• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.22 no.1
• /
• pp.87-94
• /
• 2008

A method for improving current THD of Valley-fill rectifier is proposed in this paper. The proposed topology combines a boosting inductor with Valley-fill rectifier which carry out AC/DC conversion and PFC simultaneously The boosting effect by PWM switching makes low THD current and improve of Valley-fill rectifier. The operation modes and THD of input current are analyzed as applied the boosting inductor, and the optimum value of boosting inductor is determined A 100[W] single-stage converter has been designed and tested. Experimental results are resented to verify the validity of the proposed method.

• Advances in Energy Research
• /
• v.6 no.2
• /
• pp.91-101
• /
• 2019

This paper proposes an efficient data-driven approach to build models for predicting energy consumption in buildings. Data used in this research is collected by installing humidity and temperature sensors at different locations in a building. In addition to this, weather data from nearby weather station is also included in the dataset to study the impact of weather conditions on energy consumption. One of the main emphasize of this research is to make feature selection independent of domain knowledge. Therefore, to extract useful features from data, two different approaches are tested: one is feature selection through principal component analysis and second is relative importance-based feature selection in original domain. The regression model used in this research is gradient boosting regression and its optimal parameters are chosen through a two staged coarse-fine search approach. In order to evaluate the performance of model, different performance evaluation metrics like r2-score and root mean squared error are used. Results have shown that best performance is achieved, when relative importance-based feature selection is used with gradient boosting regressor. Results of proposed technique has also outperformed the results of support vector machines and neural network-based approaches tested on the same dataset.

• Transactions of Materials Processing
• /
• v.31 no.4
• /
• pp.173-178
• /
• 2022

The present study employed two different machine-learning approaches, the extreme gradient boosting (XGB) and light gradient boosting machine (LGBM), to predict a compressive deformation behavior of additively manufactured Ti-6Al-4V. Such approaches have rarely been verified in the field of metallurgy in contrast to artificial neural network and its variants. XGB and LGBM provided a good prediction for elongation to failure under an extrapolated condition of processing parameters. The predicting accuracy of these methods was better than that of response surface method. Furthermore, XGB and LGBM with optimum hyperparameters well predicted a deformation behavior of Ti-6Al-4V additively manufactured under the extrapolated condition. Although the predicting capability of two methods was comparable, LGBM was superior to XGB in light of six-fold higher rate of machine learning. It is also noted this work has verified the LGBM approach in solving the metallurgical problem for the first time.

• Geomechanics and Engineering
• /
• v.37 no.6
• /
• pp.539-554
• /
• 2024

This study explores development of prediction model for seismic site classification through the integration of machine learning techniques with horizontal-to-vertical spectral ratio (HVSR) methodologies. To improve model accuracy, the research employs outlier detection methods and, synthetic minority over-sampling technique (SMOTE) for data balance, and evaluates using seven machine learning models using seismic data from KiK-net. Notably, light gradient boosting method (LGBM), gradient boosting, and decision tree models exhibit improved performance when coupled with SMOTE, while Multiple linear regression (MLR) and Support vector machine (SVM) models show reduced efficacy. Outlier detection techniques significantly enhance accuracy, particularly for LGBM, gradient boosting, and voting boosting. The ensemble of LGBM with the isolation forest and SMOTE achieves the highest accuracy of 0.91, with LGBM and local outlier factor yielding the highest F1-score of 0.79. Consistently outperforming other models, LGBM proves most efficient for seismic site classification when supported by appropriate preprocessing procedures. These findings show the significance of outlier detection and data balancing for precise seismic soil classification prediction, offering insights and highlighting the potential of machine learning in optimizing site classification accuracy.

• The Korean Journal of Applied Statistics
• /
• v.18 no.2
• /
• pp.343-354
• /
• 2005

The goal of this paper is to compare classification performances and to find a better classifier based on the characteristics of data. The compared methods are CART with two ensemble algorithms, bagging or boosting and SVM. In the empirical study of twenty-eight data sets, we found that SVM has smaller error rate than the other methods in most of data sets. When comparing bagging, boosting and SVM based on the characteristics of data, SVM algorithm is suitable to the data with small numbers of observation and no missing values. On the other hand, boosting algorithm is suitable to the data with number of observation and bagging algorithm is suitable to the data with missing values.

• Tribology and Lubricants
• /
• v.34 no.2
• /
• pp.55-59
• /
• 2018

This paper proposes a new type of electro-mechanical wedge brake for commercial vehicles. The brake operates on a novel mechanism for self-boosting braking friction forces using eccentric shafts, and involves wedges that are inserted between the rampbridge and traverse; this self-boosting mechanism is explained herein. A dynamic analysis using ADAMS was conducted, and the findings are reported. The constraint and contact conditions are explained to verify the precision of the dynamic analysis. The dynamic analysis shows that in the proposed mechanism, the self-boosting effect occurs as desired. However, it is also noted that the system has a limitation in terms of the production of unlimited braking forces that can jam the roller inside the wedges. After demonstrating the self-boosting effect, dynamic analyses are performed for several values of the wedge angles and friction coefficients between the brake pads and disks. Conventionally, a lower wedge angle has been suggested owing to its provision of a larger clamping force for given friction coefficients. However, it is noted that lower wedge angles can lead to a higher probability of occurrence of undesirable high braking forces, which can jam the roller into the wedge; thus, a larger wedge angle is preferable for avoiding the undesirable jamming phenomena. These analysis results are presented and discussed herein.

• Transactions of the Korean hydrogen and new energy society
• /
• v.24 no.6
• /
• pp.573-579
• /
• 2013

Hydrogen engine with homogeneous charged compression ignition can achieve high efficiency by high compression ratio and rapid chemical reaction rates spatially. However, it needs to expansion of the operation range with over-all load conditions which is very narrow due to extremely high pressure rise rate. The adoption of the lean boosting in a HCCI $H_2$ engine is expected to be effective in expansion of operation range since minimum compression ratio for spontaneous ignition is decreased by low temperature combustion and increased surround in-cylinder pressure. In order to grasp its possibility by using lean boosting in the HCCI $H_2$ engine, compression ratio required for spontaneous ignition, expansion degree of the operation range and over-all engine performance are experimentally analyzed with the boosting pressure and supply energy. As the results, it is found that minimum compression ratio for spontaneous ignition is down to the compression ratio(${\varepsilon}$=19) of conventional diesel engine due to decreased self-ignition temperature, and operation range is extended to 170% in term of the equivalence ratio and 12 times in term of the supply energy than that of naturally aspirated type. Though indicated thermal efficiency is decreased by reduced compression ratio, it is over at least 46%.

• Korean Journal of Construction Engineering and Management
• /
• v.17 no.1
• /
• pp.28-39
• /
• 2016

Since 2002, Korea Government has introduced Green Standard for Energy and Environmental Design Certification for reducing GHG emission in building area. However, total number of G-SEED Certification is only around 1% of total number of approved apartment buildings despite the various boosting policies. In this situation, most boosting policies and policy improvement researches are leaning toward the supplier's aspect. However, comprehensive relation and dynamics between consumer and supplier has to be considered because housing market is operated by market participants' mutual interaction. Therefore, this research presents system dynamics models based on decision making analysis of consumer and supplier in G-SEED Certification apartment building market. Then, this research evaluate the validity of boosting policies using the model. The proposed analysis can assist government to make next G-SEED Certification boosting policy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.1
• /
• pp.70-75
• /
• 2022

Accurately measuring location is necessary to provide a variety of services. The data for indoor positioning measures the RSSI values from the WiFi device through an application of a smartphone. The measured data becomes the raw data of machine learning. The feature data is the measured RSSI value, and the label is the name of the space for the measured position. For this purpose, the machine learning technique is to study a technique that predicts the exact location only with the WiFi signal by applying an efficient technique to classification. Ensemble is a technique for obtaining more accurate predictions through various models than one model, including backing and boosting. Among them, Boosting is a technique for adjusting the weight of a model through a modeling result based on sampled data, and there are various algorithms. This study uses Xgboost among the above techniques and evaluates performance with other ensemble techniques.

• KEPCO Journal on Electric Power and Energy
• /
• v.5 no.3
• /
• pp.173-179
• /
• 2019

Cryogenic air separation unit produces various gases such as $N_2$, $O_2$, and Ar by liquefying air. The process also varies with diverse production conditions. The one for SNG production among them has lower efficiency compared to other air separation unit because it requires ultrapure $O_2$ with purity not lower than 99.5%. Among factors that reduce the efficiency of air separation unit, power consumption due to compress air and heat duty of double column were representatives. In this study, simulation of the air separation unit for SNG production was carry out by using ASEPN PLUS. In the results of the simulation, 18.21 kg/s of at least 99.5% pure $O_2$ was produced and 33.26 MW of power was consumed. To improve the energy efficiency of air separation unit for SNG production, the sensitivity analysis for power consumption, purities and flow rate of $N_2$, $O_2$ production in the air separation unit was performed by change of air boosting ratios. The simulated model has three types of air with different pressure levels and two air boosting ratio. The air boosting ratio means flow rate ratio of air by recompressing in the process. As increasing the first air boosting ratio, $N_2$ flow rate which has purity of 99.9 mol% over increase and $O_2$ flow rate and purity decrease. As increasing the second air boosting ratio, $N_2$ flow rate which has purity of 99.9 mol% over decreases and $O_2$ flow rate increases but the purity of $O_2$ decreases. In addition, power consumption of compressing to increase in the two cases but results of heat duty in double column were different. The heat duty in double column decreases as increasing the first air boosting ratio but increases as increasing the second air boosting ratio. According to the results of the sensitivity analysis, the optimum air boosting ratios were 0.48 and 0.50 respectively and after adjusting the air boosting ratios, power consumption decreased by approximately 7% from $0.51kWh/O_2kg$ to $0.47kWh/O_2kg$.