Prediction of Target Displacement of Steel Moment Frames Using Artificial Neural Networks

In this paper, the application of artificial neural network (ANN) in predicting seismic response of steel moment frames is investigated. The objective of this research is to predict roof displacement and base shear (ANN outputs) in the target displacement. The total of 460 database were prepared for modeling neural network using finite element method (FEM) by changing six parameters (the input parameters of ANN) including the number of bays, the number of stories, bays width, inertia moment of beams, cross section area of columns and design spectral acceleration. A training set of 276 prepared database were used as training data and the validation set of 184 database were used as validation data in the next step. In the present study, two ANNs were trained; a multilayer perseptron (MLP) with Levenberg–Marquardt (LM) back propagation algorithms and a Radial Basis function (RBF), both with different structures and the best structure for each of them was obtained. The performance of ANNs was evaluated using mean square error (MSE) and correlation coefficient (R2) criteria. Results indicate that using both MLP and RBF ANNs for predicting target displacement have been appropriate and have low error as well as high speed. Furthermore, RBF network has a higher speed in training process of data compared to MLP network.

Keywords:

Steel moment frame , RBF , LM , Neural network , Target displacement