http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
( Hyunbin Kim ),( Mingyu Kim ),( Yonggun Park ),( Sang-Yun Yang ),( Hyunwoo Chung ),( Ohkyung Kwon ),( Hwanmyeong Yeo ) 한국목재공학회 2019 목재공학 Vol.47 No.2
목재의 결점은 생장과정에서 또는 가공 중에 다양한 형태로 발생한다. 따라서 목재를 이용하기 위해서는 목재의 결점을 정확하게 분류하여 용도에 맞는 목재 품질을 객관적으로 평가할 필요가 있다. 하지만 사람에 의한 등급구분과 수종구분은 주관적 판단에 의해 차이가 발생할 수 있기 때문에 목재 품질의 객관적 평가 및 목재 생산의 고속화를 위해서는 컴퓨터 비전을 활용한 화상분석 자동화가 필요하다. 본 연구에서는 SIFT+k-NN 모델과 CNN 모델을 통해 옹이의 종류를 자동으로 구분하는 모델을 구현하고 그 정확성을 분석해보고자 하였다. 이를 위하여 다섯 가지 국산 침엽수종으로부터 다양한 형태의 옹이 이미지 1,172개를 획득하여 학습 및 검증에 사용하였다. SIFT+k-NN 모델의 경우, SIFT 기술을 이용하여 옹이 이미지에서 특성을 추출한 뒤, k-NN을 이용하여 분류를 진행하였으며, 최대 60.53%의 정확도로 분류가 가능하였다. 이 때 k-index는 17이었다. CNN 모델의 경우, 8층의 convolution layer와 3층의 hidden layer로 구성되어있는 모델을 사용하였으며, 정확도의 최대값은 1205 epoch에서 88.09%로 나타나 SIFT+k-NN 모델보다 높은 결과를 보였다. 또한 옹이의 종류별 이미지 개수 차이가 큰 경우, SIFT+k-NN 모델은 비율이 높은 옹이 종류로 편향되어 학습되는 결과를 보였지만, CNN 모델은 이미지 개수의 차이에도 편향이 심하지 않아 옹이 분류에 있어 더 좋은 성능을 보였다. 본 연구 결과를 통해 CNN 모델을 이용한 목재 옹이의 분류는 실용가능성에 있어 충분한 정확도를 보이는 것으로 판단된다. Various wood defects occur during tree growing or wood processing. Thus, to use wood practically, it is necessary to objectively assess their quality based on the usage requirement by accurately classifying their defects. However, manual visual grading and species classification may result in differences due to subjective decisions; therefore, computer-vision-based image analysis is required for the objective evaluation of wood quality and the speeding up of wood production. In this study, the SIFT+k-NN and CNN models were used to implement a model that automatically classifies knots and analyze its accuracy. Toward this end, a total of 1,172 knot images in various shapes from five domestic conifers were used for learning and validation. For the SIFT+k-NN model, SIFT technology was used to extract properties from the knot images and k-NN was used for the classification, resulting in the classification with an accuracy of up to 60.53% when k-index was 17. The CNN model comprised 8 convolution layers and 3 hidden layers, and its maximum accuracy was 88.09% after 1205 epoch, which was higher than that of the SIFT+k-NN model. Moreover, if there is a large difference in the number of images by knot types, the SIFT+k-NN tended to show a learning biased toward the knot type with a higher number of images, whereas the CNN model did not show a drastic bias regardless of the difference in the number of images. Therefore, the CNN model showed better performance in knot classification. It is determined that the wood knot classification by the CNN model will show a sufficient accuracy in its practical applicability.
Hyunbin Kim,Yeonjung Han,Yonggun Park,Sang-yun Yang,Hyunwoo Chung,Chang-deuk Eom,Hyun-mi Lee,Hwanmyeong Yeo 한국목재공학회 2017 목재공학 Vol.45 No.6
Predicting the amount and distribution of moisture content within wood allows calculating the various mechanical dynamics of the wood as well as determining the drying time. For boxed-heart wood with a large cross-section, since it is difficult to measure the moisture content of the interior, it is necessary to predict the moisture content distribution. This study predicted the moisture movement in boxed-heart red pine timber, during high temperature drying, by using the three-dimensional finite difference method for the efficient drying process. During drying for 72 h, the predicted and actual moisture content of the tested wood tended to decrease at a similar rate. In contrast, the actual moisture content at 196 and 240 h was lower than predicted because surface checking of the wood occurred from 72 h and excessive water emission was unexpectedly occurred from the checked and splitted surface.
Hyunbin Jo,Kiseop Kang,Jong-Keun Park,Changkook Ryu,Hyunsoo Ahn,Younggun Go 대한기계학회 2020 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.34 No.2
Computational fluid dynamics (CFD) has become an essential tool for optimizing the design and diagnosing the operation of a boiler. However, the validity of the results depends on the degree of numerical diffusion as well as the reliability of the submodels. This study aims to assess mesh sensitivity in the reacting two-phase flow of pulverized coal in a common tangential-firing boiler. Three mesh versions were constructed for the boiler with the number of cells ranging between 1.2 million and 5.4 million, corresponding to 0.0114 -0.0022 m 3 per cell in the burner zone. The velocity distribution was found to be highly sensitive compared to temperature, heat flux, and NO concentration. By contrast, the use of key performance parameters such as total wall heat absorption, exit NOx concentration, and carbon conversion, was not appropriate criteria for the mesh sensitivity test. These parameters were determined by integration over the entire surface or volume, which made them sensitive to the overall reaction stoichiometry instead of the mesh fineness. It suggests that the use of a coarse mesh could be acceptable in evaluating the key performance parameters influenced by major operation variables, such as air distribution and fuel properties. However, sufficient mesh fineness is necessary for studies requiring accurate prediction of detailed flow patterns such as the evaluation of burner tilting/yawing or ash deposition on the wall.