is
applied to the Duffing oscillator and Wen’s degrading nonlinear systems.
Finally, the accuracy of this method is illustrated by comparing the
results of the predicted response with the measured one. |