• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.10a
• /
• pp.439-440
• /
• 2004

전력시스템의 부하주파수제어는 전력계통운용에 있어서 가장 중요하게 다루어야 한다. 본 논문에서는 강인한 퍼지제어기를 얻고자, 다층 신경회로망을 이용하여 퍼지제어기 멤버쉽 함수의 전건부 및 후건부 파라미터들을 시스템에 알맞게 자기 조정하기 위해 최급구배법에 근거한 오차 역전파 알고리즘으로 적응 학습시킬 수 있는 뉴로-퍼지제어기의 구조 및 알고리즘을 제안하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.46.3-46
• /
• 2001

The overall aim of this research is to develop a computer communication interface based on brain-wave bio potentials for physically disabled people. The work focuses on using EOG and EMG signals to input characters one by one using cursor movements on a GUI screen. The Cyberlink TM system is used to acquire brain waves in real time with electrodes. EMG and EOG signals are used to direct a cursor in order to select, or to click on a character on the screen. We present a novel method for automatic EOG pattern detection by using wavelet transforms with a neuro-fuzzy approach ...

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.102.1-102
• /
• 2002

In this paper, we propose Self-organizing neurofuzzy networks(SONFN) and discuss their comprehensive design methodology. The proposed SONFN is generated from the mutually combined structure of both neurofuzzy networks (NFN) and polynomial neural networks(PNN) for model identification of complex and nonlinear systems. NFN contributes to the formation of the premise part of the SONFN. The consequence part of the SONFN is designed using PNN. The parameters of the membership functions, learning rates and momentum coefficients are adjusted with the use of genetic optimization. We discuss two kinds of SONFN architectures and propose a comprehensive learning algorithm. It is shown that this network...

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2002.07a
• /
• pp.176-181
• /
• 2002

국내 저온저장고의 문제점은 재래식 제어방식과 냉각방식으로 인한 온도분포의 불균일과 시스템 성능 저해, 청과물의 생리적인 특성을 고려하지 알은 냉기의 유속과 습도제어, 청과물의 저온저장 중 발생되는 환경가스 제거기술의 미흡으로 인한 땀은 감모율 발생 그리고 청과물의 생리적인 특성을 고려하지 않은 저온저장고의 최적 설계기술 미흡 등을 들 수 있다. (중략)

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1995.10b
• /
• pp.243-248
• /
• 1995

본 논문에서는 신경회로망의 학습능력을 이용하여 AC 모터의 속도제어에 이용된 기 존의 PI제어기의 문제점을 보완하고자 한다. 기존의 아날로그 PI제어기에서는 각 비례, 적분 파라메타를 개발자가 조정하여 고정하면 부하가 변동될 경우 적응성이 떨어지는 문제점을 안고 있었다. 본 논문에서 제시된 디지털 신경망제어기는 학습을 통해 새로운 환경에 적응 가능하다는 점에 가정하여 설계하고 성능을 비교 평가하였다. 본 논문에서 사용된 신경회로 망의 구조는 신경망중에서 가장 범용적으로 사용되는 다층 퍼셉트론 모델구조를 선택하였 다. 신경망 제어기장치로는 인텔 8097 마이크로 콘트롤러를 이용하였다.

• Journal of Korean Society of Forest Science
• /
• v.104 no.2
• /
• pp.277-284
• /
• 2015

This study aims to evaluate the impact of forest therapy on neuro-cognitive, psychosocial, and physiological aspect of adolescent internet addiction risk group. We have classified potential and high risk user group as internet addiction risk group according to the criteria of Korean Internet Addiction Proneness Scale(K Scale). Based on the results of k-scale from the adolescents in metropolitan area from May to July 2013, 25 people were selected as Internet addiction risk group. We have randomized 13 participants joining forest therapy camp and 12 participants not joining one, and analyzed the change of the two groups with Continuous Performance, Kimberly S. Young, Connor-Davidson Resilience, Relationship Change Scale, heart rate variability and cortisol. Statistically significant changes were observedd in neuro-cognitive, psychosocial, and physiological variables, Through this study, we can consider that the therapy healing may relieve the level of internet addiction and can be an alternative to control emotional stability and impulsive behavior.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2261-2263
• /
• 2001

Fuzzy controller design consists of intuition, and any other information about how to control system, into a set of rules. These rules can then be applied to the system. It is very important to decide parameters of IF-THEN rules. Because fuzzy controller can make more adequate force to the plant by means of parameter optimization, which is accomplished by learning procedure. In this paper, we apply fuzzy controller designed to the Swing-UP Inverted pendulum.

• Journal of information and communication convergence engineering
• /
• v.8 no.2
• /
• pp.205-211
• /
• 2010

In this study, a Magnetic stimulation Pulse Train control technique is introduced and applied to Flyback converter operating in discontinuous conduction mode. In contrast to the conventional pulse width modulation control scheme, the principal idea of a Magnetic stimulation Pulse Train is to achieve output voltage regulation using high and low power pulses. The proposed technique is applicable to any converter operating in discontinuous conduction. However, this work mainly focuses on Flyback topology. In this paper, the main mathematical concept of the new control algorithm is introduced and simulations as well as experimental results are presented.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1993.10a
• /
• pp.402-405
• /
• 1993

This paper presents design.dynamic modeling and control issues of a novel type of an ER valve-cylinder system incorporating with an electro-rheological(ER) fluid. The yield stress of the ER fluid to be employed to the proposed system is evaluated as a function of applied electric fields. The design and manufacturing process of the ER valve which features fast system response and simple mechanism are undertaken on the basis of model parameters. The governing equation for the hydraulic and pneumatic model is constructed by incorporation with the field-dependent Bingham behavior of the ER fluid. An effective neuro controller is proposed to realize an accurate position control.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.51 no.2
• /
• pp.99-104
• /
• 2002

In this paper, we construct a hybrid intelligent controller based on a fusion scheme of GA(Genetic Algorithm) and FCM(Fuzzy C-Means) clustering-based ANFIS(Adaptive Neuro-Fuzzy Inference System). In the structure identification, a set of fuzzy rules are generated for a given criterion by FCM clustering algorithm. In the parameter identification, premise parameters are optimally searched by adaptive GA. On the other hand, consequent parameters are estimated by RLSE(Recursive Least Square Estimate) to reduce the search space. Finally, we applied the proposed method to the truck backer-upper control and obtained a better performance than previous works.