• 전기학회논문지
• /
• 제57권11호
• /
• pp.2108-2116
• /
• 2008

The paper concerns Fuzzy C-Means clustering based Radial Basis Function neural networks (FCM-RBFNN) and the optimization of the network is carried out by means of Particle Swarm Optimization(PSO). FCM-RBFNN is the extended architecture of Radial Basis Function Neural Network(RBFNN). In the proposed network, the membership functions of the premise part of fuzzy rules do not assume any explicit functional forms such as Gaussian, ellipsoidal, triangular, etc., so its resulting fitness values directly rely on the computation of the relevant distance between data points by means of FCM. Also, as the consequent part of fuzzy rules extracted by the FCM - RBFNN model, the order of four types of polynomials can be considered such as constant, linear, quadratic and modified quadratic. Weighted Least Square Estimator(WLSE) are used to estimates the coefficients of polynomial. Since the performance of FCM-RBFNN is affected by some parameters of FCM-RBFNN such as a specific subset of input variables, fuzzification coefficient of FCM, the number of rules and the order of polynomials of consequent part of fuzzy rule, we need the structural as well as parametric optimization of the network. In this study, the PSO is exploited to carry out the structural as well as parametric optimization of FCM-RBFNN. Moreover The proposed model is demonstrated with the use of numerical example and gas furnace data set.

• 한국전기전자재료학회논문지
• /
• 제18권1호
• /
• pp.1-5
• /
• 2005

A new model of plasma etch process was constructed by using a radial basis function network (RBFN). This technique was applied to an etching of silicon carbide films in a NF$_3$ inductively coupled plasma. Experimental data to train RBFN were systematically collected by means of a 2$^4$ full factorial experiment. Appropriateness of prediction models was tested with test data consisted of 16 experiments not pertaining to the training data. Prediction performance was optimized with variations in three training factors, the number of pattern units, width of radial basis function, and initial weight distribution between the pattern and output layers. The etch responses to model were an etch rate and a surface roughness measured by atomic force microscopy. Optimized models had the root mean-squared errors of 26.1 nm/min and 0.103 nm for the etch rate and surface roughness, respectively. Compared to statistical regression models, RBFN models demonstrated an improvement of more than 20 % and 50 % for the etch rate and surface roughness, respectively. It is therefore expected that RBFN can be effectively used to construct prediction models of plasma processes.

• 자원ㆍ환경경제연구
• /
• 제25권2호
• /
• pp.299-320
• /
• 2016

본 연구는 자료포락분석의 target-setting approach를 기초로 우리나라 16개 지자체의 에너지 효율성을 추정하고, 에너지 효율향상을 통해 저감할 수 있는 에너지 소비수준을 계측한다. 나아가 에너지 믹스변화에 의한 지역별 환경성과를 분석하고 그에 따른 이산화탄소 감축효과를 평가한다. 분석결과, 표본기간 2004년~2013년 동안 평균적으로 14.0%의 에너지 비효율이 존재하며, 특히 석유연료의 비효율적 사용이 주요 광역시를 중심으로 크게 나타났다. 또한 에너지 소비구조의 변화를 통해 에너지 효율향상과 추가적인 이산화탄소 저감가능성이 발생하며, 적극적인 에너지 믹스전략의 필요성을 확인할 수 있었다.

• Progress in Superconductivity
• /
• 제12권1호
• /
• pp.27-31
• /
• 2010

A superconductor flywheel energy storage system (SFES) is an electro-mechanical battery which transforms electrical energy into mechanical energy for storage, and vice versa. Many aspects of the quasi-static behavior of flywheel rotors still need to be studied closely, and the rotors require a stable and highly efficient supporting system such as high temperature superconductor (HTS) bearings, which offer dynamic stability without the use of active control. Quasi-static properties of HTS bearings in the radial direction provide data to solve problems which may occur in a running system. Since stiffness in countering rotor vibration is the main parameter for designing an HTS bearing system, we investigated the quasi-static properties of the magnetic force between permanent magnets(PMs) and HTS bulks in the radial direction. We measured radial stiffness, and discovered that bearing stiffness varied greatly depending on the number of active HTS bulks. This is valuable data for predicting the change in stiffness during partial HTS bearing failure. The quasi-static test results are used for optimal design and performance prediction for the 100 kWh class superconductor bearing.

• 전기학회논문지
• /
• 제60권7호
• /
• pp.1385-1390
• /
• 2011

A coaxial-conical-radial transmission line conversion circuits have been investigated to realize a low loss high performance microwave power divider/combiner. In order to optimize the characteristics of the device, the power divider/combiner was designed separately with two parts-the inner part and the outer part. Utilizing the rectangular approximation of the outer part, we can design the low loss device which is not affected by the partition number N of the outer part. The small return loss which is lower than 20dB was obtained on the frequency range of 5.15GHz(7.45~12.60GHz). A conical connector was employed for smooth connection between the central coaxial line and the outer radial line. Making use of the $47^{\circ}$ and $90^{\circ}$ 2-stage conical connector, the return loss lower than 30dB was obtained on the operating frequency range of 5GHz. The total return loss of the designed divider/combiner was lower than 20dB on the frequency range of 5GHz for the partition number N=11, N=12 and N=16.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 1997년도 추계학술대회논문집; 한국과학기술회관; 6 Nov. 1997
• /
• pp.36-42
• /
• 1997

A prototype of 500Wh class flywheel energy storage device was designed and manufactured to check the previously predicted system performance. The system was intentionally designed to show rigid body behavior up to the maximum operating speed of 60000Tpm and to have its 2nd rigid critical mode, of which nodal point lies on the flywheel center of mass, around 4000 to 6000rpm with radial magnetic bearing stiffness of l.e+6 N/m. Numerous experiments an the system behavior showed that the PM axial bearing, designed utilizing a commercial code, acts as resonably as predicted and, most importantly, the system becomes stable after the 2nd critical speed. The EM radial bearing, however, was found out to have orthotropic property with much less radial stiffness values than expected, so that it was observed that the 2nd forward and backward critical modes were excited at 310 and 590rpm respectively with larger vibration amplitudes. Thus, in order to improve the system dynamic behavior, the EM radial bearing is currently being re designed so as to get bigger stiffness and, in turn, smoother operation of the system.

• Journal of Electrical Engineering and Technology
• /
• 제7권4호
• /
• pp.636-645
• /
• 2012

This study introduces an information granular-based fuzzy radial basis function neural networks (FRBFNN) based on multiobjective optimization and weighted least square (WLS). An improved multiobjective space search algorithm (IMSSA) is proposed to optimize the FRBFNN. In the design of FRBFNN, the premise part of the rules is constructed with the aid of Fuzzy C-Means (FCM) clustering while the consequent part of the fuzzy rules is developed by using four types of polynomials, namely constant, linear, quadratic, and modified quadratic. Information granulation realized with C-Means clustering helps determine the initial values of the apex parameters of the membership function of the fuzzy neural network. To enhance the flexibility of neural network, we use the WLS learning to estimate the coefficients of the polynomials. In comparison with ordinary least square commonly used in the design of fuzzy radial basis function neural networks, WLS could come with a different type of the local model in each rule when dealing with the FRBFNN. Since the performance of the FRBFNN model is directly affected by some parameters such as e.g., the fuzzification coefficient used in the FCM, the number of rules and the orders of the polynomials present in the consequent parts of the rules, we carry out both structural as well as parametric optimization of the network. The proposed IMSSA that aims at the simultaneous minimization of complexity and the maximization of accuracy is exploited here to optimize the parameters of the model. Experimental results illustrate that the proposed neural network leads to better performance in comparison with some existing neurofuzzy models encountered in the literature.

• 한국항공우주학회지
• /
• 제36권9호
• /
• pp.898-906
• /
• 2008

본 연구에 적용된 터빈은 2단으로 구성되며, 첫 번째 단에는 축류형 터빈이 적용되고 두 번째 단에는 반경류형 터빈이 적용되었다. 축류형 터빈에서 동익의 평균반경은 70mm 이며, 반경류형 터빈의 외경은 입구에서 68mm였다. 실험에서 반경류형 터빈의 경우에는 두 개의 다른 형태가 적용되었으며, 최적의 설계변수를 확인하기 위하여 노즐의 각도를 3가지로 변경하면서 실험을 수행하였다. 터빈의 형상에 따른 성능평가를 위하여 총비토오크를 기준으로 비교하였다. 실험의 결과에서 낮은 부분분사에서 작동하면서 고토오크를 얻기 위한 소형터빈의 성능에는 노즐 각도가 가장 중요한 설계변수임을 보여주었다. 부분분사율이 3.4%이면서 노즐의 분사각도가 $75^{\circ}$인 경우에 두 번째 단에 반경류형 터빈을 장착하였을 때 총비토오크는 13%향상하는 결과를 보여주었다.

• 전기학회논문지
• /
• 제66권5호
• /
• pp.833-842
• /
• 2017

In this study, the design methodology of radial basis function neural networks based on incremental K-means clustering is introduced for learning and processing the big data. If there is a lot of dataset to be trained, general clustering may not learn dataset due to the lack of memory capacity. However, the on-line processing of big data could be effectively realized through the parameters operation of recursive least square estimation as well as the sequential operation of incremental clustering algorithm. Radial basis function neural networks consist of condition part, conclusion part and aggregation part. In the condition part, incremental K-means clustering algorithms is used tweights of the conclusion part are given as linear function and parameters are calculated using recursive least squareo get the center points of data and find the fitness using gaussian function as the activation function. Connection s estimation. In the aggregation part, a final output is obtained by center of gravity method. Using machine learning data, performance index are shown and compared with other models. Also, the performance of the incremental K-means clustering based-RBFNNs is carried out by using PSO. This study demonstrates that the proposed model shows the superiority of algorithmic design from the viewpoint of on-line processing for big data.

• 한국통신학회논문지
• /
• 제28권5C호
• /
• pp.452-460
• /
• 2003

본 논문에서는 optimal Bayesian equalization solution인 RBF(radial basis function)를 이용한 등화기 (RE)의 구조를 보다 단순화하고, 비선형 왜곡 등의 심각한 정보 신호의 손상에 대한 보상 능력을 향상시키기 위하여 비선형 다층 결합을 갖는 RBF측 이용한 등화기(RNE)를 새로이 제안한다. 기존의 RE는 RBF로 구성된 은닉층의 출력 값을 선형 결합하여 등화기 출력을 얻는다. 이와 달리 새로이 제안하는 RNE는 기존의 RE에서 RBF로 구성된 은닉층의 출력 값에 대한 결합 기법으로 perceptron을 이용한 비선형 다층 결합을 사용한다. 제안한 equalizer를 결정궤환 방식이 있는 경우와 없는 경우의 등화기로 각각 구현한다. 실험 결과 제안한 등화기는 선형 간섭이 존재하는 디지털 통신 시스템과 비선형 왜곡이 존재하는 자기기록 시스템에서보다 간단한 구조로 기존의 optimal Bayesian 등화기와 거의 같거나 우수한 비트 오류 화률 성능 및 MSE(men squared error) 수렴 특성을 나타내었다.