• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1995.10b
• /
• pp.249-257
• /
• 1995

In this paper, we demeonstrate that neural networks can be used effectively for the control of nonlinear dynamical system. To adaptively control a plant, there are two distinct approach. these are direct control and indirect control. Both direct and Indirect adaptive control are trained using static back propagation. In indirect, using the resulting identification model, which contains neural networks and linear dynamical elements as subsystems, the parameters of the controller are adjusted.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.2
• /
• pp.265-273
• /
• 2016

A water wall system is one of the most important components of a boiler in a thermal power plant, and it is a nonlinear Multi-Input and Multi-Output (MIMO) system, with 6 inputs and 3 outputs. Three models are developed and comp for the controller design, including a linear model, a multilayer feed-forward neural network (MFNN) model and an Echo State Network (ESN) model. First, the linear model is developed by linearizing a given nonlinear model and is analyzed as a function of the operating point. Second, the MFNN and the ESN are developed by using training data from the nonlinear model. The three models are validated using Matlab with nonlinear input-output data that was not used during training.

• Proceedings of the KIEE Conference
• /
• 1993.11a
• /
• pp.326-328
• /
• 1993

Modelling theory, based on differential equations, is not an adequate tool for solving the problems of complex system. Identification of complex system using GMDH(group method of data handling) is more appropriate for this problems. In this paper, GMDH algorithm is used to identify the nonlinear plant and to design model following nonlinear control system. Simulation for the DC motor show the good performance of model following nonlinear control system.

• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.2
• /
• pp.189-199
• /
• 1999

This paper presents an optimization algorithm for a stable Self Dynamic Neural Network(SDNN) using genetic algorithm. Optimized SDNN is applied to a problem of controlling nonlinear dynamical systems. SDNN is dynamic mapping and is better suited for dynamical systems than static forward neural network. The real-time implementation is very important, and thus the neuro controller also needs to be designed such that it converges with a relatively small number of training cycles. SDW has considerably fewer weights than DNN. Since there is no interlink among the hidden layer. The object of proposed algorithm is that the number of self dynamic neuron node and the gradient of activation functions are simultaneously optimized by genetic algorithms. To guarantee convergence, an analytic method based on the Lyapunov function is used to find a stable learning for the SDNN. The ability and effectiveness of identifying and controlling a nonlinear dynamic system using the proposed optimized SDNN considering stability is demonstrated by case studies.

• Journal of KSNVE
• /
• v.8 no.5
• /
• pp.887-899
• /
• 1998

It has been resulted that Lagrange multiplier method with statistical approach was superior to traditional harmonic balance method in identifying the nonlinear loudspeaker parameters when output signals were contaminated with Gaussian random noise. We have known that the displacement-dependent characteristic values of nonlinear parameters identified by traditional harmonic balance method were estimated less than original values by the increase of output noise and the stiffness coefficients were very sensitive to output noise. Also, by the sensitivity analysis we have verified that the harmonic distortions in acoustic radiation was mainly due to nonlinearity of force factor caused by uneven magnetic fields and that reducing the nonlinearity of damping coefficients were very effective for improving second harmonic distrotion of acoustic radiation.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.11a
• /
• pp.185-188
• /
• 1997

In this paper, we execute identification, linearization, and control of a nonlinear system using recurrent neural networks. In general nonlinear control system become complex because of nonlinearity and uncertainty. And though we compose nonlinear control system based on the model, it is difficult to get good control ability. So we identify the nonlinear control system using the recurrent neural networks and execute feedback linearization of identified model, In this process we choose the optional linear system, and the system which will have to be feedback linearized if trained to follow the linearity between input and output of the system we choose. We the feedback linearized system by applying standard linear control strategy and simulation. And we evaluate the effectiveness by comparing the result which is linearized theoretically.

• Proceedings of the KIEE Conference
• /
• 1998.11b
• /
• pp.537-539
• /
• 1998

In this paper, we construct the on-line model structure for the nonlinear process systems using the adaptive fuzzy-neural network. Adaptive fuzzy-neural network usually consists of two distinct modifiable structure, with both, the premise and the consequent part. These two parts can be adapted by different optimization methods, which are the hybrid learning procedure combining gradient descent method and least square method. To achieve the on-line model structure, we use the recursive least square method for the consequent parameter identification of nonlinear process. We design the interface between PLC and main computer, and construct the monitoring and control simulator for the nonlinear process. The proposed on-line modeling to real process is carried out to obtain the effective and accurate results.

• Proceedings of the KIEE Conference
• /
• 2004.05a
• /
• pp.22-25
• /
• 2004

In active noise control (ANC) system, the convergence behavior of the Filtered- X Least Mean Square (FXLMS) algorithm may be affected by nonlinear distortion in the secondary path as in the power amplifiers (e.g., saturation), loudspeakers and transducers. This distortion may yields degrading the error reduction performance of the ANC systems. In this paper, the authors of this paper propose a more improved and stable FXLMS algorithm to compensate for the undesirable nonlinearity of the secondary-path, whereby the third-order Volterra model was employed for the identification of the nonlinear secondary-path. In particular, the proposed approach was based on the modification of the conventional FXLMS algorithm. Finally, the simulation results showed that the proposed approach yields better convergence property and more stable performance in the ANC systems.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.329-332
• /
• 1997

This paper deals with the attitude control problem of nonlinear MIMO propeller setup. Multivariable GPC[Generalized Predictive Control] is adopted as the main controller, and it is implemented by TMS320C31 in the current paper. The main object of control is to move the propellers to wanted positions. System identification is performed to configure the system. Performance of the multivariable predictive controller implemented is shown via some experiments, which shows the controller meets the adequate control purpose.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.299-303
• /
• 1995

This paper charcterizes dynamics of cold tandem minns, and constructs it state-space model of which are linear time invariant, using subspace method. Step responses particularly show the influence on mass transfer delay. Input-output data set are obtained form nonlinear differential equations including mass transfer delay and nonlinearity. It is shown that the identified state-apace model well approximates the original systems dynamics.