• Journal of Electrical Engineering and Technology
• /
• 제9권6호
• /
• pp.1873-1881
• /
• 2014

This paper deals with the design of multi-machine power system stabilizers (PSSs) and Static var compensator (SVC) using Modified shuffled frog leaping algorithm (MSFLA). The effectiveness of the proposed scheme for optimal setting of the PSSs and SVC controllers has been attended. The PSSs and SVC controllers designing is converted to an optimization problem in which the speed deviations between generators are involved. In order to compare the capability of PSS and SVC, they are designed independently once, and in a coordinated mode once again. The proposed method is applied on a multi-machine power system under different operating conditions and disturbances to confirm the effectiveness of it. The results of tuned PSS controller based on MSFLA (MSFLAPSS) and tuned SVC controller based on MSFLA (MSFLA SVC) are compared with the Strength pareto evolutionary algorithm (SPEA) and Particle swarm optimization (PSO) based optimized PSS and SVC through some performance to reveal its strong performance.

• 전자공학회논문지B
• /
• 제30B권8호
• /
• pp.54-63
• /
• 1993

This paper proposes a method for improving the performances of the neural network for optimization by an optimal estimation of initial states. The optimal initial state that leads to the global minimum is estimated by using the stochastic approximation. And then the update rule of Hopfield model, which is the high speed deterministic algorithm using the steepest descent rule, is applied to speed up the optimization. The proposed method has been applied to the tavelling salesman problems and an optimal task partition problems to evaluate the performances. The simulation results show that the convergence speed of the proposed method is higher than conventinal Hopfield model. Abe's method and Boltzmann machine with random initial neuron output setting, and the convergence rate to the global minimum is guaranteed with probability of 1. The proposed method gives better result as the problem size increases where it is more difficult for the randomized initial setting to give a good convergence.

• 화약ㆍ발파
• /
• 제38권4호
• /
• pp.16-25
• /
• 2020

터널 발파 굴착 시 발생되는 진동을 저감시키기 위해 사용되는 MSP(Multi-setting smart-investigation of the ground and pre-large hole boring method) 공법은 1회 천공 시 수평방향으로 50m에 달하는 장거리를 천공하기 때문에 고 중량 해머비트와 롯드의 일방향 회전으로 롯드의 처짐과 우향 현상이 동반된다. 이는 전문가의 경험과 시공 이력을 바탕으로 가변적인 세팅을 통해 일부 보정되고 있다. 그러나 암반 특성, 장비 상태, 경험 부족 등은 목표 지점으로부터 천공 오차를 발생시키는 원인이 되며, 큰 이격 오차 발생 시 재시공으로 인한 공기 증가와 경제적 손실이 발생된다. 본 연구에서는 딥러닝을 활용하여 상황별 천공 장비의 최적 세팅조건 산정 모델을 개발하였으며, 학습 과정에서 발생 가능한 과적합 문제를 방지하기 위해 dropout, early stopping, pre-training 기법들을 사용하여 향상된 결과를 도출하였다. 본 연구를 통해 대구경 천공 장비의 상황별 초기세팅 산정 모델 개발의 높은 가능성을 확인했으며, 지속적인 데이터 수집과 다양한 인자들의 추가 학습을 통해 최적화된 세팅 가이드라인을 개발할 수 있을 것으로 기대된다.

• 경영과학
• /
• 제12권2호
• /
• pp.105-127
• /
• 1995

This paper solves different machine-part group formation (MPGF) problems using genetic algorithms to demonstrate that it can be a new robust alternative to the conventional heuristic approaches for optimization problems. We first give an overview of genetic algorithms: Its principle, various considerations required for its implementation, and the method for setting up parameter values are explained. Then, we describe the MPGF problem which are critical to the successful operation of cellular manufacturing or flexible manufacturing systems. We concentrate on three models of the MPGF problems whose forms of the objective function and/or constraints are quite different from each other. Finally, numerical examples of each of the models descibed above are solved by using genetic algorithms. The result shows that the solutions derived by genetic algorithms are comparable to those obtained through problem-specific heuristic methods.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2010년도 춘계학술대회 논문집
• /
• pp.65-66
• /
• 2010

To improve the gear noise quality, gear tooth grinding machine are widely used in automotive industry. While using the gear profile grinding machine to improve the gear tooth quality of the transmission, several defects such as chattering, tooth waves that cause the gear noise occasionally happened. But it is very difficult to solve that problem, because there is no one who knows the setting up the optimal grinding condition appropriately. The abnormal manufacturing conditions which make the gear noise make the engineer to spend a lot of time, effort, and money. Due to demands for solving the serious abnormal gear noise happened in the new FF 6th stage automatic transmission in the mass product stage, the vibration checking process in the worm wheel axis, work rotation and fixed axis of the grinding machine were adapted to find the root causes. As a result, gear profile wave are affected by the work rotation axis's unbalance which is caused by worm wheel feeding speed. And a primary and the secondary grinding feeding speed, cutting oil, work fixed forces are also proved as the important factors. After setting up the grinding condition reported in this paper, it was adapted successfully to the grinding machine to manufacture the new FF 6th speed automatic transmissions' output gear. The gear noise was dramatically disappeared and the process and results will offer good guides to the engineers who manufacture the gear with the grinding machine.

• 한국소음진동공학회논문집
• /
• 제20권7호
• /
• pp.665-671
• /
• 2010

To improve the gear noise quality, gear tooth grinding machine are widely used in automotive industry. While using the gear profile grinding machine to improve the gear tooth quality of the transmission, several defects such as chattering, tooth waves that cause the gear noise occasionally happened. But it is very difficult to solve that problem, because there is no one who knows the setting up the optimal grinding condition appropriately. The abnormal manufacturing conditions which make the gear noise make the engineer to spend a lot of time, effort, and money. Due to demands for solving the serious abnormal gear noise happened in the automatic transmission in the mass product stage, the vibration checking process in the worm wheel axis, work rotation and fixed axis of the grinding machine were adapted to find the root causes. As a result, gear profile wave are affected by the work rotation axis's unbalance which is caused by worm wheel feeding speed. And a primary and the secondary grinding feeding speed, cutting oil, work fixed forces are also proved as the important factors. After setting up the grinding condition reported in this paper, it was adapted successfully to the grinding machine to manufacture the new automatic transmissions' gear. The gear noise was dramatically disappeared and the process and the results will offer good guides to the engineers who manufacture the gear with the grinding machine.

• 한국도로학회논문집
• /
• 제20권3호
• /
• pp.59-64
• /
• 2018

PURPOSES : We propose a parameter-setting-free harmony-search (PSF-HS) algorithm to determine the individual sound power levels of noise sources in the cases of industrial or road noise environment. METHODS :In terms of using methods, we use PSF-HS algorithm because the optimization parameters cannot be fixed through finding the global minimum. RESULTS:We found that the main advantage of the PSF-HS heuristic algorithm is its ability to find the best global solution of individual sound power levels through a nonlinear complex function, even though the parameters of the original harmony-search (HS) algorithm are not fixed. In an industrial and road environment, high noise exposure is harmful, and can cause nonauditory effects that endanger worker and passenger safety. This study proposes the PSF-HS algorithm for determining the PWL of an individual machine (or vehicle), which is a useful technique for industrial (or road) engineers to identify the dominant noise source in the workplace (or road field testing case). CONCLUSIONS : This study focuses on providing an efficient method to determine sound power levels (PWLs) and the dominant noise source while multiple machines (or vehicles) are operating, for comparison with the results of previous research. This paper can extend the state-of-the-art in a heuristic search algorithm to determine the individual PWLs of machines as well as loud machines (or vehicles), based on the parameter-setting-free harmony-search (PSF-HS) algorithm. This algorithm can be applied into determining the dominant noise sources of several vehicles in the cases of road cross sections and congested housing complex.

• 지적과 국토정보
• /
• 제51권2호
• /
• pp.83-106
• /
• 2021

대기오염, 지구온난화 문제 등 환경 문제의 심각성이 대두되면서 청정 연료의 관심이 커지고 있다. 그 중 수소는 기존 화석연료와는 달리 연소 시 부산물로 수분만이 발생하는 대표적인 친환경 에너지원으로 현재 다양한 분야에서 주목을 받고 있다. 물류 분야에서도 수소를 활용한 물류 네트워크를 구축하기 위해 다양한 정책적 노력이 활발히 이루어지고 있다. 이러한 수소 물류 네트워크의 구축에 있어 수소충전소의 입지 결정은 매우 중요한 문제이다. 최근 개발된 수소추진(수소연료전지) 화물차에 수소를 공급하는 충전소는 수소 기반 물류체계가 본격적으로 자리 잡는 데 있어 필수 불가결한 요소이다. 이러한 수소충전소의 최적 입지를 결정하는 선행연구는 대부분 수리적 모형에 기반한 최적화 기법만을 사용하여 수소충전소의 최적 입지를 결정하고자 하였다. 본 연구에서는 기존 연구의 동향과는 차별화하여 최적화 기법의 중요한 투입 변수 중 하나인 충전소 후보지에 대한 공간적 특성을 검토하는 방법으로 머신러닝 모형들을 활용하고 그 적용가능성을 확인하였다. 머신러닝은 다양한 분야에서 우수한 성과를 증명한 기법이지만 수소충전소의 최적 입지를 결정하는 연구 분야에서는 아직 적용된 바가 없다. 이를 위해 본 연구에서는 개별공시지가, 수소공급지와의 거리 등 전국 고속도로 휴게소와 고속도로의 무작위 지점들의 위치와 관련된 변수들을 독립변수로 선정하여 단일 머신러닝 모형과 앙상블 모형을 적용하고 그 성과를 비교하였다. 분석 결과, 랜덤포레스트(Random Forest) 모형이 가장 우수한 성과를 보였으며, 다른 모형들 또한 우수한 분류 성능을 보여 최적 입지 문제에 대해 공간적 특성을 예비적으로 검토하는 방법론으로써 머신러닝의 적용 가능성을 확인할 수 있었다. 따라서 머신러닝 모형은 수소충전소의 최적 입지 결정 분야에서 향후 최적화 기법을 적용한 연구의 예비적 검토 방법론으로 널리 활용할 수 있을 것으로 기대된다.

• 대한산업공학회지
• /
• 제39권5호
• /
• pp.361-366
• /
• 2013

Prediction of process parameters is very important in parameter design. If predictions are fairly accurate, the quality improvement process will be useful to save time and reduce cost. The concept of dual response approach based on response surface methodology has widely been investigated. Dual response approach may take advantages of optimization modeling for finding optimum setting of input factor by separately modeling mean and variance responses. This study proposes an alternative dual response approach based on machine learning techniques instead of statistical analysis tools. A hybrid neural network-genetic algorithm has been proposed for the purpose of parameter design. A neural network is first constructed to model the relationship between responses and input factors. Mean and variance responses correspond to output nodes while input factors are used for input nodes. Using empirical process data, process parameters can be predicted without performing real experimentations. A genetic algorithm is then applied to find the optimum settings of input factors, where the neural network is used to evaluate the mean and variance response. A drug formulation example from pharmaceutical industry has been studied to demonstrate the procedures and applicability of the proposed approach.

• 대한화학회지
• /
• 제53권6호
• /
• pp.653-662
• /
• 2009

흡수, 분포, 대사, 배설 특성 및 독성을 예측하기 위한 효과적인 툴을 개발하는 것은 신약개발의 초기단계에서 NCE(new chemical entity)에 대한 가장 중요한 업무 중의 하나이다. 최근에 이런 시도중의 하나로서 ADME/T(absorption, distribution, metabolism, excretion, toxicity)관련 성질들의 예측에 support vector machine(SVM)을 이용하고 있다. 그리고 SVM은 ADME/T 성질들을 정확하게 예측하는데 많이 사용 되고 있다. 그러나 SVM 모델링에 두 가지 문제가 있다. 특성 선택(feature selection) 과 매개변수 설정(parameter setting)은 여전히 해결해야 할 과제이다. 이 두 가지 문제들은 SVM 분류의 효율성과 정확도에 결정적인 영향을 끼친다. 특히 특성 선택과 최적화된 SVM 변수의 설정은 서로 영향을 주기 때문에 동시에 다루어져야 한다. 여기서 우리는 genetic algorithm(GA) – 특성 선택에 사용 – 과 grid search(GS) method– 변수최적화에 사용 – 두 가지를 통합하는 효과적인 해결책을 제시하였다. ADME/T관련 성질 중 하나인 심장부정맥을 야기시키는 hERG 이온채널 저해제 분류 모델이 여기서 제안된 GA-GS-SVM을 위해 할당되고 테스트 되었다. 1891개의 화합물을 가지는 트레이닝 셋으로 단일 모델 3개, 앙상블 모델 3개, 총 6개의 모델을 만들었고 175개의 외부 데이터를 테스트 셋으로 사용하여 검증하였다. 데이터의 불균형 문제를 해결하기 위하여 GA-GS-SVM 단일 모델에 의한 예측 정확도와 GA-GS-SVM 앙상블 모델 예측 정확도를 비교하였으며, 앙상블모델을 사용하여 예측의 정확도를 높일 수 있었다.