• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.9 no.4
• /
• pp.56-61
• /
• 2000

Cognition and control of grinding trouble occurring during the grinding process are classified into a quantitative knowledge which depends on experimental data and qualitative knowledge which relies on skilful engineers. Grinding operations include a large number of functional parameters, since there are several ways of coping with grinding trouble. One is the qualitative method which depends on empirical knowledge utilizing the skilful experts from the workship, the other is the quantitative method which utilizes the experimental data obtained by a sensor. But, they are all difficult to accomplish from the grinding trouble-shooting system. The reason is that grinding troubles are now easily controlled in the quantitative method, and therefore, trouble-shooting has mainly relied on the knowledge of skilful engineers. Thus, there is an important issue of how a grinding trouble-shooting system can be designed and what knowledge is utilized among the large amount of grinding trouble information. In this paper, basic strategy to develop the grinding database of rule-based model, which is strongly depended upon experience and intuition , is described.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.12
• /
• pp.84-91
• /
• 2004

A CCD camera with a laser stripe was applied to realize the automatic weld seam tracking in GMAW. It takes relatively long time to process image on-line control using the basic Hough transformation, but it has a tendency of robustness over the noises such as spatter and arc tight. For this reason, it was complemented with adaptive Hough transformation to have an on-line processing ability for scanning specific weld points. The adaptive Hough transformation was used to extract laser stripes and to obtain specific weld points. The 3-dimensional information obtained from the vision system made it possible to generate the weld torch path and to obtain the information such as width and depth of weld line. In this study, a neural network based on the generalized delta rule algorithm was adapted for the process control of GMA, such as welding speed, arc voltage and wire feeding speed.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.11a
• /
• pp.448-451
• /
• 2005

For measuring a traffic symbolic confusion quantity and symbolic air pleasantness, we use fuzzy sensor algorithm maded by symbolic information quantity. But for implementation of fuzzy sensor, we use some symbolic information item, this method cannot produce precise output because we use vague fuzzy rule method and we cannot abundance fuzzy for precision of fuzzy rule method. For this reason this paper introduce new fuzzy sensor algorithm composed of not fuzzy rule method but using Analytic Hierachy Process. To prove that new method is good, two type of fuzzy sensor applied to traffic signal controller and through much passing vehicle, two fuzzy sensor compared each other.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.18 no.2
• /
• pp.302-312
• /
• 1994

In this study, a fuzzy theory is introduced to control the cross-sectional strip shape in cold rolling. A fuzzy controller is developed based on the production data and the operational knowledge. The cold rolled products are characterized into several types based on their irregularities. For each type of irregular strip shape, fuzzy controller calculates the changes of bender forces of work and intermediate rolls using fuzzy control algorithm. To simulate the continuous shape control, fuzzy controller is linked with emulator which is developed using neural network. The developed fuzzy controller and emulator simulate the cold rolling process until the irregularities converge to the tolerable range to produce unifrom cross-sectional strip shape. The results from this simulation are reasonable for various irregular strip shapes.

• 제어로봇시스템학회:학술대회논문집
• /
• 1986.10a
• /
• pp.431-436
• /
• 1986

The design and manufacture of injection molded polymeic parts with desired mechanical properties is a costly process dominated by empiricism, including the modification of actual tooling. This paper presents an interactive computer-based design system for injection molded plastic parts. This knowledge-based synthesis system provides a rational design strategy for injection molding and molded parts. It synergistically combines a rule-based expert system for hurestic knowledge with analytical process simulation programs. The theremomechanical properties of a molded part such as the effect of molecular orientation and weldline strength are predicted by the analysis programs; while the expert system interprets the analytical results from the process simulation, evaluates the design, and generates recommendations for optimal design alternatives. The heuristic knowledge of injection molding is formalized as production rules of the expert consultation system.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.558-561
• /
• 2002

A CCD camera with a laser strip was applied to realize the automation of welding Process in GMAW. It takes relatively long time to process image on-line control using the basic Hough transformation, but it has a tendency of robustness over the noise such spatter and arc light. The adaptive Hough transformation was used to extract the laser stripe and to obtain specific weld points In this study, a neural network based on the generalized delta rule algorithm was adapted for the process control of GMA, such as welding speed, arc voltage and wire feeding speed.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.173-174
• /
• 2007

In this paper, a new speed sensorless control based on an instantaneous reactive power and a fuzzy PI compensator are proposed for the interior permanent magnet synchronous motor (IPMSM) drives. The conventional fixed gain PI and PID controllers are very sensitive to step change of command speed, parameter variations and load disturbance. Also, to the estimated speeds are compensated by using an instantaneous reactive power in synchronously rotating reference frame. In a fuzzy compensator, the system control parameters are adjusted by a fuzzy rule based system, which is a logical model of the human behavior for process control. The effectiveness of algorithm is confirmed by the experiments.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.693-698
• /
• 1991

This paper describes a fuzzy rule-based assembly algorithm for precision parts mating, The difficulties in devising reliable assembly strategies result from the complexity of the assembly process and the uncertainty such as imperfect knowledge of the parts being assembled as well as the limitations of the devices performing the assembly. To cope with above problems, we propose an assembly algorithm utilizing fuzzy set theory. The presented method allows us to represent the uncertainty by using fuzzy membership function and treat nonlinear sapping from measured force/torque to corrective motions using rules. Finally, the performance of this method is evaluated through a series of experiments. Experimental results show that the proposed method can be effectively used for chamferless and precision parts mating.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.1114-1115
• /
• 2007

In this paper, a new speed sensorless control based on a fuzzy compensator are proposed for the interior permanent magnet synchronous motor (IPMSM) drives. The conventional proportional plus integrate(PI) control are very sensitive to step change of the command speed, parameter variations and load disturbance. To cope with these problems of the PI control, the estimated speeds are compensated by using the fuzzy logic controller (FLC). In the FLC used by the speed compensator of the IPMSM, the system control parameters are adjusted by the fuzzy rule based system, which is a logical model of the human behavior for process control. The effectiveness of algorithm is confirmed by the experiments.

• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.3
• /
• pp.273-283
• /
• 2000

In this paper we suggest an optimal design method of Fuzzy-Neural Networks(FNN) model for complex and nonlinear systems. The FNNs use the simplified inference as fuzzy inference method and Error Back Propagation Algorithm as learning rule. And we use a HCM(Hard C-Means) Clustering Algorithm to find initial parameters of the membership function. The parameters such as parameters of membership functions learning rates and momentum weighted value is proposed to achieve a sound balance between approximation and generalization abilities of the model. According to selection and adjustment of a weighting factor of an aggregate objective function which depends on the number of data and a certain degree of nonlinearity (distribution of I/O data we show that it is available and effective to design and optimal FNN model structure with a mutual balance and dependency between approximation and generalization abilities. This methodology sheds light on the role and impact of different parameters of the model on its performance (especially the mapping and predicting capabilities of the rule based computing). To evaluate the performance of the proposed model we use the time series data for gas furnace the data of sewage treatment process and traffic route choice process.