• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.4
• /
• pp.1106-1127
• /
• 2012

Service oriented architecture (SOA) lends itself to model the application components to coarse-grained services in such a way that the composition of different services could be feasible. Service composition fulfills numerous service requirements by constructing composite applications with various services. As it is the case in many real-world applications, different users have diverse QoS demands issuing for composite applications. In this paper, we present a service composition framework for a typical service overlay network (SON) considering both multiple QoS constraints and load balancing factors. Moreover, a service selection algorithm based on niching technique and particle swarm optimization (PSO) is proposed for the service composition problem. It supports optimization problems with multiple constraints and objective functions, whether linear or nonlinear. Simulation results show that the proposed algorithm results in an acceptable level of efficiency regarding the service composition objective under different circumstances.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.8
• /
• pp.551-560
• /
• 2004

In this paper, we propose a new architecture of Self-Organizing Fuzzy Polynomial Neural Networks (SOFPNN) that is based on a genetically optimized multilayer perceptron with fuzzy polynomial neurons (FPNs) and discuss its comprehensive design methodology involving mechanisms of genetic optimization, especially genetic algorithms (GAs). The proposed SOFPNN gives rise to a structurally optimized structure and comes with a substantial level of flexibility in comparison to the one we encounter in conventional SOFPNNs. The design procedure applied in the construction of each layer of a SOFPNN deals with its structural optimization involving the selection of preferred nodes (or FPNs) with specific local characteristics (such as the number of input variables, the order of the polynomial of the consequent part of fuzzy rules, and a collection of the specific subset of input variables) and addresses specific aspects of parametric optimization. Through the consecutive process of such structural and parametric optimization, an optimized and flexible fuzzy neural network is generated in a dynamic fashion. To evaluate the performance of the genetically optimized SOFPNN, the model is experimented with using two time series data(gas furnace and chaotic time series), A comparative analysis reveals that the proposed SOFPNN exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literatures.

• Structural Engineering and Mechanics
• /
• v.70 no.3
• /
• pp.339-350
• /
• 2019

This research focuses on finite element model updating and damage assessment of structures at element level based on global nondestructive test results. For this purpose, an optimization system is generated to minimize the structural dynamic parameters discrepancies between numerical and experimental models. Objective functions are selected based on the square of Euclidean norm error of vibration frequencies and modal assurance criterion of mode shapes. In order to update the finite element model and detect local damages within the structural members, modern optimization techniques is implemented according to the evolutionary algorithms to meet the global optimized solution. Using a simulated numerical example, application of genetic algorithm (GA), particle swarm (PSO) and artificial bee colony (ABC) algorithms are investigated in FE model updating and damage detection problems to consider their accuracy and convergence characteristics. Then, a hybrid multi stage optimization method is presented merging advantages of PSO and ABC methods in finding damage location and extent. The efficiency of the methods have been examined using two simulated numerical examples, a laboratory dynamic test and a high-rise building field ambient vibration test results. The implemented evolutionary updating methods show successful results in accuracy and speed considering the incomplete and noisy experimental measured data.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.187-198
• /
• 2022

This paper addresses the maintenance optimization problem in multi-component systems in which parts are connected in series, carrying out several missions interspersed with scheduled finite breaks. Due to limited time or resources, maintenance actions can be only carried out on a limited set of components. The decision maker then has to decide which components to maintain to ensure a pre-specified performance level during next mission. Most of the existing models in the literature usually assume only one system and enough spare parts. However, there are situations in which maintenance is required for multiple systems of the same type. To overcome this restrictive assumption, this study optimizes the maintenance problem considering the lack of repair parts and cannibalism for many identical systems. This study presents two optimization models with different objectives to solve the problem and analyzes the results so that the decision maker can decide. The results of this study are expected to be used for the maintenance of multiple systems of the same type, such as swarm drones.

• Nuclear Engineering and Technology
• /
• v.52 no.7
• /
• pp.1471-1480
• /
• 2020

This research presents a case study on the remediation of a radioactive waste (uranium: U) utilizing a multi-objective fuzzy optimization in an electrocoagulation process for the iron-stainless steel and aluminum-stainless steel anode/cathode systems. The incorporation of the cumulative uncertainty of result, operational cost and energy consumption are essential key elements in determining the feasibility of the developed model equations in satisfying specific maximum contaminant level (MCL) required by stringent environmental regulations worldwide. Pareto-optimal solutions showed that the iron system (0 ㎍/L U: 492 USD/g-U) outperformed the aluminum system (96 ㎍/L U: 747 USD/g-U) in terms of the retained uranium concentration and energy consumption. Thus, the iron system was further carried out in a multi-objective analysis due to its feasibility in satisfying various uranium standard regulatory limits. Based on the 30 ㎍/L MCL, the decision-making process via fuzzy logic showed an overall satisfaction of 6.1% at a treatment time and current density of 101.6 min and 59.9 mA/㎠, respectively. The fuzzy optimal solution reveals the following: uranium concentration - 5 ㎍/L, cumulative uncertainty - 25 ㎍/L, energy consumption - 461.7 kWh/g-U and operational cost based on electricity cost in the United States - 60.0 USD/g-U, South Korea - 55.4 USD/g-U and Finland - 78.5 USD/g-U.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.6 no.1
• /
• pp.33-38
• /
• 2006

In this paper, we propose a new architecture of Fuzzy Polynomial Neural Networks(FPNN) by means of genetically optimized Fuzzy Polynomial Neuron(FPN) and discuss its comprehensive design methodology involving mechanisms of genetic optimization, especially Genetic Algorithms(GAs). The conventional FPNN developed so far are based on mechanisms of self-organization and evolutionary optimization. The design of the network exploits the extended Group Method of Data Handling(GMDH) with some essential parameters of the network being provided by the designer and kept fixed throughout the overall development process. This restriction may hamper a possibility of producing an optimal architecture of the model. The proposed FPNN gives rise to a structurally optimized network and comes with a substantial level of flexibility in comparison to the one we encounter in conventional FPNNs. It is shown that the proposed advanced genetic algorithms based Fuzzy Polynomial Neural Networks is more useful and effective than the existing models for nonlinear process. We experimented with Medical Imaging System(MIS) dataset to evaluate the performance of the proposed model.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.31A no.9
• /
• pp.146-155
• /
• 1994

In this paper, we desribe a new system, called BEST, that is used to develop a macromodel or behavioral model easily. It automatically calculates the component values of macromodel represented by equations to satisfy the given specification. Also, it gives the way to analyze both the behavioral model and transistor level circuit, and then compare the analysis results of them to check the correspondence under specific temperature and bias condition, and BEST optimizes the component values of macromodel. Other feature is to characterize MOSFET as switch model which consists of PWL-RC network. Finally, it is possible to generage multi-level netlist which consists of macro/switch/transistor level circuits, and user can determine the trade-off between simulation speed and accuracy. With the graphic user interface form of macromodel development system described above. BEST enable designers to make macromodel by themselves and to uas it. We applied BEST to develop the macromodel for the test circuit and got the 18.6 times simulation speed up with preserving the accuracy within 10% compared to the conventional transistor level circuit simulation. Also, applicability of optimization capability was verified.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10a
• /
• pp.321-326
• /
• 1992

In this paper, a high performance graphics system is suggested and its hardware architecture and software structure are described. The developed graphics system is a multi-processing system that uses 6 i860 RISC CPU's and supports PHIGS language in a hardware level. The software is programmed with respect to the graphics pipeline and the software modules are distributed into each processor for the optimization of the performance. The implemented graphics system can draw about 100,000 3D polygons second.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.14 no.2
• /
• pp.237-247
• /
• 2001

강상판교는 부재수가 많고 구조적 거동이 복잡하여 재래적인 단일수준 (CSL) 알고리즘을 이용하여 최적화하는 것이 매우 어렵기 때문에 본 연구에서는 강상판교를 효율적으로 최적화하기 위해 다단계 최적설계 (MLDS) 알고리즘이 제안되었다. 강상판교를 주형과 강상판으로 나누기 위해 등위법이 사용되었고, 시스템 최적화를 위하여 설계 변수를 줄이는 분해법이 사용되었다. 효율적인 최적설계를 위해 다단계 최적설계 알고리즘은 제약조건 소거기법(Constraint Deletion)과 응력 재해석 같은 근사화 기법을 도입하였다. 변위해석을 위한 제약조건 소거기법은 교량의 최적화에 효율적인 것으로 검증되었고, 제안된 응력 재해석 기법 또한 설계민감도 해석을 필요로 하지 않으므로 매우 효율적이다. MLDS 알고리즘의 적용성과 강건성은 다양한 수치예제를 사용하여 기존의 단일수준 알고리즘과 비교하였다.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.15 no.2 s.95
• /
• pp.225-231
• /
• 2005

This paper presents a design method for the structural-acoustic coupled radiator that can emit sound in the desired direction. A coupled system that has a finite space and a semi-infinite space separated by two flexible walls and an opening is considered. An objective function is selected to maximize radiation power on a main axis and minimize a side lobe level. To get initial values, prediction of a pressure distribution on field points and radiation pattern of the structural-acoustic coupling system is shown at a coupled-resonant frequency. Three different optimization methods are adapted to design the coupled radiator. Pressure and intensity distribution of the designed radiator is presented.