• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제8권3호
• /
• pp.185-191
• /
• 2008

In this paper, experimental studies of a neural network (NN) control technique for non-model based position control of the x-y table robot are presented. Decentralized neural networks are used to control each axis of the x-y table robot separately. For an each neural network compensator, an inverse control technique is used. The neural network control technique called the reference compensation technique (RCT) is conceptually different from the existing neural controllers in that the NN controller compensates for uncertainties in the dynamical system by modifying desired trajectories. The back-propagation learning algorithm is developed in a real time DSP board for on-line learning. Practical real time position control experiments are conducted on the x-y table robot. Experimental results of using neural networks show more excellent position tracking than that of when PD controllers are used only.

• 한국정밀공학회지
• /
• 제26권6호
• /
• pp.50-58
• /
• 2009

Micro laser fabrication techniques can potentially be used for the manufacture of microstructures on the thin flat surfaces with large diameter that are frequently used in semiconductor industries. However, the large size of wafers can cause the degraded machining accuracy of the surface because it can be tilted or distorted by geometric errors of machines or the holding fixtures, etc. To overcome these errors the off-line focusing error compensation method is proposed. By using confocal autofocus system, the focusing error profile of machined surface is measured along the pre-determined path and can be compensated at the next machining process by making the corrected motion trajectories. The experimental results for silicon wafers and invar flat surfaces show that the proposed method can compensate the focusing error within the level of below $6.9{\mu}m$ that is the depth of focus required for the laser micromachining process.

• 한국정밀공학회지
• /
• 제16권6호
• /
• pp.83-89
• /
• 1999

This paper presents the in-process runout compensation methodology to improve the surface quality of circular contouring cut in end milling process. The runout compensation system is based on the manipulation of workpiece position relative to cutter in minimizing the cutting force oscillation at spindle frequency. the basic concept of this approach is realized on a end milling machine whose machining table accommodates a set of orthogonal translators perpendicular to the spindle axis. The system performed that measuring the runout related cutting force component, formulating PI controlling commands, and the manipulating the workpiece position to counteract the variation of chip load during the circular contouring cut. To evaluate the runout compensation system performance, experimental study based on the implementation of two-axes PI force control is presented in the context of cutting force regulation and part surface finish improvement.

• 한국지능시스템학회논문지
• /
• 제14권3호
• /
• pp.375-382
• /
• 2004

신경회로망을 이용한 XY 테이블의 비선형 보상기법을 제안한다. 제안된 신경망 제어기는 시스템의 비선형 성분에 의한 성능저하를 보상하는 신경회로망과 시스템의 안정화를 위한 비례미분(PD) 제어기로 구성된다. 신경망 보상 구조가 적응적이고 추적오차와 파라미터 추정치가 유계가 되는 신경망 파라미터 동조알고리듬과 안정도 증명을 제시한다. 신경망 제어기를 위치 테이블에 실험함으로써 비선형 성분에 의한 성능저하를 줄이는 효과를 보여준다.

• 방송공학회논문지
• /
• 제27권5호
• /
• pp.812-815
• /
• 2022

햇빛 아래에서 디지털 기기에 표시되는 영상은 일반적으로 원본 영상보다 어둡게 인식되어 시인성이 저하된다. 더 나은 시인성을 위해서, 주변광에 적응적인 전역 휘도 보상 혹은 톤 매핑이 필요하다. 하지만 기존의 기법들은 색차 보상에 한계가 존재하고, 무거운 계산 비용 때문에 실제 환경에서 활용하는데 어려움이 존재한다. 이를 해결하기 위해 본 논문에서는 휘도와 색차를 모두 보상하는 Piece-wise Linear Enhancement Curves (PLECs) 기반 영상 개선 기법을 제안한다. 이때, PLECs은 딥러닝을 통해 회귀 되며, lookup table 형식으로 구현되어 실시간 동작이 가능하다. 실험 결과 제안 방법이 낮은 계산 비용으로 원본 영상 대비 더 나은 시인성을 가짐을 보인다

• International Journal of Control, Automation, and Systems
• /
• 제2권1호
• /
• pp.92-99
• /
• 2004

In this paper, the decoupled neural network reference compensation technique (DRCT) is applied to the control of a two degrees-of-freedom inverted pendulum mounted on an x-y table. Neural networks are used as auxiliary controllers for both the x axis and y axis of the PD controlled inverted pendulum. The DRCT method known to compensate for uncertainties at the trajectory level is used to control both the angle of a pendulum and the position of a cart simultaneously. Implementation of an on-line neural network learning algorithm has been implemented on the DSP board of the dSpace DSP system. Experimental studies have shown successful balancing of a pendulum on an x-y plane and good position control under external disturbances as well.

• 한국생산제조학회지
• /
• 제7권6호
• /
• pp.132-140
• /
• 1998

Recently, precision machining technology has been developed continuously in order to make high productivity and quality assurance of the precision parts of several industrial fields. Waviness may occur on the surface of the machined parts due to the table motion error and the dynamic cutting mechanism between the tool and the workpiece. The waviness may fall off the form accuracy of the precision machine parts. In the research, a micro cutting device with piezoelectric actuator has been developed to control precise depth of cut and compensate the waviness on the surface of the workpiece. Experiments have been carried out in the precision lathe. The characteristics of the surface profile and cause of the waviness profile have been analyzed and waviness profiles of some cause have been compared with those of experiments.

• 한국정밀공학회지
• /
• 제21권8호
• /
• pp.65-72
• /
• 2004

For the burrs formed in machining are irregular and very sharp in shape, it is usually very difficult to measure burr accurately. It was proved that micro burr geometry can be measured imprecision by the Conoprobe sensor using conoscopic holography method. We developed 3D burr measurement system using this sensor. The system is composed of Conoprobe sensor, XY table, controller and 3D measurement program. Some measurements using the developed system are conducted for the burrs formed in micro drilling and piercing. Specific software fur burr measurement includes several function, calculation of burr volume, average burr height. Burs formed on a curved surface were compensated and measured successfully using the basic surface compensation function.

• 반도체디스플레이기술학회지
• /
• 제12권1호
• /
• pp.53-59
• /
• 2013

Chip mounter which is used to pick chips from the pre-specified position and place them on the target location of PCB is an essential device in semiconductor and LCD industries. Quick and high precision positioning is the key technology needed to increase productivity of chip mounters. As increasing acceleration and deceleration of placing motion, structural vibration induced from inertial reactive force and flexibility of mounter structure becomes a serious problem degrading positioning accuracy. Motivated from these, this paper proposed a new control design algorithm which combines a mounter structure acceleration feedforward compensation and an extended sliding mode control for fine positioning and suppression of structural vibration, simultaneously. The feasibility of the proposed control design was verified along with some simulation results.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.102.4-102
• /
• 2002

A deadzone compensator is designed for a positioning system using fuzzy logic. The classification property of fuzzy logic systems make them a natural candidate for the rejection of errors induced by the deadzone, which has regions in which it behaves differently. A tuning algorithm is given for the fuzzy logic parameters, so that the deadzone compensation scheme becomes adaptive, guaranteeing small tracking errors and bounded parameter estimates, formal nonlinear stability proofs are given to show that the tracking error is small. The fuzzy logic deadzone compensator is implemented on a positioning system to show its efficacy. 1. Deadzone Compansation 2. XY positioning table 3. Fuzzy Logic 4. Actuator nonlinearity