• 산업공학
• /
• 제8권3호
• /
• pp.61-73
• /
• 1995

As the level of maunfacturing system automation increases, the issues of modeling and simulation of AMS(Automated Manufacturing System) are becoming more important. Proposed in this paper is the JR-Net(Job Resource relation-Net) modeling framework which naturally mimics the process of designing an AMS by FA(Factory Automation) engineers. Its main purpose is to provide a modeling tool which facilitate modeling work of AMS for FA engineers unfamiliar with simulation modeling. The proposed modeling scheme is based on the extensive observation that typical AMSs are built from the set of 'standard' components(or catalog items). As an application of the proposed model, two real examples of FMS('G7'FMS model plant, RPI FMS) are modeled by JR-Net, and in case of FMS model plant, a simulation program development procedure using JR-Net modeling results is explained. Finally, simulation result of FMS model plant is analyzed.

• 수산해양기술연구
• /
• 제24권1호
• /
• pp.12-16
• /
• 1988

정치망 어장의 어도 연구와 관련된 정치망 어장부근의 해저지형과 조류의 관측을 행하였다. 거제도 동부의 2 해역, 도장포와 능포어장과 남해도 동부의 2 해역, 양화금과 마안도 부근에서 수심관측과 25시간 정점 조류 관측 및 레이더 코오너리플렉터에 의한 표층의 표류실험을 병행하였다. 해저지형의 관측결과 거제도 동부 해역에서는 만의 남쪽에 경사가 심한 골이 형성되어 있고, 그 부근에 어구가 부설되어 있었다. 조류의 관측결과 거제도 동부해역에서는 좌선회의 경향을 보였고 남해도 양화금에서는 우선회의 경향이 뚜렷하였으며 마안도 부근에서는 일정하지 않았다. 항류성분과 조류의 회전 및 지형 등이 조화되어 외해에서 만에 접근한 어군이 해저 골 부근으로 접근하면서 점차 농밀군을 이루게 되어 정치망 어구에 접근하는 것으로 생각된다.

• 수산해양기술연구
• /
• 제32권2호
• /
• pp.125-131
• /
• 1996

In order to investigate the relation between the environmental properties and the catch fluctuation of set net fishing grounds located in the coastal waters of Yosu, oceanographic observations on the fishing grounds were carried out by the training ship ofYosu Fisheries University from January, 1990 to September, 1992, and the data obtained were compared with the catch data from the joint market ofYosu fisheries cooperative society from 1984 to 1993. The resuItes obtained are summerized as follows : 1. The ranges of water temperature and salinity in the fishing ground was 7.0 to $27^{\circ}C.$and 26.6 to 33.2${\textperthousand}$, and water temperature increased from March to August and decreased from September to February of following year. 2. The salinity in the fishing grounds was relatively high without significant changes from November to June of the following year. From July, however, the salinity decreased to continue a low value till September and then increased. The salinity in the fishing ground was dominated mainly by the precipitation and its variation was large at the north entrance of set net fishing ground, influenced greatly by the land waters from the river of Somjin, but small in the offshore of the fishing grounds. 3. The fishes caught by the set nets were arranged in order of catch as follows; Spanish mackerel> Horse mackerel > Sardine > Anchovy > Hair tail. The catches of Anchovy and Sardine were high in April to May and those of Hair tail in June to July, but Spanish mackerel and Horse mackerel were caught for whole period of fishing. Spanish mackerel was caught most in September and least in April and their means were largest in August and smallest in June. 4. The ranges of optimum water temperature for fishing by the set nets was 13.5 to $25^{\circ}C.$, and in the ranges the catches increased with increasing temperature. The ranges of optimum salinity for fishing varied between 25.0 and 32.0${\textperthousand}$.

• 수산해양기술연구
• /
• 제43권4호
• /
• pp.261-273
• /
• 2007

To analyze quantitative fluctuation in abundance and species composition in coastal waters of Dolsan, Yeosu, the fished were collected by gape net from March to November, 2000. The fish species caught by set net collected fishes were identified 63 species, 56 families, 42 orders, and the number of appearance and biomass was 2,230,297 individuals and 16,076.8kg. The most dominant orders were Perciformes, Clupeiformes and Tetraodontiformes which accounted for 71.4% of the total. The dominant species in number were Engraulis japonicus, Sardinops melanostictus, Trichiurus lepturus which accounted for 99.2% (2,211,642 individuals) of the total fishes collected. The dominant species in biomass were Engraulis japonicus which accounted for 79.7% (12,807g) of the total fishes collected. Temporal occurence of the dominant species such as the Engraulis japonicus, Sardinops melanostictus, Trichiurus japonicus, Ilisha elongata, Leiognathus nuchalis was closely correlated with water temperature, which is expressed as following regression equation, $y=0.0864x-0.2311(r^2＝0.3516)$. The species collected during the sampling yearly period were Engraulis japonicus, and migratory fish were Ilisha elongata, Trichiurus japonicus, Scomberomorus nipphnius, Scomber japonicus, Konosirus punctatus, Sphyraena pinguis, Pseudosciaena polyactis.

• 한국수산과학회지
• /
• 제32권1호
• /
• pp.105-111
• /
• 1999

제주도 서부 연안역인 한림 정치망어장의 해황과 어획량 변동과의 관계를 파악하기 위해 1995년$\~$1996년에 실시한 정선 및 정점조사의 수온 및 염분자료, 시계열분석, 단기변동, 해수유동상황과 1994년$\~$1996년의 한림 정치망의 어획량 변동에 관해 검토가 분석한 결과를 요약하면 다음과 같다. 1) 한림 정치망에 가장 많이 잡히는 어종은 전갱이 ($69.2\%$)이고 그 다음으로 고등어 ($18.4\%$), 갈치 ($5.6\%$), 오징어($2.7\%$), 독가시치 ($1.4\%$)의 순이며. 조업기간은 5월에서 12월까지로 6월과 10월에 어획량의 피크가 있고 이중 10월에 년중 최고 어획량이 나타난다. 2) 한림 정치망에서는 밀물인 북류성분과 썰물인 남류성분이 명료히 나타나 해수의 연직혼합이 원활하고 남류의 지속기간(3시간 이상)이 길어 외측의 중$\cdot$저층수가 강하게 영향을 미쳐 어장까지 공급되어, 일별 평균수온이 낮고 염분 상승내지는 고염분수가 출현할 때 좋은 어획량을 보이는 경향이 있다. 또 대조기인 망이나 삭보다 소조기인 상$\cdot$하현에 어획량이 많g으며, 남$\~$남동풍이 3$\~$6.5m/sec정도 볼 때 호어가 나타날 가능성이 높다.

• 한국어류학회지
• /
• 제20권1호
• /
• pp.28-35
• /
• 2008

제주도 귀덕 정치망 어장의 유영생물 조성과 변동양상을 알아보기 위하여 2004년 4월부터 12월까지 어업이 행해지는 동안 매일 조사한 결과를 요약하면 다음과 같다. 1. 조사기간 동안 총어종수 21종과 총어획량 45,473.2 kg의 유영생물이 어획되었으며, 이중 어류가 17종 34,285.4 kg, 두족류가 4종 11,187.8 kg이었다. 2. 어획된 유영생물 중에는 전갱이와 독가시치가 가장 많은 비율로 전체 어획량의 44.3%를 차지하였으며, 그 외 흰오징어, 잿방어, 방어, 화살오징어, 부시리 등이 54.4%이었다. 3. 주 우점어종인 전갱이와 독가시치는 어기동안 대부분 어획되었으나, 이중 전갱이는 수온이 높은 여름철과 가을철에 많이 어획된 반면, 독가시치는 여름철에 많이 어획되었다. 4. 귀덕 정치망의 어획량은 봄철에서 여름철로 갈수록 증가하는 경향이었으나 일 변동 폭은 크게 나타났으며, 특히 여름철 전후의 많은 어획량은 우점종인 전갱이와 독가시치, 잿방어, 화살오징어, 흰오징어 등의 어장가입과 관련 있었다. 5. 또한, 어기가 시작되는 봄철에는 방어와 흰오징어가 우점하였다.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 1992년도 춘계공동학술대회 발표논문 및 초록집; 울산대학교, 울산; 01월 02일 May 1992
• /
• pp.436-443
• /
• 1992

Presented in the paper is a systematic approach to constructing a Petri net model of FAS (flexible assembly system). Petri net is widely used in modeling automated manufacturing systems. But, it found to be very difficult for an FA engineer to build a correct model of an FAS with Petri net symbols (ie, place, transition, and token) from the beginning. An automated manufacturing system in general is built from a set of "standard" hardware components. An FAS in particular is usually composed of assembly robots, work tables, conveyor lines, buffer storages, part feeders, etc. In the proposed modeling scheme, each type of standard resources is represented as a standard "module" which is a sub Petri net. Then, the model of a FAS can be conveniently constructed using the predefined modules the same way the FAS itself is built from the standard components. The network representation of a FAS is termed a JR-net (job resource relation net) which is easy to construct. This JR net is then mechanically converted to a formal Petri net (to simulate the behavior of the FAS). The proposed modeling scheme may easily be extended to the modeling of other types of automated manufacturing systems such as FMS and AS/RS.ch as FMS and AS/RS.

• IEIE Transactions on Smart Processing and Computing
• /
• 제4권1호
• /
• pp.35-43
• /
• 2015

Over the past couple of years, tremendous progress has been made in applying deep learning (DL) techniques to computer vision. Especially, deep convolutional neural networks (DCNNs) have achieved state-of-the-art performance on standard recognition datasets and tasks such as ImageNet Large-Scale Visual Recognition Challenge (ILSVRC). Among them, GoogLeNet network which is a radically redesigned DCNN based on the Hebbian principle and scale invariance set the new state of the art for classification and detection in the ILSVRC 2014. Since there exist various deep learning techniques, this review paper is focusing on techniques directly related to DCNNs, especially those needed to understand the architecture and techniques employed in GoogLeNet network.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.551-552
• /
• 2021

본 논문에서는 변환 학습에 기반을 둔 다중 클래스 영상 장면 분류 방법을 제시한다. ImageNet 대형 이미지 데이터 세트에서 사전 훈련된 네트워크 모델에 의존하여 다중 클래스의 자연 장면 이미지를 분류한다. 실험에서는 최적화된 ResNet 모델을 Kaggle의 Intel Image Classification 데이터 셋에 분류하여 우수한 결과를 얻었다.

• 수산해양기술연구
• /
• 제42권3호
• /
• pp.127-133
• /
• 2006

An estimation of the headline height of a bottom trammel net set across under uniform current was achieved numerically from a differential equations describing the forces of the net and compared with the measured value in a flume tank experiment. The analysis on the shape of the bottom trammel net with the headline free was based on the equilibrium equation of the bottom gill net which was modified and slack of the trammel net was varied with net depth as shown in the tank experiment. The differential equations were solved by a forth-order Runge-Kutta method. The estimated headline heights with varied slack was found to be closer than that with constant slack when compared with the actual values.