• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.707-712
• /
• 1991

In machining a part in CAD/CAM system, it is required that the drawing information should be automatically generated, modified, deleted, and thus be used as an general information throughout the entire manufacturing process. This research addresses basic entities(point, line, circle, arc) for design feature and combination of this features, based on GT concepts, with minimum user's manual input. This paper deals with the generalization of operating system which can cover the s parts which appears in mechanical part handbook and the basic constitutional part of sold base. The system developed shows a strong application impact on automatic process planning system of medium - size injection sold companies.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2001.04a
• /
• pp.300-305
• /
• 2001

Competitive power is rapidly manufacture product required consumers. Therefore, modern industry have changed from small item many production to many item small production. rapid production is necessary thing at the product development. Thus, rapid prototyping is appeared. If the graphic model was made by CAD, the production can be made in short term. That provide what the part was directly tested by the worker. It provide believable data. This study is experiment on surface roughness of part at FDM

• Journal of KIISE
• /
• v.43 no.10
• /
• pp.1085-1093
• /
• 2016

Community-based Question Answering system is a system which provides answers for each question from the documents uploaded on web communities. In order to enhance the capacity of question analysis, former methods have developed specific rules suitable for a target region or have applied machine learning to partial processes. However, these methods incur an excessive cost for expanding fields or lead to cases in which system is overfitted for a specific field. This paper proposes a multiple machine learning method which automates the overall process by adapting appropriate machine learning in each procedure for efficient processing of community-based Question Answering system. This system can be divided into question analysis part and answer selection part. The question analysis part consists of the question focus extractor, which analyzes the focused phrases in questions and uses conditional random fields, and the question type classifier, which classifies topics of questions and uses support vector machine. In the answer selection part, the we trains weights that are used by the similarity estimation models through an artificial neural network. Also these are a number of cases in which the results of morphological analysis are not reliable for the data uploaded on web communities. Therefore, we suggest a method that minimizes the impact of morphological analysis by using character features in the stage of question analysis. The proposed system outperforms the former system by showing a Mean Average Precision criteria of 0.765 and R-Precision criteria of 0.872.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.28 no.1
• /
• pp.1-10
• /
• 2003

A recent trend In flexible manufacturing systems (FMS) Is to utilize the Identical versatile machines with fast tool delivery devices. Unlike a conventional FMS where parts are fed to the machines with the required tools, tools are acquired from other machines using a tool delivery system and parts can be finished on the same machine In these FMS. Therefore it Is more important problem 4o plan tool flow using tool delivery system In these FMS rather than part flow In conventional FMS. According to the existing study, In FMS 20∼30 percent of the total management cost Is the cost related with tools and It Is possible to reduce the tool Inventory by 40 percent using efficient tool allocation. In this study, In FMS under dynamic tool allocation strategy, a new method of part release considering tool flow at the stage of part release Is proposed. In order to prove the efficiency of the proposed part release It is compared with other part release through simulation experiments. Performance measures in these experiments are the throughput and the number of tardy parts.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2002.10a
• /
• pp.359-364
• /
• 2002

In engineering design environment it is hard to link design data and system because the types of them are disparate. Therefore, the importance of metadata has increased. Some researches have been executed to develop metadata. But they cannot interact with other metadata and are difficult to extend. The purpose of this paper is to develop a common metadata structure which represents the general information of mechanical part assembly using XML, and to use it as base documents in order to integrate design data and systems. It is composed of part and assembly documents. Part document represents the information of a part independently to part type. Assembly document represents the location of part documents which compose an assembly. Common documents can be used as a broker between design data and systems and improve interpretability and reusability of document. We applied the developed common document structure to 2-stage spur gear drive.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.1609-1613
• /
• 2003

This research focused on the development of automatically exclusive production equipment of corrupad as changing manual system into automatic system to increase the output. Therefore the minimization of the problem of the rewinding mechanism with eccentric cantilever structure is key to the achievement of the high performance for automation production. Proto-type corrupad rewinding machine is manufactured after considering the effect of the rotational vibration and natural frequency of the structure of machine by using 3D design packages such as ADAMS and I-deas. For evaluating the performance of the proto-type machine, simulations of dynamic and static characteristics using 3D design packages, a series of modal tests by accelerometer and measurements of dynamic behavior by high-speed camera for rewinding part, were carried out. As a result, the proto-type machine was not affected with the rotational vibration. Whirling error of eccentric cantilever structure in driving is small. Therefore the machine developed is most suitable to produce corrupad automatically. However reinforcement of the structure in axial direction is required due to so vibration in that direction.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.25 no.5
• /
• pp.313-320
• /
• 2016

The need for high-strength, multi-axis, and multi-functional machine tools has recently increased because of part complexity and workpiece strength. However, most of the machine tool manufacturers rely on experience for a detailed design because of the shortcomings in the existing design technology. This study uses a topology optimization method to more effectively design a large multi-functional machine tool considering static stiffness. The ram, saddle, and column parts are important structures in a machine tool. Hence, they are selected for the finite element method analysis. Based on this analysis, the optimized internal rib structure for those parts is designed for desirable rigidity and weight. This structure could possibly provide the required design technology for machine tool manufacturers.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.9 no.1
• /
• pp.49-54
• /
• 2010

An integrated machining center is developed for high precision and productivity manufacturing. The developed machine is composed of the high precision spindle using ball bearings, the high stiffness bed and the three axis CNC controller with the high resolution AC servo motor. In this paper, structural and modal analysis for the developed machine are carried out to check the design criteria of machine. The analysis is carried out by FEM simulation with using the commercial software, CATIA V5, ANSYS and ARMD. The simulation model of machine is made by shell and solid finite elements. This study also presents the measurement system on the modal analysis of an integrated machining center. The weak part of the machine is found by the analytical evaluation. The results provide with the structural modification data for good dynamic behaviors. And the safety of machine is confirmed by the modal analysis of modified machine design. As this study results can be trustworthy with the analysis of ANSYS and CATIA, integrated machining center can be successfully developed.

• Journal of radiological science and technology
• /
• v.42 no.1
• /
• pp.9-17
• /
• 2019

Although digital mammography is a representative method for breast cancer detection. It has a limitation in detecting and classifying breast tumor due to superimposed structures. Machine learning, which is a part of artificial intelligence fields, is a method for analysing a large amount of data using complex algorithms, recognizing patterns and making prediction. In this study, we proposed a technique to improve the diagnostic accuracy of energy-selective mammography by training data using the machine learning algorithm and using dual-energy measurements. A dual-energy images obtained from a photon-counting detector were used for the input data of machine learning algorithms, and we analyzed the accuracy of predicted tumor thickness for verifying the machine learning algorithms. The results showed that the classification accuracy of tumor thickness was above 95% and was improved with an increase of imput data. Therefore, we expect that the diagnostic accuracy of energy-selective mammography can be improved by using machine learning.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.4_2
• /
• pp.481-490
• /
• 2021

In the ultrasonic welding machine, when the load fluctuates, the L and C of the piezo element in the oscillation part change. As a result, the resonant frequency is changed, so it is necessary to match the operating frequency of the ultrasonic welding machine to the new resonant frequency. That is, in order to maximize the output of the oscillation unit of the ultrasonic welding machine, it is inevitable to follow the resonance frequency. Accordingly, many methods for following the resonant frequency are being actively studied. In addition, in order to check the effect of external inductance on the operation of the ultrasonic welding machine, The equivalent circuit of the piezo element was analyzed by including the external inductance for resonance in the equivalent circuit of the piezo element, and the method of selecting an appropriate inductance was described. In this paper, we propose a new system that allows the switching frequency of the inverter to tracking the resonance frequency even if the resonance frequency is changed due to the load of the ultrasonic welding machine.