• Title/Summary/Keyword: 발전성능시험

Search Result 366, Processing Time 0.028 seconds

A study on the rock mass classification in boreholes for a tunnel design using machine learning algorithms (머신러닝 기법을 활용한 터널 설계 시 시추공 내 암반분류에 관한 연구)

  • Lee, Je-Kyum;Choi, Won-Hyuk;Kim, Yangkyun;Lee, Sean Seungwon
    • Journal of Korean Tunnelling and Underground Space Association
    • /
    • v.23 no.6
    • /
    • pp.469-484
    • /
    • 2021
  • Rock mass classification results have a great influence on construction schedule and budget as well as tunnel stability in tunnel design. A total of 3,526 tunnels have been constructed in Korea and the associated techniques in tunnel design and construction have been continuously developed, however, not many studies have been performed on how to assess rock mass quality and grade more accurately. Thus, numerous cases show big differences in the results according to inspectors' experience and judgement. Hence, this study aims to suggest a more reliable rock mass classification (RMR) model using machine learning algorithms, which is surging in availability, through the analyses based on various rock and rock mass information collected from boring investigations. For this, 11 learning parameters (depth, rock type, RQD, electrical resistivity, UCS, Vp, Vs, Young's modulus, unit weight, Poisson's ratio, RMR) from 13 local tunnel cases were selected, 337 learning data sets as well as 60 test data sets were prepared, and 6 machine learning algorithms (DT, SVM, ANN, PCA & ANN, RF, XGBoost) were tested for various hyperparameters for each algorithm. The results show that the mean absolute errors in RMR value from five algorithms except Decision Tree were less than 8 and a Support Vector Machine model is the best model. The applicability of the model, established through this study, was confirmed and this prediction model can be applied for more reliable rock mass classification when additional various data is continuously cumulated.

A Distributed Web-DSS Approach for Coordinating Interdepartmental Decisions - Emphasis on Production and Marketing Decision (부서간 의사결정 조정을 위한 분산 웹 의사결정지원시스템에 관한 연구)

  • 이건창;조형래;김진성
    • Proceedings of the Korea Inteligent Information System Society Conference
    • /
    • 1999.10a
    • /
    • pp.291-300
    • /
    • 1999
  • 인터넷을 기반으로 한 정보통신의 급속한 발전이라는 기업환경의 변화에 적응하기 위해서 기업은 점차 모든 경영시스템을 인터넷을 기반으로 하도록 변화시키고 있을 뿐만 아니라, 기업 조직 또한 전세계를 기반으로한 글로벌 기업 형태로 변화하고 있다. 이러한 급속한 경영환경의 변화로 인해서 기업 내에서는 종전과는 다른 형태의 부서간 상호의사결정조정 과정이 필요하게 되었다. 일반 기업들을 대상으로 한 상호의사결정의 지원과정에 대해서는 기존에 많은 연구들이 있었으나 글로벌기업과 같은 네트워크 형태의 새로운 형태의 기업에 있어서의 상호의사결정과정을 지원할 수 있는 의사결정지원시스템에 대해서는 단순한 그룹의사결정지원시스템 또는 분산의사결정지원시스템과 같은 연구들이 주를 이루고 있다. 따라서 본 연구에서는 인터넷 특히, 웹을 기반으로 한 기업의 글로벌경영 및 분산 경영에서 비롯되는 부서간 상호의사결정이라는 문제를 효율적으로 지원할 수 있는 기업의 글로벌경영 및 분산 경영에서 비롯되는 부서간 상호의사결정이라는 문제를 효율적으로 지원할 수 있는 메커니즘을 제시하고 이에 기반한 프로토타입 형태의 시스템을 구현하여 성능을 검증하고자 한다. 특히, 기업 내에서 가장 대표적으로 상호의사결정지원이 필요한 생산과 마케팅 부서를 대상으로 상호의사결정지원 메커니즘을 개발하고 실험을 진행하였다. 그 결과 글로벌 기업내의 생산과 마케팅 부서간 상호의사결정을 효율적으로 지원 할 수 있는 상호조정 메카니즘인 개선된 PROMISE(PROduction and Marketing Interface Support Environment)를 기반으로 한 웹 분산의사결정지원시스템 (Web-DSS : Web-Decision Support Systems)을 제안하는 바이다.자대상 벤처기업의 선정을 위한 전문가시스템을 구축중이다.의 밀도를 비재무적 지표변수로 산정하여 로지스틱회귀 분석과 인공신경망 기법으로 검증하였다. 로지스틱회귀분석 결과에서는 재무적 지표변수 모형의 전체적 예측적중률이 87.50%인 반면에 재무/비재무적 지표모형은 90.18%로서 비재무적 지표변수 사용에 대한 개선의 효과가 나타났다. 표본기업들을 훈련과 시험용으로 구분하여 분석한 결과는 전체적으로 재무/비재무적 지표를 고려한 인공신경망기법의 예측적중률이 높은 것으로 나타났다. 즉, 로지스틱회귀 분석의 재무적 지표모형은 훈련, 시험용이 84.45%, 85.10%인 반면, 재무/비재무적 지표모형은 84.45%, 85.08%로서 거의 동일한 예측적중률을 가졌으나 인공신경망기법 분석에서는 재무적 지표모형이 92.23%, 85.10%인 반면, 재무/비재무적 지표모형에서는 91.12%, 88.06%로서 향상된 예측적중률을 나타내었다.ting LMS according to increasing the step-size parameter $\mu$ in the experimentally computed. learning curve. Also we find that convergence speed of proposed algorithm is increased by (B+1) time proportional to B which B is the number of recycled data buffer without complexity of computation. Adaptive transversal filter with proposed data recycling buffer

  • PDF

Preparation of flexible energy storage device based on reduced graphene oxide (rGO)/conductive polymer composite (환원된 그래핀 옥사이드/전도성 고분자 복합체를 이용한 플렉시블 에너지 저장 매체의 개발)

  • Jeong, Hyeon Taek;Cho, Jae Bong;Kim, Jang Hun;Kim, Yong Ryeol
    • Journal of the Korean Applied Science and Technology
    • /
    • v.34 no.2
    • /
    • pp.280-288
    • /
    • 2017
  • Nanocarbon base materials such as, graphene and graphene hybrid with high electrochemical performances have great deal of attention to investigate flexible, stretchable display and wearable electronics in order to develop portable and high efficient energy storage devices. Battery, fuel cell and supercapacitor are able to achieve those properties for flexible, stretchable and wearable electronics, especially the supercapacitor is a promise energy storage device due to their remarkable properties including high power and energy density, environment friendly, fast charge-discharge and high stability. In this study, we have fabricated flexible supercapacitor composed of graphene/conductive polymer composite which could improve its electrochemical performance. As a result, specific capacitance value of the flexible supercapacitor (unbent) was $198.5F\;g^{-1}$ which decreased to $128.3F\;g^{-1}$ (65% retention) after $500^{th}$ bending cycle.

Visualization of Geo-spatial Data and Public Data Using Mobile Operating Environment in the eGovernment Standard Framework (전자정부 표준 프레임워크 모바일 실행환경 기반 공공데이터와 공간데이터 시각화)

  • Kim, Kwangseob;Lee, Kiwon
    • Spatial Information Research
    • /
    • v.23 no.1
    • /
    • pp.9-17
    • /
    • 2015
  • Recently new web trends and mobile technologies are expanding and developing so fast. To improve the implementation efficiency of information systems, eGovernment standard framework has been developed and distributed. Recently, eGovernment standard framework for mobile environment was further developed. In addition, many types of public data produced by public organizations supported by government are being opened through public data portal according to Government 3.0 policy. Demands regarding web standards and common framework usages for mobile application development in most business fields dealing with any types of contents are increasing. However, to link those things to geo-spatial data or integrate those with them are an early stage in the geo-spatial application field, compared to other application fields. Based on these backgrounds, a mobile web application system was designed and implemented to present visualization functionalities of public data and geo-spatial data using HTML5 components under mobile operation environment in eGovernment standard framework in this study. It is expected that this system can be applied to develop many mobile application business models, by the further works such as application of core developing environment in eGovernment standard framework, additional functionalities, and high performance to satisfy with user requirements for a certain target application.

Development of Standard Specification of Korea Radio based Train Control System(KRTCS-2) for Conventional & High Speed Railway (일반·고속철도용 무선기반 열차제어시스템(KRTCS-2) 표준사양 개발)

  • Kim, Chan-ho;Park, Jong-won;Lee, Kang-gyoo;Sung, Dong-il;Yun, Hak-sun
    • Journal of the Korean Society for Railway
    • /
    • v.19 no.6
    • /
    • pp.736-743
    • /
    • 2016
  • In accordance with the trend of higher speed and automation, the Train Control System is building on the technology of control methods using radio in the technology of exchanging information by wire, toward a wireless communication method that will be applied using LTE-R radio communication technology with $4^{th}$ generation LTE mobile communication a $2^{nd}$ generation GSM-R. Therefore, a standard specification suitable for the Korea Radio based Train Control System-2(below KRTCS-2) for the 350km/h class using wireless communication is created; a prototype based on the standard specification is installed on a high-speed train and is installed on a test section(Ik san-Jeong eup) on the Honam high speed line to ensure the reliability and safety of the standard specifications, which are verified through various performance tests. In the future, the standard specification that has been established as a national railway standard, and the standard specifications will be commercialized by applying the train control system to conventional and High speed railway lines.

200kW Turbine Development for Organic Rankine Cycle System (200kW급 ORC용 터빈 개발)

  • Lim, Hyung-Soo;Choi, Bum-Seog;Park, Moo-Ryong;Park, Jun-Young;Yoo, Il-Su;Seo, Jeong-Min;Hwang, Soon-Chan;Yoon, Eui-Soo;Han, Sang-Jo
    • Transactions of the KSME C: Technology and Education
    • /
    • v.1 no.1
    • /
    • pp.107-113
    • /
    • 2013
  • This paper presents the process of turbine development for Organic Rankine Cycle(ORC) system. Development of turbine for ORC system is hot issue in the electric generation market due to the characteristic of organic refrigerant which the evaporate temperature is lower than general refrigerant. Recently, the industry have an interest about ORC turbine development in Korea, and they presented numerous research results. In developing the turbine, several processes can be considered. However, there was few document about ORC turbine development because of the trade secret. This paper can be used as a reference in developing ORC turbine.

Study on the Drying Characteristics of Poultry Manure for Its Dryer Development (계분건조기 개발을 위한 계분의 건조특성 연구)

  • 장동일
    • Korean Journal of Poultry Science
    • /
    • v.20 no.3
    • /
    • pp.141-149
    • /
    • 1993
  • In order to develop a poultry manure dryer, a pilot dryer was designed and drying experiments were conducted to investigate the drying characteristics of poultry manure. According to the results, the pilot dryer could be operated without any air pollution problems. When poultry manure was dried from 79.2%(w.b. basis) moisture content, the final moisture content ranged from 38.7% to 57.9% depending upon the drying conditions. The drying results showed that drying rate was 189.8~198.0 kg/h and moisture evaporation rate was 124.0~125.4kg-$H_2$O/L. For this drying, electricity requirement was 9.5~19.3 Wh/kg and fuel consumption rate was 6.9~9.3 kg-$H_2$O/L with 50.2~65.1% thermal efficiency.

  • PDF

A Study on Deep Learning based Aerial Vehicle Classification for Armament Selection (무장 선택을 위한 딥러닝 기반의 비행체 식별 기법 연구)

  • Eunyoung, Cha;Jeongchang, Kim
    • Journal of Broadcast Engineering
    • /
    • v.27 no.6
    • /
    • pp.936-939
    • /
    • 2022
  • As air combat system technologies developed in recent years, the development of air defense systems is required. In the operating concept of the anti-aircraft defense system, selecting an appropriate armament for the target is one of the system's capabilities in efficiently responding to threats using limited anti-aircraft power. Much of the flying threat identification relies on the operator's visual identification. However, there are many limitations in visually discriminating a flying object maneuvering high speed from a distance. In addition, as the demand for unmanned and intelligent weapon systems on the modern battlefield increases, it is essential to develop a technology that automatically identifies and classifies the aircraft instead of the operator's visual identification. Although some examples of weapon system identification with deep learning-based models by collecting video data for tanks and warships have been presented, aerial vehicle identification is still lacking. Therefore, in this paper, we present a model for classifying fighters, helicopters, and drones using a convolutional neural network model and analyze the performance of the presented model.

The Verification of Computer Simulation of Nitinol Wire Stent Using Finite Element Analysis (유한요소법을 이용한 나이티놀 와이어 스텐트의 전산모사 실험 데이터 검증)

  • Kim, Jin-Young;Jung, Won-Gyun;Jeon, Dong-Min;Shin, Il-Gyun;Kim, Han-Ki;Shin, Dong-Oh;Kim, Sang-Ho;Suh, Tae-Suk
    • Progress in Medical Physics
    • /
    • v.20 no.3
    • /
    • pp.139-144
    • /
    • 2009
  • Recently, the mathematical analysis of stent simulation has been improved, with the help of development of various tool which measure mechanical property and location of stent in artery. The most crucial part of the stent modeling is how to design ideal stent and to evaluate the interaction between stent and artery. While there has been great deal of researches on the evaluation of the expansion, stress distribution, deformation of the stent in terms of the various parameters, few verification through computer simulation has been performed about deformation and stress distribution of the stent. In this study, we have produced the corresponding results between experimental test using Universal Testing Machine and computer simulation for the ideal model of stent. Also, we have analyzed and compared stress distribution of stent in the cases of that with membrane and that without membrane. The results of this study would provide minimum change of plan and good quality for ideal stent replacing damaged artery through the analysis using computer simulation in the early stage of stent design.

  • PDF

The Necessity of Structural Performance Informations of Sandwich Panels for The Stability of Industry Building using Sandwich Panel as Roof Assemblies. (지붕하중 증가에 따른 공장건물 안정성확보를 위한 지붕외장재의 구조성능정보의 필요성)

  • Kang, Kyung-Soo
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.18 no.11
    • /
    • pp.725-730
    • /
    • 2017
  • The strength ratio of the main structures of buildings gradually increasing, due to the advances made in analysis and cost saving techniques. In this study, to examine the stability of industry buildings using sandwich panels as roof assemblies, we examine the changes in the moment strength ratio of the main structures caused by increasing the roof load. This study adopts the PEB structure and three H-steel structure as the structural analysis models. In the case where the additional load exceeds about 11% of the roof design load, the strength ratio exceeds 1 for the main structure. In the case where the additional load exceeds about 36%(of the roof design load), the working moment exceeds the plastic moments, which leads to major damage to the structure. This study compares 1) the maximum load according to the purlin spaces, 2) the maximum load by KS, and 3) the maximum load calculated from the test results of the manufacturer.The maximum bearing load of the panels determined by all three methods exceeds the structure failure threshold load of the main structure. This study provides evidence that an unexpected increase in the roof load might cause the whole structure to collapse, due to the failure of the main structural members, before the failure of the roof assemblies. Therefore, information on the structural performance of the sandwich panels is required for the structural design, and the sandwich panels should be considered to be an integral part of the overall structural design.