• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.05a
• /
• pp.581-582
• /
• 2006

This paper presents an integrated machining error compensation method based on PNN(Polynomial Neural Network) approach and inspection database of OMM(On-Machine-Measurement) system. To efficiently analyze the machining errors, two machining error parameters are defined and modeled using the PNN approach, which is used to determine machining errors for the considered cutting conditions. Experiments are carried out to validate the approaches proposed in this paper. In result, the proposed methods can be effectively implemented in a real machining situation, producing much fewer errors.

• Journal of Electrical Engineering and Technology
• /
• v.3 no.4
• /
• pp.520-527
• /
• 2008

This work focuses on the evaluation of active power filter which is controlled by fuzzy logic and neural network based controller for harmonic mitigation and power factor enhancement. The APF consists of a variable DC voltage source and a DC/AC inverter. The task of an APF is to make the line current waveform as close as possible to a sinusoid in phase with the line voltage by injecting the compensation current. The compensation current is estimated using adaptive neural network. Using the estimated current, the proposed APF is controlled using neural network and fuzzy logic. Computer simulations of the proposed APF are performed using MATLAB. The results show that the proposed techniques for the evaluation of APF can reduce the total harmonic distortion less than 3% and improve the power factor of the system to almost unity.

• Journal of Power Electronics
• /
• v.8 no.4
• /
• pp.354-362
• /
• 2008

This paper presents neural load torque compensation method which is composed of a deadbeat load torque observer and gains compensation by a parameter estimator. As a result, the response of the PMSM (permanent magnet synchronous motor) obtains better precision position control. To reduce the noise effect, the post-filter is implemented by a MA (moving average) process. The parameter compensator with an RLSM (recursive least square method) parameter estimator is adopted to increase the performance of the load torque observer and main controller. The parameter estimator is combined with a high performance neural load torque observer to resolve problems. The neural network is trained in online phases and it is composed by a feed forward recall and error back-propagation training. During normal operation, the input-output response is sampled and the weighting value is trained multi-times by the error back-propagation method at each sample period to accommodate the possible variations in the parameters or load torque. As a result, the proposed control system has a robust and precise system against load torque and parameter variation. Stability and usefulness are verified by computer simulation and experiment.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.51 no.10
• /
• pp.573-580
• /
• 2002

This paper presents neural load disturbance observer that used to deadbeat load torque observer and regulation of the compensation gain by parameter estimator As a result, the response of PMSM follows that of the nominal plant. The load torque compensation method is compose of a neural deadbeat observer. To reduce of the noise effect, the post-filter, which is implemented by MA process, is proposed. The parameter compensator with RLSM(recursive least square method) parameter estimator is suggested to increase the performance of the load torque observer and main controller. The proposed estimator is combined with a high performance neural torque observer to resolve the problems. As a result, the proposed control system becomes a robust and precise system against the load torque and the parameter variation. A stability and usefulness, through the verified computer simulation and experiment, are shown in this paper.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1820-1823
• /
• 1997

For the Cartesian space position controlled robot, it is required to have the accurate mapping from the Cartesian space to the joint space in order to command the desired joint trajectories correctly. since the actual mapping from Cartesian space to joint space is obtained at the joint coordinate not at the actuator coordinate, uncertainty in Jacobian can be present. In this paper, two feasible neural network schemes are proposed to compensate for the kinematic Jacobian uncertainties. Uncertainties in Jacobian can be compensated by identifying either actuator Jacobian off-line or the inverse of that in on-line fashion. the case study of the stenciling robot is examined.

• Proceedings of the KIEE Conference
• /
• 1994.07a
• /
• pp.294-297
• /
• 1994

A robust position tracking controller of the BLDDM sensitive to the load torque disturbance and inertia variation is constructed It is consisted of the linear feedback controller and the nonlinear feedforward compensator using the neural network. With effietive feedforward compensation of neural network, the robust position control can be obtained, which is verified by computer simulations.

• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.7
• /
• pp.84-90
• /
• 2003

This paper develops a control method that is composed of the proportional control algorithm and the learning algorithm based on the recurrent neural networks (RNN) for the position control of a pneumatic rodless cylinder. The proportional control algorithm is suggested for the modeled pneumatic system, which is obtained easily simplifying the system, and the RNN is suggested for the compensation of the modeling errors and uncertainties of the pneumatic system. In the proportional control, two zones are suggested in the phase plane. One is the transient zone for the smooth tracking and the other is the small movement zone for the accurate position control with eliminating the stick-slip phenomenon. The RNN is connected in parallel with the proportional control for the compensation of modeling errors and frictions, compressibilities, and parameter uncertainties in the pneumatic control system. This paper experimentally verifies the feasibility of the proposed control algorithm for such pneumatic systems.

• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.86-88
• /
• 2007

In the semiconductor manufacturing industry, the heterodyne laser interferometer plays as an ultra-precise measurement system. However, the heterodyne laser interferometer has some unwanted nonlinearity error which is caused from frequency-mixing. This is an obstacle to improve the measurement accuracy in nanometer scale. In this paper we propose a compensation algorithm based on RLS(recursive least square) method and artificial intelligence method, which reduce the nonlinearity error in the heterodyne laser interferometer. With the capacitance displacement sensor we get a reference signal which can be transformed into the intensity domain. Using the back-propagation Neural Network method, we train the network to track the reference signal. Through some experiments, we demonstrate the effectiveness of the proposed algorithm in measurement accuracy.

• Journal of Power Electronics
• /
• v.2 no.1
• /
• pp.1-10
• /
• 2002

An advanced active power filter for the compensation of instantaneous harmonic current components in nonlinear current load is presented in this paper. A novel signal processing technique using an adaptive neural network algorithm is applied for the detection of harmonic components generated by three-phase nonlinear current loads and this method can efficiently determine the instantaneous harmonic components in real time. The control strategy of the switching signals to compensate current harmonics of the three-phase inverter is also discussed and its switching signals are generated with the space voltage vector modulation scheme. The validity of this active filtering processing system to compensate current harmonics is substantiated on the basis of simulation results.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.2
• /
• pp.113-119
• /
• 2002

An FLNN-based neural network controller is applied to precise positioning of XY table with friction as the extension study of [11]. The neural network identifies the frictional farces of the table. Its weight adaptation rule, named the reinforcement adaptive learning rule, is derived from the Lyapunov stability theory. The experimental results with 2-DOF XY table verify the effectiveness of the proposed control scheme. It is also expected that the proposed control approach is applicable to a wide class of mechanical systems.