• Proceedings of the KIPE Conference
• /
• 2000.07a
• /
• pp.78-81
• /
• 2000

The backlight inverter used in a laptop computer is investigated in this paper. It has been difficult for the electromagnetic transformer in the inverter to have a high efficiency and compact profile. In this study the piezoelectric transformer(PT) is used to reduce the loss and volume compared to the standard electromagnetic transformer. Comparison with the experimental inverter with the PT has been shown to validated the simulation program using the equivalent circuit model of the PT. A simple dimming control circuit was experimentally demonstrated and shown to have broad control.

• Proceedings of the KIEE Conference
• /
• 2005.07a
• /
• pp.120-123
• /
• 2005

This paper, for the establishment of power system models and test procedures for the dynamic performance test of transformer protective relay, presents power system model, environment establishement between RTDS and protective relay, and the dynamic performance test generated internal fault or external fault.

• Proceedings of the KIEE Conference
• /
• 1999.07c
• /
• pp.1410-1412
• /
• 1999

Protective relay for transformer operates in general by comparing with the differential current and the restraint current. These kinds of currents are changed on magnitude and phasor during the fault according to winding type and vector group. This paper presents the differential and restraint currents and operational principle of differential protective relay for two-winding and three-winding transformer with graphical model. It is developed using MATLAB for an educational purpose on engineer related in power system and protection in university and power utility including large factory.

• Proceedings of the KSR Conference
• /
• 2000.11a
• /
• pp.740-747
• /
• 2000

This paper describes insulation characteristics and partial discharge for the SF6 gas insulated transformer. The characteristic of gas insulated transformer and the degradation sequence of solid insulation under SF6 gas atmosphere were explained. The model electrode system of the types that the aramid papers were inserted between two sphere electrodes was prepared. The partial discharge tests were carried out to that system and the insulation characteristics were considered.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.12
• /
• pp.579-586
• /
• 2021

Time series forecasting refers to predicting future time information based on past time information. Accurately predicting future information is crucial because it is used for establishing strategies or making policy decisions in various fields. Recently, a transformer model has been mainly studied for a time series prediction model. However, the existing transformer model has a limitation in that it has an auto-regressive structure in which the output result is input again when the prediction sequence is output. This limitation causes a problem in that accuracy is lowered when predicting a distant time point. This paper proposes a sequential decoding model focusing on the style transformation technique to handle these problems and make more precise time series forecasting. The proposed model has a structure in which the contents of past data are extracted from the transformer-encoder and reflected in the style-based decoder to generate the predictive sequence. Unlike the decoder structure of the conventional auto-regressive transformer, this structure has the advantage of being able to more accurately predict information from a distant view because the prediction sequence is output all at once. As a result of conducting a prediction experiment with various time series datasets with different data characteristics, it was shown that the model presented in this paper has better prediction accuracy than other existing time series prediction models.

• Proceedings of the KIEE Conference
• /
• 2006.07a
• /
• pp.103-104
• /
• 2006

Since the first proposition of IEC61850 object model at 1993, many questions about making a seamless model have been issued. the reason which they have worry about is that the functions of the equipment are supposed to be changed properly and new equipment and scheme are need to be introduced according to user's application. To handle those issues, TC57 which is a IEC committee for power control and communication has continuously updated the object model. Nowadays along with the new object model involving power quality, distribution resource and wind power, the committee has a plan to announce the revision of IEC61850-7-4. In the study, authors will present the prediction and diagnosis object models for transformer. Transformer models for protection and control have already been dealt with in the international standard but the models for prediction and diagnosis have never mentioned until now. Designing the prediction and diagnosis functions with the existing IEC61850-7-4, it'll be shown what is a proper object model for prediction and diagnosis.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.23 no.5
• /
• pp.359-365
• /
• 2018

This study introduces a model predictive control method for controlling a cascaded flying capacitor multilevel rectifier used as an AC-DC rectifier of a solid-state transformer for DC distribution systems. The proposed method reduces the number of states that need to be considered in model predictive control by separately controlling input current, output DC link voltage, and flying capacitor voltage. Thus, calculation time is shortened to facilitate the level expansion of the cascaded flying capacitor multilevel rectifier. The selection of weighting factors did not present difficulties because the weighting factors in the cost function of the conventional model predictive control are not used. The effectiveness of the proposed method is verified through computer simulation using powersim and experiment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• pp.1996-2015
• /
• 2023

High-definition (HD) maps can provide precise road information that enables an autonomous driving system to effectively navigate a vehicle. Recent research has focused on leveraging semantic segmentation to achieve automatic annotation of HD maps. However, the existing methods suffer from low recognition accuracy in automatic driving scenarios, leading to inefficient annotation processes. In this paper, we propose a novel semantic segmentation method for automatic HD map annotation. Our approach introduces a new encoder, known as the convolutional transformer hybrid encoder, to enhance the model's feature extraction capabilities. Additionally, we propose a multi-level fusion module that enables the model to aggregate different levels of detail and semantic information. Furthermore, we present a novel decoupled boundary joint decoder to improve the model's ability to handle the boundary between categories. To evaluate our method, we conducted experiments using the Bird's Eye View point cloud images dataset and Cityscapes dataset. Comparative analysis against stateof-the-art methods demonstrates that our model achieves the highest performance. Specifically, our model achieves an mIoU of 56.26%, surpassing the results of SegFormer with an mIoU of 1.47%. This innovative promises to significantly enhance the efficiency of HD map automatic annotation.

• Nuclear Engineering and Technology
• /
• v.56 no.4
• /
• pp.1284-1295
• /
• 2024

Due to increasing operational security demands, digital and intelligent condition monitoring of nuclear power plants is becoming more significant. However, establishing an accurate and effective anomaly detection model is still challenging. This is mainly because of data characteristics of nuclear power data, including the lack of clear class labels combined with frequent interference from outliers and anomalies. In this paper, we introduce a Transformer-based unsupervised model for anomaly detection of nuclear power data, a modified loss function based on the maximum correntropy criterion (MCC) is applied in the model training to improve the robustness. Experimental results on simulation datasets demonstrate that the proposed Trans-MCC model achieves equivalent or superior detection performance to the baseline models, and the use of the MCC loss function is proven can obviously alleviate the negative effect of outliers and anomalies in the training procedure, the F1 score is improved by up to 0.31 compared to Trans-MSE on a specific dataset. Further studies on genuine nuclear power data have verified the model's capability to detect anomalies at an earlier stage, which is significant to condition monitoring.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.4
• /
• pp.169-178
• /
• 2022

Morphemes are most primitive units in a language that lose their original meaning when segmented into smaller parts. In Korean, a sentence is a sequence of eojeols (words) separated by spaces. Each eojeol comprises one or more morphemes. Korean morphological analysis (KMA) is to divide eojeols in a given Korean sentence into morpheme units. It also includes assigning appropriate part-of-speech(POS) tags to the resulting morphemes. KMA is one of the most important tasks in Korean natural language processing (NLP). Improving the performance of KMA is closely related to increasing performance of Korean NLP tasks. Recent research on KMA has begun to adopt the approach of machine translation (MT) models. MT is to convert a sequence (sentence) of units of one domain into a sequence (sentence) of units of another domain. Neural machine translation (NMT) stands for the approaches of MT that exploit neural network models. From a perspective of MT, KMA is to transform an input sequence of units belonging to the eojeol domain into a sequence of units in the morpheme domain. In this paper, we propose a deep learning model for KMA. The backbone of our model is based on the BERT-fused model which was shown to achieve high performance on NMT. The BERT-fused model utilizes Transformer, a representative model employed by NMT, and BERT which is a language representation model that has enabled a significant advance in NLP. The experimental results show that our model achieves 98.24 F1-Score.