• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.173.4-173
• /
• 2001

This paper presents a stable nonlinear adaptive control for AUV(Autonomous Underwater Vehicle) by using neural network. AUV's dynamics are highly nonlinear, and their hydrodynamic coefficients vary with different operational conditions. In this paper, the nonlinear uncertainties of the AUV's dynamics are approximated by using LPNN(Linearly parameterized Neural Network). The presented controller is consist of three parallel terms; linear feedback control, sliding mode control, and adaptive control(LPNN). Lyapunov theory is used to guarantee the stability of tracking errors and neural network´s weights errors. Numerical simulations for nonlinear control of the AUV show the effectiveness of the proposed techniques.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.4
• /
• pp.341-349
• /
• 2004

In this paper, the decentralized neural network control of the reference compensation technique is proposed to control a 2-DOF inverted pendulum on an x-y plane. The cart with the 2-DOF inverted pendulum moves on the x-y plane and the 2-DOF inverted pendulum rotates freely on the x-y axis. Since the 2-DOF inverted pendulum is divided into two 1-DOF inverted pendulums, the decentralized neural network control is applied not only to balance the angle of pendulum, but also to control the position tracking of the cart. Especially, a circular trajectory tracking is tested for position tracking control of the cart while maintaining the angle of the pendulum. Experimental results show that position control of the inverted pendulum system is successful.

• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.2
• /
• pp.189-199
• /
• 1999

This paper presents an optimization algorithm for a stable Self Dynamic Neural Network(SDNN) using genetic algorithm. Optimized SDNN is applied to a problem of controlling nonlinear dynamical systems. SDNN is dynamic mapping and is better suited for dynamical systems than static forward neural network. The real-time implementation is very important, and thus the neuro controller also needs to be designed such that it converges with a relatively small number of training cycles. SDW has considerably fewer weights than DNN. Since there is no interlink among the hidden layer. The object of proposed algorithm is that the number of self dynamic neuron node and the gradient of activation functions are simultaneously optimized by genetic algorithms. To guarantee convergence, an analytic method based on the Lyapunov function is used to find a stable learning for the SDNN. The ability and effectiveness of identifying and controlling a nonlinear dynamic system using the proposed optimized SDNN considering stability is demonstrated by case studies.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.1012-1016
• /
• 1991

An effective visual servo control system for robotic manipulators based on neural networks is proposed. For this control system, firstly, one neural network is used to learn the mapping relationship between the robot's joint space and the video image space. However, in the proposed control scheme, this network is not used in itself, but its first and second derivatives are used to generate servo commands for the robot. Secondly, an adaptive Adaline network is used to identify the dynamics of the robot and also to generate the proper torque commands. Computer simulation has been performed indicating its superior performance. As far as the authors know, this is the first time attempt of the use of neural networks for a visual servo control of robots that compensates for their changing dynamics.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.1022-1027
• /
• 1991

A new method to control a robot manipulator by neural networks is proposed. The controller is composed of both a PD controller and a neural network-based feedforward controller. MLP(multi-layer perceptron) neural network is used for the feedforward controller and trained by BP(back-propagation) learning rule. Error terms for BP learning rule are composed of the outputs of a PD controller and the acceleration errors of manipulator joints. We compare the proposed method with existing ones and contrast performances of them by simulation. Also, We discuss the real application of the proposed method in consideration of the learning time of the neural network and the time required for sensing the joint acceleration.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1996.10a
• /
• pp.39-42
• /
• 1996

Modeling techniques such as linear regression have been used to predict hurricane activity many months in advance of the start of the hurricane season with some success. In this paper, we construct feedforward neural networks to model Atlantic basin hurricane activity and compare the predictions of our neural network models to the predictions produced by statistical models found in the weather forecasting literature. We find that our neural network models produce reasonably accurate predictions that, for the most part, compare favorably to the predictions of statistical models.

• 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.

• 제어로봇시스템학회:학술대회논문집
• /
• 1995.10a
• /
• pp.505-508
• /
• 1995

The automatic interpretation of awake background electroencephalogram (EEG), consisting of quantitative EEG interpretation and EEG report making, has been developed by the authors based on EEG data visually inspected by an electroencephalographer (EEGer). The present study was focused on the adaptability of the automatic EEG interpretation which was accomplished by the constructive neural network with forgetting factor. The artificial neural network (ANN) was constructed so as to give the integrative decision of the EEG by using the input signals of the intermediate judgment of 13 items of the EEG. The feature of the ANN was that it adapted to any EEGer who gave visual inspection for the training data. The developed method was evaluated based on the EEG data of 57 patients. The re-trained ANN adapted to another EEGer appropriately.

• 제어로봇시스템학회:학술대회논문집
• /
• 1995.10a
• /
• pp.119-122
• /
• 1995

Neural network has found wide applications in the system identification, modeling, and realization based on its function approximation capability. THe system governe dby nonlinear dynamics is hard to be identified by the neural network because there exist following difficulties. FIrst, the training samples obtained by the stae trajectory are apt to be nonuniform over the region of interest. Second, the system may becomje unstable while attempting to obtain the samples. This paper deals with these problems in discrete-time system and suggest effective solutions which provide stability and uniform sampliing by the virtue of robust control theory and heuristic algorithms.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.12
• /
• pp.1218-1225
• /
• 2008

This paper presents the design of a neural network based adaptive control for missile is presented. The application model is Exocet MM40, which is derived from missile DATCOM database. Acceleration of missile by tail Fin control cannot be controllable by DMI (Dynamic Model Inversion) directly because it is non-minimum phase system. So, the inner loop consists of DMI and NN (Neural Network) and the outer loop consists of PI controller. In order to satisfy the performances only with PI controller, it is necessary to do some additional process such as gain tuning and scheduling. In this paper, all flight area would be covered by just one PI gains without tuning and scheduling by applying mixture control technique of conventional controller and NN to the outer loop. Also, the simulation model is designed by considering non-minimum phase system and compared the performances to distinguish the validity of control law with conventional PI controller.