• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.138-140
• /
• 2004

In this study, we develop a remocon inspection automatic system using machine vision technique. By our proposed inspection system, the inspection accuracy and processing time was considerably improved.

• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.5
• /
• pp.5-10
• /
• 2003

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.14 no.6
• /
• pp.122-128
• /
• 2015

Recently, as the demand for high efficiency, multi-function machine tools has increased, domestic machine tool industries are investing in research and development for Gantry-Type Machining centers. In this thesis, for the purpose of evaluating machining accuracy and designing a machine tool structure, a simplified model of the main frame is suggested. The results show the general characteristics of the optimum design, and the approach is shown as practicable for the preliminary design analysis and improvement of a conceptual design of a Gantry-Type Machining center. This paper's results are expected to improve the static characteristics of Gantry-Type Machine centers. The three-dimensional finite element models proved that the modeling method might be applied to real machine tool structures.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.1203-1206
• /
• 2003

After the micro turning lathe was developed in the last year by AMR Laboratory, a micro-milling machine is developed for micro machining. This machine is integrated with PZT-driven micro-sliders, micro-linear encoders, air turbine spindle which has maximum 150.000 rpm. It is applicable to milling and drilling machining. This paper shows the possibility of micro machining and characteristics of micro end milling process by using micro machine. A machining of micro barrier ribs using 0.2 mm flat type end mill was achieved by micro-milling machine. As experimental results show the machining capability and positional accuracy of this machine is good enough for machining micro parts.

• Journal of the Korean Society for Precision Engineering
• /
• v.18 no.3
• /
• pp.143-151
• /
• 2001

Machine tool errors have to be characterized and predicted to improve machine tool accuracy. A real-time error compensation system has been developed based on volumetric error synthesis model which is composed of machine tool errors. This paper deals with new algorithm about verification of machine tool errors. This new algorithm uses a simplified volumetric error synthesis model. This simplified model is constructed with only main components among the error components of the machine. The main error components are analyzed by ball bar test of hemispherical helix. The novel measurement method using ball bar system has many advantages which are more efficient, easier to use than conventional measurement system.

• Proceedings of the KSME Conference
• /
• 2003.11a
• /
• pp.1793-1797
• /
• 2003

After the micro turning lathe was developed in the last year by AMR Laboratory in Yeungnam university, a micromilling machine is developed for micro/meso machining. This machine is integrated with PZT-driven micro-sliders, micro-linear encoders, aerostatic spindle which has maximum 150,000 rpm. It is applicable to milling and drilling of micro scale. This paper presents the possibility of micro/meso machining and characteristics of micro end milling process by using micro machine. A machining of micro parts using 0.2 mm flat end mill was achieved by micro-milling machine. Experimental results show the machining capability and positional accuracy of this machine is good enough for machining micro parts.

• Journal of Electrical Engineering and information Science
• /
• v.2 no.4
• /
• pp.79-85
• /
• 1997

A unified, modular and decoupled approach for the simulation of converter fed induction machine systems is presented. The system under consideration could have semiconductor devices connected to the stator or the rotor of the induction machine for the purpose of controlling its performance. The machine model, however is invariant to these aspects. The model spans the circuit and equation domains of description thus allowing he advantages of both these domains of descriptions to be utilized. The results obtained using this machine and switch model for a VSI fed induction machine (stator fed, rotor shorted0 are compared with those from laboratory experiment to establish the validity and accuracy of th approach. Results for a slip energy recovery system are also presented and compared with those of earlier workers to establish the performance of the models and algorithms in he doubly-fed mode of operation of induction machine systems.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.15 no.2
• /
• pp.19-28
• /
• 2019

The purpose of this study is to examine the trends on machine learning and deep learning research in the published journals from the Web of Science Database. To achieve the study purpose, we used the abstracts of 20,664 articles published between 1990 and 2017, which include the word 'machine learning', 'deep learning', and 'artificial neural network' in their titles. Twenty major research topics were identified from topic modeling analysis and they were inclusive of classification accuracy, machine learning, optimization problem, time series model, temperature flow, engine variable, neuron layer, spectrum sample, image feature, strength property, extreme machine learning, control system, energy power, cancer patient, descriptor compound, fault diagnosis, soil map, concentration removal, protein gene, and job problem. The analysis of the time-series linear regression showed that all identified topics in machine learning research were 'hot' ones.

• Design & Manufacturing
• /
• v.17 no.1
• /
• pp.27-32
• /
• 2023

In this paper, we intend to predict the mass of the spiral using CAE and machine learning. First, We generated 125 data for the experiment through a complete factor design of 3 factors and 5 levels. Next, the data were derived by performing a molding analysis through CAE, and the machine learning process was performed using a machine learning tool. To select the optimal model among the models learned using the learning data, accuracy was evaluated using RMSE. The evaluation results confirmed that the Support Vector Machine had a good predictive performance. To evaluate the predictive performance of the predictive model, We randomly generated 10 non-overlapping data within the existing injection molding condition level. We compared the CAE and support vector machine results by applying random data. As a result, good performance was confirmed with a MAPE value of 0.48%.

• Korea Trade Review
• /
• v.46 no.2
• /
• pp.281-299
• /
• 2021

This paper analyzes the feasibility of using machine learning methods to forecast the employment. The machine learning methods, such as decision tree, artificial neural network, and ensemble models such as random forest and gradient boosting regression tree were used to forecast the employment in Busan regional economy. The following were the main findings of the comparison of their predictive abilities. First, the forecasting power of machine learning methods can predict the employment well. Second, the forecasting values for the employment by decision tree models appeared somewhat differently according to the depth of decision trees. Third, the predictive power of artificial neural network model, however, does not show the high predictive power. Fourth, the ensemble models such as random forest and gradient boosting regression tree model show the higher predictive power. Thus, since the machine learning method can accurately predict the employment, we need to improve the accuracy of forecasting employment with the use of machine learning methods.