• 한국항해항만학회지
• /
• 제47권4호
• /
• pp.182-190
• /
• 2023

본 연구에서는 벌크 선박의 연료 소비를 예측하기 위해 XGBoost와 SHapley Additive exPlanation (SHAP)을 사용하는 예측 모델을 제안한다. 기존 연구에서도 선박 엔진 데이터와 기상데이터를 활용하였지만 선박 연료소모량 예측 모델에 대한 예측 결과의 신뢰성과 예측 모델 구현에 사용된 변수들에 대한 설명이 부족한 한계가 있었다. 이러한 문제를 해결하기 위해 본 연구에서는 XGBoost와 SHAP를 사용하여 예측 모델을 개발하였다. 이 연구는 연구 배경, 범위, 관련 규정 및 이전 연구들, 그리고 연구 방법론에 대한 소개를 제공하며, 또한 벌크선 데이터 정제 방법과 예측 모델 결과의 검증을 설명한다.

• 대한안전경영과학회지
• /
• 제19권4호
• /
• pp.157-167
• /
• 2017

Solar energy has been known as a successful alternative energy source, however it requires a large area to build power generation facilities compared to other energy sources such as nuclear power. Weather factors such as rainy weather or night time impact on solar power generation because of lack of insolation and sunshine. In addition, solar power generation is vulnerable to external elements such as changes in temperature and fine dust. There are four seasons in the Republic of Korea hereby variations of temperature, insolation and sunshine are broad. Currently factors that cause find dust are continuously flowing in to Korea from abroad. In order to build a solar power plant, a large area is required for a limited domestic land hereby selecting the optimal location for the plant that maximizes the efficiency of power generation is necessary. Therefore, this research analyze the optimal site for solar power generation plant by implementing analytic hierarchy process based on weather factors such as fine dust. In order to extract weather factors that impact on solar power generation, this work conducts a case study which includes a correlation analysis between weather information and power generation.

• Safety and Health at Work
• /
• 제9권1호
• /
• pp.42-52
• /
• 2018

Background: Maintenance operations on-board ships are highly demanding. Maintenance operations are intensive activities requiring high man-machine interactions in challenging and evolving conditions. The evolving conditions are weather conditions, workplace temperature, ship motion, noise and vibration, and workload and stress. For example, extreme weather condition affects seafarers' performance, increasing the chances of error, and, consequently, can cause injuries or fatalities to personnel. An effective human error probability model is required to better manage maintenance on-board ships. The developed model would assist in developing and maintaining effective risk management protocols. Thus, the objective of this study is to develop a human error probability model considering various internal and external factors affecting seafarers' performance. Methods: The human error probability model is developed using probability theory applied to Bayesian network. The model is tested using the data received through the developed questionnaire survey of >200 experienced seafarers with >5 years of experience. The model developed in this study is used to find out the reliability of human performance on particular maintenance activities. Results: The developed methodology is tested on the maintenance of marine engine's cooling water pump for engine department and anchor windlass for deck department. In the considered case studies, human error probabilities are estimated in various scenarios and the results are compared between the scenarios and the different seafarer categories. The results of the case studies for both departments are also compared. Conclusion: The developed model is effective in assessing human error probabilities. These probabilities would get dynamically updated as and when new information is available on changes in either internal (i.e., training, experience, and fatigue) or external (i.e., environmental and operational conditions such as weather conditions, workplace temperature, ship motion, noise and vibration, and workload and stress) factors.

• Journal of the Korean Data and Information Science Society
• /
• 제28권2호
• /
• pp.395-406
• /
• 2017

전력 공급 시스템의 효율적인 운영을 위해 전력수요예측은 필수적이다. 본 연구에서는 군집분석과 분류분석을 이용하여 일 단위 시간별 전력수요량 시계열 패턴의 유형을 살펴보고자 한다. 전력거래소에서 수집된 2008년 1월 1일부터 2012년 12월 31일까지의 일 단위 시간별 전력수요량 데이터를 추세성분, 계절성분, 오차 성분으로 구성된 시계열 자료로 변환하여 사용하였다. 추세성분을 제거한 시계열 자료의 패턴을 구분하기 위한 군집 분석방법은 k-평균 군집분석 (k-means), 가우시안혼합모델 혼합 모델 군집분석 (Gaussian mixture model), 함수적 군집분석 (functional clustering)을 고려하였다. 주성분분석을 통해 24시간 자료를 2개의 요인로 축소한 후 k-평균 군집분석과 가우시안 혼합 모델, 함수적 군집분석을 수행하였다. 군집분석 결과를 토대로 2008년부터 2011년까지 총 4년간 데이터를 4가지 분류분석방법인 의사결정나무, RF (random forest), Naive bayes, SVM (support vector machine)을 통해 훈련시켜 2012년 군집을 예측하였다. 분석 결과 가우시안 혼합 분포기반 군집분석과 RF를 이용한 군집예측 결과의 성능이 가장 우수하였다.

• Advances in environmental research
• /
• 제3권3호
• /
• pp.253-281
• /
• 2014

The quest for enhanced thermal comfort for dwellings encompasses the holistic utilization of improved building fabric, impact of weather variation and amongst passive cooling design consideration the provision of appropriate ventilation and shading strategy. Whilst thermal comfort is prime to dwellings considerations, limited research has been done in this area with the attention focused mostly on non-dwellings. This paper examines the current and future thermal comfort implications of four different standard construction specifications which show a progressive increase in thermal mass and airtightness and is underpinned by the newly developed CIBSE adaptive thermal comfort method for assessing the risk of overheating in naturally ventilated dwellings. Interactive investigation on the impact of building fabric variation, natural ventilation scenarios, external shading and varying occupants' characteristics to analyse dwellings thermal comfort based on non-heating season of current and future weather patterns of London and Birmingham is conducted. The overheating analysis focus on the whole building and individual zones. The findings from the thermal analysis simulation are illustrated graphically coupled with statistical analysis of data collected from the simulation. The results indicate that, judicious integrated approach of improved design options could substantially reduce the operating temperatures in dwellings and enhance thermal comfort.

• 한국산업융합학회 논문집
• /
• 제22권5호
• /
• pp.499-509
• /
• 2019

This paper discusses energy use monitoring and analysis as part of a study on a low-cost energy supply management system that links an existing database with weather information with no real-time monitor for energy demand of buildings using renewable energy, generator and energy storage systems. This study is targeted at small and medium-sized buildings and aims to monitor energy use with a small number of sensors at low cost by applying an energy management system (EMS). The present study can help overcome the limitations of high-cost EMS applied to large commercial and public buildings. We developed current, indoor temperature and human motion sensors and installed them in an office of a company in a sample building. Through these sensors, we analyzed energy use patterns and the effects of weather information and human motion on the energy use. Furthermore, we analyzed the correlations between the total KEPCO energy use of the sample building and weather by comparing these two data. The results showed that the office energy use of a company was more affected by human motions than by weather information. The comparison between the total energy use of the Building and weather information found that external temperature had an effect on the energy use.

• 대기
• /
• 제33권5호
• /
• pp.561-570
• /
• 2023

In order to improve the predictability of marine high-impacts weather such as typhoon and high waves, the marine observation network is an essential because it could be rapidly changed by strong air-sea interaction. In this regard, the National Institute of Meteorological Sciences, Korea Meteorological Administration (NIMS/KMA) has promoted the Argo float observation program since 2001 to participate in the International Argo program. In this study, current status and future direction of the NIMS/KMA Argo program are presented through the internal meeting and external expert forum. To date, a total of 264 Argo floats have been deployed into the offshore around the Korean Peninsula and the Northwestern Pacific Ocean. The real-time and delayed modes quality control (QC) system of Argo data was developed, and an official regional data assembling center (call-sign 'KM') was run. In 2002, the Argo homepage was established for the systematic management and dissemination of Argo data for domestic and international users. The future goal of the NIMS/KMA Argo program is to improve response to the marine high-impacts weather through a marine environment monitoring and observing system. The promotion strategy for this is divided into four areas: strengthening policy communication, developing observation strategies, promoting utilization research, and activating international cooperation.

• 대한원격탐사학회지
• /
• 제2권1호
• /
• pp.49-54
• /
• 1986

This study has been intended to design an optimum meteorological information system appropriate for Korea as a part of 5 year development plan. The 5 year plan was that to set up new direction in order to modernize meteorological data acquisition, processing and information distribution. The detailed research has been led to presentation of optimum meteorological information system of Korea eventually, selecting the computerization of communication as the primary object of modernization. In the study, research concerning effective equipment configuration, data communications internal as wall as external, and the related implementations has been carried out with the approach of system component consideration under system application design. As tile results of the study, integrated network of meterorological data communication was presented including earth quakes, radar, aerologic, marine weather observations and so on.

• 디지털융복합연구
• /
• 제20권3호
• /
• pp.41-52
• /
• 2022

국내 공공도서관은 1, 2차 도서관 발전 종합계획을 토대로 양적 성장을 이루었으나, 질적으로는 다소 부족한 점이 있어 이를 개선하기 위한 다양한 연구가 수행되었다. 대다수 선행연구에서는 사회·경제적 요인과 통계분석에 한정되어 수행된 한계점이 있다. 이에 본 연구에서는 시공간적 개념을 적용하여 강우와 폭염으로 인한 공공도서관 대출 수요 감소를 정량적으로 산출하고, 기상 변화로 도서 대출 수요 감소가 높은 지역과 그렇지 않은 지역을 군집화하여 공공도서관 내·외부 요인들과 결합한 후 기상변화에 따른 공공도서관 대출 수요 변화를 분석하였다. 분석 결과 공공도서관별 기상으로 인한 감소 차이가 존재하였으며, 공공도서관의 특성과 공간적 위치에 따라 일부 다르게 나타났다. 또한, 기온이 35℃ 이상인 폭염일 경우 도서 대출 수요 감소 폭이 많이 증가하였으며, 랜덤포레스트 모형으로 분석한 결과 유의미한 요인이 도출되었다. 내적 요인으로는 좌석 수, 장서 수, 면적이 도출되었으며, 외적 요인으로는 공공도서관 접근 경사로, 카페, 독서실, 10대 유동인구, 30/40대 여성 유동인구가 중요한 변수로 분석되었다. 이러한 분석 결과는 특정 시즌 기상을 고려한 공공도서관 이용 활성화 정책 수립에 이바지할 것으로 판단되며, 연구의 한계점도 제시하였다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2022년도 학술발표회
• /
• pp.334-334
• /
• 2022

Improvement of old-fashioned rain gauge systems for automatic, timely, continuous, and accurate precipitation observation is highly essential for weather/climate prediction and natural hazards early warning, since the occurrence frequency and intensity of heavy and extreme precipitation events (especially floods) are recently getting more increase and severe worldwide due to climate change. Although rain gauge accuracy of 0.1 mm is recommended by the World Meteorological Organization (WMO), the traditional rain gauges in both weighting and tipping bucket types are often unable to meet that demand due to several existing technical limitations together with higher production and maintenance costs. Therefore, we aim to introduce a newly developed and cost-effective hybrid rain gauge system at 0.1 mm accuracy that combines advantages of weighting and tipping bucket types for continuous, automatic, and accurate precipitation observation, where the errors from long-term load cells and external environmental sources (e.g., winds) can be removed via an automatic drainage system and artificial intelligence-based data quality control procedure. Our rain gauge system consists of an instrument unit for measuring precipitation, a communication unit for transmitting and receiving measured precipitation signals, and a database unit for storing, processing, and analyzing precipitation data. This newly developed rain gauge was designed according to the weather instrument criteria, where precipitation amounts filled into the tipping bucket are measured considering the receiver's diameter, the maximum measurement of precipitation, drainage time, and the conductivity marking. Moreover, it is also designed to transmit the measured precipitation data stored in the PCB through RS232, RS485, and TCP/IP, together with connecting to the data logger to enable data collection and analysis based on user needs. Preliminary results from a comparison with an existing 1.0-mm tipping bucket rain gauge indicated that our developed rain gauge has an excellent performance in continuous precipitation observation with higher measurement accuracy, more correct precipitation days observed (120 days), and a lower error of roughly 27 mm occurred during the measurement period.