• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.11A
• /
• pp.1079-1085
• /
• 2007

This Paper Proposes a new optimization algorithm named by GBNSGA-II(Goal-pareto Based Non-dominated Sorting Genetic Algorithm-II) which uses Goal Programming to find non-dominated solutions in NSGA-II. Although the conventional NSGA is very popular to solve multiobjective optimization problem, its high computational complexity, lack of elitism and difficulty of selecting sharing parameter have been considered as problems to be overcome. To overcome these problems, NSGA-II has been introduced as the alternative for multiobjective optimization algorithm preventing aforementioned defects arising in the conventional NSGA. Together with advantageous features of NSGA-II, this paper proposes rather effective optimization algorithm formulated by purposely combining NSGA-II algorithm with GP (Goal Programming) subject to satisfying multiple objectives as possible as it can. By conducting computer simulations, the superiority of the proposed GBNSGA-II algorithm will be verified in the aspects of the effectiveness on optimization process in presence of a priori constrained goals and its fast converging capability.

• Journal of the Korean Society for Precision Engineering
• /
• v.18 no.11
• /
• pp.155-160
• /
• 2001

To achieve high precision cutting as well as production capability in the machine tool, it is needed to develop excellent rigidity statically, dynamically and thermally as well. In order to predict the qualitative behavior of a machine tool, simultaneous analysis of mechanics and heat transfer is required. Generally, machine tool designers have solved designing problems based on partial estimation of the specified rigidity. This study clears the inter-relationship between therm, and propose multi-phase optimization of machine tool structure using a genetic algorithm. The multi-phase solution method is consists of a series of mechanical design problem. At this first phase of static design problem, multi-objective optimization for the purpose of minimization of the total weight and static compliance minimization is solved using the Pareto Genetic Algorithm.

• Computational Structural Engineering
• /
• v.7 no.1
• /
• pp.117-124
• /
• 1994

Multi-level Multi-objective optimization(MLMO) for reinforced concrete framed structure is performed, and compared with the results of single-level single-objective optimization. MLMO method allows flexibility to meet the design needs such as deflection and cost of structures using weighting factors. Using Multi-level formulation, the numbers of constraints and variables are reduced at each levels, and the optimization formulation becomes simplified. The force approximation method is used to reflect the variation in design variables between the substructures, and thus coupling is maintained. And the linear approximated constraints and objective function are used to reduce the number of structural analysis in optimization process. It is shown that the developed algorithm with move limit can converge effectively to optimal solution.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.3
• /
• pp.495-504
• /
• 2013

Evolutionary algorithms have been applied to multi-objective optimization problems by approximation methods using computational intelligence. Those methods have been improved gradually in order to generate more exactly many approximate Pareto optimal solutions. The paper introduces a new method using support vector machine to find an approximate Pareto frontier in multi-objective optimization problems. Moreover, this paper applies an evolutionary algorithm to the proposed method in order to generate more exactly approximate Pareto frontiers. Then a decision making with two or three objective functions can be easily performed on the basis of visualized Pareto frontiers by the proposed method. Finally, a few examples will be demonstrated for the effectiveness of the proposed method.

• The KIPS Transactions:PartB
• /
• v.15B no.1
• /
• pp.53-60
• /
• 2008

This paper proposes a new multiobjective optimization method for discriminative training of hidden Markov models (HMMs) used as the recognizer for automatic lipreading. While the conventional Baum-Welch algorithm for training HMMs aims at maximizing the probability of the data of a class from the corresponding HMM, we define a new training criterion composed of two minimization objectives and develop a global optimization method of the criterion based on simulated annealing. The result of a speaker-dependent recognition experiment shows that the proposed method improves performance by the relative error reduction rate of about 8% in comparison to the Baum-Welch algorithm.

• Journal of Ocean Engineering and Technology
• /
• v.11 no.4
• /
• pp.227-238
• /
• 1997

다목적함수 최적화를 효과적으로 수행하기 위하여 유전자 알고리즘과 직접탐색법을 결합하여 혼성형 최적화기법을 구현하였다. 이 방법은 유전자 알고리즘을 사용하여 최적점이 존재할 가능성이 높은 영역을 탐색한 후, 이 영역에서 직접탐색법을 사용하여 최종해를 찾는다. 따라서 탐색의 효율을 향상시키고 계산시간을 절약할 수 있는 장점이 있다. 그러나 최적화기법이 효율적이지만, 최적화기법을 사용하기 위해서는 전문가의 전문지식이 필요하다. 따라서 실제 최적화를 수행하기 위해서는 관련 분야의 전문지식과 최적화기법이 효율적으로 결합되는 것이 필요하다.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.15 no.4
• /
• pp.591-598
• /
• 2002

In the ship structural design, the material cost of hull weight and the overall cost of construction processes should be minimized considering safety and reliability. In the past, minimum weight design has been mainly focused on reducing material cost and increasing dead weight reflect the interests of a ship's owner. But, in the past experience, the minimum weight design has been inevitably lead to increasing the construction cost. Therefore, it is necessary that the designer of ship structure should consider both structural weight and construction cost. In this point of view, multi-objective optimization technique is proposed to design the ship structure in this study. According to the proposed algorithm, the results of optimization were compared to the structural design of actual VLCC(Very Large Crude Oil Carrier). Objective functions were weight cost and construction cost of VLCC, and ES(Evolution Strategies), one of the stochastic search methods, was used as an optimization solver. For the scantlings of members and the estimations of objectives, classification rule was adopted for the longitudinal members, and the direct calculation method, GSDM(Generalized Slope Deflection Method), lot the transverse members. To choose the most economical design point among the results of Pareto optimal set, RFR(Required Freight Rate) was evaluated for each Pareto point, and compared to actual ship.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.05a
• /
• pp.177-181
• /
• 2003

PID(Proportional-Integral-Derivative)제어기는 제어악고리즘의 단순성과 실 현장에서의 강인성 등으로 산업용 보일러의 제어시스템서 주로 이용되어 왔다. 그러나 다중 루프를 가진 보일러 시스템에서는 루프간의 상호 간섭 영향 등으로 부하 변화에 따라 요구되는 증기(steam)압력, 증기 유량(steam flow)변화 등을 동시에 만족하도록 급수 유량, 연교 유량, 공기 유량 등을 PlH제어기만으로 제어하는 것은 어렵다. 본 연구에서는 보일러 시스템의 다목적 성능 최적화에 각각의 적합도 함수 $f_{a}$ , $f_{b}$, $f_{c}$를 정의하고 면역 알고리즘을 이용해 최적화를 구하고 그 결과에 대한 특성과 유효성을 검토하였다.다.다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2010.05a
• /
• pp.67-71
• /
• 2010

홍수기 다목적댐 운영의 목적은 홍수조절용량을 최대한 이용하여 하류 주요 지점의 첨두홍수량을 저감시키거나, 계획홍수량을 초과하지 않도록 방류량과 방류시점을 조절함으로써 홍수 피해규모를 최소화하는 것이다. 본 연구에서는 홍수기 다목적댐 운영에서 다목적 최적화의 한 형태인 goal programming의 적용성을 검토하였다. 실제 강우사상을 이용하여 단일저수지 운영과 저수지 연계운영을 실시하였다. 단일 저수지 운영을 적용하기 위한 시험유역으로는 충주댐 유역을 선정하였고 저수지 연계운영을 적용하기 위한 시험유역으로는 안동댐과 임하댐 유역을 선정하였다. goal programming의 결과 분석을 위해 저수지 모의운영 모형인 HEC-5 모형의 결과와 비교, 분석하였다. goal programming을 이용할 경우 HEC-5 운영결과보다 안정적인 운영결과를 얻을 수 있었다. goal programming을 이용한 최적화 운영의 경우 전구간의 유입량을 알고 있다는 점에서 실제 저수지 운영과는 차이가 있다. 그러나 적절한 제약조건을 적용하고 홍수예경보를 이용하여 예보된 유입량을 활용하면 최적의 방류시점과 방류량을 산정하여 홍수기 다목적댐을 효율적으로 운영할 수 있으며 주요 지점의 홍수량도 저감할 수 있을 것으로 판단된다.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.14 no.2
• /
• pp.1-13
• /
• 2010

This paper proposes an optimal design method for the nonlinear seismic isolated bridge. The probabilities of failure at the pier and the seismic isolator are considered as objective functions for optimal design, and a multi-objective optimization technique is employed to efficiently explore a set of multiple solutions optimizing mutually-conflicting objective functions at the same time. In addition, a stochastic linearization method is incorporated into the multi-objective optimization framework in order to effectively estimate the stochastic responses of the bridge without performing numerous nonlinear time history analyses during the optimization process. As a numerical example to demonstrate the efficiency of the proposed method, the Nam-Han river bridge is taken into account, and the proposed method and the existing life-cycle-cost based design method are both applied for the purpose of comparing their seismic performances. The comparative results demonstrate that the proposed method not only shows better seismic performance but also is more economical than the existing cost-based design method. The proposed method is also proven to guarantee improved performance under variations in seismic intensity, in bandwidth and in the predominant frequency of the seismic event.