• Transactions on Control, Automation and Systems Engineering
• /
• v.3 no.1
• /
• pp.58-65
• /
• 2001

This paper proposes a self tuning fuzzy inference method by the genetic algorithm in the fuzzy-sliding mode control for a robot. Using this method, the number of inference rules and the shape of membership functions are optimized without an expert in robotics. The fuzzy outputs of the consequent part are updated by the gradient descent method. And, it is guaranteed that he selected solution become the global optimal solution by optimizing the Akaikes information criterion expressing the quality of the inference rules. The trajectory tracking simulation and experiment of the polishing robot show that the optimal fuzzy inference rules are automatically selected by the genetic algorithm and the proposed fuzzy-sliding mode controller provides reliable tracking performance during the polishing process.

• Journal of the Korean Society for Precision Engineering
• /
• v.29 no.3
• /
• pp.266-272
• /
• 2012

This paper has aims to share fundamental knowledge for magnetic abrasive polishing and to mainly introduce recent research results. In order to enhance a magnetic flux density for nonferrous materials, advanced magnetic abrasive polishing system which is called 2nd generation system was established by electro-magnet array table, and the effectiveness of the electromagnet array table was evaluated in real polishing experiments. To increase adhesiveness of the abrasives in high speed polishing, a silicone gel agent was proposed and carbon nanotube particles as new magnetic abrasives were applied in the magnetic abrasive polishing. In addition, a strategy for optimal step-over determination by heuristic algorithm was introduced for applying large size workpiece. Curved surfaces having a uniform radius were simulated and tested with installed electro-magnet array table.

• Journal of Mechanical Science and Technology
• /
• v.15 no.5
• /
• pp.580-591
• /
• 2001

This paper proposes a fuzzy-sliding mode control which is designed by a self tuning fuzzy inference method based on a genetic algorithm. Using the method, the number of inference rules and the shape of the membership functions of the proposed fuzzy-sliding mode control are optimized without the aid of an expert in robotics. The fuzzy outputs of the consequent part are updated by the gradient descent method. It is further guaranteed that the selected solution becomes the global optimal solution by optimizing Akaikes information criterion expressing the quality of the inference rules. In order to evaluate the learning performance of the proposed fuzzy-sliding mode control based on a genetic algorithm, a trajectory tracking simulation of the polishing robot is carried out. Simulation results show that the optimal fuzzy inference rules are automatically selected by the genetic algorithm and the trajectory control result is similar to the result of the fuzzy-sliding mode control which is selected through trial error by an expert. Therefore, a designer who does not have expert knowledge of robot systems can design the fuzzy-sliding mode controller using the proposed self tuning fuzzy inference method based on the genetic algorithm.

• Journal of Digital Contents Society
• /
• v.3 no.1
• /
• pp.113-122
• /
• 2002

The flatness of a silicon wafer concerned with ULSI chip is one of the most critical parameters ensuring high yield of wafers. The polishing process that measures and controls the flatness of a silicon wafer is one of the important process in various processes for production silicon wafer, which are still being done today by manual. But engineers in polishing process are requested to have many experiences and to check silicon wafers one by one. In this paper, we propose an algorithm used interpolation that estimates wafer's shape and sorts wafers automatically, then we can control the flatness of wafers in polishing process by automatic system.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2010.11a
• /
• pp.137-138
• /
• 2010

• 제어로봇시스템학회:학술대회논문집
• /
• 1999.10a
• /
• pp.173-176
• /
• 1999

This paper shows a self tuning fuzzy inference method by the genetic algorithm in the fuzzy-sliding mode control for a Polishing robot. Using this method, the number of inference rules and the shape of membership functions are determined by the genetic algorithm. The fuzzy outputs of the consequent part are derived by the gradient descent method. Also, it is guaranteed that .the selected solution become the global optimal solution by optimizing the Akaike's information criterion expressing the quality of the inference rules. It is shown by simulations that the method of fuzzy inference by the genetic algorithm provides better learning capability than the trial and error method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.9
• /
• pp.786-795
• /
• 2000

In this paper, a new impedance force control method for deburring and polishing process is proposed. The proposed method is robust to deal with unknown environment stiffness as unknown well as environment location. An adaptive technique is used to minimize the force error occurred due to unknown environment surface profile. A robust position control algorithm based on time-delayed information is used to cancel out uncertainties in robot dynamics. A three link robot manipulator is used to demonstrate performances of the proposed control on deburring and polishing tasks. Stability analysis for the adaptive control is presented and its results are confirmed by simulations.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.182-182
• /
• 2000

This paper proposes a self tuning fuzzy inference method by the genetic algorithm in the fuzzy-sliding mode control for a robot. Using this method, the number of inference rules and the shape of membership functions are optimized without an expert in robotics. The fuzzy outputs of the consequent part are updated by the gradient descent method. And, it is guaranteed that the selected solution become the global optimal solution by optimizing the Akaike's information criterion. The trajectory trucking experiment of the polishing robot system shows that the optimal fuzzy inference rules are automatically selected by the genetic algorithm and the proposed fuzzy-sliding model controller provides reliable tracking performance during the polishing process.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.20 no.2
• /
• pp.174-179
• /
• 2011

This paper focuses on the optimal step-over value for magnetic tool path. Since magnetic flux density is changed according to distance from center of magnetic tool. Enhanced surface roughness is also different according to change of radius. Therefore, to get a identical surface roughness on workpiece, it is necessary to find optimal tool path including step-over. In this study, response surface models for surface roughness according to change of radiuses were developed, and then optimal enhanced surface roughness for each radius was selected using genetic algorithm and simulated annealing to investigate relation between radius and surface roughness. As a result, it found that step-over value of 6.6mm is suitable for MAP of magnesium alloy.

• Journal of Digital Contents Society
• /
• v.5 no.4
• /
• pp.251-256
• /
• 2004

The flatness of a silicon wafer concerned with ULSI chip is one of the most critical parameters ensuring high yield of wafers. That is necessary to constitute the circuit with high quality for he surface of silicon wafer, which comes to be base to make the direct circuit of the semiconductor, Flatness, therefore, is the most important factor to guarantee it wafer with high quality. The process of polishing is one of the most crucial production line among 10 processing stages to change the rough surface into the flatnees with best quality. Currently at this process, it is general for an engineer in charge to observe, judge and control the model of wafer from the monitor of measuring equipment with his/her own eyes to enhance the degree of flatness. This, however, is quite a troublesome job for someone has to check of process by one's physical experience. The purpose of this study is to approach the model of wafer with digital contents and to apply the result of the research for an algorithm which enables to control the polishing process by means of measuring the degree of flatness automatically, not by person, but by system. In addition, this paper shows that this algorithm proposed for the whole wafer flatness enables to draw an estimated algorithm which is for the thickness of sites to measure the degree of flatness for each site of wafer.