• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1377-1379
• /
• 1996

In this paper, each parameter was identified by the gradient descent method to overcome difficulty deciding fuzzy rules of FLC for the unknown process and the type of membership Junctions. Usually PID or optimal control theories have been mostly usee in control field so far. However, optimal control requires much time for calculation because of adaptation for disturbance and nonlinearity. And intricate technique such as MRAS which can be realized only by an expert are limited to be used in the systems requiring rapid and precise response because of comparatively longer calculating time and complicateness. Gradient descent method is a method to find Z minimizing a function about a certain vector Z. And required output of FLC is gained using gradient approaching method in order to adapt control rule parameters of FLC. Simulation proved validation of this algorithm.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.1982-1983
• /
• 2007

In this work, the $TiO_2$ pigment influence in HDPE dielectric strength was analyzed. Chemical and structural characterizations were made to identify changes during the processing and your influence in the electrical properties. Formulations containing 0, 0.5, 1, 2.5, 4 and 6 of titanium dioxide were processed by extrusion and injection molding with stabilization-antioxidants, ultraviolet stabilizers and plasticizers. The electrical strength tests were analyzed by the statistical distribution of Weibull, and the maximum likelihood method. The high concentrations present lower values to electrical strength. The ${\beta}$ parameter could be using to insulator particles dispersion. The TiO2 concentration variation shows that these incorporations implicate strength values increase has a maximum (5,35MV/cm). High pigment concentration induces a little falls in property values. Observing the ${\beta}$ parameter, minimum experiment electric field (Ebmin) and electric strength value, found that the best electric perform formulation was the formulation with 2.5% TiO2 weight.

• Proceedings of the KIEE Conference
• /
• 1990.11a
• /
• pp.407-412
• /
• 1990

This note presents a novel algorithm for a continuous-time direct adaptive pole placement control for single-input single-out nonminimum phase systems. Although the resulting overall closed-loop system is locally stable, assumptions about parameter convergence or the nature of the external input are not considered.

• Proceedings of the KIEE Conference
• /
• 1989.11a
• /
• pp.397-400
• /
• 1989

This study is to design a method of parameter estimation for a second order linear time invarient system of self-tuning controller utilizing the neural network theory proposed by Hopfield. The result is compared with the other methods which are commonly used in controller theories.

• Proceedings of the KIEE Conference
• /
• 1999.11b
• /
• pp.15-17
• /
• 1999

This paper proposes that optimal design using GA of BLDC motor. To estimate this optimal design method, the performance characteristics of BLDC motor is computed by the equivalent magnetic circuit network method and FEM. To estimate especially the dynamic characteristics of BLDC, we compute the parameter of electrical circuit using FEM.

• Proceedings of the KIEE Conference
• /
• 1983.07a
• /
• pp.154-155
• /
• 1983

• Proceedings of the KIEE Conference
• /
• 1983.07a
• /
• pp.126-129
• /
• 1983

• Journal of Power Electronics
• /
• v.17 no.2
• /
• pp.398-410
• /
• 2017

This work presents the design of a dual extended Kalman filter (EKF) as a state/parameter estimator suitable for adaptive state-of-charge (SoC) estimation of an automotive lithium-iron-phosphate ($LiFePO_4$) cell. The design of both estimators is based on an experimentally identified, lumped-parameter equivalent battery electrical circuit model. In the proposed estimation scheme, the parameter estimator has been used to adapt the SoC EKF-based estimator, which may be sensitive to nonlinear map errors of battery parameters. A suitable weighting scheme has also been proposed to achieve a smooth transition between the parameter estimator-based adaptation and internal model within the SoC estimator. The effectiveness of the proposed SoC and parameter estimators, as well as the combined dual estimator, has been verified through computer simulations on the developed battery model subject to New European Driving Cycle (NEDC) related operating regimes.

• Journal of IKEEE
• /
• v.22 no.1
• /
• pp.14-20
• /
• 2018

The purpose of training a convolutional neural network (CNN) is to obtain weight factors that give high classification accuracies. The initial values of hyper-parameters affect the training results, and it is important to train a CNN with a suitable hyper-parameter set of a learning rate, a batch size, the initialization of weight factors, and an optimizer. We investigate the effects of a single hyper-parameter while others are fixed in order to obtain a hyper-parameter set that gives higher classification accuracies and requires shorter training time using a proposed VGG-like CNN for training since the VGG is widely used. The CNN is trained for four datasets of CIFAR10, CIFAR100, GTSRB and DSDL-DB. The effects of the normalization and the data transformation for datasets are also investigated, and a training scheme using merged datasets is proposed.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2513-2515
• /
• 2005

Recently genetic algorithm techniques have widely used in adaptive and control schemes for production systems. However, generally it costs a lot of time for leaming in the case applied in control system. Furthermore, the physical meaning of genetic algorithm constructed as a result is not obvious. And this method has been used as a learning algorithm to estimate the parameter of a genetic algorithm used for identification of the process dynamics of Butter-Worth analog filter and it was shown that this method offered superior capability over the genetic algorithm. A genetic algorithm is used to solve the parameter identification problem for linear and nonlinear digital filters. This paper goal estimate Butter-Worth analog filter parameter using the genetic algorithm.