• Journal of the Korean Institute of Landscape Architecture
• /
• v.51 no.3
• /
• pp.70-82
• /
• 2023

The recent surge of IT and data acquisition is shifting the paradigm in all aspects of life, and these advances are also affecting academic fields. Research topics and methods are being improved through academic exchange and connections. In particular, data-based research methods are employed in various academic fields, including landscape architecture, where continuous research is needed. Therefore, this study aims to investigate the possibility of developing a landscape preference evaluation and prediction model using machine learning, a branch of Artificial Intelligence, reflecting the current situation. To achieve the goal of this study, machine learning techniques were applied to the landscaping field to build a landscape preference evaluation and prediction model to verify the simulation accuracy of the model. For this, wind power facility landscape images, recently attracting attention as a renewable energy source, were selected as the research objects. For analysis, images of the wind power facility landscapes were collected using web crawling techniques, and an analysis dataset was built. Orange version 3.33, a program from the University of Ljubljana was used for machine learning analysis to derive a prediction model with excellent performance. IA model that integrates the evaluation criteria of machine learning and a separate model structure for the evaluation criteria were used to generate a model using kNN, SVM, Random Forest, Logistic Regression, and Neural Network algorithms suitable for machine learning classification models. The performance evaluation of the generated models was conducted to derive the most suitable prediction model. The prediction model derived in this study separately evaluates three evaluation criteria, including classification by type of landscape, classification by distance between landscape and target, and classification by preference, and then synthesizes and predicts results. As a result of the study, a prediction model with a high accuracy of 0.986 for the evaluation criterion according to the type of landscape, 0.973 for the evaluation criterion according to the distance, and 0.952 for the evaluation criterion according to the preference was developed, and it can be seen that the verification process through the evaluation of data prediction results exceeds the required performance value of the model. As an experimental attempt to investigate the possibility of developing a prediction model using machine learning in landscape-related research, this study was able to confirm the possibility of creating a high-performance prediction model by building a data set through the collection and refinement of image data and subsequently utilizing it in landscape-related research fields. Based on the results, implications, and limitations of this study, it is believed that it is possible to develop various types of landscape prediction models, including wind power facility natural, and cultural landscapes. Machine learning techniques can be more useful and valuable in the field of landscape architecture by exploring and applying research methods appropriate to the topic, reducing the time of data classification through the study of a model that classifies images according to landscape types or analyzing the importance of landscape planning factors through the analysis of landscape prediction factors using machine learning.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.11 no.3
• /
• pp.258-265
• /
• 2006

In this paper, an active clamping sepic-flyback converter has been proposed, which is suitable for a fuel cell based power generation system. The proposed converter is superposition of sepic converter mode and flyback mode. It has outstanding high boosting output voltage, component utilization and high efficiency characteristics under the inherently severe low output voltage of the fuel cell generator. In this paper, the validity of the proposed converter has been verified by the informative simulation and experimental results that make used of the PEMFC.

• Journal of Biosystems Engineering
• /
• v.26 no.3
• /
• pp.263-270
• /
• 2001

This study was conducted in order to develop wind-water heating system where frictional heat is creased between the rotor and working fluid when they are rotating in the cylindrical heat generator. The wind-water heating system is composed of rotor, stator, working fluid, motor, inverter and heat generation tank. Instead of wind turbine, we have used an electrical motor of 30㎾ to rotate the rotor in this system. Two working fluids and six levels of rotor rpm were tested to quantify heat amounts generated by the system. Generally, as motor rpm goes up heat amount increases that we have expected. At the same rpm, viscous fluid showed up better performance than the water, generating more heat by 10$\^{C}$ difference. The greatest heat amount of 31,500kJ/h was obtained when the system constantly drained out the hot water of at the flow rate of 500ℓ/h. Power consumption rate of the motor was measured by thee phase electric power meter where the largest power consumption rate was 14㎾ when motor rpm was 600 and gained heat was 31,500kJ/h, that indicated total thermal efficiency of the wind power water heating system was 62%.

• Journal of Advanced Navigation Technology
• /
• v.20 no.4
• /
• pp.265-274
• /
• 2016

In this study, the system was composed of the booster chopper and the power converter, which is a pulse width modulation (PWM) voltage inverter using a hybrid power generation system solar cell energy and wind force, Furthermore, in order to compensate the PWM voltage type inverter was linked with the general commercial power source, and through a normal operation of energy storage system (ESS), the system operated the LED Taxi Light by Wavelength according to Meteorological Changes at the airport in an efficient manner. The performance of the system was compared with the solar cell characteristics specification. In addition, for phase synchronization with the PWM voltage type inverter, the grid voltage was detected so as to operate the grid voltage and inverter output in the same phase and to connect the surplus electric power with the system. Finally, by developing a control circuit at the same time from which an excellent dynamic characteristics can be obtained through applying to the airport runway taxi light, it was concluded that a variety of taxi light can be pursued.

• Journal of IKEEE
• /
• v.21 no.2
• /
• pp.105-114
• /
• 2017

This paper proposes a design method of an LCL-filter for grid-tied three-level inverter systems. The demand for three-phase PWM inverters in applications such as wind or solar power generation systems has been increase in recent years. To reduce harmonic components caused by switching operation, such inverters are connected to the grid via an LCL filter. Although there are research results for designing LCL-filter, the modulation method should be fully considered to make the filter perform desired cancellation ability with minimized size. This paper presents the design methodology for an LCL-filter that is optimized for SVM switching operations. The simulation and experimental results verify the validity of the LCL-filter designed with proposed method in this paper.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.2
• /
• pp.179-184
• /
• 2016

The electrical load testing system developed from this study was designed to control rated-capacity-testing or variable-load-testing in an active and precise manner and save electric energy during testing, and also to convert the saved electric energy through the electrical load testing system to grid line. As for the device under testing, it was designed to be applied to not only transformer, rectifier, voltage regulator, inverter which require grid voltage source but, also applied to electric power, aerogenerator, photovoltaic, hybrid generator, battery, etc. which do not require grid voltage source. The system was designed to return the power consumed during the testing to the grid line by connecting the synchronizing pwm inverter circuit to the grid voltage source, and was also made to enable the being-tested system from disuse of approximately 93.4% energy when compared to the conventional load testing system which has used the passive resistor.

• Atmosphere
• /
• v.26 no.3
• /
• pp.373-386
• /
• 2016

The future variability of Wind Energy Density (WED) over the Korean Peninsula under RCP climate change scenario is projected using ensemble analysis. As for the projection of the future WED, changes between the historical period (1981~2005) and the future projection (2021~2050) are examined by analyzing annual and seasonal mean, and Coefficient of Variation (CV) of WED. The annual mean of WED in the future is expected to decrease compared to the past ones in RCP 4.5 and RCP 8.5 respectively. However, the CV is expected to increase in RCP 8.5. WEDs in spring and summer are expected to increase in both scenarios RCP 4.5 and RCP 8.5. In particular, it is predicted that the variation of CV for WED in winter is larger than other seasons. The time series of WED for three major wind farms in Korea exhibit a decrease trend over the future period (2021~2050) in Gochang for autumn, in Daegwanryeong for spring, and in Jeju for autumn. Through analyses of the relationship between changes in wind energy and pressure gradients, the fact that changes in pressure gradients would affect changes in WED is identified. Our results can be used as a background data for devising a plan to develop and operate wind farm over the Korean Peninsula.

• Journal of Environmental Science International
• /
• v.29 no.7
• /
• pp.729-737
• /
• 2020

This study estimates the greenhouse gas (GHG) emissions reduction resulting from photovoltaic and wind power technologies using a bottom-up approach for an indirect emission source (scope 2) in South Korea. To estimate GHG reductions from photovoltaic and wind power activities under standard operating conditions, methodologies are derived from the 2006 IPCC guidelines for national GHG inventories and the guidelines for local government greenhouse inventories of Korea published in 2016. Indirect emission factors for electricity are obtained from the 2011 Korea Power Exchange. The total annual GHG reduction from photovoltaic power (23,000 tons CO_2eq) and wind power (30,000 tons CO_2eq) was estimated to be 53,000 tons CO_2eq. The estimation of individual GHGs showed that the largest component is carbon dioxide, accounting for up to 99% of the total GHG. The results of estimation from photovoltaic and wind power were 63.60% and 80.22% of installed capacity, respectively. The annual average GHG reductions from photovoltaic and wind power per year per unit installed capacity (MW) were estimated as 549 tons CO_2eq/yr·MW and 647 tons CO_2eq/yr·MW, respectively. Finally, the results showed that the level of GHG reduction per year per installed capacity of photovoltaic and wind power is 62% and 42% compared to the CDM project, respectively.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.43 no.10
• /
• pp.920-927
• /
• 2015

In this paper, numerical results of sectional analysis and stress recovery were compared with the results of VABS through the blade analysis library. The results of recovery analysis for one-dimensional model including the stiffness matrix is compared with the calculated three-dimensional stress results of three-dimensionial FEM based on the principle of virtual work. We discuss the configuration of the blade analysis library and compare verifications of numerical analysis results of VABS. Blade analysis library through dimensional reduction and stress recovery is intended to be utilized in conjunction with pre- and post-processing of the analysis program of the composite blade, high-altitude uav's wing, wind blades and tilt rotor blade.

• Journal of Korea Society of Industrial Information Systems
• /
• v.21 no.3
• /
• pp.29-33
• /
• 2016

Development of the distributed energy resources such as photovoltaic, wind, and fuel cell has increased rapidly due to the rising demand for clean energy utilization. On the other hand, the distribution system became complex and has problems such as degradation of power factor and current unbalance caused by power converters, reactive power and unbalanced loads. To solve these problems, this paper proposes a 3-phase 4-leg type power conditioning system with compensation control algorithm for the reactive power and unbalance current in distribution system using photovoltaic resource. It is simulated in PSCAD/EMTDC and the effectiveness is confirmed.