http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
고압주조한 Al-10% Mg 합금의 주조조직 및 기계적 성질에 관한 연구
정우현,정종연,이종남 ( Woo Hyon Jeong,Jong Yeon Jeong,Jong Nam Lee ) 한국주조공학회 1983 한국주조공학회지 Vol.3 No.1
In order to study the cast structure and mechanical properties of Al-10% Mg alloy solidified under the various high hydraulic pressure, ranging from O㎏f/㎠ to 2000㎏f/㎠ , the relationship between the cooling rate and the cast structure was observed, and also the mechanical test and the measurement of the specific gravity were carried out. From this experiment, results were summerized as follows; 1. The cooling rate of the alloy increased with increase of the applied pressure. 2. The formation of the piping and the porosity in the castings was surpressed by applying the high hydraulic pressure. 3. The dendrite arm spacing decreased with increase of the applied pressure. 4. Mechanical properties and specific gravity increased with the increase of the applied pressure.
컨볼루션 신경망 모델을 이용한 분류에서 입력 영상의 종류가 정확도에 미치는 영향
김민정,김정훈,박지은,정우연,이종민,Kim, Min Jeong,Kim, Jung Hun,Park, Ji Eun,Jeong, Woo Yeon,Lee, Jong Min 대한의용생체공학회 2021 의공학회지 Vol.42 No.4
The purpose of this study is to classify TIFF images, PNG images, and JPEG images using deep learning, and to compare the accuracy by verifying the classification performance. The TIFF, PNG, and JPEG images converted from chest X-ray DICOM images were applied to five deep neural network models performed in image recognition and classification to compare classification performance. The data consisted of a total of 4,000 X-ray images, which were converted from DICOM images into 16-bit TIFF images and 8-bit PNG and JPEG images. The learning models are CNN models - VGG16, ResNet50, InceptionV3, DenseNet121, and EfficientNetB0. The accuracy of the five convolutional neural network models of TIFF images is 99.86%, 99.86%, 99.99%, 100%, and 99.89%. The accuracy of PNG images is 99.88%, 100%, 99.97%, 99.87%, and 100%. The accuracy of JPEG images is 100%, 100%, 99.96%, 99.89%, and 100%. Validation of classification performance using test data showed 100% in accuracy, precision, recall and F1 score. Our classification results show that when DICOM images are converted to TIFF, PNG, and JPEG images and learned through preprocessing, the learning works well in all formats. In medical imaging research using deep learning, the classification performance is not affected by converting DICOM images into any format.
주름관 이음방식으로 수직 연결한 프리캐스트 콘크리트 수평접합부의 구조성능
김설기(Kim, Seol-Ki),서수연(Seo, Soo-Yeon),임병호(Yim, Byeong-Ho),김승훈(Kim, Seung-Hoon),유종우(Yoo, Jong-Woo),차정우(Cha, Jeong-Woo) 대한건축학회 2017 대한건축학회 학술발표대회 논문집 Vol.37 No.2
The purpose of this study is to verify the structural performance of precast concrete horizontal joint connected vertically by corrugated pipe joint method. Through the horizontal cyclic load tests, the structural performance of the PC wall horizontal joint using the corrugate pipe joint method was analyzed. Experimental results showed that the experimental strength exceeded the nominal strength. C joint specimens showed stable hysteresis characteristics, and shear failure of the PC wall dominated the overall behavior. C joint specimens showed excellent ductility and stiffness, and excellent energy dissipation capacity.