• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.29B no.7
• /
• pp.70-78
• /
• 1992

In this paper, an approach for 3-D object segmentation and classification, which is based on eigen-values of polynomial function as their surface features, using neural network is proposed. The range images of 3-D objects are classified into surface primitives which are homogeneous in their intrinsic eigenvalue properties. The misclassified regions due to noise effect are merged into correct regions satisfying homogeneous constraints of Hopfield neural network. The proposed method has advantage of processing both segmentation and classification simultaneously.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2000.11a
• /
• pp.85-88
• /
• 2000

In this paper, the ultra precision positioning system for piezoelectric actuator using hysteresis compensation has been developed. Piezoelectric actuators exhibit limited accuracy in tracking control due to their hysteresis nonlinearity. The main purpose of the proposed controller is to compensate the hysteresis nonlinearity of the piezoelectric actuator. The controller is composed of a PD, hysteresis compensation and neural network part in parallel manner, at first, the excellent tracking performance of the neural network controller was verified by experiments and was compared with the classical PD controller.

• Journal of information and communication convergence engineering
• /
• v.7 no.2
• /
• pp.125-130
• /
• 2009

A robust friction compensation scheme is proposed in this paper. The recurrent fuzzy neural network and friction parameter observer are developed with sliding mode based controller in order to obtain precise position tracking performance. For a servo system with incomplete identified friction parameters, a proposed control scheme provides a satisfactory result via some experiment.

• Proceedings of the KIEE Conference
• /
• 1989.11a
• /
• pp.397-400
• /
• 1989

This study is to design a method of parameter estimation for a second order linear time invarient system of self-tuning controller utilizing the neural network theory proposed by Hopfield. The result is compared with the other methods which are commonly used in controller theories.

• Proceedings of the KIEE Conference
• /
• 1992.07a
• /
• pp.236-238
• /
• 1992

This paper proposes a new algorithm to estimate time-varying parameters by combining KFSM(Kalman Filter with Shift Matrix) with neural network compansator. While the time varying parameters are estimated from KFSM, the error coverence of system, R(k) are compansated by neural network concurrently. The casestudy using computer simulation proves the usefullness and advantages of the proposed algorithm in this paper.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.128.3-128
• /
• 2001

In this paper we proposed that the speed of induction motor is controlled by a PI controller, which could control unknown motor using Neural Network for auto-tuning of the PI parameter. The parameters of the PI controller were adjusted to reduce the speed error of the controlled motor. The input parameters of the Neural Network controller are the speed, q-axis current, and speed reference of the induction motor respectively. The usefulness of proposed controller will be confirmed by simulation which we compare with conventional PI controller.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.146.1-146
• /
• 2001

The researches of science and engineering need the latest information from internet resources. But searching and filtering processes of appropriate web documents from huge internet resources are very complex as well as having some repeated procedures. In this paper, I propose a Personalized Agent System(PAS), which can filter World Wide Web Documents that the user is interested, such as papers. To do this, PAS uses a modified spreading activation neural network which 1 propose here. PAS observes the user´s local paper database to analyze, adapt and learn the user interests, and the then constructs the user-specified neural network model by the analyzed interests ...

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.113.1-113
• /
• 2001

The robust position control with the bound function of neural network structure is proposed for uncertain robot manipulators. The neural network structure presents the bound function and does not need the concave property of the bound function, The robust approach is to solve this problem as uncertainties are included in a model and the controller can achieve the desired properties in spite of the imperfect modeling. Simulation is performed to validate this law for four-axis SCARA type robot manipulators.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.1113-1119
• /
• 1989

Neural network control has many innovative potentials for intelligent adaptive control. Among many, it promises real time adaption, robustness, fault tolerance, and self-learning which can be achieved with little or no system models. In this paper, a dynamic robot controller has been developed based on a backpropagation neural network. It gradually learns the robot's dynamic properties through repetitive movements being initially trained with a PD controller. Its control performance has been tested on a simulated PUMA 560 demonstrating fast learning and convergence.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.1006-1011
• /
• 1991

In this paper, a neural network estimator which estimates the output of the wide range oxygen sensor is proposed, The neural network estimator is constructed to give the output of the wide range oxygen sensor from rpm, fuel injection time, throttle position, and output voltage of the exhaust gas oxygen sensor. And, using this estimator, PI controller for air-fuel ratio control is designed. Experiment results show that the proposed method gives good results for SONATA engine under light load and constant rpms.