• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.5
• /
• pp.721-731
• /
• 2018

Manpower in domestic construction sites is becoming more and more aging. Various methods have been devised to prevent productivity and quality deterioration of construction due to absence of skilled workers and difficulty in supplying manpower. Especially, many researchers study various methods such as Machine Guidance (MG) and Remote Machine Control to improve productivity and quality. Although many prior studies have been conducted since the advent of MG, There is lack of field test in a difficult site to stakeout. In this study, field test of MG excavator was carried out at difficult site to stakeout, and productivity analysis and quality evaluation were conducted. As a result of the analysis of productivity, the minimum value was 20.5%, the maximum value was 56.9%, and the average productivity in 4 days was 38.3% higher than the standard product. As a result of the analysis of quality, the horizontal error ${\pm}1cm$ and the vertical error ${\pm}2cm$ confirmed in the previous study were verified.

• The Korean Journal of Applied Statistics
• /
• v.31 no.2
• /
• pp.265-285
• /
• 2018

In this study, we applied a deep neural network model to predict four grades of fine dust $PM_{10}$, 'Good, Moderate, Bad, Very Bad' and two grades, 'Good or Moderate and Bad or Very Bad'. The deep neural network model and existing classification techniques (such as neural network model, multinomial logistic regression model, support vector machine, and random forest) were applied to fine dust daily data observed from 2010 to 2015 in six major metropolitan areas of Korea. Data analysis shows that the deep neural network model outperforms others in the sense of accuracy.

• Imaging Science in Dentistry
• /
• v.35 no.3
• /
• pp.115-119
• /
• 2005

Purpose : To evaluate the magnification error percentage in repeatedly taken panoramic radiographs of same patient and machine. Materials and Methods : 92 panoramic radiographs from 46 patients were traced and 30 horizontal and vertical measurements were made with digital sliding caliper. The results were compared with paired t-test. Results : There was no statistically significant difference between the two measurements. The overall difference as percentage error was $6.19\pm5.60\%$. The largest error as $14.61\pm12.44\%$ was found at condylar height 1, and smallest as $1.86\pm1.61\%$ at mandibular height. Overall vertical error excluding condylar height 1 was $3.76\pm3.97\%$, and the horizontal error $6.88\pm5.92\%$. Conclusion . Repeatedly taken panoramic radiographs of the same patient and machine was reliable since there was no significant percentage error difference but the percentage error ranged from $1.86\pm1.61\%\;to\;14.61\pm12.44\%$ indicating the error depends on the measuring site.

• Communications for Statistical Applications and Methods
• /
• v.25 no.2
• /
• pp.199-215
• /
• 2018

Interest in $PM_{10}$ concentrations have increased greatly in Korea due to recent increases in air pollution levels. Therefore, we consider a forecasting model for next day $PM_{10}$ concentration based on the principal elements of air pollution, weather information and Beijing $PM_{2.5}$. If we can forecast the next day $PM_{10}$ concentration level accurately, we believe that this forecasting can be useful for policy makers and public. This paper is intended to help forecast a daily mean $PM_{10}$, a daily max $PM_{10}$ and four stages of $PM_{10}$ provided by the Ministry of Environment using various data mining techniques. We use seven models to forecast the daily $PM_{10}$, which include five regression models (linear regression, Randomforest, gradient boosting, support vector machine, neural network), and two time series models (ARIMA, ARFIMA). As a result, the linear regression model performs the best in the $PM_{10}$ concentration forecast and the linear regression and Randomforest model performs the best in the $PM_{10}$ class forecast. The results also indicate that the $PM_{10}$ in Seoul is influenced by Beijing $PM_{2.5}$ and air pollution from power stations in the west coast.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_3
• /
• pp.1711-1720
• /
• 2020

Particulate matter (PM) that has been artificially generated during the recent of rapid industrialization and urbanization moves and disperses according to weather conditions, and adversely affects the human skin and respiratory systems. The purpose of this study is to predict the PM10 concentration in Seoul using meteorological factors as input dataset for multiple linear regression (MLR), support vector machine (SVM), and random forest (RF) models, and compared and evaluated the performance of the models. First, the PM10 concentration data obtained at 39 air quality monitoring sites (AQMS) in Seoul were divided into training and validation dataset (8:2 ratio). The nine meteorological factors (mean, maximum, and minimum temperature, precipitation, average and maximum wind speed, wind direction, yellow dust, and relative humidity), obtained by the automatic weather system (AWS), were composed to input dataset of models. The coefficients of determination (R2) between the observed PM10 concentration and that predicted by the MLR, SVM, and RF models was 0.260, 0.772, and 0.793, respectively, and the RF model best predicted the PM10 concentration. Among the AQMS used for model validation, Gwanak-gu and Gangnam-daero AQMS are relatively close to AWS, and the SVM and RF models were highly accurate according to the model validations. The Jongno-gu AQMS is relatively far from the AWS, but since PM10 concentration for the two adjacent AQMS were used for model training, both models presented high accuracy. By contrast, Yongsan-gu AQMS was relatively far from AQMS and AWS, both models performed poorly.

• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.862-863
• /
• 2015

This paper presents an improved estimation procedure for the contribution to no-load flux linkage created by the permanent magnet (PM) in interior permanent magnet synchronous machines. In the proposed method, the saturation effect in stator and rotor cores are taken into account by utilizing the frozen permeability method (FPM). This improved procedure can evaluate the contribution for each local element in the PM to the no-load flux linkage. According to the analysis results, an effective PM topology optimal design can be carried out to achieve high utilization ratio of PM in the machine. In order to determine the threshold of the low contribution of PM for removing, one multi-objective optimization model is proposed. Based on the optimal threshold, the final optimal topology design of PM can be achieved.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.12
• /
• pp.1820-1827
• /
• 2012

This paper is to present a new method of cogging torque reduction for axial flux PM machines of multiple rotor surface mounted magnets. In order to start softly and to run a power generator even the case of weak wind power, reduction of cogging torque is one of the most important issues for a small wind turbine, Cogging torque is an inherent characteristic of PM machines and is caused by the geometry shape of the machine. Several methods have been already applied for reducing the cogging torque of conventional radial flux PM machines. Even though some of these techniques can be also applied to axial flux machines, manufacturing cost is especially higher due to the unique construction of the axial flux machine stator. Consequently, a simpler and low cost method is proposed to apply on axial flux PM machines. This new method is actually applied to a generator of 1.0kW, 16-poles axial flux surface magnet disc type machine with double-rotor-single-stator for small wind turbine. Design optimization of the adjacent magnet pole-arc which results in minimum cogging torque as well as assessment of the effect on the maximum available torque using 3D Finite Element Analysis (FEA) is investigated in this design. Although the design improvement is intended for small wind turbines, it is also applicable to larger wind turbines.

• Proceedings of the KIEE Conference
• /
• 2001.04a
• /
• pp.393-396
• /
• 2001

According to the development of power electronic element(GTO, IGBT) and material for electrical machines(permanent magnet, super conductor), the technology for electrical machines is nowaday rapidly developing. Here with, a novel electrical machine, based on the new conception of transverse flux configuration leads to a considerable Increase in power density and enables simultaneously high efficiency. The transverse flux machine with PM excitation will be applied to gearless direct drives for railway traction system and magnetic levitation system. The designed and measured performance of transverse machine for railway traction system and magnetic levitation system revealed a great potential of system improvements to reduce linear motor mass and increase efficiency.

• Journal of Magnetics
• /
• v.20 no.4
• /
• pp.421-426
• /
• 2015

This paper presents a practical method for estimation of average temperature in the permanent magnet (PM) of electric machine by using finite element analysis (FEA) and dynamo load experiment. First of all, the temperature effect of PM to the torque has been employed by FEA in order to evaluate the Temperature-Torque characteristic curve. The 1st order polynomial equation which is torque attenuation coefficient is derived by the FEA result of the Temperature-Torque curve. Next, torque saturation test with constant current condition is performed by dynamo load experiment. Then, the temperature trend can be estimated by adding the initial starting temperature using the torque attenuation coefficient and torque saturation curve. Lastly, estimated temperature is validated by infrared thermometer which measures temperature of PM surface. The comparison between the estimated result and experimental result gives a good agreement within a deviation of maximum $8^{\circ}C$.

• Proceedings of the KIEE Conference
• /
• 2008.10c
• /
• pp.93-95
• /
• 2008

Nowadays more attention is paid to the developing high efficiency electrical machines for energy saving and protection of natural resources. In general, the electromagnetic losses appearing in electrical machines are widely classified into copper loss, core loss and rotor loss. Particularly, in permanent magnet (PM) machines, core loss forms a larger portion of the total losses than in another machine. So, satisfactory prediction of core loss at the design or analysis stage of PM machines is essential to active high efficiency and high performance. This paper deals with analysis of magnetic field distribution due to geometry of stator core for magnetic core loss calculation of multi-pole PM synchronous machine.