• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.7
• /
• pp.728-733
• /
• 2009

This paper presents the compensation of mechanical deflection error in SCARA robot. End of robot gripper is deflected by weight of arm and pay-load. If end of robot gripper is deflected constantly regardless of robot configuration, it is not necessary to consider above mechanical deflection error. However, deflection in end of gripper varies because that moment of each axis varies when robot moves, it affects the relative accuracy. I propose the compensation method of deflection error using neural network. FEM analysis to obtain the deflection of gripper end was carried out on various joint angle, the results is used in neural network teaming. The result by simulation showed that maximum relative accuracy reduced maximum 9.48% on a given working area.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2003.04a
• /
• pp.312-318
• /
• 2003

We propose a new technique for the cruise control system design of a mobile robot with three drive wheel. The proposed control scheme uses a Gaussian function as a unit function in the fuzzy neural network and back propagation algorithm to train the fuzzy neural network controller in the framework of the specialized teaming architecture. It is proposed a learning controller consisting of too neural network-fuzzy based on independent reasoning and a connection net with fixed weights to simply the neural networks-fuzzy. The performance of the proposed controller is shown by performing the computer simulation for trajectory tracking of the speed and azimuth of a mobile robot driven by three independent wheels.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.7
• /
• pp.517-524
• /
• 2004

For real world applications of reinforcement learning techniques, function approximation or generalization will be required to avoid curse of dimensionality. For this, an improved function approximation-based reinforcement teaming method is proposed to speed up convergence by using CA-CMAC(Credit-Assigned Cerebellar Model Articulation Controller). To show that our proposed CACRL(CA-CMAC-based Reinforcement Learning) performs better than the CRL(CMAC- based Reinforcement Learning), computer simulation and experiment results are illustrated, where a swing-up control Problem of an acrobot is considered.

• Proceedings of the KIEE Conference
• /
• 1997.07c
• /
• pp.1137-1140
• /
• 1997

This paper presents a fuzzy-neural network controller technique on the load frequency control of two-area power system. Firstly, Fuzzy controller a series of initial selected rules are improved by means of the proposed technique. Secondly, scale factors for error, change rate of error and control input are optimized by the given error back-pagation teaming algorithms. Finally, the related simulation results show that the proposed fuzzy neural network controller technique are more powerful than conventional ones.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.179-181
• /
• 2007

This paper presents the desired position control of the mobile inverted pendulum system(MIP). The MIP is required to track the circular trajectory in the xy plane through the kinematic Jacobian relationship between the xy plane and the joint space. The reference compensation technique of the radial basis function(RBF) network is used as a neural network control method. The back-propagation teaming algorithm of the RBF network is derived and embedded on a DSP board. Experimental studies of tracking the circular trajectory are conducted.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.113-117
• /
• 2002

PID controllers, which have been widely used in industry, have a simple structure and robustness to modeling error. But it is difficult to have uniformly good control performance in system parameters variation or different velocity command. In this paper, we propose a nonlinear adaptive PR controller based on an Immune feedback mechanism and a gradient descent teaming. This algorithm has a simple structure and robustness to system parameters variation. To verify performances of the proposed nonlinear adaptive PID controller, the speed control of nonlinear DC motor Is peformed. The simulation results show that the proposed control systems are effective in tracking a command velocity under system parameters variation

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.4
• /
• pp.329-339
• /
• 2003

A neural network based adaptive controller design method is proposed for reconfigurable flight control systems in the presence of variations in aerodynamic coefficients or control effectiveness decrease caused by control surface damage. The neural network based adaptive nonlinear controller is developed by making use of the backstepping technique for command following of the angle of attack, sideslip angle, and bank angle. On-line teaming neural networks are implemented to guarantee reconfigurability and robustness to the uncertainties caused by aerodynamic coefficients variations. The main feature of the proposed controller is that the adaptive controller is designed with assumption that not any of the nonlinear functions of the system is known accurately, whereas most of the previous works assume that only some of the nonlinear functions are unknown. Neural networks loam through the weight update rules that are derived from the Lyapunov control theory. The closed-loop stability of the error states is also investigated according to the Lyapunov theory. A nonlinear dynamic model of an F-16 aircraft is used to demonstrate the effectiveness of the proposed control law.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.16 no.4
• /
• pp.351-357
• /
• 2003

An easy learning elevator originated is opened to compare the existed teaming equipment, and it had a high studied efficiency that the sequence control circuit can open and close with the wire. The structure of equipment to be controlled from the first floor to the fifth floors is demostrated by the constructive apparatus with the lamps to express the function of the open-close of the door according to the cage moving with a mechanical actuation of the forward reverse breaker and the motor of load, and the mechanical actuation of hand-operation control components of push-button S/W and L/S and relay etc. These components let connect each other in order to control of the elevator function with the auto program and the designed sequence control circuit. Consequently the cage could go and come till 1∼5 steps with an auto program of the elevator and the sequence control circuit. The sequence control circuit is controlled by the step of forward and reverse to follow as that the sensor function of L/S1 ∼ L/S5 let posit with the control switchs of S/W1 ∼ S/W5 of PLC testing panel and switchs of S/W1 ∼ S/W5 installed on the transparent acryl plate of the frame. In here, improved apparatus is the hand-auto operation combined learning equipment to study the principle and technique of the originate sequence control circuit and the auto program of PLC.

• Journal of the Korean Institute of Navigation
• /
• v.23 no.3
• /
• pp.35-44
• /
• 1999

This research aims to seek active control of ball-beam position stability by resorting to neural networks whose layers are given bias weights. The controller consists of an LQR (linear quadratic regulator) controller and a neural networks controller in parallel. The latter is used to improve the responses of the established LQR control system, especially when controlling the system with nonlinear factors or modelling errors. For the learning of this control system, the feedback-error learning algorithm is utilized here. While the neural networks controller learns repetitive trajectories on line, feedback errors are back-propagated through neural networks. Convergence is made when the neural networks controller reversely learns and controls the plant. The goals of teaming are to expand the working range of the adaptive control system and to bridge errors owing to nonlinearity by adjusting parameters against the external disturbances and change of the nonlinear plant. The motion equation of the ball-beam system is derived from Newton's law. As the system is strongly nonlinear, lots of researchers have depended on classical systems to control it. Its applications of position control are seen in planes, ships, automobiles and so on. However, the research based on artificial control is quite recent. The current paper compares and analyzes simulation results by way of the LQR controller and the neural network controller in order to prove the efficiency of the neural networks control algorithm against any nonlinear system.

• Journal of Korean Elementary Science Education
• /
• v.21 no.2
• /
• pp.143-157
• /
• 2002

The aims of this study are to develop web-based learning materials for science and environmental education of elementary school. The effect of environmental education was divided into eight to measure: the awareness of using web as environmental material, the ability to use web as environmental material. the awareness of environmental problems, the satisfaction for environmental education using web, the awareness of preserving local environment, self-leading ability to learn environment, the effect of using environment homepage, and the internalization of environmental awareness. This study obtained the following results; First, as a result of post-test, the average of the test group of web-based learning was 1.29 points higher than the control group having traditional learning in the awareness of using web as environmental material, showing a statistically significant difference. Second, as a result of post-test, the average of the test group of web-based learning was 2.80 points higher than the control group in the ability to use web as environmental material, showing a statistically significant difference. Third, as a result of post-test, the average of the test group of web-based learning was 1.10 points higher than the control group in the awareness of environmental problems, showing a statistically significant difference. Fourth, as a result of post-test, the average of the test group of web-based teaming was 0.89 points higher than the control group in the satisfaction for environmental education using web, showing a statistically significant difference. Fifth, as a result of post-test, the average of the test group of web-based learning was 1.70 points higher than the control group in the self-leading ability to learn environment, showing a statistically significant difference. Sixth, as a result of post-test, the average of the test group of web-based learning was 1.21 points higher than the control group in the effect of using environment homepage, showing a statistically significant difference. Finally, as a result of post-test, the average of the test group of web-based learning was 1.39 points higher than the control group in the internalization of environmental awareness, showing a statistically significant difference. Based on these results, it is assumed that the teaching method which applied web-based teaming to science and environmental education in elementary school is a effective strategy for elementary science and on environmental education.