• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.149-152
• /
• 2002

본 연구에서는 밸브의 입출력 류량 검출 센싱 장치 및 류량 성능 특성 곡선을 측정하는 소프트웨어를 개발하였다. 본 개발품은 기체 또는 액체의 양을 조절하는 밸브의 정밀한 제품을 생산할 수 있는 시스템이다. 멤버쉽함수의 최적한 폭을 자기동조에 의해 선정할 수 있었으며, 이를 이용하여 밸브의 압력 제어 성능을 보다 정밀하게 보정 할 수 있었다. 기체 또는 액체의 유량을 조절하는 감압 자동 조절밸브의 성능을 온라인으로 시험 할 수 있는 소프트웨어를 국산화하였다. 본 제품의 개발 결과 우수한 성능을 가진 감압 밸브 성능자동 보정 시험 검사용 소프트웨어임을 확인하였다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.236-243
• /
• 1998

퍼지 제어기는 유도전동기에 대한 정확한 수학적 모델링의 과정 없이 IF-THEN 규칙으로 제어하는 비선형 제어기로서 과도 응답 특성과 외란에 대한 강인성 면에서 고전 제어 방식보다 우수한 성능을 보여준다. 그러나 입출력 변수의 공간을 균등하게 나누고 일정한 형태의 삼각형 멤버쉽 함수를 이용한 퍼지 제어기는 한정된 성능 이상을 기대할 수없다. 다라서 퍼지 제어기의 성능을 항상시키기 위해서는 멤버쉽 함수의 폭과 위치를 조정하는 것이 필요하다. 본 연구에서는 퍼지 제어기의 각 변수에 할당된 삼각형 멤버쉽 함수의 폭을 유도 전동기의 광범위한 속도에서의 과도 응답 상태에 EK랄 rkqustlzladmfhTJ 유도 전동기의 성능을 향상시키는 방법에 대해 연구하였다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.117-122
• /
• 1998

A servo system requires faster and more accurate dynamic reponses. Generally a PD control is mainly used to obtain the precision, and in the other hand a fuzzy control to improve the transient response and to cope with the nonlinearity of systems. Recently hybrid control, which is attempted to combine the advantages of PD control and a Fuzzy control was proposed, but this technique requires complicate design procedures. Therefore in this paper, designed on the Fuzzy controller with a various series rules, width of membership functions. And also it was showed to have the excellent adaptive performances against disturbances and the usefulness of this controller from the results of simulations.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.4
• /
• pp.110-118
• /
• 1997

Multi-layer neural networks with error back-propagation algorithm have a great potential for identifying nonlinear systems with unknown characteristics. However, because they have a demerit that the speed of convergence is too slow, various methods for improving the training characteristics of backpropagition networks have been proposed. In this paper, a fuzzy division method is proposed to improve the convergence speed, which can find out an effective fuzzy division by the tuning of membership function and independently train each neural network after dividing the network model into several parts. In the simulations, the proposed method showed that the optimal fuzzy partitions could be found from the arbitray initial ones and that the convergence speed was faster than the traditional method without the fuzzy division.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2005.11a
• /
• pp.373-376
• /
• 2005

본 논문에서는 이와 같은 요청에 부합되는 강인한 처지제어기를 얻고자, 다층 신경회로망을 이용하여 퍼지제어기 멤버쉽 함수의 전건부 및 후건부 파라미터들을 시스템에 알맞게 자기 조정하기 위해 최급구배법(Steepest Gradient Method)에 근거한 오차 역전파 알고리즘으로 적응 학습시킬 수 있는 뉴로-퍼지제어기 (Neuro-Fuzzy Control : NFC)의 구조 및 알고리즘을 제안하였다.

• 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.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.5 no.2
• /
• pp.58-69
• /
• 1995

In this paper GFI (Generalized Fuzzy Isodata) and FI (Fuzzy Isodata) algorithms are studied and applied to the tire tread pattern classification problem. GFI algorithm which repeatedly grouping the partitioned cluster depending on the fuzzy partition matrix is general form of GI algorithm. In the constructing the binary tree using GFI algorithm cluster validity, namely, whether partitioned cluster is feasible or not is checked and construction of the binary tree is obtained by FDH clustering algorithm. These algorithms show the good performance in selecting the prototypes of each patterns and classifying patterns. Directions of edge in the preprocessed image of tire tread pattern are selected as features of pattern. These features are thought to have useful information which well represents the characteristics of patterns.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.5
• /
• pp.701-706
• /
• 2007

Recently, a number of researches about linear magnetorheological(MR) damper using valve-mode characteristics of MR fluid have sufficiently undertaken, but researches about rotary MR damper using shear-mode characteristics of MR fluid are not enough. In this paper, we performed vibration control of shear-mode MR damper for unlimited rotating actuator of mobile robot. Also fuzzy logic based vibration control for shear-mode MR damper is suggested. The parameters, like scaling factor of input/output and center of the triangular membership functions associated with the different linguistic variables, are tuned by genetic algorithm. Simulation results demonstrate the effectiveness of the fuzzy-skyhook controller for vibration control of shear-mode MR damper under impact force.

• Journal of Advanced Navigation Technology
• /
• v.16 no.4
• /
• pp.586-592
• /
• 2012

One approach of the control of a nonlinear system that has gained some success employs a fuzzy structure in cooperation with a neural network(ANFIS). The traditional ANFIS can only model and control the process in single-dimensional output nature in spite of multi-dimensional input. The membership function parameters are tuned using a combination of least squares estimation and back-propagation algorithm. In the case of a mobile robot, we need to drive left and right wheel respectively. In this paper, we proposed the control system architecture for a mobile robotic system that employs the 2-input 2-output ANFIS controller for trajectory tracking. Simulation results and preliminary evaluation show that the proposed architecture is a feasible one for mobile robotic systems.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.1
• /
• pp.61-66
• /
• 2002

A position control algorithm for a flexible manipulator is studied. The proposed algorithm is based on a fuzzy theory with a Steady State Genetic Algorithm(SSGA) and an Adaptive Genetic Algorithms(AGA). The proposed controller for a flexible manipulator have decreased 90.8%, 31.8%, 31.3% in error when compared with a conventional fuzzy controller, fuzzy controller using neural network, fuzzy controller using evolution strategies, respectively when the weight and the velocity of end-point are 0.8k9 and 1m/s, respectively.