• 한국정밀공학회지
• /
• 제12권5호
• /
• pp.157-165
• /
• 1995

In this paper the comparison between the neural networks and traditional approaches as nonlinear system identification methods are considered. Two model structures of neural networks are the state space model and the input output model neural networks. The traditional methods are the AutoRegressive eXogeneous Input model and the Nonlinear AutoRegressive eXogeneous Input model. Computer simulation for an analytic dynamic model of a single input single output nonlinear system has been done for all the chosen models. Model validation for the obtained models also has been done with testing inputs of the sinusoidal, ramp and the noise ramp.

• Smart Structures and Systems
• /
• 제4권3호
• /
• pp.319-342
• /
• 2008

Identification of the nonlinear hysteretic behavior of a reinforced concrete (RC) bridge pier subjected to earthquake loads is carried out based on acceleration measurements of the earthquake motion and bridge responses. The modified Takeda model is used to describe the hysteretic behavior of the RC pier with a small number of parameters, in which the nonlinear behavior is described in logical forms rather than analytical expressions. Hence, the modified extended Kalman filter is employed to construct the state transition matrix using a finite difference scheme. The sequential modified extended Kalman filter algorithm is proposed to identify the unknown parameters and the state vector separately in two steps, so that the size of the problem for each identification procedure may be reduced and possible numerical problems may be avoided. Mode superposition with a modal sorting technique is also proposed to reduce the size of the identification problem for the nonlinear dynamic system with multi-degrees of freedom. Example analysis is carried out for a continuous bridge with a RC pier subjected to earthquake loads in the longitudinal and transverse directions.

• 한국조명전기설비학회지:조명전기설비
• /
• 제9권6호
• /
• pp.71-77
• /
• 1995

This paper deals with design method of learning fuzzy controller for control of an unknown nonlinear plant using the self-tuning algorithm of fuzzy inference rules. In this method the fuzzy identification model obtained that the joined identification model of nonlinear part and linear identification model of linear part by fuzzy inference systems. This fuzzy identification model ordered self-tuning by Decent method so as to be servile to nonlinear plant. A the end, designed learning fuzzy controller of fuzzy identification model have learning structure to model reference adaptive system. The simulation results show that th suggested identification and learning control schemes are practically feasible and effective.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 하계종합학술대회논문집
• /
• pp.917-920
• /
• 1998

In this paper, we propose a modified elman neural network structure for nonlinear system identification. The proposed structure is that all of network output feed back into hidden units and output units. Learning algorithm is standard back-propagation algorithm. The simulation showed the effectiveness of using the modified elman neural network structure in the nonlinear system identification.

• 전기의세계
• /
• 제29권11호
• /
• pp.742-750
• /
• 1980

The problem of nonlinear time-invariant system identification by estimation of Wiener kernels is studied for discrete time systems with inputs having symmetric probability distributions. G-functionals are constructed. It is further shown that under idealized conditions, these seemingly different techniques yield the same results. The results of identification of asimulated second degree system is presented.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.899-902
• /
• 1993

A neural model predictive control strategy combining a neural network for plant identification and a nonlinear programming algorithm for solving nonlinear control problems is proposed. A constrained nonlinear optimization approach using successive quadratic programming combined with neural identification network is used to generate the optimum control law for complex continuous chemical reactor systems that have inherent nonlinear dynamics. The neural model predictive controller (MNPC) shows good performances and robustness. To whom all correspondence should be addressed.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1992년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 19-21 Oct. 1992
• /
• pp.236-242
• /
• 1992

Multi-layered neural networks are applied to the identification and control of nonlinear dynamical system. Traditional adaptive control techniques can only deal with linear systems or some special nonlinear systems. A scheme for combining multi-layered neural networks with model reference network techniques has the capability to learn the nonlinearity and shows the great potential for adaptive control. In many interesting cases the system can be described by a nonlinear model in which the control input appears linearly. In this paper the identification of linear and nonlinear part are performed simultaneously. The projection algorithm and the new estimation method which uses the delta rule of neural network are compared throughout the simulation. The simulation results show that the identification and adaptive control schemes suggested are practically feasible and effective.

• Structural Engineering and Mechanics
• /
• 제76권1호
• /
• pp.101-114
• /
• 2020

In this paper, an improved experience-based learning algorithm (EBL), termed as IEBL, is proposed to solve the nonlinear hysteretic parameter identification problem with Bouc-Wen model. A quasi-opposition-based learning mechanism and new updating equations are introduced to improve both the exploration and exploitation abilities of the algorithm. Numerical studies on a single-degree-of-freedom system without/with viscous damping are conducted to investigate the efficiency and robustness of the proposed algorithm. A laboratory test of seven lead-filled steel tube dampers is presented and their hysteretic parameters are also successfully identified with normalized mean square error values less than 2.97%. Both numerical and laboratory results confirm that, in comparison with EBL, CMFOA, SSA, and Jaya, the IEBL is superior in nonlinear hysteretic parameter identification in terms of convergence and accuracy even under measurement noise.

• 한국자동차공학회논문집
• /
• 제11권4호
• /
• pp.158-164
• /
• 2003

The suspension system of cars is composed of dampers and springs, which usually have nonlinear characteristics. The nonlinear characteristics make the differences in the results of analytical models and experiments. In this study, the nonlinear system identification method which does not assume a special form for nonlinear dynamic systems and minimize the error by calculating the error reduction ratio is devised to estimate the nonlinear parameters of the suspension system of an EF-SONATA car from the field running test data. The results show that the spring has a cubic nonlinear term and the damper has a coupled nonlinear term. Also, the numerical results with the estimated nonlinear parameters agree well with the field test data for the different running speeds.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 Proceedings of the Korea Automatic Control Conference, 11th (KACC); Pohang, Korea; 24-26 Oct. 1996
• /
• pp.36-39
• /
• 1996

This paper proposes identification and control algorithm of nonlinear systems and the proposed fuzzy-neural network has following characteristics. The network is roughly divided into premise and consequence. The consequence function is nonlinear function which consists of three parameters and the membership function in the premise contains of two parameters. The parameters in premise and consequence are learned by the extended back-propagation algorithm which has a modified form of the generalized delta rule. Simulation results on the identification show that this method is more effective than that of Narendra [3]. The indirect fuzzy-neural control is made of the fuzzy-neural identification and controller. Result on the indirect fuzzy-neural control shows that the proposed fuzzy-neural network can be efficiently applied to nonlinear systems.