• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.21 no.7
• /
• pp.75-83
• /
• 2007

IEC code based decision nile have been widely applied to detect incipient faults in power transformers. However, this method has a drawback to achieve the diagnosis with accuracy without experienced experts. In order to resolve this problem, we propose an artificial diagnosis algorithm to detect faults of power transformers using Self-Organizing Feature Map(SOM). The proposed method has two stages such as model construction and diagnostic procedure. First, faulty model is constructed by feature maps obtained by unsupervised learning for training data. And then, diagnosis is performed by compare feature map with it obtained for test data. Also the proposed method usぉms the possibility and degree of aging as well as the fault occurred in transformer by clustering and distance measure schemes. To demonstrate the validity of proposed method, various experiments are unformed and their results are presented.

• Journal of the Semiconductor & Display Technology
• /
• v.4 no.1 s.10
• /
• pp.9-16
• /
• 2005

In this paper, with loosely coupled transformer Relies-parallel resonant type DC/DC converter is analyzed and adopted to the power source of a TFLM(Transverse Flux Linear Motor). To get more efficient operating mode of the series-parallel resonant type DC/DC converter, theoretical analysis using normalized parameters are accepted. The analysis includes a specially made ferrite transformer with two separately wound half cores in order to evaluate analytically and experimentally the changes in magnetizing the leakage fluxes and inductances caused by the distance between the halves. The proposed converter must be operated in switching Pattern III among the three switching patterns for the Zero Voltage Switching operation. According to Pulse Frequency Modulation(PFM) control method, the output voltage of the proposed circuit can be controlled. The results of the theoretical development are compared with practical measurements from a prototype system.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.24 no.4
• /
• pp.403-409
• /
• 2013

In this work, a CMOS two stage differential power amplifier which includes Marchand balun, transformer and injection-locked buffer is presented. The power amplifier is targeted for 70 GHz frequency band and fabricated using 65 nm technology. The measurement results show 8.5 dB maximum voltage gain at 71.3 GHz and 7.3 GHz 3 dB bandwidth. The measured maximum output power is 8.2 dBm, input $P_{1dB}$ is -2.8 dBm, output $P_{1dB}$ is 4.6 dBm and maximum power added efficiency is 4.9 %. The power amplifier consumes 102 mW DC power from 1.2 V supply voltage.

• Journal of the Korean Magnetics Society
• /
• v.6 no.6
• /
• pp.388-396
• /
• 1996

Magnetic properties of sintered Fe-79Ni-4Mo cores made of centrifugal atomized powders were investigated. $H_{c}$ and $\mu_{a}$ of the cores sintered at $1350^{\circ}C$ for 2 hours measured at 60 Hz at a magnetic field of 10 Oe showed the best properties. Particularly the properties of $H_{c}$ and $\mu_{a}$ measured at low field (< 0.2 Oe) were found to increase with increasing the particle size of the core samples. It resulted from the domain wall motion depending on the grain size of sintered bodies. The best D, C magnetic properties of $H_{c}$ and $\mu_{max}$ were 0.085 Oe and 40000, respectively. A, C properties of the same cores showed the $\mu_{a}$ of 11000. The magnetic properties of sintered cores always exhibited an enhanced AC/DC performance by using the powders mixed with two different particle sizes. Those properties of cores are expected to apply for current transformer.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.5
• /
• pp.1686-1693
• /
• 2014

In this paper, oil-paper samples composed of transformer windings were used to investigate the insulation degradation process subjected to partial discharge (PD), with artificial defects inside to simulate the PD induced insulation degradation. To determine appropriate test voltages, the breakdown time obtained through a group of accelerated electrical degradation tests under high voltages was firstly fitted by two-parameter Weibull model to acquire the average breakdown time, which was then applied to establish the inverse power law life model to choose advisable test voltages. During the electrical degradation process, PD signals were synchronously detected by an ultra-high frequency (UHF) sensor from inception to breakdown. For PD analysis, the whole degradation process was divided into ten stages, and chaos theory was introduced to analyze the variation of three chaotic parameters with the development of electrical degradation, namely the largest Lyapunov exponent, correlation dimension and Komogorov entropy of PD amplitude time series. It is shown that deterministic chaos of PD is confirmed during the oil-paper degradation process, and the obtained results provide a new effective tool for the diagnosis of degradation of oil-paper insulation subjected to PD.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.501-512
• /
• 2021

Recently, a breakthrough has been made in the NLP area by Transformer techniques based on encoder-decoder. However, this only can be used in mainstream languages where millions of dataset are well-equipped, such as English and Chinese, and there is a limitation that it cannot be used in non-mainstream languages where dataset are not established. In addition, there is a deflection problem that focuses on the beginning of the document in mechanical summarization. Therefore, these methods are not suitable for documents with flows such as fairy tales and novels. In this paper, we propose a hybrid summarization method that does not require a dataset and improves the deflection problem using GAN with two adaptive discriminators. We evaluate our model on the CNN/Daily Mail dataset to verify an objective validity. Also, we proved that the model has valid performance in Korean, one of the non-mainstream languages.

• Korean Journal of Cognitive Science
• /
• v.34 no.3
• /
• pp.197-226
• /
• 2023

Generative Text Summarization is one of the Natural Language Processing tasks. It generates a short abbreviated summary while preserving the content of the long text. ROUGE is a widely used lexical-overlap based metric for text summarization models in generative summarization benchmarks. Although it shows very high performance, the studies report that 30% of the generated summary and the text are still inconsistent. This paper proposes a methodology for evaluating the performance of the summary model without using the correct summary. AggreFACT is a human-annotated dataset that classifies the types of errors in neural text summarization models. Among all the test candidates, the two cases, generation summary, and when errors occurred throughout the summary showed the highest correlation results. We observed that the proposed evaluation score showed a high correlation with models finetuned with BART and PEGASUS, which is pretrained with a large-scale Transformer structure.

• Korean Journal of Artificial Intelligence
• /
• v.11 no.4
• /
• pp.9-13
• /
• 2023

In this study, we explored the potential of integrating interactive AI callbot technology into the medical consultation domain as part of a broader service development initiative. Aimed at enhancing patient satisfaction, the AI callbot was designed to efficiently address queries from hospitals' primary users, especially the elderly and those using phone services. By incorporating an AI-driven callbot into the hospital's customer service center, routine tasks such as appointment modifications and cancellations were efficiently managed by the AI Callbot Agent. On the other hand, tasks requiring more detailed attention or specialization were addressed by Human Agents, ensuring a balanced and collaborative approach. The deep learning model for voice recognition for this study was based on the Transformer model and fine-tuned to fit the medical field using a pre-trained model. Existing recording files were converted into learning data to perform SSL(self-supervised learning) Model was implemented. The ANN (Artificial neural network) neural network model was used to analyze voice signals and interpret them as text, and after actual application, the intent was enriched through reinforcement learning to continuously improve accuracy. In the case of TTS(Text To Speech), the Transformer model was applied to Text Analysis, Acoustic model, and Vocoder, and Google's Natural Language API was applied to recognize intent. As the research progresses, there are challenges to solve, such as interconnection issues between various EMR providers, problems with doctor's time slots, problems with two or more hospital appointments, and problems with patient use. However, there are specialized problems that are easy to make reservations. Implementation of the callbot service in hospitals appears to be applicable immediately.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3383-3397
• /
• 2023

Scene graphs serve as semantic abstractions of images and play a crucial role in enhancing visual comprehension and reasoning. However, the performance of Scene Graph Generation is often compromised when working with biased data in real-world situations. While many existing systems focus on a single stage of learning for both feature extraction and classification, some employ Class-Balancing strategies, such as Re-weighting, Data Resampling, and Transfer Learning from head to tail. In this paper, we propose a novel approach that decouples the feature extraction and classification phases of the scene graph generation process. For feature extraction, we leverage a transformer-based architecture and design an adaptive calibration function specifically for predicate classification. This function enables us to dynamically adjust the classification scores for each predicate category. Additionally, we introduce a Distribution Alignment technique that effectively balances the class distribution after the feature extraction phase reaches a stable state, thereby facilitating the retraining of the classification head. Importantly, our Distribution Alignment strategy is model-independent and does not require additional supervision, making it applicable to a wide range of SGG models. Using the scene graph diagnostic toolkit on Visual Genome and several popular models, we achieved significant improvements over the previous state-of-the-art methods with our model. Compared to the TDE model, our model improved mR@100 by 70.5% for PredCls, by 84.0% for SGCls, and by 97.6% for SGDet tasks.

• Analytical Science and Technology
• /
• v.23 no.3
• /
• pp.247-254
• /
• 2010

This study was carried out to produce Reference Materials (RMs) for Proficiency Testing (PT) of PCBs in waste analytical laboratories. Two RMs were prepared from used transformer oil samples and PCB free transformer oil by spiking PCBs standard solutions. The spiked PCB RMs were homogenized by mixing and settling up to 90 days. Homogenized concentration of PCBs with Arochlor 1254 (6 ppm), 1254:1260 (1:1) (5 ppm) were observed in 60 days stationary phase but Arochlor 1260 (3.5 mg/L) were observed in 90 days stationary phase. One-way ANOVA test were carried out and showed that the RMs were suitably homogenized, which can be used for proficiency testing. The Relative Standard Deviations (RSDs) of analytical results were 3.51~5.01% for the PCBs RMs in 10 replicates. The expanded uncertainty of PCBs analytical procedure were 0.26~0.49.