• 한국지진공학회논문집
• /
• 제12권2호
• /
• pp.9-22
• /
• 2008

이 논문에서는 구조물의 내진성능 향상을 위한 방법으로서 구조부재 및 수동형 감쇠기의 통합최적설계기법을 제시한다. 이는 구조부재 및 감쇠기의 최적배치를 다루는 최적화기법이다. 통합시스템의 최적설계를 위하여 다목적최적화기법을 도입하고, 이를 보다 효율적으로 다루기 위하여 목표신뢰성 제한조건을 갖는 다목적최적화문제로 재구성하였다. 수치해석 예제를 통하여 다양한Pareto 최적해를 제시하였으며, 이들이 기존 설계방법에 상응하는 순차적 설계방법 및 가중합방법에 따른 단일목적함수 최적화방법을 포괄함을 검증하였다. 여러 Pareto 최적해로부터 강성 및 감쇠장치의 사용량을 달리하는 3가지 대표설계안을 선택하고 이들의 내진성능을 다양한 지진하중에 대하여 비교 분석하였다. 이로부터 제시하는 방법이 구조물의 내진성능 향상을 위한 설계방법으로서 효율적으로 적용될 수 있을 것으로 기대된다.

• International Journal of Control, Automation, and Systems
• /
• 제1권2호
• /
• pp.194-202
• /
• 2003

In this paper, we introduce a category of Multi-FNN (Fuzzy-Neural Networks) models, analyze the underlying architectures and propose a comprehensive identification framework. The proposed Multi-FNNs dwell on a concept of fuzzy rule-based FNNs based on HCM clustering and evolutionary fuzzy granulation, and exploit linear inference being treated as a generic inference mechanism. By this nature, this FNN model is geared toward capturing relationships between information granules known as fuzzy sets. The form of the information granules themselves (in particular their distribution and a type of membership function) becomes an important design feature of the FNN model contributing to its structural as well as parametric optimization. The identification environment uses clustering techniques (Hard C - Means, HCM) and exploits genetic optimization as a vehicle of global optimization. The global optimization is augmented by more refined gradient-based learning mechanisms such as standard back-propagation. The HCM algorithm, whose role is to carry out preprocessing of the process data for system modeling, is utilized to determine the structure of Multi-FNNs. The detailed parameters of the Multi-FNN (such as apexes of membership functions, learning rates and momentum coefficients) are adjusted using genetic algorithms. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between approximation and generalization (predictive) abilities of the model. To evaluate the performance of the proposed model, two numeric data sets are experimented with. One is the numerical data coming from a description of a certain nonlinear function and the other is NOx emission process data from a gas turbine power plant.

• 전기학회논문지
• /
• 제67권8호
• /
• pp.1071-1079
• /
• 2018

In this study, the design methodology as well as network architecture of Support Vector Machine based Polynomial Neural Network, which is a kind of the dynamically generated neural networks, is introduced. The Support Vector Machine based polynomial neural networks is given as a novel network architecture redesigned with the aid of polynomial neural networks and Support Vector Machine. The generic polynomial neural networks, whose nodes are made of polynomials, are dynamically generated in each layer-wise. The individual nodes of the support vector machine based polynomial neural networks is constructed as a support vector machine, and the nodes as well as layers of the support vector machine based polynomial neural networks are dynamically generated as like the generation process of the generic polynomial neural networks. Support vector machine is well known as a sort of robust pattern classifiers. In addition, in order to enhance the structural flexibility as well as the classification performance of the proposed classifier, multi-objective particle swarm optimization is used. In other words, the optimization algorithm leads to sequentially successive generation of each layer of support vector based polynomial neural networks. The bench mark data sets are used to demonstrate the pattern classification performance of the proposed classifiers through the comparison of the generalization ability of the proposed classifier with some already studied classifiers.

• 동력기계공학회지
• /
• 제21권1호
• /
• pp.5-10
• /
• 2017

Pitch drive system in wind turbine is composed by the planetary gear system to satisfied its required performance such as long life and light weight for gear train. When the planetary gear system can reduce its volume and weight, the power consumption of the wind turbine can be reduced. In this study, the planetary gear system of the pitch drive system in medium-sized wind turbine is obtained for weight reduction by shape optimization method. And the planetary gear system is verified for their strength by the structural analysis.

• Structural Engineering and Mechanics
• /
• 제52권6호
• /
• pp.1209-1224
• /
• 2014

In Current paper, the voltages of patches optimization are carried out for minimizing the power consumption of piezoelectric patches and maximum vertical displacement of symmetrically FML panels using the modified multi-objective Elitist-Artificial Bee Colony (E-ABC) algorithm. The voltages of patches, panel length/width ratios, ply angles, thickness of metal sheets and edge conditions are chosen as design variables. The classical laminated plate theory (CLPT) is considered to model the transient response of the panel, and numerical results are obtained by the finite element method. The performance of the E-ABC is also compared with the PSO algorithm and shows the good efficiency of the E-ABC algorithm. To check the validity, the transient responses of isotropic and orthotropic panels are compared with those available in the literature and show a good agreement.

• 한국정밀공학회지
• /
• 제29권3호
• /
• pp.319-323
• /
• 2012

Transmission is one of the important pars to transmit power from engine to wheels. Mass reduction gears can make the engine power requirement reduce, and can make dynamic performance and fuel efficiency of vehicle improve. Transmission gears are modified for mass reduction without changing their tooth shapes, face widths, and modules by using shape optimization and re-check process. Also structural stability is verified by FEA.

• 한국공간구조학회논문집
• /
• 제3권3호
• /
• pp.75-83
• /
• 2003

The purpose of this study is to obtain the optimum shape of cable domes by using the real coding genetic algorithm. Generally, the structural performance of the cable domes is influenced very sensitively by pre-stress, geometry and length of the mast because of flexible system. So, it is very important to decide the optimum shape to get maximum stiffness of cable domes. We use the analytical model to verify the usefulness of this algorithm for shape optimization and analyze the roof system of Seoul olympic gymnastic arena as analytical model of a practical structures. It is confirmed lastly that the optimum shape domes have more stiffness than initial shape ones.

• Structural Engineering and Mechanics
• /
• 제57권1호
• /
• pp.161-178
• /
• 2016

This research is aimed to design and analyze the performance of double dynamic vibration absorber (DVA) using a pendulum and a spring-mass type absorber for reducing vibration of two-DOF vibration system. The conventional fixed-points method and genetics algorithm (GA) optimization procedure are utilized in designing the optimal parameter of DVA. The frequency and damping ratio are optimized to determine the optimal absorber parameters. The simulation results show that GA optimization procedure is more effective in designing the double DVA in comparison to the fixed-points method. The experimental study is conducted to verify the numerical result.

• Structural Engineering and Mechanics
• /
• 제78권1호
• /
• pp.77-86
• /
• 2021

Local school buildings are critical facilities that can provide shelter in disasters such as earthquakes, so they must be more resistant to seismic forces than other structures. In this study, a sensitivity analysis was conducted to determine which columns-as the most critical members in a reinforced concrete building-most urgently require seismic retrofitting. The sensitivity analysis was conducted using an optimization technique with the location of each column as a parameter. A numerical model was developed to simulate a realistic collapse mode through a three-dimensional dynamic analysis. Based on numerical analysis results, it was found that the columns positioned in the lower floors, such as the first floor and in the outer part of a building, urgently require retrofitting. For reinforcement of the RC columns, which has been proven for its performance in previous research, was applied. Through this study, the importance of appropriate retrofitting is demonstrated. Further, a method for determining the appropriate location for retrofitting-when retrofitting is not possible on the entire structure-is presented.

• Earthquakes and Structures
• /
• 제23권4호
• /
• pp.329-338
• /
• 2022

This work addresses the optimization controller design problem combining the AI evolution bat (EB) optimization algorithm with a fuzzy controller in the practical application of a reinforced concrete frame structure. This article explores the use of an intelligent EB strategy to reduce the dynamic response of Lead Rubber Bearing (LRB) composite reinforced concrete frame structures. Recently developed control units for plant structures, such as hybrid systems and semi-active systems, have inherently non-linear properties. Therefore, it is necessary to develop non-linear control methods. Based on the relaxation method, the nonlinear structural system can be stabilized by properly adjusting the parameters. Therefore, the behavior of a closed-loop system can be accurately predicted by determining the behavior of a closed-loop system. The performance and durability of the proposed control method are demonstrated by numerical simulations. The simulation results show that the proposed method is a viable and feasible control strategy for seismically tuned composite reinforced concrete frame structures.