• Journal of Electrical Engineering and Technology
• /
• 제9권3호
• /
• pp.859-865
• /
• 2014

Optimization of an electric machine is mainly a nonlinear multi-modal problem. For the optimization of the multi-modal problem, many function calls are required with much consumption of time. To address this problem, this paper proposes a novel hybrid algorithm in which function calls are less than conventional methods. Specifically, the proposed method uses the kriging metamodel and the fill-blank technique to find an approximated solution in a whole problem region. To increase the convergence speed in local peaks, a parallel gradient assisted simplex method is proposed and combined with the kriging meta-model. The correctness and usefulness of the proposed hybrid algorithm is verified through a mathematical test function and applied into the practical optimization as the cogging torque minimization for an interior permanent magnet synchronous machine.

• Communications for Statistical Applications and Methods
• /
• 제17권2호
• /
• pp.141-151
• /
• 2010

Hybrid fuzzy regression analysis is used for integrating randomness and fuzziness into a regression model. Least squares support vector machine(LS-SVM) has been very successful in pattern recognition and function estimation problems for crisp data. This paper proposes a new method to evaluate hybrid fuzzy linear and nonlinear regression models with crisp inputs and fuzzy output using weighted fuzzy arithmetic(WFA) and LS-SVM. LS-SVM allows us to perform fuzzy nonlinear regression analysis by constructing a fuzzy linear regression function in a high dimensional feature space. The proposed method is not computationally expensive since its solution is obtained from a simple linear equation system. In particular, this method is a very attractive approach to modeling nonlinear data, and is nonparametric method in the sense that we do not have to assume the underlying model function for fuzzy nonlinear regression model with crisp inputs and fuzzy output. Experimental results are then presented which indicate the performance of this method.

• 한국산업정보학회:학술대회논문집
• /
• 한국산업정보학회 1997년도 춘계학술대회 발표논문집
• /
• pp.235-246
• /
• 1997

Hybrid fuzzy gain scheduling controller is composed of a PD control and a fuzzy control for taking the advantage of each scheme. The key structure of the hybrid fuzzy gain scheduling control scheme is so called a switch which calculates weighting values between the fuzzy controller and the PD controller. However, due to the requirement of the switch , the hybrid fuzzy gain scheduling control scheme needs extra fuzzy logic processing, thus the structure is complicated. and requires more calculation time. To eliminate the drawbacks, a new hybrid fuzzy gain scheduling control scheme is proposed in this paper. In the proposed scheme, the membership function, for calculating of weithting value, and the input and output membership functions are combined. Thus the proposed hybrid scheme does not require switch for calculation of weighting value, and as a result, the calculation time is faster and the structure is more simple than the existing hybrid controller. Computer simulation results for an inverted pendulum model under Pole-Placement PID controller, fuzzy gain scheduling controller,existing hybrid controller , and proposed hybrid controller are compared to demonstrate the good property of the proposed hybrid controller.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제50권7호
• /
• pp.339-349
• /
• 2001

This paper suggests an optimal identification method for complex and nonlinear system modeling that is based on Fuzzy-Neural Networks(FNN). The proposed Hybrid Identification Algorithm is based on Yamakawa's FNN and uses the simplified inference as fuzzy inference method and Error Back Propagation Algorithm as learning rule. In this paper, the FNN modeling implements parameter identification using HCM algorithm and hybrid structure combined with two types of optimization theories for nonlinear systems. We use a HCM(Hard C-Means) clustering algorithm to find initial apexes of membership function. The parameters such as apexes of membership functions, learning rates, and momentum coefficients are adjusted using hybrid algorithm. The proposed hybrid identification algorithm is carried out using both a genetic algorithm and the improved complex method. Also, an aggregated objective function(performance index) with weighting factor is introduced to achieve a sound balance between approximation and generalization abilities of the model. According to the selection and adjustment of a weighting factor of an aggregate objective function which depends on the number of data and a certain degree of nonlinearity(distribution of I/O data), we show that it is available and effective to design an optimal FNN model structure with mutual balance and dependency between approximation and generalization abilities. To evaluate the performance of the proposed model, we use the time series data for gas furnace, the data of sewage treatment process and traffic route choice process.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2019년도 학술발표회
• /
• pp.363-363
• /
• 2019

활성화 함수(activation function)는 기계학습(machine learning)의 학습과정에 비선형성을 도입하여 심층적인 학습을 용이하게 하고 예측의 정확도를 높이는 중요한 요소 중 하나이다(Roy et al., 2019). 일반적으로 기계학습에서 사용되고 있는 활성화 함수의 종류에는 계단 함수(step function), 시그모이드 함수(sigmoid 함수), 쌍곡 탄젠트 함수(hyperbolic tangent function), ReLU 함수(Rectified Linear Unit function) 등이 있으며, 예측의 정확도 향상을 위하여 다양한 형태의 활성화 함수가 제시되고 있다. 본 연구에서는 기계학습을 통하여 수위예측 시 정확도 향상을 위하여 Hybrid 활성화 함수를 제안하였다. 연구대상지는 조수간만의 영향을 받는 한강을 대상으로 선정하였으며, 2009년 ~ 2018년까지 10년간의 수문자료를 활용하였다. 수위예측 알고리즘은 Python 내 Tensorflow의 RNN (Recurrent Neural Networks) 모델을 이용하였으며, 강수량, 수위, 조위, 댐 방류량, 하천 유량의 수문자료를 학습시켜 3시간 및 6시간 후의 수위를 예측하였다. 예측정확도 향상을 위하여 입력 데이터는 정규화(Normalization)를 시켰으며, 민감도 분석을 통하여 신경망모델의 은닉층 개수, 학습률의 최적 값을 도출하였다. Hybrid 활성화 함수는 쌍곡 탄젠트 함수와 ReLU 함수를 혼합한 형태로 각각의 가중치($w_1,w_2,w_1+w_2=1$)를 변경하여 정확도를 평가하였다. 그 결과 가중치의 비($w_1/w_2$)에 따라서 예측 결과의 RMSE(Roote Mean Square Error)가 최소가 되고 NSE (Nash-Sutcliffe model Efficiency coefficient)가 최대가 되는 지점과 Peak 수위의 예측정확도가 최대가 되는 지점을 확인할 수 있었다. 본 연구는 현재 Data modeling을 통한 수위예측의 정확도 향상을 위해 기초가 되는 연구이나, 향후 다양한 형태의 활성화 함수를 제안하여 정확도를 향상시킨다면 예측 결과를 통하여 침수예보에 대한 의사결정이 가능할 것으로 기대된다.

• 한국통신학회논문지
• /
• 제39A권3호
• /
• pp.140-148
• /
• 2014

본 논문은 전자기파 신호 계산에 있어 하이브리드 방식의 기저 함수로써 Gaussian 함수를 제안하고자 한다. 하이브리드 방식은 전반부 시간 및 낮은 주파수 데이터를 이용하여 후반부 시간 및 높은 주파수 데이터를 구하는 방식이다. 시간을 이용한 MOT, 주파수를 이용한 MOM 방식의 장점만을 가져오기 때문에 전자기 분석 데이터를 구하기 위한 시간이 감소되며 오차가 적다는 장점이 있다. 이를 위해서는 기저 함수를 필요로 하며 Hermite, Laguerre를 기저 함수로 사용한 기존의 방법과의 비교를 통해 제안된 방법의 성능을 확인하였다.

• 한국군사과학기술학회지
• /
• 제26권3호
• /
• pp.273-280
• /
• 2023

Recently electronic safety and arming device(ESAD) has attracted increasing attention due to its design flexibility. However, ESAD can be armed unintentionally due to a malfunction of an external device or interface. Thus ESAD needs an internally generated arming signal independent from the external device. In this paper, a new sensor-hybrid ESAD(SHESAD) with a flight environment sensing function for generating arming signal internally is proposed and a sled test based method is also suggested for evaluating its functions. Through the test results, the operability of the flight environment sensing function was confirmed. Also, it is shown that the proposed test method is suitable for verification of ESAD with the flight environment sensing function.

• 대한전기학회논문지:전기기기및에너지변환시스템부문B
• /
• 제48권6호
• /
• pp.294-300
• /
• 1999

There is a growing interest in hybrid electric vehicles due to environmental concerns. Recent efforts are directed toward developing an improved main component systems for the hybrid electric vehicle applications. Soon after the introduction of electric starter for internal combustion engine early this century, despite being energy efficient and nonpolluting, electric vehicle lost the battle completly to internal combustion engine due to its limited range and inferior performance. Hybrid Electric vehicles offer the most promising solutions to reduce the emission of vehicles. This paper describes a method for cost reduction estimation of parallel hybrid electric vehicle. We used a cost reduction structure that consisted of five major subsystems (three-type and two-type motor) for parallel hybrid electric vehicle. Especially, we estimated the potential for cost reductions in parallel hybrid electric vehicle as a function of time using the learning curve. Also, we estimated the potentials of cost by depreciation.

• The Journal of Advanced Prosthodontics
• /
• 제13권4호
• /
• pp.216-225
• /
• 2021

PURPOSE. The aim of this study is to evaluate the effects of canine guidance occlusion and group function occlusion on the degree of stress to the bone, implants, abutments, and crowns using finite element analysis (FEA). MATERIALS AND METHODS. This study included the implant-prosthesis system of a three-unit bridge made of monolithic zirconia and hybrid abutments. Three-dimensional (3D) models of a bone-level implant system and a titanium base abutment were created using the original implant components. Two titanium implants, measuring 4 × 11 mm each, were selected. The loads were applied in two oblique directions of 15° and 30° under two occlusal movement conditions. In the canine guidance condition, loads (100 N) were applied to the canine crown only. In the group function condition, loads were applied to all three teeth. In this loading, a force of 100 N was applied to the canine, and 200-N forces were applied to each premolar. The stress distribution among all the components of the implant-bridge system was assessed using ANSYS SpaceClaim 2020 R2 software and finite element analysis. RESULTS. Maximum stress was found in the group function occlusion. The maximum stress increased with an increase in the angle of occlusal force. CONCLUSION. The canine guidance occlusion with monolithic zirconia crown materials is promising for implant-supported prostheses in the canine and premolar areas.

• Journal of applied mathematics & informatics
• /
• 제17권1_2_3호
• /
• pp.719-736
• /
• 2005

An understanding of Fourier series and their generalization is important for physics and engineering students, as much for mathematical and physical insight as for applications. Students are usually confused by the so-called Gibbs' phenomenon, an overshoot between a discontinuous function and its approximation by a Fourier series as the number of terms in the series becomes indefinitely large. In this paper we give short story of Gibbs phenomenon in chronological order.