• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2008년도 제39회 하계학술대회
• /
• pp.1140-1141
• /
• 2008

The paper proposes a novel control algorithm for tracking maximum power of PV generation system. The maximum power of PV array is determinated by a insolation and temperature. Prior considered the term in PV generation system is how maximum power point is accurately tracked. The paper proposes a Fuzzy-Neuro control algorithm so as to accurately track those maximum power points. The proposed control algorithm comprises the antecedence part of fuzzy rule and clustering method, multi-layer neural network in the consequent part. Fuzzy-Neuro has the advantages which are depicted both high performance and robustness in Fuzzy control and high adaptive control in Neural Network. Specially, it can show the outstanding control performance for parameter variations appling to non-linear character of PV array. In paper, the tracking speed and the accuracy prove the validity through comparing a proposed algorithm with a conventional one.

• 한국융합학회논문지
• /
• 제9권7호
• /
• pp.231-240
• /
• 2018

자동차 산업은 국제유가 상승, 차량가격 상승 등 다양한 위기에 직면해 있다. 정부 규제완화와 더불어 생산 효율성 증가를 위한 경영개선 노력이 필요하다. 본 논문에서는 조달물류 개선을 목표로 실제 회사에서 사용 중인 요인들을 바탕으로 Fuzzy-AHP-TOPSIS를 활용하여 조달물류 평가모델을 구축하였다. G사 자동차 3개 공장을 평가대상으로 Fuzzy-AHP 분석한 결과, 장기 품질문제 해결, 자재결품 정지시간 최소화, 장비사고 방지, 단기 품질문제 해결이 가장 중요한 요인으로 파악되었다. TOPSIS 분석결과 B공장의 조달물류가 가장 잘 이루어지고 있는 것으로 나타났다. 제시된 평가모델을 사용하여 향후 주기적인 조달물류 관련 평가가 가능하며, 이는 자동차 산업 효율화에 기여할 수 있다는 시사점을 갖는다.

• 디지털융복합연구
• /
• 제19권8호
• /
• pp.319-325
• /
• 2021

무선 기술의 고도화 및 이동통신 기술의 인프라가 빠르게 성장함에 따라 AI 기반 플랫폼을 적용한 시스템이 사용자의 주목을 받고 있다. 특히 사용자의 취향이나 관심사 등을 이해하고, 선호하는 아이템을 추천해주는 시스템은 고도화된 전자상거래 맞춤형 서비스 및 스마트 홈 등에 적용되고 있다. 그러나 이러한 추천 시스템은 다양한 사용자들의 취향이나 관심사 등에 대한 선호도를 실시간으로 반영하기 어렵다는 문제가 있다. 본 연구에서는 이러한 문제를 해소하기 위해 GRU(Gated Recurrent Unit) 언어 모델을 이용한 Fuzzy-AHP 기반 영화 추천 시스템을 제안하였다. 본 시스템에서는 사용자의 취향이나 관심사를 실시간으로 반영하기 위해 Fuzzy-AHP를 적용하였다. 또한 대중들의 관심사 및 해당 영화의 내용을 분석하여 사용자가 선호하는 요인과 유사한 영화를 추천하기 위해 GRU 언어 모델 기반의 모델을 적용하였다. 본 추천 시스템의 성능을 검증하기 위해 학습 모듈에서 사용된 스크래핑 데이터를 이용하여 학습 모델의 적합성을 측정하였으며, LSTM(Long Short-Term Memory) 언어 모델과 Epoch 당 학습 시간을 비교하여 학습 수행 속도를 측정하였다. 그 결과 본 연구의 학습 모델의 평균 교차 검증 지수가 94.8%로 적합하다는 것을 알 수 있었으며, 학습 수행 속도가 LSTM 언어 모델보다 우수함을 확인할 수 있었다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2002년도 춘계학술대회 및 임시총회
• /
• pp.199-202
• /
• 2002

This parer concerns a design methodology of the observer-based output-feedback digital controller for Takagj-Sugeno (TS) fuzzy systems using intelligent digital redesign (IDR). The term of IDR involves converting an analog fuzzy-mode-based controller into an equivalent digital one in the sense of state-matching. The considered IDR problem is viewed as convex minimization problems of the norm distances between linear operators to be matched. The stability condition is easily embedded and the separations principle is explicitly shown.

• Journal of Information Processing Systems
• /
• 제9권1호
• /
• pp.89-102
• /
• 2013

The paper presents a fuzzy based impulse noise filter for both gray scale and color images. The proposed approach is based on the technique of boundary discriminative noise detection. The algorithm is a multi-step process comprising detection, filtering and color correction stages. The detection procedure classifies the pixels as corrupted and uncorrupted by computing decision boundaries, which are fuzzified to improve the outputs obtained. In the case of color images, a correction term is added by examining the interactions between the color components for further improvement. Quantitative and qualitative analysis, performed on standard gray scale and color image, shows improved performance of the proposed technique over existing state-of-the-art algorithms in terms of Peak Signal to Noise Ratio (PSNR) and color difference metrics. The analysis proves the applicability of the proposed algorithm to random valued impulse noise.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1988년도 추계학술대회 논문집 학회본부
• /
• pp.118-121
• /
• 1988

Load forecasting is an important issue as for the economic dispatch and there have been many researches which are classfied into two classes, time series method and factor analysis method. But the former is not adaptive for a sudden change of a correlated factor and the latter is not inefficient as the factor estimation is not easy. To make matters worse, both of them are not good for the estimation of special days. It is because the load forecasting is not a problem modeled precisely in mathematics, but a problem requires experience and knowledge those can solve it case by case. In this viewpoint, an expert system is proposed which can use complicated experience of an expert by use of fuzzy decision.

• 제어로봇시스템학회논문지
• /
• 제13권4호
• /
• pp.335-343
• /
• 2007

This paper deals with the method to estimate the friction in a system. We study a nonlinear friction model to estimate the friction in an inverted pendulum and approximate the friction model using fuzzy basis functions expansion. To demonstrate the friction observer using FBFs, we derive a update rule based on the error term that is formed by the output from a real system and observer output with a friction estimate. And two compensation algorithms to improve the response of an inverted pendulum are proposed. The first method that a observer parameter is updated in on-line and the friction is compensated at the same time. The second method is to compensate the friction with observer parameter estimated priori. The two methods is compared through the experimental results.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제50권8호
• /
• pp.367-375
• /
• 2001

In Underwater Flight Vehicle depth control system, the followings must be required. First, it needs robust performance which can get over modeling error, parameter variation and disturbance. Second, it needs accurate performance which have small overshoot phenomenon and steady state error to avoid colliding with ground surface or obstacles. Third, it needs continuous control input to reduce the acoustic noise and propulsion energy consumption. Finally, it needs interpolation method which can sole the speed dependency problem of controller parameters. To solve these problems, we propose a depth control method using Fuzzy Sliding Mode Controller with feedforward control-plane bias term and Neural Network Interpolator. Simulation results show the proposed method has robust and accurate control performance by the continuous control input and has no speed dependency problem.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.445-445
• /
• 2000

This paper proposes the MIMO indirect adaptive fuzzy controller to control the two-link manipulators. The input-output linearization technique, equivalent control input plus integral term, augmented error model and recursive least square adaptive law are used fer the controller. The linear type of fuzzifier-defuzzifier fuzzy logic system used for nonlinear function makes easy to farm the error model and able to follow the adaptive system approach. Such that control approach, the control system is not required joint speed and accerelation measurement and easy to implement and tune. The simulation results showed that the proposed controller has good control performance, stability, very small tracking error, decoupling, fast convergence, robust to parameter variation and load.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2002년도 하계학술대회 논문집 D
• /
• pp.2525-2527
• /
• 2002

The objective of this paper is to design a force feedback controller for bilateral control of a master-slave manipulator system using adaptive fuzzy sliding mode control. In a bilateral control system, the motion of the master device is followed by slave the one. While the force applied to the slave is reflected on the master. In this paper a proposed controller applied to the system. Adding a switching control term to the input robustness is improved. Also the knowledge of the system dynamics is not needed. The computer simulation results show the performance of the proposed adaptive fuzzy sliding mode controller.