• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.10a
• /
• pp.315-320
• /
• 1997

Rule minimization technique adapted from rough set theory was applied to remove redundant knowledge which is not necessary to make a knowledge base. New algorithm to diagnose fault using Improved Fuzzy Cognitive Maps(I-FCMs), and Fuzzy Associative Memory(FAM) is proposed. I-FCM[22] is superior to gathering knowledge from many experts and descries dynamic behaviors of systems very well. I-FCM is not only a knowledge base, but also a inference engine. FAM has learning capability like neural network[12]. Rule minimization and composition of I-FCM and FAM make it possible to construct compact knowledge base and breaks the border between inference engine and knowledge base.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10a
• /
• pp.441-446
• /
• 1992

We propose a control architecture for the fuzzy logic control of robot manipulators and a rule base derivation method for a fuzzy logic controller(FLC) using a neural network. The control architecture is composed of FLC and PD(positional Derivative) controller. And a neural network is designed in consideration of the FLC's structure. After the training is finished by BP(Back Propagation) and FEL(Feedback Error Learning) method, the rule base is derived from the neural network and is reduced through two stages - smoothing, logical reduction. Also, we show the performance of the control architecture through the simulation to verify the effectiveness of our proposed method.

• Proceedings of the KIEE Conference
• /
• 1998.07c
• /
• pp.1094-1096
• /
• 1998

An intelligent power transformer protective relaying algorithm based on fuzzy decision-making is proposed. To distinguish external faults with CT saturation, overexcitation and inrush conditions from internal faults, a newly designed fuzzy-rule base is used. The Dempster-Shafer's rule of combition is used for fuzzy inference. A series of the S/W and H/W tests show the proposed protection algorithm has practically sufficient sensitivity and selectivity.

• Proceedings of the KIEE Conference
• /
• 1993.07a
• /
• pp.436-438
• /
• 1993

A rule based fuzzy expert system in self-tune PID controllers is presented in this paper. The rule base. the core of the expert system, is extracted from the Wills' tuning map and the author's knowledge about the implicit relations between PID gains and controlled output response. The overall control system consists of the relay feedback scheme and the expert system, where the one is responsible for initial tuning and the other for subsequent tuning. The PID control system with the proposed fuzzy expert system, shows better convergence rate and control performances than those of a Litt in spite of the fact that the two rule bases are extracted from the same maps provided by Wills.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.689-693
• /
• 1996

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.16 no.5
• /
• pp.104-111
• /
• 2002

This paper presents a fuzzy rule extraction method using EM(Expectation-Maximization) algorithm and a design method of adaptive neuro-fuzzy control. EM algorithm is used to estimate a maximum likelihood of a GMM(Gaussian Mixture Model) and cluster centers. The estimated clusters is used to automatically construct the fuzzy rules and membership functions for ANFIS(Adaptive Neuro-Fuzzy Inference System). Finally, we applied the proposed method to the water temperature control system and obtained better results with respect to the number of rules and SAE(Sum of Absolute Error) than previous techniques such as conventional fuzzy controller.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.3 no.3
• /
• pp.173-183
• /
• 1998

In this paper, an auto-tuning method for fuzzy controller's membership functions based on the neural network is presented. The neural network emulator offers the path which reforms the fuzzy controller's membership functions and fuzzy rule, and the reformed fuzzy controller uses for speed control of induction motor. Thus, in the case of motor parameter variation, the proposed method is superior to a conventional method in the respect of operation time and system performance. 32bit micro-processor DSP(TMS320C31) is used to achieve the high speed calculation of the space voltage vector PWM and to build the self-learning fuzzy control algorithm. Through computer simulation and experimental results, it is confirmed that the proposed method can provide more improved control performance than that PI controller and conventional fuzzy controller.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.3 no.2
• /
• pp.138-145
• /
• 2003

Performance assessment was introduced to improvement of self-directed learning and method of assessment for differenced learning as the seventh educational curriculum is enforced. Performance assessment is overcoming limitation about problem solving ability and higher thinking abilities assessment that is problem of a written examination and get into the spotlight by way for quality of class and school normalization. But, performance assessment has problems about possibilities of assessment fault by appraisal, fairness, reliability, and validity of grading, ambiguity of grading standard, difficulty about objectivity security etc. This study proposes fuzzy performance assessment system to solve problem of the conventional performance assessment. This paper presented an objective and reliable performance assessment method through fuzzy reasoning, design fuzzy membership function and define fuzzy rule analyzing factor that influence in each sacred ground of performance assessment to account principle subject. Also, performance assessment item divides by formation estimation and subject estimation and designed membership function in proposed performance assessment method. Performance assessment result that is worked through fuzzy performance assessment system can pare down burden about appraisal's fault and provide fair and reliable assessment result through grading that have correct standard and consistency to students.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.24.2-27
• /
• 1996

This paper is a study on the fuzzy force control of a miniature gripper driven by piezoelectric bimorph actuator. The system is composed of two flexible cantilevers, a stepping motor, a laser displacement transducer and two semiconductor force sensors attached to the beams. Obtained results show that the present artificial finger system works well as a miniature gripper, which produces approximately 0.06N force in the maximum. Further, the fuzzy position/force control algorithm is applied to the soft-handing gripper for stable grasping of a object. It revealed that the fuzzy rule-based controller be efficient controller for the stable drive of the flexible miniature gripper. It also showed that two semiconductor strain gauges located in the flexible beam play an important roles for force control, position control and vibration suppression control.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.50 no.5
• /
• pp.233-240
• /
• 2001

This paper presents a time series prediction method using a fuzzy rule-based system. Extracting fuzzy rules by performing a simple one-pass operation on the training data is quite attractive because it is easy to understand, verify, and extend. The simplest method is probably to relate an estimate, x(n+k), with past data such as x(n), x(n-1), ..x(n-m), where k and m are prefixed positive integers. The relation is represented by fuzzy if-then rules, where the past data stand for premise part and the predicted value for consequence part. However, a serious problem of the method is that it cannot handle nonstationary data whose long-term mean is varying. To cope with this, a new training method is proposed, which utilizes the difference of consecutive data in a time series. In this paper, typical previous works relating time series prediction are briefly surveyed and a new method is proposed to overcome the difficulty of prediction nonstationary data. Finally, computer simulations are illustrated to show the improved results for various time series.