• 제목/요약/키워드: The optimum support

검색결과 386건 처리시간 0.026초

대학 캠퍼스 냉·난방시스템 최적화 방안 연구 (A Study on the Optimization of Heating and Cooling System in University Campus)

  • 박소연;박효순;이상혁;김지연;홍성희
    • KIEAE Journal
    • /
    • 제10권6호
    • /
    • pp.139-144
    • /
    • 2010
  • The demands are increasing for the efficient heating and cooling system and thermal comfort environment because of changes in climate and environment, and deterioration of buildings and facilities can cause education budget to increase. So the study to apply heating and cooling system to university is urgently needed to improve an optimum energy saving system, educational environment and convenience of maintenance. For this reason, we selected a university campus in Seoul then came to understand the current situation and found some problems. We drew alternatives from comparative analysis of them. It selects representative building and carries out economic analysis to evaluate characteristics of energy consumption and economics on each type of heating and cooling system. As a result we drew the optimum system from those processes as previously stated. We studied 3 available systems, absorption chiller, EHP(Electric Heat Pump) and GHP(Gas Engine Heat Pump). According to LCC analysis suppose that the value of EHP is 1, it came out that the value of absorption chiller is 1.5 and the value of GHP is 2.2. This study, suggesting the optimum heating and cooling system, will support educational and research activities furthermore effect to maximize energy efficiency. Ultimately it is expected that it will contribute to make eco-friendly Green Campus.

Improved marine predators algorithm for feature selection and SVM optimization

  • Jia, Heming;Sun, Kangjian;Li, Yao;Cao, Ning
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제16권4호
    • /
    • pp.1128-1145
    • /
    • 2022
  • Owing to the rapid development of information science, data analysis based on machine learning has become an interdisciplinary and strategic area. Marine predators algorithm (MPA) is a novel metaheuristic algorithm inspired by the foraging strategies of marine organisms. Considering the randomness of these strategies, an improved algorithm called co-evolutionary cultural mechanism-based marine predators algorithm (CECMPA) is proposed. Through this mechanism, search agents in different spaces can share knowledge and experience to improve the performance of the native algorithm. More specifically, CECMPA has a higher probability of avoiding local optimum and can search the global optimum quickly. In this paper, it is the first to use CECMPA to perform feature subset selection and optimize hyperparameters in support vector machine (SVM) simultaneously. For performance evaluation the proposed method, it is tested on twelve datasets from the university of California Irvine (UCI) repository. Moreover, the coronavirus disease 2019 (COVID-19) can be a real-world application and is spreading in many countries. CECMPA is also applied to a COVID-19 dataset. The experimental results and statistical analysis demonstrate that CECMPA is superior to other compared methods in the literature in terms of several evaluation metrics. The proposed method has strong competitive abilities and promising prospects.

An assessment of machine learning models for slump flow and examining redundant features

  • Unlu, Ramazan
    • Computers and Concrete
    • /
    • 제25권6호
    • /
    • pp.565-574
    • /
    • 2020
  • Over the years, several machine learning approaches have been proposed and utilized to create a prediction model for the high-performance concrete (HPC) slump flow. Despite HPC is a highly complex material, predicting its pattern is a rather ambitious process. Hence, choosing and applying the correct method remain a crucial task. Like some other problems, prediction of HPC slump flow suffers from abnormal attributes which might both have an influence on prediction accuracy and increases variance. In recent years, different studies are proposed to optimize the prediction accuracy for HPC slump flow. However, more state-of-the-art regression algorithms can be implemented to create a better model. This study focuses on several methods with different mathematical backgrounds to get the best possible results. Four well-known algorithms Support Vector Regression, M5P Trees, Random Forest, and MLPReg are implemented with optimum parameters as base learners. Also, redundant features are examined to better understand both how ingredients influence on prediction models and whether possible to achieve acceptable results with a few components. Based on the findings, the MLPReg algorithm with optimum parameters gives better results than others in terms of commonly used statistical error evaluation metrics. Besides, chosen algorithms can give rather accurate results using just a few attributes of a slump flow dataset.

사장교의 설계를 위한 최적 지지조건 결정 (Determination of Optimal Support for Cable-stayed Bridge Designs)

  • 안주옥;윤영만
    • 한국방재학회 논문집
    • /
    • 제3권4호
    • /
    • pp.103-109
    • /
    • 2003
  • 사장교 설계에서 최적의 지지조건을 결정하기 위해 사장교 전체구조계의 교축방향에 대해서 주형의 지지조건에 따른 활하중, 풍하중과 지진하중에 의한 주형, 주탑단면력 및 케이블력의 변화를 3차원 수치해석을 통해 검토하였다. 교축방향의 적합한 경계조건 도입은 주형의 지지점과 주탑의 기초부의 반력뿐만 아니라 주형의 휨모멘트에서 많은 변화를 유도할 수 있다. 본 수치해석의 예에서, 종방향 탄성계수값은 활하중이 작용 할 경우는 약 100tonf/m/bearing, 지진하중이 작용 할 경우는 약 100tonf/m/bearing 에서 최적의 지지조건임을 알 수 있다. 즉 본 해석대상 교량에서 종방향 탄성계수값이 $100{\sim}1000tonf/m/bearing$ 일 경우의 지지조건에서 최적의 지지조건을 얻었으며, 이 조건에서 주탑의 단면력을 합리적으로 결정할 수 있음을 알 수 있다.

운항 안전 및 효율성 향상을 위한 최적 항로 평가 시스템 기본 연구 (Basic Research of Optimum Routing Assessment System for Safe and Efficient Voyage)

  • 이진호;최경순;박건일;김문성;방창선
    • 대한조선학회논문집
    • /
    • 제42권1호
    • /
    • pp.57-63
    • /
    • 2005
  • This paper introduces basic research of optimum routing assessment system as voyage support purpose which can obtain safe and efficient route. In view point of safety, the prediction of ship motion should be evaluated in the condition of rough weather This part includes general seakeeping estimation based on 3 dimensional panel method and parametric roil prediction. For increasing voyage efficiency, ETA(Estimated Time of Arrival) and fuel consumption should be calculated considering speed reduction and power increase due to wave effects based on added resistance calculation and ship performance characteristics. Basically, the weather forecast is assumed to be prepared previously to operate this system. The idea of these factors in this system will be helpful to escape from dangerous voyage situation by wave conditions and to make optimum route planning based on ETA and fuel consumption.

기체분리용 세라믹 복합분리막의 개발: I. 극미세 입자 실리카 졸의 코팅 특성 (Development of Ceramic Composite Membranes for Gas Separation: I. Coating Characteristics of Nanoparticulate SiO2 Sols)

  • 현상훈;;윤성필
    • 한국세라믹학회지
    • /
    • 제29권6호
    • /
    • pp.496-504
    • /
    • 1992
  • Alumina tubes suitable for the support of gas separation membranes have been prepared by the slipcasting technique. These supports have the average pore size of 0.1 ${\mu}{\textrm}{m}$ within the narrow distribution. The sol-gel dipcoating process of nanoparticulate sols is very sensitive to microstructure of the support, and the coating on the inside surface of the tube is found to be more successful than on the outside surface. Nanoparticulate silica sols (0.82 mol/ι) have been synthesized by an interfacial hydrolysis reaction between TEOS and high alkaline water. When coating an alumina tube with these sols, the minimum limits of the particle size and the aging time required for forming the coated gel layer at the given pH are provided. It is optimum to coat the support with less concentrated sols stabilized through aging for the appropriate time (more than 22 days) at the lower pH (pH 2.0) for producing a reproducible crack free thin film coating in composite membranes.

  • PDF

궤도 유지관리 의사결정 지원 시스템 개발 (Decision-making support system for track maintenance)

  • 이지하;임남형;양신추
    • 한국철도학회:학술대회논문집
    • /
    • 한국철도학회 2003년도 추계학술대회 논문집(II)
    • /
    • pp.454-459
    • /
    • 2003
  • The process of determining whether, when, where and how to intervene, of deciding on optimum allocation of resources and minimizing the cost is a very complex problem: different track sections tend to behave differently under the effects of loading; decision-making processes for maintenance work are closely interrelated technically and economically; decision-making for maintenance plans is based on a large quantity of technical and economic information, extensive knowledge and above all experience. For that reason, It is considered very important to develope objective and computer-aided decision-making support system for track maintenance plan. On this paper, we reviewed ECOTRACK system and present the plan of develope decision-making support system for track maintenance appropriate to local condition.

  • PDF

하수슬러지를 이용한 생물담체 개발 - 기초물성 평가 및 황토최적혼합비 결정 - (Development of Biomedia using Waste Sewage Sludge - Evaluation of Basic Properties and Determination of Optimum Mixing Ratio of Sludge and Loess -)

  • 정수일;손인식;정승현;정병곤
    • 한국물환경학회지
    • /
    • 제26권2호
    • /
    • pp.225-230
    • /
    • 2010
  • Dumping of waste sludge to ocean will be prohibited in Jananuary, 2012. Thus, various methods of sludge recycling are intensively studied. To present new way of sewage sludge recycling method, feasibility of making porous biological support media was investigated. Porous biological support media was made of sludge cake from sewage treatment plant and loess. They were mixed in varying ratio and burnt in high temperature to ensure sufficient mechanical strength. It was evaluated that about 67% of sewage sludge were ignitible. The ignitible portion play an important role in making pore in biomedia during ignition process. It was evaluated that optimum mixing ratio of loess to sludge cake was 25% in respect of compressive strength. In results of observation using scanning electron microscope (SEM), inner structure of biomedia become simple when the contents of loess are increased.

변형된 Support Vector Machine을 이용한 유비쿼터스 데이터 마이닝 (Ubiquitous Data Mining Using Hybrid Support Vector Machine)

  • 전성해
    • 한국지능시스템학회논문지
    • /
    • 제15권3호
    • /
    • pp.312-317
    • /
    • 2005
  • 유비쿼터스 컴퓨팅 환경은 정치, 경제, 사회, 문화, 교육 등 대부분의 분야에 많은 영향을 주고 있다. 인터넷에 비해 훨씬 거대한 유비쿼터스 네트워크 환경이 효과적으로 운영되기 위해서는 네트워크에 접속한 다양한 컴퓨터들이 스스로 지능을 가지고 주어진 상황에서 최적의 의사결정을 할 수 있어야 한다. 현재 많은 분야에서 데이터 마이닝은 지능형 시스템 구축을 위한 효과적인 분석도구로 사용되고 있다. 지능화된 유비쿼터스 컴퓨팅 환경의 구현을 위한 유비쿼터스 데이터 마이닝을 위하여 본 논문에서는 변형된 Support Vector Machine 기법을 제안하였다. 유비쿼터스 컴퓨팅 환경에서 상당 부분의 데이터가 센서를 통하여 수집된다. 센서 네트워크를 통하여 수집된 데이터는 상당부분 잡음을 포함한 데이터이다. 제안 기법은 특히 센서 네트워크를 통한 스트림 데이터의 잡음을 제거하는 데 목적을 두고 있다. 본 논문의 실험에서는 유비쿼터스 센서 네트워크를 나타내는 다양한 분포로부터 시뮬레이션 데이터를 생성하여 제안 방법의 성능 평가를 수행하였다.

영구지보재로서 고성능 숏크리트의 적정 배합비 도출 (Mix Proportions of High Performance Shotcrete for Permanent Support)

  • 원종필;김황희;김정훈;박경훈;장창일;이상우
    • 한국콘크리트학회:학술대회논문집
    • /
    • 한국콘크리트학회 2006년도 춘계 학술발표회 논문집(II)
    • /
    • pp.41-44
    • /
    • 2006
  • Recently, single shell lining method of construction is studied by economical method of construction to make use of high-performance shotcrete of permanent shotcrete lining concept in the UStA, Europe, Japan etc. High-performance shotcrete use is essential as permanent support that single shell lining method of construction has two functions of lining and support to shotcrete. In this research, optimum accelerator amount was decided after setting time test using alkai-free and cement mineral accelerator. Also replacement ratio of silica fume and fly-ash was determined.

  • PDF