http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Neuro-Generalized Minimum Variance Controller Applied To Earthquake Engineering Problems
L. GUENFAF,M. DJEBIRI 제어로봇시스템학회 2011 제어로봇시스템학회 국제학술대회 논문집 Vol.2011 No.10
This paper presents a neural network-based control method applied to civil engineering structures. The neural network learns the control task from an already existing controller, which is the generalized minimum variance (GMV) controller. The objective is to take advantage of the generalization capabilities and the nonlinear behavior of neural networks in order to overcome the limitations of the existing controller and even to improve its performances. Simulation results demonstrate the effectiveness of the neural network controller and its capability to compensate for structural parameter variations.
Gain Scheduling GMV using Gaussian Function for Nonlinear hysteretic Structural Systems
L. GUENFAF,S. ALLAOUA,M. DJEBIRI,M.S. BOUCHERIT,F. BOUDJEMA 제어로봇시스템학회 2012 제어로봇시스템학회 국제학술대회 논문집 Vol.2012 No.10
In this paper, a generalized minimum variance algorithm using the gain scheduling technique is presented. First, we linearize the nonlinear model of the structure around a number of desired states representing regions of evolution of the structural response. Around each state, an Auto-Regressive-Moving-Average-eXogen (ARMAX) model of the structure is determined and a local GMV control law is developed. The control consists on switching-on or switching-off a local GMV controller depending on the actual state of the system. The approach consists on using gaussian membership functions related to the domains around the points of linearization. The control from the local GMV controllers is weighed by these functions and added together to produce the final control.