• Proceedings of the KIEE Conference
• /
• 2001.07a
• /
• pp.467-469
• /
• 2001

This paper presents an efficient location estimation methodology for a partial discharge(PD) source in the power transformer. The methodology previously proposed is not suitable for locating a PD source because the ultrasonic signal with medium attenuated through the inner structure. In general, the propagation characteristic of ultrasonic signal with medium is different. Therefore, using this propagation characteristic, we can detect the location of PD source. In this paper, the proposal algorithm finds the PD source using three sensors attached to one side of the transformer without attenuation of the ultrasonic signal and applying the neural network based geometrical method. The proposed methodology demonstrates the effectiveness and validity on an experimental transformer.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.88.4-88
• /
• 2001

In this paper, we propose a solver for differential equations, using a multi-layer neural network. The multi-layer neural network is a transformer function originally where the function is differential and the explicit representation has been developed. The learning determines the response of neural networks; however, the response is not equal to the output values. The differential relations are also the response. The differential conditions can be also set as teaching data; therefore, there is a possibility to reach a new solver for the differential equations. Since it is unknown how to define the input data for the neural network solver during long terms, we could not derive the expressions. Recently, the analogue type neural network is known and it transforms any vector to another The "any" must be...

• The Journal of Korea Robotics Society
• /
• v.19 no.3
• /
• pp.266-273
• /
• 2024

With the rising interaction between robots and humans, detecting collisions has become increasingly vital for ensuring safety. In this paper, we propose a novel approach for detecting collisions without using force torque sensors or tactile sensors, utilizing a Transformer-based neural network architecture. The proposed collision detection approach comprises a torque estimator network that predicts the joint torque in a free-motion state using Synchronous time-step encoding, and a collision discriminator network that predicts collisions by leveraging the difference between estimated and actual torques. The collision discriminator finally creates a binary tensor that predicts collisions frame by frame. In simulations, the proposed network exhibited enhanced collision detection performance relative to the other kinds of networks both in terms of prediction speed and accuracy. This underscores the benefits of using Transformer networks for collision detection tasks, where rapid decision-making is essential.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.65 no.4
• /
• pp.280-284
• /
• 2016

Stability and reliability of a power system in many respects depend on the condition of power transformers. Essential devices as power transformers are in a transmission and distribution system. Being one of the most expensive and important elements, a power transformer is a highly essential element, whose failures and damage may cause the outage of a power system. To detect the power transformer faults, dissolved gas analysis (DGA) is a widely-used method because of its high sensitivity to small amount of electrical faults. Among the various diagnosis methods, Rogers diagonsis method has been widely used in transformer in service. But this method cannot offer accurate diagnosis for all the faults. This paper proposes a fault diagnosis method of oil-filled power transformers using PNN(Probability Neural Network) based Rogers diagnosis method. The test result show better performance than conventional Rogers diagnosis method.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.127.2-127
• /
• 2001

A transformer is one of the most important elements in the power network. Transformer faults could cause costly repairs and be dangerous to personnel. To avoid this, its reliable operation has great significance and, therefore, the diagnosis system of the transformer is necessitated. The dissolved gas-in-oil analysis (DGA) is the worldwide popular method of detecting faults such as a hot spot or partial discharges inside the transformer. DGA, however, is not a reliable technique to identify aging phenomena and mechanical faults including insulation failure, inter-turn short, etc. To overcome the drawbacks of DGA, the transfer function method is used to identify effectively these kinds of the mechanical faults. The transformer has a unique transfer function independent of the shape of the input waveform, which can be evaluated through sweep test. This transfer function changes by winding ...

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.9
• /
• pp.1146-1151
• /
• 2018

Recently, researches on the intelligence of electric power facilities have been trying to apply artificial intelligence techniques as computer platforms have improved. In particular, faults occurring in substation should be able to quickly identify possible faults and minimize power fault recovery time. This paper presents fault location technique for 154kV substation using neural network. We constructed a training matrix based on the operating conditions of the circuit breaker and IED to identify the fault location of each component of the target 154kV substation, such as line, bus, and transformer. After performing the training to identify the fault location by the neural network using Weka software, the performance of fault location discrimination of the designed neural network was confirmed.

• Journal of the Korean Society of Radiology
• /
• v.18 no.5
• /
• pp.541-549
• /
• 2024

The various structures of artificial neural networks, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), have been extensively studied and served as the backbone of numerous models. Among these, a transformer architecture has demonstrated its potential for natural language processing and become a subject of in-depth research. Currently, the techniques can be adapted for image processing through the modifications of its internal structure, leading to the development of Vision transformer (ViT) models. The ViTs have shown high accuracy and performance with large data-sets. This study aims to develop a ViT-based model for detecting pneumonia using chest X-ray images and quantitatively evaluate its performance. The various architectures of the ViT-based model were constructed by varying the number of encoder blocks, and different patch sizes were applied for network training. Also, the performance of the ViT-based model was compared to the CNN-based models, such as VGGNet, GoogLeNet, and ResNet. The results showed that the traninig efficiency and accuracy of the ViT-based model depended on the number of encoder blocks and the patch size, and the F1 scores of the ViT-based model ranged from 0.875 to 0.919. The training effeciency of the ViT-based model with a large patch size was superior to the CNN-based models, and the pneumonia detection accuracy of the ViT-based model was higher than that of the VGGNet. In conclusion, the ViT-based model can be potentially used for pneumonia detection using chest X-ray images, and the clinical availability of the ViT-based model would be improved by this study.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1784-1789
• /
• 2021

Korean sentiment classification task is used in real-world services such as chatbots and analysis of user's purchase reviews. And due to the development of deep learning technology, neural network models with high performance are being applied. However, the neural network model is not easy to interpret what the input sentences are predicting due to which words, and recently, model interpretation methods for interpreting these neural network models have been popularly proposed. In this paper, we used the LIME algorithm among the model interpretation methods to interpret which of the words in the input sentences of the models learned with the korean sentiment classification dataset. As a result, the interpretation of the Bi-LSTM model with 85.24% performance included 25,283 words, but 84.20% of the transformer model with relatively low performance showed that the transformer model was more reliable than the Bi-LSTM model because it contains 26,447 words.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.14 no.1
• /
• pp.84-92
• /
• 2001

In this papers, we proposed the new method in order to diagnosis aging state of transformers. For wavelet transform, Daubechies filter is used, we can obtain wavelet coefficients which is used to extract feature of statistical parameters (maximum value, average value, dispersion skewness, kurtosis) about each acoustic emission signal. Also, these coefficients are used to identify normal and fault signal of internal partial discharge in transformer. As improved method for classification use neural network. Extracted statistical parameters are input into an back-propagation neural network. The number of neurons of hidden layer are obtained through Result of Cross-Validation. The network, after training, can decide whether the test signal is early aging state, alst aging state or normal state. In quantity analysis, capability of proposed method is superior to compared that of classical method.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.351-360
• /
• 2022

Image blurring is a phenomenon that occurs due to factors such as movement of a subject and shaking of a camera. Recently, the research for image deblurring has been actively conducted based on convolution neural networks. In particular, the method of guiding the restoration process via the difference between blur and sharp images has shown the promising performance. This paper proposes a novel method for improving the deblurring performance based on the distortion information. To this end, the transformer-based neural network module is designed to guide the restoration process. The proposed method efficiently reflects the distorted region, which is predicted through the global inference during the deblurring process. We demonstrate the efficiency and robustness of the proposed module based on experimental results with various deblurring architectures and benchmark datasets.