Insu Jung
Insu Jung has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Jiayi Fan
Seoul National University of Science and Technology
3 shared publications - Yongkeun Lee
Department of Semiconductor Engineering, Seoul National University of Science and Technology, Seoul, South Korea
3 shared publications Bong Hwan Hong
Korea Institute of Radiological & Medical Sciences, Republic of Korea
2 shared publicationsDong Hyun An
1 shared publicationGaram Hahn
1 shared publicationGun Uk Kang
1 shared publication
Latest Publications
- Open Access
Position Estimation of a Two-Phase Switched Reluctance Motor at Standstill
In this paper, a sensorless position detection method of a two-phase switched reluctance motor (SRM) at standstill is proposed based on the voltage pulse injection method. Due to the torque dead zone and the lack of starting capability in the two-phase SRM, a rotor with a stepped structure is adopted to ensure continuous torque generation. The inductance characteristics of the asymmetric SRM are analyzed, and the region of the rotor position is categorized into linear regions and nonlinear regions with several key rotor positions and threshold values of self-inductance. A simple analytical model of the phase self-inductance profile of the asymmetric rotor SRM is proposed, which only requires a few linear equations, to replace the conventional look-up table. A pulse injection-based position estimation method is proposed based on the aforementioned analytical model. Short voltage pulses are injected into both phases at the same time to determine the position where the rotor is actually located at standstill. The proposed position detection method is simple and requires no extra circuitry. The simulation results are given and show the proposed estimation method can acquire a precise rotor position accurately at a standstill condition.
Open AccessPosition Estimation of a Two-Phase Switched Reluctance Motor at Standstill
In this paper, a sensorless position detection method of a two-phase switched reluctance motor (SRM) at standstill is proposed based on the voltage pulse injection method. Due to the torque dead zone and the lack of starting capability in the two-phase SRM, a rotor with a stepped structure is adopted to ensure continuous torque generation. The inductance characteristics of the asymmetric SRM are analyzed, and the region of the rotor position is categorized into linear regions and nonlinear regions with several key rotor positions and threshold values of self-inductance. A simple analytical model of the phase self-inductance profile of the asymmetric rotor SRM is proposed, which only requires a few linear equations, to replace the conventional look-up table. A pulse injection-based position estimation method is proposed based on the aforementioned analytical model. Short voltage pulses are injected into both phases at the same time to determine the position where the rotor is actually located at standstill. The proposed position detection method is simple and requires no extra circuitry. The simulation results are given and show the proposed estimation method can acquire a precise rotor position accurately at a standstill condition.
- Open Access
- 12 December 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (24) , 11796
Online Monitoring of Power Converter Degradation Using Deep Neural Network
Power semiconductor devices in the power converters used for motor drives are susceptible to wear-out and failure, especially when operated in harsh environments. Therefore, detection of degradation of power devices is crucial for ensuring the reliable performance of power converters. In this paper, a deep learning approach for online classification of the health states of the snubber resistors in the Insulated Gate Bipolar Transistors (IGBTs) in a three-phase Brushless DC (BLDC) motor drive is proposed. The method can locate one out of the six IGBTs experiencing a snubber resistor degradation problem by measuring the voltage waveforms of the three shunt resistors using voltage sensors. The range of the degradation of the snubber resistors for successful classification is also investigated. The off-the-shelf deep Convolutional Neural Network (CNN) architecture ResNet50 is used for transfer learning to determine which snubber resistor has degraded. The dataset for evaluating the above classification scheme of IGBT degradation is obtained by measuring the shunt voltage waveforms with varying snubber resistance and reference current. Then, the three-phase voltage waveforms are converted into greyscale images and RGB spectrogram images, which are later fed into the deep CNN. Experiments are carried out on the greyscale image dataset and the spectrogram image dataset using four-fold cross-validation. The results show that the proposed scheme can classify seven classes (one class for normal condition and six classes for abnormal condition in one of the six IGBTs in a three-phase BLDC drive) with over 95% average accuracy within a specific range of snubber resistance. Using grayscale images and using spectrogram-based RGB images yields similar accuracy.
- 12 December 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (24) , 11796
Open AccessOnline Monitoring of Power Converter Degradation Using Deep Neural Network
Power semiconductor devices in the power converters used for motor drives are susceptible to wear-out and failure, especially when operated in harsh environments. Therefore, detection of degradation of power devices is crucial for ensuring the reliable performance of power converters. In this paper, a deep learning approach for online classification of the health states of the snubber resistors in the Insulated Gate Bipolar Transistors (IGBTs) in a three-phase Brushless DC (BLDC) motor drive is proposed. The method can locate one out of the six IGBTs experiencing a snubber resistor degradation problem by measuring the voltage waveforms of the three shunt resistors using voltage sensors. The range of the degradation of the snubber resistors for successful classification is also investigated. The off-the-shelf deep Convolutional Neural Network (CNN) architecture ResNet50 is used for transfer learning to determine which snubber resistor has degraded. The dataset for evaluating the above classification scheme of IGBT degradation is obtained by measuring the shunt voltage waveforms with varying snubber resistance and reference current. Then, the three-phase voltage waveforms are converted into greyscale images and RGB spectrogram images, which are later fed into the deep CNN. Experiments are carried out on the greyscale image dataset and the spectrogram image dataset using four-fold cross-validation. The results show that the proposed scheme can classify seven classes (one class for normal condition and six classes for abnormal condition in one of the six IGBTs in a three-phase BLDC drive) with over 95% average accuracy within a specific range of snubber resistance. Using grayscale images and using spectrogram-based RGB images yields similar accuracy.
- Open Access
- 27 August 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (17) , 7929
A Study on Multiple Factors Affecting the Accuracy of Multiclass Skin Disease Classification
Diagnosis of skin diseases by human experts is a laborious task prone to subjective judgment. Aided by computer technology and machine learning, it is possible to improve the efficiency and robustness of skin disease classification. Deep transfer learning using off-the-shelf deep convolutional neural networks (CNNs) has huge potential in the automation of skin disease classification tasks. However, complicated architectures seem to be too heavy for the classification of only a few skin disease classes. In this paper, in order to study potential ways to improve the classification accuracy of skin diseases, multiple factors are investigated. First, two different off-the-shelf architectures, namely AlexNet and ResNet50, are evaluated. Then, approaches using either transfer learning or trained from scratch are compared. In order to reduce the complexity of the network, the effects of shortening the depths of deep CNNs are investigated. Furthermore, different data augmentation techniques based on basic image manipulation are compared. Finally, the choice of mini-batch size is studied. Experiments were carried out on the HAM10000 skin disease dataset. The results show that the ResNet50-based model is more accurate than the AlexNet-based model. The transferred knowledge from the ImageNet database helps to improve the accuracy of the model. The reduction in stages of the ResNet50-based model can reduce complexity while maintaining good accuracy. Additionally, the use of different types of data augmentation techniques and the choice of mini-batch size can also affect the classification accuracy of skin diseases.
- 27 August 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (17) , 7929
Open AccessA Study on Multiple Factors Affecting the Accuracy of Multiclass Skin Disease Classification
Diagnosis of skin diseases by human experts is a laborious task prone to subjective judgment. Aided by computer technology and machine learning, it is possible to improve the efficiency and robustness of skin disease classification. Deep transfer learning using off-the-shelf deep convolutional neural networks (CNNs) has huge potential in the automation of skin disease classification tasks. However, complicated architectures seem to be too heavy for the classification of only a few skin disease classes. In this paper, in order to study potential ways to improve the classification accuracy of skin diseases, multiple factors are investigated. First, two different off-the-shelf architectures, namely AlexNet and ResNet50, are evaluated. Then, approaches using either transfer learning or trained from scratch are compared. In order to reduce the complexity of the network, the effects of shortening the depths of deep CNNs are investigated. Furthermore, different data augmentation techniques based on basic image manipulation are compared. Finally, the choice of mini-batch size is studied. Experiments were carried out on the HAM10000 skin disease dataset. The results show that the ResNet50-based model is more accurate than the AlexNet-based model. The transferred knowledge from the ImageNet database helps to improve the accuracy of the model. The reduction in stages of the ResNet50-based model can reduce complexity while maintaining good accuracy. Additionally, the use of different types of data augmentation techniques and the choice of mini-batch size can also affect the classification accuracy of skin diseases.
- 1 July 2017
- Published by Elsevier in Applied Radiation and Isotopes
- Vol. 125, 180-184
Pressure control of a proton beam–irradiated water target through an internal flow channel–induced thermosyphon
- 1 July 2017
- Published by Elsevier in Applied Radiation and Isotopes
- Vol. 125, 180-184
Pressure control of a proton beam–irradiated water target through an internal flow channel–induced thermosyphon
- 24 July 2012
- Published by Korean Physical Society in Journal of the Korean Physical Society
- Vol. 61 (2) , 193-196
Radio-frequency system of the KIRAMS-30 cyclotron for RI mass production
- 24 July 2012
- Published by Korean Physical Society in Journal of the Korean Physical Society
- Vol. 61 (2) , 193-196
Radio-frequency system of the KIRAMS-30 cyclotron for RI mass production