• Journal of the Korean Institute of Intelligent Systems
• /
• v.5 no.4
• /
• pp.77-86
• /
• 1995

The new architecture that fuzzy logic control(FLC) with difficulties for tuning membership function (MF) is parallel with neural networks(NN) to be learned from the output of FLC is proposed. Therefore proposed scheme has the characteristics to utilize the expert knowledge in design process, to be learned during the operation without any learning mode. In this architecture, the function of the FLC is to supply the sliding surface which is constructed on the phase plane by rule base for giving the desired control characteristics and learning criterion of NN and the stabilization of the control performance before NN is learned, The function of the NN is to let the system trajectory be tracked to the sliding surface and reached to the stable point.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.41 no.3
• /
• pp.17-24
• /
• 2004

We present a P-type iterative learning control(ILC) scheme for uncertain robotic systems that perform the same tasks repetitively. The proposed ILC scheme comprises a linear feedback controller consisting of position error, and a feedforward and feedback teaming controller updated by current velocity error. As the learning iteration proceeds, the joint position and velocity mrs converge uniformly to zero. By adopting the learning gain dependent on the iteration number, we present joint position and velocity error bounds which converge at the arbitrarily tuned rate, and the joint position and velocity errors converge to zero in the iteration domain within the adopted error bounds. In contrast to other existing P-type ILC schemes, the proposed ILC scheme enables analysis and tuning of the convergence rate in the iteration domain by designing properly the learning gain.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.6
• /
• pp.1182-1189
• /
• 1994

In this paper, we evaluate the performance of a fuzzy controller with a self-learning structure. The fuzzy controller is based on a fuzzy logic that approximates and effectively represents the uncertain phenomena of the real world. The fuzzy controller has control of a plant with a fuzzy inference logic. However, it is not easy to decide the membership function of a fuzzy controller and its controlrule. This problem can be solved by designing a self-learning controller that improves its own contropllaw to its goal with a performance table. The fuzzy controller is implemented with a 386PC, an interface board, a D/A converter, a PWM(Pulse Width Modulation) motor drive-circuit, and a sensing circuit, for error and differential of error. Since a Ball and Beam System is used in the experiment, the validity of the fuzzy controller with the self-learning structure can be evaluated through the actual experiment and the computer simulation of the real plant. The self-learning fuzzy controller reduces settling time by just under 10%.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.5
• /
• pp.393-396
• /
• 2002

This note investigates the necessity of properness constraint on iterative learning controllers from the viewpoint of the initial condition problem. It is shown that unless the iterative learning controller is proper, the teaming control input may grow unboundedly and thus not be feasible in practice, though the convergence of tracking error is theoretically guaranteed. In addition, this note analyzes the effects of initial condition misalignment in the iterative learning control system on the control input and convergence property.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.37 no.3
• /
• pp.72-83
• /
• 2000

This paper presents the implementation of the position control system for 3 phase induction motor using reaching mode controller and neural networks. The reaching mode controller is used to bring the position error and speed error trajectories toward the sliding surface and to train neural networks at the first time. The structure of the reaching mode controller consists of the switch function of sliding surface. And feedforward neural networks approximates the equivalent control input using the reference speed and reference position and actual speed and actual position measured form an encoder and, are tuned on-line. The reaching mode controller and neural networks are applied to the position control system for 3 phase induction motor and, are compared with a PI controller through computer simulation and experiment respectively. The results are illustrated that the output of reaching mode controller is decreased and feedforward neural networks take charge of the main part for the control action, and the proposed controllers show better performance than the PI controller in abrupt load variation and the precise control is possible because the steady state error can be minimized by training neural networks.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.1
• /
• pp.9-17
• /
• 2021

In this paper, we present a simple and fast supervised learning framework based on model predictive control so as to learn motion controllers for a physic-based character to track given example motions. The proposed framework is composed of two components: training data generation and offline learning. Given an example motion, the former component stochastically controls the character motion with an optimal controller while repeatedly updating the controller for tracking the example motion through model predictive control over a time window from the current state of the character to a near future state. The repeated update of the optimal controller and the stochastic control make it possible to effectively explore various states that the character may have while mimicking the example motion and collect useful training data for supervised learning. Once all the training data is generated, the latter component normalizes the data to remove the disparity for magnitude and units inherent in the data and trains an artificial neural network with a simple architecture for a controller. The experimental results for walking and running motions demonstrate how effectively and fast the proposed framework produces physics-based motion controllers.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.477-480
• /
• 2005

본 논문에서는 신경망과 유전자 알고리즘의 장점을 결합하고, 개선된 유전자 알고리즘 기반의 역전파 신경망 알고리즘을 이용한 신경망 학습 효과를 살펴 본다. 유전자 알고리즘을 이용한 신경망 학습은 비선형 함수를 이용하여 발생시킨 모의 자료를 통하여 수행하고 학습 수렴의 정도와 학습 속도 등을 비교할 수 있는 모의실험 결과를 일반 신경망 학습 결과와 함께 제시한다. 모의실험의 결과로서 유전자 알고리즘을 적용한 신경망 제어기가 일반 신경망 학습 결과보다 수렴 정확도 및 학습 속도에서 더 좋은 결과를 나타내 주고 있다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.289-295
• /
• 1998

본 논문은 빠른 학습과 정확한 근사 능력을 갖는 새로운 CMAC 신경망 기반 퍼지 제어기르 제안한다. 제안한 CMAC 신경망 기반 퍼지 제어기(CBFLC)는 한 학습 주기 동안 전향 및 역전파 연산시 신경망내 유닛중 극히 일부분만이 활성화되어 학습에 참가하므로 학습 시간이 매우 빠르고, 비퍼지화 연산시 소속 함수의 중심값 뿐 아니라 폭을 동시에 고려하여 정확한 근사화를 얻는다. 제안한 퍼지 제어기내 입？출력 소속 함수의 중심값 및 폭 등의 구조적 파라메터들은 역전파 알고리즘에 의해 갱신된다. 제안한 CMAC 신경망 기반 퍼지 제어기를 트럭 후진 주차문제에 적용하여 근사화 능력 및 제어 성능면에서 여러 다른 퍼지 제어기들과 비교한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.5
• /
• pp.395-400
• /
• 2000

In this paper, we propose a new neuro-fuzzy controller based on reinforcement learning. The proposed system is composed of neuro-fuzzy controller which decides the behaviors of an agent, and dynamic recurrent neural networks(DRNNs) which criticise the result of the behaviors. Neuro-fuzzy controller is learned by reinforcement learning. Also, DRNNs are evolved by genetic algorithms and make internal reinforcement signal based on external reinforcement signal from environments and internal states. This output(internal reinforcement signal) is used as a teaching signal of neuro-fuzzy controller and keeps the controller on learning. The proposed system will be applied to controller optimization and adaptation with unknown environment. In order to verifY the effectiveness of the proposed system, it is applied to collision avoidance of an autonomous mobile robot on computer simulation.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.19 no.6
• /
• pp.82-86
• /
• 2005

PID controller is widely used as automatic equipment for industry. However when a system has various characters of intermittence or continuance, a new parameter decision for accurate control is a bud task. As a method of solving this problem, in this paper, a teaming gain regulator as PID controller functions is presented. A propriety teaming gain of system is decided by a rule of Delta learning. The function of proposed loaming gain regulator is verified by simulation results of DC motor.