• Proceedings of the KIPE Conference
• /
• 2005.07a
• /
• pp.333-335
• /
• 2005

In this paper, supposed to solve these problem to PID parameters controller algorithm using ANN. In the proposed algorithm, the parameters of the controller were adjusted to reduce by on-line system the error of the speed of IM. In this process, EBPANN was constituted to an output error value of an IM and conspired an input and output. The performance of the self-tuning controller is compared with that of the PID controller tuned by conventional method (Ziehler-Nichols). The effectiveness of the proposed control method is verified thought the Matlab Simulink and experimental results.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.3013-3015
• /
• 2000

The stabilization control of Inverted Pendulum(IP) system is difficult because of its nonlinearity and structural unstability. Futhermore, a series of conventional techniques such as the pole placement and the optimal control based on the local linearizations have narrow stabilizable regions, At the same time, the fine tunings of their gain parameters are also troublesome, Thus, in this paper, an Evolving Neural Network ControlleY(ENNC) which its structure and its connection weights are optimized simultaneously by Real Variable Elitist Genetic Algorithm (RVEGA) was presented for stabilization of an IP system with nonlinearity, This proposed ENNC was described by a simple genetic chromosome. Through the simulation and experimental results, we showed that the finally acquired optimal ENNC was very useful in the stabilization control of IP system.

• Proceedings of the KIEE Conference
• /
• 1998.07c
• /
• pp.1024-1026
• /
• 1998

In this paper we present a Neural network approach to select weighting matrices of Linear-Quadratic-Gaussian (LQG) controller for TCSC control. The selection of weighting matrices is usually carried out by trial and error. A weighting matrices of LQG control selected effectively using Neural network. It is shown that simulation results in application of this method to one machine infinite bus system are satisfactory.

• Proceedings of the KIEE Conference
• /
• 2000.07b
• /
• pp.1159-1161
• /
• 2000

This paper presents a speed control system of induction motor using neural network The speed control of induction motor was designed to NNC(Neural Network Controller) and NNE(Neural Network Estimator) used backpropagation, the NNE was constituted to be get an error value of output of an induction motor and conspire an input/output. NNC is controled to be made the error of reference speed and actual speed decrease, and in order to determine the weighting of NNC can be back propagated through the NNE, and it is adapted to the outside circumstances and system characters with learning ability.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.2467-2469
• /
• 2000

In this paper, the DSP implementation of induction motor drive is presented on the viewpoint of the design and experiment. The speed estimation of control system for induction motor drive is designed on the base of neural network speed estimator. This neural network speed estimator is experimentally applied to the induction motor system. This system provides the satisfactory results.

• Proceedings of the KIEE Conference
• /
• 1998.07a
• /
• pp.257-259
• /
• 1998

The Switched Reluctance Motor (SRM) has good properties to the adjustable speed control. But, high torque ripple and noise decrease this merit and make unstable state. Also, because of the saturation in the magnetic circuit, it is difficult to predict the inductance profile. If the inductance pronto is known, it's possible to make flat-top torque by applying some control strategy. This paper suggests method to develope flat-top torque using a Artificial Neural Network(ANN) method that can calculate a nonlinear inductance profile.

• Proceedings of the KIEE Conference
• /
• 1998.11b
• /
• pp.499-501
• /
• 1998

In this paper, we present a self-compensating PID controller which consists of a conventional PID controller that controls the linear components and a neural controller that controls the higher order and nonlinear components. This controller is based on the Harris's concept where he explained that the adaptive controller consists of the PID control term and the disturbance compensating term. The resulting controller's architecture is also found to be very similar to that of Wang's controller. This controller adds a self-tuning ability to the existing PID controller without replacing it by compensating the control errors through the neuro-controller. When applied to an actual magnetic levitation system which is known to be very nonlinear, it has also produced an excellent results.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.807-809
• /
• 1995

In this paper, a design of the sliding mode controller using neural networks is proposed. The overall control system consists of a neural network controller and a reaching mode control input. The neural network controller approximates the equivalent control on the sliding surface and reaching mode control input is used to bend the entire system trajectories toward the sliding surface. The proposed controller is applied to the position control of a DC servo motor.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.600-602
• /
• 1995

The paper presents neural network control techniques for load frequency control of two area power system. Using learning algorithm of error back propagation after learning accept input on the optimal control $e_{i}$, $\dot{e}_{i}$, and $u_{i}$ frequency characteristic and tie-line load flow characteristic investigated dynamic. From result simulation, frequency deviation and tie-line load flow deviation have reduction remarkable.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.855-858
• /
• 1995

A neural network has very simple construction (input, output and connection weight) and then it can be robusted against some disturbance. In this paper, we proposed a neuro-controller using a Multi-Layered neural network which is combined with PD controller. The proposed neuro-controller is learned by backpropagation learning rule with momentum and neuro-controller adjusts connection weight in neural network to make approximate dynamic model of DC Servo motor. Computer Simulation results show that the proposed neuro-controller's performance is better than that of origianl PD controller.