• 대한전기학회논문지:시스템및제어부문D
• /
• 제50권11호
• /
• pp.532-540
• /
• 2001

In this paper, we propose a probabilistic tabu search strategy for function optimization. It is composed of two procedures, one is Basic search procedure that plays a role in local search, and the other is Restarting procedure that enables to diversify search region. In basic search procedure, we use Belief space and Near region to create neighbors. Belief space is made of high-rank neighbors to effectively restrict searching space, so it can improve searching time and local or global searching capability. When a solution is converged in a local area, Restarting procedure works to search other regions. In this time, we use Probabilistic Tabu Strategy(PTS) to adjust parameters such as a reducing rate, initial searching region etc., which makes enhance the performance of searching ability in various problems. In order to show the usefulness of the proposed method, the PTS is applied to the minimization problems such as De Jong functions, Ackley function, and Griewank functions etc., the results are compared with those of GA or EP.

• 한국안광학회지
• /
• 제6권2호
• /
• pp.121-127
• /
• 2001

additive 감쇠에 의한 감쇠 최소 자승법에 가우스 소거법과 Jacobian 행렬을 직교 변환시킨 SVD(singular value decomposition)법을 적용하여 조건수가 양호한 triplet 사진 렌즈계에 적용하여 수렴 속도와 안정성을 비교하였다. SVD 직교화 방법을 적용한 감쇠 최소 자승 법이 최소 merit 함수에 보다 안정되고 빠르게 수렴하였다. SVD 방법을 적용한 최적화에서 적절한 merit 함수를 얻을 수 있지만 오차 함수의 비선형성으로 인해 merit 함수가 국부 최소 점에 수업하는 경우가 있어서 간단한 전역 최적화 방법인격자 법으로 최적화를 실시하여 SVD 방법에 의한 merit 함수보다 낮은 전역 최소 점에 수렴하게 하였다.

• Journal of Electrical Engineering and Technology
• /
• 제9권4호
• /
• pp.1315-1323
• /
• 2014

Although the power density in Double Stator Switched Reluctance Motor (DSSRM) has been improved, the torque ripple is still very high. So, it is important to reduce the torque ripple for specific applications such as Electric Vehicles (EVs). In This paper, an effective rotor shaping optimization technique for torque ripple reduction of DSSRM is presented. This method leads to the lower torque pulsation without significant reduction in the average torque. The method is based on shape optimization of the rotor using Finite Element Method and Taguchi's optimization method for rotor reshaping for redistribution of the flux so that the phase inductance profile has smoother variation as the rotor poles move into alignment with excited stator poles. To check on new design robustness, mechanical analysis was used to evaluate structural conformity against local electromagnetic forces which cause vibration and deformation. The results show that this shape optimization technique has profound effect on the torque ripple reduction.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.2078-2093
• /
• 2019

Visual smoke recognition is a challenging task due to large variations in shape, texture and color of smoke. To improve performance, we propose a novel smoke recognition method by combining dual-encoded features that are extracted from both spatial and Curvelet domains. A Curvelet transform is used to filter an image to generate fifty sub-images of Curvelet coefficients. Then we extract Local Binary Pattern (LBP) maps from these coefficient maps and aggregate histograms of these LBP maps to produce a histogram map. Afterwards, we encode the histogram map again to generate Dual-encoded Local Binary Patterns (Dual-LBP). Histograms of Dual-LBPs from Curvelet domain and Completed Local Binary Patterns (CLBP) from spatial domain are concatenated to form the feature for smoke recognition. Finally, we adopt Gaussian Kernel Optimization (GKO) algorithm to search the optimal kernel parameters of Support Vector Machine (SVM) for further improvement of classification accuracy. Experimental results demonstrate that our method can extract effective and reasonable features of smoke images, and achieve good classification accuracy.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 제38회 하계학술대회
• /
• pp.425-426
• /
• 2007

In power systems operation, state estimation takes an important role in security control. For the state estimation problem, conventional optimization algorithm, such as weighted least squares (WLS) method, has been widely used. But these algorithms have disadvantages of converging local optimal solution. In these days, a modern heuristic optimization methods such as Particle Swarm Optimization (PSO), are introducing to overcome the problems of classical optimization. In this paper, we suggested parallel particle swarm optimization (PPSO) to search an optimal solution of state estimation in power systems. To show the usefulness of the proposed method over the conventional PSO, proposed method is applied on the IEEE-57 bus system.

• International Journal of Aeronautical and Space Sciences
• /
• 제14권4호
• /
• pp.324-333
• /
• 2013

The purpose of this paper is to improve the efficiency of multi-objective topology optimization using a genetic algorithm (GA) with bar-system representation. We proposed a new GA using an elite initial population obtained from a Solid Isotropic Material with Penalization (SIMP) using a weighted sum method. SIMP with a weighted sum method is one of the most established methods using sensitivity analysis. Although the implementation of the SIMP method is straightforward and computationally effective, it may be difficult to find a complete Pareto-optimal set in a multi-objective optimization problem. In this study, to build a more convergent and diverse global Pareto-optimal set and reduce the GA computational cost, some individuals, with similar topology to the local optimum solution obtained from the SIMP using the weighted sum method, were introduced for the initial population of the GA. The proposed method was applied to a structural topology optimization example and the results of the proposed method were compared with those of the traditional method using standard random initialization for the initial population of the GA.

• 한국도로학회논문집
• /
• 제8권4호
• /
• pp.159-179
• /
• 2006

도로의 구조 시설기준에 관한 규칙과 국도의 노선계획 설계지침에 준하여 실행되는 현행 노선선정방법과, 컴퓨터 발전과 함께 국내외에서 연구되고 있는 선형최적화 모형식으로 사례연구 구간의 도로 노선을 선정하여 노선 특성을 비교 분석해본 결과, 현행 노선선정방법은 단계별, 구간별로 순차적인 노선선정이 이루어지는 국지적 최적을 추구하나, 선형 최적화 모형식 선정방법은 모든 설계요소가 동시에 고려된 체계최적(System Optimal)의 노선탐색 능력이 있는 것으로 분석되었다. 또한 선형최적화 모형에서 기존 설계공종별 실제공사비로 비용함수를 보정하여 노선을 선정한 결과 현실에 부합되게 설계되었으며, 경제성이 높은(B/C=1.66) 대안 노선이 탐색되었다. 선형최적화 설계모형은 터널 종단에서 종단 경사가 변화하는 등 보완될 점이 있음에도 타당성조사와 기본설계단계에서 노선선정 도구로서 설계시간 및 비용단축, 다양한 대안 노선의 검토 등의 많은 장점을 지니고 있음이 확인되었다.

• 한국컴퓨터정보학회논문지
• /
• 제15권9호
• /
• pp.47-55
• /
• 2010

선형 제약 만족 최적화 문제는 선형식으로 표현 가능한 목적함수 및 복잡한 제약조건을 포함하는 조합 최적화 문제를 의미한다. 정수계획법은 이와 같은 문제를 해결하는 데 매우 효과적인 기법으로 알려져 있지만 문제의 규모가 커질 경우 준최적해를 도출하기까지 매우 많은 시간과 메모리를 요구한다. 본 논문에서는 지역 탐색과 정수계획법을 결합하여 탐색 성능을 향상할 수 있는 방안을 제시한다. 기본적으로 대상 문제의 해결을 위해 지역 탐색의 가장 단순한 형태인 단순 언덕오르기 탐색을 사용하되 이웃해 생성 시 정수계획법을 적용한다. 또한 부가적으로 초기해 생성을 위해 제약 프로그래밍을 활용한다. N-Queens 최대화 문제를 대상으로 한 실험 결과, 본 논문에서 제시한 기법을 통해 다른 탐색 기법들보다 훨씬 더 좋은 해를 도출할 수 있음을 확인할 수 있었다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 춘계학술대회 논문집 전기기기 및 에너지변환시스템부문
• /
• pp.74-76
• /
• 2007

A hybrid optimization method is proposed for cogging torque reducing in BLDC motor. The proposed hybrid optimization method comprises a response surface method (RSM) and a gradient search method (GSM). The RSM is effective and global method in optimization problem but having large approximation error. The GSM is accurate and fast search method for optimal solution but having local behavior. To reduce approximation error and computation time a hybrid method (RSM+GSM) is proposed method. To illustrate the effectiveness of the proposed method, a comparison between conventional RSM and the proposed hybrid method is made. A simulation results verify that the hybrid method can achieve favorable design performance.

• 전기학회논문지
• /
• 제56권6호
• /
• pp.1023-1030
• /
• 2007

This paper presents a new and efficient approach for solving the economic dispatch (ED) problems with nonconvex cost functions using particle swarm optimization (PSO). Although the PSO is easy to implement and has been empirically shown to perform well on many optimization problems, it may easily get trapped in a local optimum when solving problems with multiple local optima and heavily constrained. This paper proposes an improved PSO, which combines the conventional PSO with chaotic sequences (CPSO). The chaotic sequences combined with the linearly decreasing inertia weights in PSO are devised to improve the global searching capability and escaping from local minimum. To verify the feasibility of the proposed method, numerical studies have been performed for two different nonconvex ED test systems and its results are compared with those of previous works. The proposed CPSO algorithm outperforms other state-of-the-art algorithms in solving ED problems, which consider valve-point and multi-fuels with valve-point effects.