• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.6
• /
• pp.106-118
• /
• 1998

The study concerns a design procedure of rule-based systems. The proposed rule-based fuzzy modeling implements system structure and parameter identification in the efficient from of "IF..., THEN..." statements, and exploits the theory of system optimization and fuzzy implication rules. The method for rule-based fuzzy modeling concerns the from of the conclusion part of the the rules that can be constant. Both triangular and Gaussian-like membership function are studied. The optimization hinges on an autotuning algorithm that covers as a modified constrained optimization method known as a complex method. The study introduces a weighted performance index (objective function) that helps achieve a sound balance between the quality of results produced for the training and testing set. This methodology sheds light on the role and impact of different parameters of the model on its performance. The study is illustrated with the aid of two representative numerical examples.

• Journal of Korean Institute of Industrial Engineers
• /
• v.16 no.2
• /
• pp.109-117
• /
• 1990

In this paper we study a mathematical programming model for the single-card KANBAN system in a multi-stage capacitated general-type-structure production. Until now this production type setting has not been studied. The modeling of this problem results in a complex integer programming which can be modified to the more simple integer programming model. We present a heuristic method and some numerical examples. Though the presented method doesn't always find an optimal solution, this method guarantees to find a feasible solution. We expect this work to be practised in the real fields.

• International Journal of Control, Automation, and Systems
• /
• v.5 no.1
• /
• pp.79-85
• /
• 2007

In this paper, a real-coded genetic algorithm is proposed for identification of time delay systems from step responses. FOPDT(First-Order Plus Dead-Time) and SOPDT(Second-Order Plus Dead-Time) systems, which are the most useful processes in this field, but are difficult for system identification because of a long dead-time problem and a model mismatch problem. Genetic algorithms have been successfully applied to a variety of complex optimization problems where other techniques have often failed. Thus, the modified crossover operator of a real-code genetic algorithm is proposed to effectively search the system parameters. The proposed method, using a real-coding genetic algorithm, shows better performance characteristics when compared to the usual area-based identification method and the directed identification method that uses step responses.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.22 no.2
• /
• pp.115-123
• /
• 2018

This paper discusses extended Kalman filter method for solving learning problems of multilayered neural networks. A lot of learning algorithms for deep layered network are sincerely suffered from complex computation and slow convergence because of a very large number of free parameters. We consider an efficient learning algorithm for deep neural network. Extended Kalman filter method is applied to parameter estimation of neural network to improve convergence and computation complexity. We discuss how an efficient algorithm should be developed for neural network learning by using Extended Kalman filter.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2006.05a
• /
• pp.43-46
• /
• 2006

In this study on the appliable Asphalt sheet of monolithic and inorganic matter waterproofing material using of field because of problem of complex waterproofing sheet. Before this cement polymer modified waterproof coating and appliable asphalt sheet of monolithic whether have stability by method of construction about all style waterproofing that evaluate to new method of construction development naturally big emphasis put and try to approach. Did performance test item first at, as a result, drew by suitable thing in all KS items. This is considered to have more effective spot construction work because if means that have stability by material as well as method of construction.

• 한국전산유체공학회:학술대회논문집
• /
• 1999.05a
• /
• pp.66-72
• /
• 1999

A numerical simulation method has been under development for solving turbulent flows around a ship model in maneuvering motion using the Reynolds Averaged Navier-Stokes equations. The method used second-order finite differences, collocated grids, pressure-Poisson equation and four-stage Runge-Kutta scheme as key components of the solution method. A modified Baldwin-Lomax model is used for the turbulence closure. This paper presents a preliminary result of the computational study on turbulent flows past a ship model in drift motion. Calculations are carried out for a Series 60 $C_B=0.6$ ship model, for which detailed experimental data are available. The results of the present calculations are compared with the experimental data for hydrodynamic forces acting on the model as well as velocity distributions at longitudinal sections. Only fair agreements has been achieved. The computational results show the complex asymmetrical shear flow patterns including three-dimensional separations followed by formation of bilge vortices both in bow and stern regions.

• KIEE International Transactions on Power Engineering
• /
• v.5A no.1
• /
• pp.40-45
• /
• 2005

Substation facilities have become extremely large and complex parts of electric power systems. The development of condition monitoring and diagnosis techniques has been a very significant factor in the improvement of substation transformer security. This paper presents a method to analyze the cause, the degree, and the aging process power transformers by the Self Organizing Map (SOM) method. Dissolved gas data were non-linearly transformed by the sigmoid function in SOM that works much the same way as the human decision making process. The potential for failure and the degree of aging of normal transformers are identified by using the proposed quantitative criterion. Furthermore, transformer aging is monitored by the proposed criterion for a set of transformers. To demonstrate the validity of the proposed method, a case study is performed and its results are presented.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.49 no.7
• /
• pp.378-388
• /
• 2000

In this paper, we propose Fuzzy Polynomial Neural Networks(FPNN) based on Polynomial Neural Networks(PNN) and Fuzzy Neural Networks(FNN) for model identification of complex and nonlinear systems. The proposed FPNN is generated from the mutually combined structure of both FNN and PNN. The one and the other are considered as the premise part and consequence part of FPNN structure respectively. As the consequence part of FPNN, PNN is based on Group Method of Data Handling(GMDH) method and its structure is similar to Neural Networks. But the structure of PNN is not fixed like in conventional Neural Networks and self-organizing networks that can be generated. FPNN is available effectively for multi-input variables and high-order polynomial according to the combination of FNN with PNN. Accordingly it is possible to consider the nonlinearity characteristics of process and to get better output performance with superb predictive ability. As the premise part of FPNN, FNN uses both the simplified fuzzy inference as fuzzy inference method and error back-propagation algorithm as learning rule. The parameters such as parameters of membership functions, learning rates and momentum coefficients are adjusted using genetic algorithms. And we use two kinds of FNN structure according to the division method of fuzzy space of input variables. One is basic FNN structure and uses fuzzy input space divided by each separated input variable, the other is modified FNN structure and uses fuzzy input space divided by mutually combined input variables. In order to evaluate the performance of proposed models, we use the nonlinear function and traffic route choice process. The results show that the proposed FPNN can produce the model with higher accuracy and more robustness than any other method presented previously. And also performance index related to the approximation and prediction capabilities of model is evaluated and discussed.

• Polymer(Korea)
• /
• v.38 no.2
• /
• pp.232-239
• /
• 2014

Poly(lactic acid)(PLA) nanocomposites containing various nanofillers were synthesized using the solution intercalation method. Organically modified bentonite clay (NSE), octadecylamine-graphene oxide (ODA-GO), and an NSE/ODA-GO complex were utilized as nanofillers in the fabrication of PLA hybrid films. PLA hybrid films with varying nanofiller contents in the range of 0-10 wt% were examined and compared in terms of their thermomechanical properties, morphologies, and oxygen permeabilities. Transmission electron microscopy (TEM) confirmed that most of the NSE and ODA-GO nanofillers were dispersed homogeneously throughout the PLA matrix on the nanoscale, although some agglomerate NSE/ODA-GO complex particles were also formed. Among the three nanofillers for PLA hybrid films, the NSE/ODA-GO complex showed the best improvement in film thermal stability. In contrast, NSE and ODA-GO exhibited the best improvement in tensile mechanical properties and oxygen barrier properties of the PLA hybrid films, respectively.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.2
• /
• pp.126-135
• /
• 2002

The study is concerned with an approach to the design of new architectures of fuzzy neural networks and the discussion of comprehensive design methodology supporting their development. We propose an Adaptive Fuzzy Polynomial Neural Networks(APFNN) based on Fuzzy Neural Networks(FNN) and Self-organizing Networks(SON) for model identification of complex and nonlinear systems. The proposed AFPNN is generated from the mutually combined structure of both FNN and SON. The one and the other are considered as the premise and the consequence part of AFPNN, respectively. As the premise structure of AFPNN, FNN uses both the simplified fuzzy inference and error back-propagation teaming rule. The parameters of FNN are refined(optimized) using genetic algorithms(GAs). As the consequence structure of AFPNN, SON is realized by a polynomial type of mapping(linear, quadratic and modified quadratic) between input and output variables. In this study, we introduce two kinds of AFPNN architectures, namely the basic and the modified one. The basic and the modified architectures depend on the number of input variables and the order of polynomial in each layer of consequence structure. Owing to the specific features of two combined architectures, it is possible to consider the nonlinear characteristics of process system and to obtain the better output performance with superb predictive ability. The availability and feasibility of the AFPNN are discussed and illustrated with the aid of two representative numerical examples. The results show that the proposed AFPNN can produce the model with higher accuracy and predictive ability than any other method presented previously.