• Proceedings of the KIEE Conference
• /
• 1999.07b
• /
• pp.724-727
• /
• 1999

In this paper, the direct and indirect neural adaptive controller are combined based on the Lyapunov synthesis approach. The proposed adaptive controller is constructed from RBF neural network and a set of fuzzy IF-THEN rules. And the weighting parameters are adjusted on-line according to some adaptation law for the purpose of controlling the plant to track a given trajectory. In this scheme, fuzzy IF-THEN rules are used to decide the combined weighting factor. It is shown that all the signals in the closed-loop system are uniformly bounded under mild assumptions. The effectiveness of the proposed control scheme is demonstrated through the control of one-link rigid robotics manipulator.

• 제어로봇시스템학회:학술대회논문집
• /
• 1995.10a
• /
• pp.408-411
• /
• 1995

In this paper, we discuss the force control of flexible manipulators. Since the force control of flexible manipulators with planar one or two links using the distributed-parameter modeling has been the subject of a considerable number of publications until now, real time computations of the force control schemes are possible. But, application of those control schemes to multi-link spatial manipulators is fairly complicated. In this paper, we apply a concise hybrid position/force control scheme for a flexible manipulators. We use a lumped-parameter modeling for the flexible manipulators. The Hamilton's principle is applied to derive the equations of motion for the system and then, state-space model is obtained by the Lagrange's method. Finally, comparison of simulation results with experimental results is given to show the performance of our method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.05a
• /
• pp.456-459
• /
• 2001

In this paper, a wavelet neural network for adaptive control was proposed. The structure of this network is similar to that of the multilayer perceptron(MLP), except that here the sigmoid functions are replated by mother wavelet function in the hidden units. The simulation result showed the effectiveness of using the wavelet neural network structure in the adaptive control of one-link manipulator.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.2383-2385
• /
• 2000

It is proposed a new algorithm for a neural network adaptive tracking control scheme to improve performance in this paper. In supervisory control scheme, the upper and lower bound of the parameters are directly estimated by using RBF neural network without their information, and the weighting parameters of the control input are adjusted on-line by adaptation laws. As a result, the proposed algorithm assured that the output errors go to zero without relation to existing minimum approximation errors and disturbances. The effectiveness of the proposed algorithm is demonstrated through the simulation of one-link rigid robotics manipulator.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.2753-2755
• /
• 2000

In this paper, the robust position tracking cotroller for a brushless DC motor driving a one-link robot manipulator is proposed. By using the backstepping approach, the adaptive and robust controller is appropriately designed to ensure global stability. The proposed robust backstepping controller can compensate for estimation errors in system parameters in the system with no structural changes in the controller and without destruction of the stability. The closed-loop stability of the system is shown using Lyapunov techniques. The tracking errors are shown to be globally uniformly bounded.

• Journal of the Ergonomics Society of Korea
• /
• v.12 no.1
• /
• pp.17-24
• /
• 1993

Today, rapid development and timeliness of introducing a new product be- comes a more influencing factor of determing its competitive power due to a shortened product cycle, while rapid improvement of manufacturing technology makes product design and manufacturing fuse together. This implies that prod- uct usability evaluation and improvement starts right from its design phase, resulting in less development time and cost. To make this possible, proper as- sessment of human reach is one of essential functions for ergonomic product us- ability evaluation, specifically in the platform of computer-aided ergonomic evaluation models or any CAD system with a built-in man model. In this study, an analytic reach prediction algorithm ensuring the posture that human naturally takes, is presented by employing the methods developed for robot kinematics. Among robot kinematic methods for solving the multi-link system, the resolved motion method was found to be effective to solve human reach as a redundant manipulator model. Also, the joint range availability was used as a performance fonction to guarantee human naturalness. The result is expected to be directly applicable to product usability evaluations.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.28B no.9
• /
• pp.739-746
• /
• 1991

This paper develops a modified multilayer perceptron architecture which speeds up learning as well as the net's mapping accuracy. In Phase I, a cluster partitioning algorithm like the Kohonen's self-organizing feature map or the leader clustering algorithm is used as the front end that determines the cluster to which the input data belongs. In Phase II, this cluster selects a subset of the hidden layer nodes that combines the input and outputs nodes into a subnet of the full scale backpropagation network. The proposed net has been applied to two mapping problems, one rather smooth and the other highly nonlinear. Namely, the inverse kinematic problem for a 3-link robot manipulator and the 5-bit parity mapping have been chosen as examples. The results demonstrate the proposed net's superior accuracy and convergence properties over the original backpropagation network or its existing improvement techniques.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.296-300
• /
• 2004

A new MR cylinder with built-in valves using MR fluid (MR valve) is proposed for fluid power control systems. The MR or Magneto-Rheololgical fluid is a newly developed functional fluid whose obvious viscosity is controlled by the applied magnetic field intensity. The MR cylinder is composed of cylinder with small clearance and piston with electromagnet. The differential pressure is controlled by the applied magnetic field intensity. It has the characteristics of simple, compact and reliable structure. The size of MR cylinder and piston has ${\varphi}$60mm${\times}$259mm and ${\varphi}$58mm${\times}$136.5mm in face size respectively and 0.8mm in gap length. Through experiments on the static characteristics, it is found that the differential pressure is controlled by the applied magnetic field intensity under little influence of the flow rate, which corresponds to a pressure control valve. Effectiveness of the MR cylinder is demonstrated through the position control of one link MR manipulator.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.05a
• /
• pp.370-374
• /
• 1999

The proposed algorithm used the Hybrid teaming rule in the input and hidden layer, and Back-Propagation teaming rule in the hidden and output layer. From the results of simulation of tracking control with one link manipulator as a plant, we verify the usefulness of the proposed control method to compare with common direct adaptive neural network control method; proposed hybrid teaming rule showed faster loaming time faster settling time than the direct adaptive neural network using Back-propagation algorithm. Usefulness of the proposed control method is that it is faster the learning time and settling time than common direct adaptive neural network control method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.05a
• /
• pp.348-354
• /
• 1999

In recent years, a PID controller has been used as a major control method in real control processes. This controller requires a determination of PID control gains. But it is difficult to select the best gains theoretically. Thus there have been many approaches to determine them empirically Most of them are based on experience and knowledge. In this paper, we proposed a tuning method of the PID Parameters by using neural network. To show effectiveness of the proposed method, the simulation of DC motor and one link manipulator position control is carried out.