General Approach for Training Back-Propagation Neural Networks in Vibration Control of Multidegree-of-Freedom Structures

Abstract

A general approach is proposed for back-propagation training of multilayer feed-forward (MLFF) neural networks for active control of earthquake-induced vibrations in multidegree-of-freedom structures. The training functions for adjustment of connection weights of the neural network controller are formulated in the proposed approach by minimizing a general cost function using the steepest gradient descent scheme. The proposed method can be applied for training an MLFF neural network controller in vibration control of building structures both in the pattern (online) and batch (off-line) mode. The method can be implemented in structural control systems with more than one control action. Case studies are presented to demonstrate the feasibility of implementing the training approach for effective vibration control of structures subjected to earthquake ground motions.