• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 추계 학술대회 학술발표 논문집
• /
• pp.95-98
• /
• 2003

In this paper, an adaptive fuzzy neural control of unknown nonlinear systems based on the rapid learning algorithm is proposed for optimal parameterization. We combine the advantages of fuzzy control and neural network techniques to develop an adaptive fuzzy control system for updating nonlinear parameters of controller. The Fuzzy Neural Network(FNN), which is constructed by an equivalent four-layer connectionist network, is able to learn to control a process by updating the membership functions. The free parameters of the AFN controller are adjusted on-line according to the control law and adaptive law for the purpose of controlling the plant track a given trajectory and it's initial values are off-line preprocessing, In order to improve the convergence of the learning process, we propose a rapid learning algorithm which combines the error back-propagation algorithm with Aitken's $\delta$$\^$2/ algorithm. The heart of this approach ls to reduce the computational burden during the FNN learning process and to improve convergence speed. The simulation results for nonlinear plant demonstrate the control effectiveness of the proposed system for optimal parameterization.

• Wind and Structures
• /
• 제20권3호
• /
• pp.423-448
• /
• 2015

In this paper the unsteady fluid-structure interaction (FSI) problems with large structural displacement are solved by partitioned solution approaches in the arbitrary Lagrangian-Eulerian finite element framework. The incompressible Navier-Stokes equations are solved by the characteristic-based split (CBS) scheme. Both a rigid body and a geometrically nonlinear solid are considered as the structural models. The latter is solved by Newton-Raphson procedure. The equation governing the structural motion is advanced by Newmark-${\beta}$ method in time. The dynamic mesh is updated by using moving submesh approach that cooperates with the ortho-semi-torsional spring analogy method. A mass source term (MST) is introduced into the CBS scheme to satisfy geometric conservation law. Three partitioned coupling strategies are developed to take FSI into account, involving the explicit, implicit and semi-implicit schemes. The semi-implicit scheme is a mixture of the explicit and implicit coupling schemes due to the fluid projection splitting. In this scheme MST is renewed for interfacial elements. Fixed-point algorithm with Aitken's ${\Delta}^2$ method is carried out to couple different solvers within the implicit and semi-implicit schemes. Flow-induced vibrations of a bridge deck and a flexible cantilever behind an obstacle are analyzed to test the performance of the proposed methods. The overall numerical results agree well with the existing data, demonstrating the validity and applicability of the present approaches.