• Journal of the Korean Society of Propulsion Engineers
• /
• v.8 no.3
• /
• pp.44-52
• /
• 2004

In this study, a component map generation method using experimental data and the genetic algorithms are newly proposed. In order to generate the performance map for components of this engine, after obtaining engine performance data through many experimental tests, and then the third order equations which have relationships the mass flow function the pressure ratio and the isentropic efficiency as to the engine rotational speed were derived by using the genetic algorithms. A steady-state performance analysis was performed with the generated maps of the compressor by the commercial gas turbine performance analysis program GASTURB. In comparison, it was found that the component maps can be generated from the experimental test data by using the genetic algorithms, and it was confirmed that the analysis results using the generated maps were very similar to those using the scaled maps from the GASTURB.

• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.120-122
• /
• 2006

The paper concerns the hybrid optimization of fuzzy inference systems that is based on Hierarchical Fair Competition-based Parallel Genetic Algorithms (HFCGA) and information data granulation. The granulation is realized with the aid of the Hard C-means clustering and HFCGA is a kind of multi-populations of Parallel Genetic Algorithms (PGA), and it is used for structure optimization and parameter identification of fuzzy model. It concerns the fuzzy model-related parameters such as the number of input variables to be used, a collection of specific subset of input variables, the number of membership functions, the order of polynomial, and the apexes of the membership function. In the hybrid optimization process, two general optimization mechanisms are explored. Thestructural optimization is realized via HFCGA and HCM method whereas in case of the parametric optimization we proceed with a standard least square method as well as HFCGA method as well. A comparative analysis demonstrates that the proposed algorithm is superior to the conventional methods.

• Proceedings of the KIEE Conference
• /
• 2005.05a
• /
• pp.6-8
• /
• 2005

In this paper, we discuss model identification of nonlinear data using GAs-based Fuzzy Polynomial Neural Networks(GAs-FPNN). Fuzzy Polynomial Neural Networks(FPNN) is proposed model based Group Method Data Handling(GMDH) and Neural Networks(NNs). Each node of FPNN is expressed Fuzzy Polynomial Neuron(FPN). Network structure of nonlinear data is created using Genetic Algorithms(GAs) of optimal search method. Accordingly, GAs-FPNN have more inflexible than the existing models (in)from structure selecting. The proposed model select and identify its for optimal search of Genetic Algorithms that are no. of input variables, input variable numbers and consequence structures. The GAs-FPNN model is select tuning to input variable number, number of input variable and the last part structure through optimal search of Genetic Algorithms. It is shown that nonlinear data model design using Genetic Algorithms based FPNN is more usefulness and effectiveness than the existing models.

• Journal of Korean Society of Steel Construction
• /
• v.17 no.4 s.77
• /
• pp.385-394
• /
• 2005

In this paper, a discrete optimum design program was developed using the refined fuzzy-genetic algorithms based on the genetic algorithms and the fuzzy theory. The optimum design in this study can perform section and shape optimization simultaneously for planar and spatial steel structures. In this paper, the objective function is the weight of steel structures and the constraints are the design limits defined by the design and buckling strengths, displacements, and thicknesses of the member sections. The design variables are the dimensions and coordinates of the steel sections. Design examples are given to show the applicability of the discrete optimum design using the improved fuzzy-genetic algorithms in this study.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.3
• /
• pp.406-412
• /
• 2010

In this paper, we formally define the problem of maximizing the coverage of sensor deployment, which is the optimization problem appeared in real-world sensor deployment, and analyze the properties of its solution space. To solve the problem, we proposed novel genetic algorithms, and we could show their superiority through experiments. When applying genetic algorithms to maximum coverage sensor deployment, the most important issue is how we evaluate the given sensor deployment efficiently. We could resolve the difficulty by using Monte Carlo method. By regulating the number of generated samples in the Monte Carlo evaluation of genetic algorithms, we could also reduce the computing time significantly without loss of solution quality.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.85-92
• /
• 2005

In this Paper, we develope an effective web-based learning contents using interactive genetic algorithms with modified mutation operation. In the interactive genetic algorithm, reciprocal exchange mutation is used. But. we modify the mutation operator to improve the learning effects. The new web-based learning contents using interactive genetic algorithm provide the dynamic learning contents providing and real-time test system. Especially, learners can execute the interactive genetic algorithm according to the learners' characters and interests to select the efficient learning environments and contents sequences.

• Proceedings of the KSME Conference
• /
• 2003.04a
• /
• pp.1639-1644
• /
• 2003

A hybrid genetic algorithm is developed for estimating the wall emissivities for an absorbing, emitting, and scattering media in a two-dimensional irregular geometry with diffusely emitting and reflecting opaque boundaries by minimizing an objective function, which is expressed by the sum of square errors between estimated and measured temperatures at only four data positions. The finite-volume method was employed to solve the radiative transfer equation for a two-dimensional irregular geometry. The results show that a developed hybrid genetic algorithms reduce the effect of genetic parameters on the performance of genetic algorithm and that the wall emissivities are estimated accurately without measurement errors.

• Proceedings of the KIEE Conference
• /
• 1997.11a
• /
• pp.126-129
• /
• 1997

This paper propose a new hybrid genetic algorithm for auto-tunig auzzy controller improving the performance. In general, fuzzy controller used pre-determine d moderate membership functions, fuzzy rules, and scaling factors, by trial and error. The presented algorithm estimates automatically the optimal values of membership functions, fuzzy rules, and scaling factors for fuzzy controller, using hybrid genetic algorithms. The object of the proposed algorithm is to promote search efficiency by overcoming a premature convergence of genetic algorithms. Hybrid genetic algorithm is based on genetic algorithm and modified gradient method. Simulation results verify the validity of the presented method.

• Proceedings of the KSME Conference
• /
• 2000.11a
• /
• pp.699-704
• /
• 2000

The present paper deals with a multiobjective optimization method based on the co-evolutionary genetic strategy. The co-evolutionary strategy carries out the multiobjective optimization in such way that it optimizes individual objective function as compared with each generation's value while there are more than two genetic evolutions at the same time. In this study, the designs that are out of the given constraint map compared with other objective function value are excepted by the penalty. The proposed multiobjective genetic algorithms are distinguished from other optimization methods because it seeks for the optimized value through the simultaneous search without the help of the single-objective values which have to be obtained in advance of the multiobjective designs. The proposed strategy easily applied to well-developed genetic algorithms since it doesn't need any further formulation for the multiobjective optimization. The paper describes the co-evolutionary strategy and compares design results on the simple structural optimization problem.

• Journal of Industrial Technology
• /
• v.20 no.B
• /
• pp.27-34
• /
• 2000

The definition of flatness is given by ISO, ANSI, KS, etc. but those standards don't mention about the specific methods for the flatness. So various solution models that are based on the Minimum Zone Method have been proposed as an optimization problem for the minimax curve fitting. But it has been rare to compare some optimization algorithms to make a guideline for choosing better algorithms in this field. Hence this paper examined and compared Genetic Algorithm and Simplex Method to the evaluation of flatness. As a result, Genetic Algorithm gave the better or equal flatness than Simplex Method but it has the inefficiency caused from the large number of iteration. Therefore, in the future, another researches about alternative algorithms including Hybrid Genetic Algorithm should be achieved to improve the efficiency of Genetic Algorithm for the evaluation of flatness.