• 산업기술연구
• /
• 제24권A호
• /
• pp.99-107
• /
• 2004

This paper considers reinforcement learning control with the self-organizing map. Reinforcement learning uses the observable states of objective system and signals from interaction of the system and the environments as input data. For fast learning in neural network training, it is necessary to reduce learning data. In this paper, we use the self-organizing map to parition the observable states. Partitioning states reduces the number of learning data which is used for training neural networks. And neural dynamic programming design method is used for the controller. For evaluating the designed reinforcement learning controller, an inverted pendulum of the cart system is simulated. The designed controller is composed of serial connection of self-organizing map and two Multi-layer Feed-Forward Neural Networks.

• 조명전기설비학회논문지
• /
• 제28권8호
• /
• pp.54-61
• /
• 2014

This paper proposes a boost/flux-weakening controller (BFWC) for wide speed operation range having engine and interior permanent magnet synchronous generator (IPMSG) for special equipment vehicle. The proposed BFWC exploits direct torque/flux control (DTFC) scheme based on space vector modulation method to control the constant DC voltage output within the entire speed operation range of engine. And, to improve the response characteristics of maximum torque per ampere (MTPA) operation and flux-weakening operation, the MTPA and flux-weakening feed-forward controllers are applied. To estimate feasibility and usefulness of the proposed controller, the simulation and experimental results are compared.

• 한국공작기계학회논문집
• /
• 제15권6호
• /
• pp.105-113
• /
• 2006

This work is concerned with the development of digital contouring controller for multi-axial servosystems. Digital optimal contouring controller is proposed to coordinate each of the controllers of multiple feed drives and specifically improve the contouring performance. The optimal control formation includes the contour error explicitly in the performance index to be minimized. The contouring control is exercised for straight line and circular contours. Substantial improvement in contouring performance is obtained for a range of contouring conditions. Both steady state and transient error measures have been considered. The simulation study presented has established the potential of the proposed controller to improve contouring performance.

• Journal of Advanced Marine Engineering and Technology
• /
• 제26권5호
• /
• pp.544-553
• /
• 2002

The recent amount of container freight continuously has been increased, but the low efficiency of container crane causes jamming frequently in transportation and cargo handling at port. It is required that the working velocity and safety are improved by control of moving the trolley as quick as possible without large overshoot and any residual swing motion of container at the destination. In this paper, a LQ controller for a container crane is proposed to accomplish an optimal design of improved control system for minimizing the swing motion at destination. In this scheme a mathematical model for the system is obtained in state space form. Finally, the effectiveness of the proposed controller is verified through computer simulation.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 춘계학술대회논문집B
• /
• pp.688-693
• /
• 2001

It is almost impossible to have a straight web for processing in the continuous process systems. The cambered web usually causes the strip walking and damage during process. It is necessary to identify the lateral dynamics of the cambered web for the precise control of lateral behavior. In this paper, a dynamic model of the lateral behavior for a cambered web is developed by introducing the concept of steering angle equivalent to moment caused by the camber. This model can be extended to include terms associated with moment, induced by roller's tilting, web slippage, and shear force, etc. Using this model, a new feed-forward controller is proposed to enable the on-line camber estimation, which is difficult to be measured directly, and the prediction of lateral deflection caused by camber. Computer simulation study shows that the proposed controller successfully eliminates the effect of camber and has better control performance than that of the existing PID controller.

• Journal of Advanced Marine Engineering and Technology
• /
• 제20권3호
• /
• pp.286-286
• /
• 1996

A neural predictive tracking system for the control of structure-unknown dynamic system is presented. The control system comprises a neural network modelling mechanism for the the forward and inverse dynamics of a plant to be controlled, a feedforward controller, feedback controller, and an error prediction mechanism. The feedforward controller, a neural network model of the inverse dynamics, generates feedforward control signal to the plant. The feedback control signal is produced by the error prediction mechanism. The error predictor adopts the neural network models of the forward and inverse dynamics. Simulation results are presented to demonstrate the applicability of the proposed scheme to predictive tracking control problems.

• Journal of Advanced Marine Engineering and Technology
• /
• 제20권3호
• /
• pp.154-161
• /
• 1996

A neural predictive tracking system for the control of structure-unknown dynamic system is presented. The control system comprises a neural network modelling mechanism for the the forward and inverse dynamics of a plant to be controlled, a feedforward controller, feedback controller, and an error prediction mechanism. The feedforward controller, a neural network model of the inverse dynamics, generates feedforward control signal to the plant. The feedback control signal is produced by the error prediction mechanism. The error predictor adopts the neural network models of the forward and inverse dynamics. Simulation results are presented to demonstrate the applicability of the proposed scheme to predictive tracking control problems.

• 제어로봇시스템학회논문지
• /
• 제14권10호
• /
• pp.991-997
• /
• 2008

A new RMRAC scheme far the PMSM current regulation is proposed in a synchronous frame, which is completely free from the parameter's uncertainty. A current regulator of PMSM is the inner most loop of electromechanical driving systems and plays a foundation role in the control hierarchy. When the PMSM runs in high speed, the cross-coupling terms must be compensated precisely for large system BW. In the proposed RMRAC, the input signal is composed of a calculated voltage defined by MRAC law and an output of the disturbance compensator. The gains of feed forward and feedback controller are estimated by the proposed modified gradient method, where the system disturbances are assumed as filtered current regulation errors. After the compensation of the system disturbance from error information, the corresponding voltage is fed forward to control input to compensate for real disturbances. The proposed method robustly compensates the system disturbance and cross-coupling terms. It also shows a good realtime performance due to the simplicity of control structure. Through real experiments, the efficiency of the proposed method is verified.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제8권1호
• /
• pp.82-86
• /
• 2008

The article presents ARTMAP and Fuzzy BK-Product approach underwater obstacle avoidance for the Autonomous underwater Vehicles (AUV). The AUV moves an unstructured area of underwater and could be met with obstacles in its way. The AUVs are equipped with complex sensorial systems like camera, aquatic sonar system, and transducers. A Neural integrated Fuzzy BK-Product controller, which integrates Fuzzy logic representation of the human thinking procedure with the learning capabilities of neural-networks (ARTMAP), is developed for obstacle avoidance in the case of unstructured areas. In this paper, ARTMAP-Fuzzy BK-Product controller architecture comprises of two distinct elements, are 1) Fuzzy Logic Membership Function and 2) Feed-Forward ART component. Feed-Forward ART component is used to understanding the unstructured underwater environment and Fuzzy BK-Product interpolates the Fuzzy rule set and after the defuzzyfication, the output is used to take the decision for safety direction to go for avoiding the obstacle collision with the AUV. An on-line reinforcement learning method is introduced which adapts the performance of the fuzzy units continuously to any changes in the environment and make decision for the optimal path from source to destination.

• International Journal of Control, Automation, and Systems
• /
• 제5권6호
• /
• pp.643-651
• /
• 2007

The various blood pressure simulators have been proposed to evaluate and improve the performance of the automatic sphygmomanometer. These have some problems such as the deviation of the actual blood pressure waveform, limitation in the blood pressure condition of the simulator, or difficulty in displaying the blood flow. An improved simulator using disturbance observer is proposed to supplement the current problems of the blood pressure simulator. The proposed simulator has an artificial arm model capable of feeding appropriate fluids that can generate the blood pressure waveform to evaluate the automatic sphygmomanometer. A controller was designed and thereafter, simulation was performed to control the output signal with respect to the reference input in the fluid dynamic model using the proposed proportional control valve. To minimize the external fluctuation of pressure applied to the artificial arm, a disturbance observer was designed on the plant. A hybrid controller combined with a proportional controller and feed-forward controller was fabricated after applying a disturbance observer to the control plant. Comparison of the simulations between the conventional proportional controller and the proposed hybrid controller indicated that even though the former showed good control performance without disturbance, it was affected by the disturbance signal induced by the cuff. The latter exhibited an excellent performance under both situations.