• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.5
• /
• pp.60-66
• /
• 1997

This paper presents a fuzzy inference-based reinforcement learning algorithm of dynamci recurrent neural networks, which is very similar to the psychological learning method of higher animals. By useing the fuzzy inference technique the linguistic and concetional expressions have an effect on the controller's action indirectly, which is shown in human's behavior. The intervlas of fuzzy membership functions are found optimally by genetic algorithms. And using recurrent neural networks composed of dynamic neurons as action-generation networks, past state as well as current state is considered to make an action in dynamical environment. We show the validity of the proposed learning algorithm by applying it to the inverted pendulum control problem.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.11
• /
• pp.991-997
• /
• 2013

In this paper, we propose a CFWC (CCD and fuzzy PID based width control) scheme to obtain the desired delivery width margin of a vertical rolling mill in hot strip process. A WMS(width measurement system) is composed of two line scan cameras, an edge detection algorithm, a glitch filter, and so on. A dynamic model of the mill is derived from a gauge meter equation in order to design the fuzzy PID controller. The controller is a self-learning structure to select the PID gains from the error and error rate of the width margin. The effectiveness of the proposed CFWC is verified from simulation results under a width disturbance of the entry in the mill. Using a field test, we show that the performance of the width control is improved by the proposed control scheme.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.3
• /
• pp.151-158
• /
• 1996

As an approach to design the intelligent controller for an underwater vehicle, this paper will propose a neural controller with the fuzzy weight which can tune the ocntorl rule effectively. The initial weights of th efuzzy-neural controller are constructdd by priori-information based on fuzzy control theory and tuned automatically by learning. The proposed control scheme has two improtnat characteristics of adaptation and learning under the control environment. Also it has the advantage that the precise dynamic characteristics of an underwater vehicle may not be required. The effectiveness of the proposed scheme will be demonstrated by computer simulations of an underwater vehicle.

• Proceedings of the KAIS Fall Conference
• /
• 2007.05a
• /
• pp.150-153
• /
• 2007

The intent of this paper is to describe a neural network structure called multi dynamic neural network(MDNN), and examine how it can be used in developing a learning scheme for computing robot inverse kinematic transformations. The architecture and learning algorithm of the proposed dynamic neural network structure, the MDNN, are described. Computer simulations are demonstrate the effectiveness of the proposed learning using the MDNN.

• Advances in Computational Design
• /
• v.5 no.3
• /
• pp.233-260
• /
• 2020

The main purpose to introduce model based controller in proposed control technique is to provide better and fast learning of the floating dynamics by means of fuzzy logic controller and also cancelling effect of nonlinear terms of the system. An iterative adaptive dynamic programming algorithm is proposed to deal with the optimal trajectory-tracking control problems for autonomous underwater vehicle (AUV). The optimal tracking control problem is converted into an optimal regulation problem by system transformation. Then the optimal regulation problem is solved by the policy iteration adaptive dynamic programming algorithm. Finally, simulation example is given to show the performance of the iterative adaptive dynamic programming algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.712-715
• /
• 1997

In image jacobian based visual servoing, generally, inverse jacobian should be calculated by complicated coordinate transformations. These are required excessive computation and the singularity of the image jacobian should be considered. This paper presents a visual servoing to control the pose of the robotic manipulator for tracking and grasping 3-D moving object whose pose and motion parameters are unknown. Because the object is in motion tracking and grasping must be done on-line and the controller must have continuous learning ability. In order to estimate parameters of a moving object we use the kalman filter. And for tracking and grasping a moving object we use a fuzzy inference based reinforcement learning algorithm of dynamic recurrent neural networks. Computer simulation results are presented to demonstrate the performance of this visual servoing

• 제어로봇시스템학회:학술대회논문집
• /
• 1990.10a
• /
• pp.127-130
• /
• 1990

The fuzzy logic controller which can be applied to various industrial processes is quite often dependent on the heuristics of the experienced operator. The operator's knowledge is often uncertain. Therefore an incorrect control rule on the basis of the operator's information is a cause of bad performance of the system. This paper proposes a new self-learning fuzzy control method by the fuzzy system identification using the data pairs of input and output and arbitrary initial relation matrix. The position control of a DC servo motor model is simulated to verify the effectiveness of the proposed algorithm.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.245-248
• /
• 2000

In this paper we improve the performance of autonomous mobile robot by induction of reinforcement learning concept. Generally, the system used in this paper is divided into two part. Namely, one is neural-fuzzy and the other is dynamic recurrent neural networks. Neural-fuzzy determines the next action of robot. Also, the neural-fuzzy is determined to optimal action internal reinforcement from dynamic recurrent neural network. Dynamic recurrent neural network evaluated to determine action of neural-fuzzy by external reinforcement signal from environment, Besides, dynamic recurrent neural network weight determined to internal reinforcement signal value is evolved by genetic algorithms. The architecture of propose system is applied to the computer simulations on controlling autonomous mobile robot.

• Proceedings of the KIEE Conference
• /
• 1993.07a
• /
• pp.227-230
• /
• 1993

Recently, the development of novel control methodology enables us to improve the performance of AC-machine drives by using pulse width modulation (PWM) technique. Usually, the dynamic characteristic of induction motor (IM) has been represented by the 5-th order nonlinear differential equation. This dynamics, however, can be reduced to 3-rd order dynamics by applying direct control of IM input current. This methodology concludes that it is much easier to control IM by means of the field-oriented methods employing the current controller. Therefore a precise current control is crucial to achieve a high control performance both in dynamic and steady state operations. This paper presents an adaptive fuzzy current controller with artificial neural network (ANN) for field-oriented controlled IM. This new control structure is able to adaptively minimize a current ripple while maintaining constant switching frequency. Especially the proposed controller employs neuro-computing philosophy as well as adaptive learning pattern recognizing principles with respect to variations of the system parameters. The proposed approach is applied to the IM drive system, and its performance is tested through various simulations. Simulation results show that the proposed system, compared among several known classical methods, has a superb performance.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.2
• /
• pp.106-116
• /
• 1998

A position control algorithm of a flexible manipulator is studied. The proposed algorithm is based on an ACFAC(Automatic Constructed Fuzzy Adaptive Controller) system based on the neural network learning algorithms. The proposed system learns membership functions for input variables using unsupervised competitive learning algorithm and output information using supervised outstar learning algorithm. ACFAC does not need a dynamic modeling of the flexible manipulator. An ACFAC is designed that the end point of the flexible manipulator tracks the desired trajectory. The control input to the process is determined by error, velocity and variation of error. Simulation and experiment results show a robustness of ACFAC compared with the PID control and neural network algorithms.