http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
데이터 불균형 상황에서 딥러닝 기반 원심펌프 캐비테이션 진단
유동휘(Donghwi Yoo),오현석(Hyunseok Oh) 대한기계학회 2022 대한기계학회 춘추학술대회 Vol.2022 No.11
Cavitation is a major failure mode of the centrifugal pump. However, cavitation data are difficult to obtain in the field. It leads to data imbalance between normal data and cavitation data. This paper proposes a diagnostic method that evaluates the cavitation severity of a centrifugal pump. The vibration signal dataset consists of a large amount of normal data and a small amount of cavitation data. Vibration signals are converted into frequency spectrum data by the fast Fourier transform. The Deep SVDD model is trained with the vibration frequency spectrum data. The effectiveness of the proposed method is evaluated with datasets from a 0.75 kW centrifugal pump testbed. The proposed method can diagnose the severity of the cavitation under data imbalance.
유동휘(Donghwi Yoo),최민석(Minseok Choi),김정언(Chungeon Kim),오현석(Hyunseok Oh) 대한기계학회 2022 大韓機械學會論文集A Vol.46 No.2
캐비테이션은 원심펌프의 마모 및 열화를 가속하는 주요 고장 모드 중 하나이다. 캐비테이션은 펌프의 오작동을 초래할 수 있고, 이는 시스템 전체 가동을 멈추게 할 수 있다. 따라서 캐비테이션 현상을 미리 감지하고 회피하는 것은 중요하다. 본 논문은 원심펌프에서 캐비테이션을 감지하는 준지도 학습방법을 제안한다. 1차원 진동 신호를 단시간 푸리에 변환을 통해 2차원 이미지로 변환한다. 변이형 오토인코더와 마할라노비스 거리를 사용하여 캐비테이션 심각도를 결정한다. 본 논문에서 제안한 방법을 0.75 kW 원심펌프 테스트베드에서 수집한 데이터로 평가한다. 제안한 방법은 캐비테이션의 심각도를 감지하고 캐비테이션 현상을 피할 수 있도록 도움을 줄 것으로 기대된다. Cavitation is a dominant failure mode that accelerates the wear and deterioration of pumps. Cavitation can lead to pump malfunction and, eventually, catastrophic failure of the whole system. Therefore, it is important to avoid cavitation in the pump. This paper proposes a semi-supervised learning method that detects cavitation in centrifugal pumps. One-dimensional (1D) vibration signals are converted into two-dimensional (2D) images by the short time Fourier transform. The severity of the cavitation is determined using the variational autoencoder and Mahalanobis distance. The effectiveness of the proposed method is evaluated using the data collected from a 0.75 kW hydraulic pump testbed. It is confirmed that the proposed method can detect cavitation with different severities and help avoid the cavitation phenomenon.
동시 스퍼터링 방법으로 증착한 ZnO:Al의 전기적 광학적 특성
유동휘 ( Dongwhi Yu ),오병성 ( Byungsung O ) 충남대학교 기초과학연구소 2016 忠南科學硏究誌 Vol.33 No.2
ZnO:Al thin films were grown on sodalime glass by RF magnetron co-sputtering. The RF power for ZnO target was fixed and DC power for Al target was controlled to adjust the Al contents in the films. As the DC power increased, the diffraction angle of XRD peak increased and the FWHM got smaller. The resistivity of the films decreased and the optical energy gap increased with increasing DC power. As the DC power increases, more Al atoms might be substituted with Zn atoms and the free electron density increases. With this increase in free electron density, the resistivity decrease and the optical energy gap increase can be explained. But above the specific DC power, namely above the specific Al contents, Al atoms might become interstitials and the quality of films gets worse (the FWHM of the XRD peak increases and the resistivity decreases).
데이터 불균형 상황에서 딥러닝 기반 원심펌프 캐비테이션 진단
유동휘(Donghwi Yoo),오현석(Hyunseok Oh) 대한기계학회 2022 대한기계학회 춘추학술대회 Vol.2022 No.11
Cavitation is a major failure mode of the centrifugal pump. However, cavitation data are difficult to obtain in the field. It leads to data imbalance between normal data and cavitation data. This paper proposes a diagnostic method that evaluates the cavitation severity of a centrifugal pump. The vibration signal dataset consists of a large amount of normal data and a small amount of cavitation data. Vibration signals are converted into frequency spectrum data by the fast Fourier transform. The Deep SVDD model is trained with the vibration frequency spectrum data. The effectiveness of the proposed method is evaluated with datasets from a 0.75 kW centrifugal pump testbed. The proposed method can diagnose the severity of the cavitation under data imbalance.
박주헌,조현우,박한빈,유동휘,김상균,권오훈,최강의,최성훈,Hong-Min Chu,장종원 대한침구의학회 2020 대한침구의학회지 Vol.37 No.1
Background: This study aimed to investigate the clinical effectiveness of treatment of Korean medicine on superior labrum anterior to posterior (SLAP) lesions. Methods: A total of 55 inpatients diagnosed with SLAP lesions by magnetic resonance imaging, were investigated from May 1 st , 2014 to May 31 st , 2019 at Haeundae Jaseng Hospital of Korean Medicine. The patients were sorted by gender, age, causing factor, illness duration, period of hospitalization, SLAP lesion type, complications, and treatments. Treatments included acupuncture, pharmacopuncture, Chuna therapy, herbal treatment, and physiotherapy. After treatment, the Numeric Rating Scale, Shoulder Pain and Disability Index, and European Quality of Life 5-Dimension questionnaire were used to evaluate treatment effect. Results: There were more males than females in this study (1:0.83). Patients were more likely to be in their 50s (38.18%), have an unknown etiology (70.91%), and be in the subacute disease stage (41.82%). According to the SLAP lesion type, most of the inpatients had Type 2 lesions (69.09%). For inpatients diagnosed with SLAP lesions, the mean shoulder numeric rating scale score decreased from 5.55 ± 0.90, to 4.07 ± 1.18 (p < 0.001), the mean Shoulder Pain and Disability Index score decreased from 50.35 ± 18.36, to 39.90 ± 19.34 (p < 0.001), and the mean European quality of life 5-dimension index increased from 0.70 ± 0.16, to 0.75 ± 0.13 (p < 0.01) after treatment. Conclusion: Treatment of Korean medicine effectively decreased pain and increased the quality of life of the patients with SLAP lesions in this study.
중국에 있어서의 금산규제 - 현황, 문제점 및 개선방향 -
오일환 ( Wu Rihuan ),유동휘 ( Liu Donghui ) 한국금융법학회 2021 金融法硏究 Vol.18 No.3
이 글은 중국에 있어서 금산규제의 역사 및 현황에 대하여 정리하였다. 중국의 금산규제는 상대적으로 자유로운 단계로부터 점차적으로 발전하여 비교적 완전한 규제체계를 갖춤으로써 산업자본의 금융업 진입 및 금융자본의 산업진입에 대하여 사전, 사중 및 사후적 규율을 하고 있다. 그러나 전체적으로 본다면 중국의 금산규제는 산업자본의 금융업에 대한 투자에 대하여 엄격한 제한을 하고 있지 않으며 정책상 산업자본의 금융업에 대한 지배를 허용함으로써 적지 않은 지주회사형의 금산결합형태의 그룹이 형성하기에 이르렀다. 이는 일면으로 금융의 효율성 제고와 금융혁신에 유리하지만 다른 일면으로 금융리스크와 폐단이 증가하였다. 중국의 감독기관은 이미 금산규제의 중요성을 인식하고 일련의 금산결합을 규제하는 규범성 문건을 제정하였다. 하지만 중국의 금산규제는 명확한 입법계획이 없고 다원화되고 분산된 감독을 하고 있으며, 포괄적인 원칙성 감독을 위주로 함으로써 효과적인 금산규제를 실시하지 못하고 있고 일부 제도상의 틈새와 공백도 존재하고 있다. 이에 따라 본문은 금융리스크의 방지를 금산규제의 주요목표로, 금융기관의 지배구조의 개선을 주요 방향으로 명학히 하여 지배주주의 자산이전 및 이익제공행위를 방지하고 구체적인 관계자거래제도와 리스크방지를 위한 방화벽제도를 수립하여야 한다고 주장하였다. This article reviews the history and current situation of China’s industry-finance regulation. China's industry-finance regulation has gradually evolved from a relatively free model to a more improved regulatory framework. It has regulated industrial capital investing financial capital and financial capital investing industrial capital. However, on the whole, China’s industry-finance regulations have not strictly limited the investment between industry and finance department. The industry-finance policy allows industrial capital to control the financial industry. Many industrial-financial integration corporate groups have emerged, which is conducive to improving financial efficiency and financial innovation, but also increase financial risks and hidden dangers. China’s regulators have realized the importance of industry-finance regulation, and formulated some regulatory documents to regulate industry-finance integration. However, China’s industry-finance regulation lacks clear legislative planning, and there are diversified supervision authorities. It is difficult to effectively implement industry-finance regulations, and there are also some institutional loopholes and gaps. This article believes that the prevention of financial risks should be clearly identified as the main goal of the industry-finance regulation. The main direction is to improve the corporate governance of financial institutions, prevent the transfer of assets and benefits by controlling shareholders, and establish specific related transaction systems and risk prevention system.