• 한국시스템다이내믹스학회:학술대회논문집
• /
• 한국시스템다이내믹스학회 1999년도 창립학술대회발표논문집
• /
• pp.105-132
• /
• 1999

If a system such as a port has a large boundary and complexity, and the system's substance is considered as a black box, forecast accuracy will be very low. Furthermore various components in a port exert significant influence on each other. To copy with these problem the form of structure models were introduced by using SD method. The Competitive Ports Model had several sub-systems consisting of each Unit Port models, and each Unit Port model was made by quantitative, qualitative factors and their feedback loops. The fact that all components of one port have influence on the components of the other ports should be taken into account to construct Competitive Port Models. However, with the current approach that is impossible, and in this paper, therefore, models were simplified by HFP adapted to integrate level variables of unit port models. Although many studies on modelling of port competitive situation have been conducted, both theoretical frame and methodology are still very weak. In this study, a new algorithm called ESD(Extensional System Dynamics) for the evaluation of port competition was presented, and applied to simulate port systems in northeast Asia.

• Structural Engineering and Mechanics
• /
• 제31권1호
• /
• pp.57-74
• /
• 2009

Power signals resulting from spindle and feed motor, present a rich content of physical information, the appropriate analysis of which can lead to the clear identification of the nature of the tool wear. The partial least-squares regression (PLSR) method has been established as the tool wear analysis method for this purpose. Firstly, the results of the application of widely used techniques are given and their limitations of prior methods are delineated. Secondly, the application of PLSR is proposed. The singular value theory is used to noise reduction. According to grey relational degree analysis, sample variable is filtered as part sample variable and all sample variables as independent variables for modelling, and the tool wear is taken as dependent variable, thus PLSR model is built up through adapting to several experimental data of tool wear in different milling process. Finally, the prediction value of tool wear is compare with actual value, in order to test whether the model of the tool wear can adopt to new measuring data on the independent variable. In the new different cutting process, milling tool wear was predicted by the methods of PLSR and MLR (Multivariate Linear Regression) as well as BPNN (BP Neural Network) at the same time. Experimental results show that the methods can meet the needs of the engineering and PLSR is more suitable for monitoring tool wear.

• 대한조선학회논문집
• /
• 제53권1호
• /
• pp.29-36
• /
• 2016

In shipbuilding and offshore plant construction, pipe-stools of various types are installed. Moreover, these are many quantities but they must be installed in a successive manner. Due to these characteristics the pipe-stool installation processes easily tends to cause the schedule delays in the overall production processes. In order to reduce delay, the goal of this study is to predicts production’s lead time before manufacturing. Through this predictions it’s expected to reduce total production’s lead time by improving it's process. First of all, we made MLR(Multiple Linear Regression) and PLSR(Partial Least Square Regression) model to predict pipe-spool's lead time and then compared predictability of MLR and PLSR model. If a explanatory variable is added, it will be possible to predict results precisely.

• Wind and Structures
• /
• 제34권4호
• /
• pp.321-334
• /
• 2022

Irregularity in plan shape is very common for any type of building as it enhances better air ventilation for the inhabitants. Systematic opening at the middle of the facades makes the appearance of the building plan as a butterfly one. The primary focus of this study is to forecast the force, moment and torsional coefficient of a butterfly plan shaped tall building. Initially, Computational Fluid Dynamics (CFD) study is done on the building model based on Reynolds averaged Navier Stokes (RANS) k-epsilon turbulence model. Fifty random cases of irregularity and angle of attack (AOA) are selected, and the results from these cases are utilised for developing the surrogate models. Parametric equations are predicted for all these aerodynamic coefficients, and the training of these outcomes are also done for developing Artificial Neural Networks (ANN). After achieving the target acceptance criteria, the observed results are compared with the primary CFD data. Both parametric equations and ANN matched very well with the obtained data. The results are further utilised for discussing the effects of irregularity on the most critical wind condition.

• Computers and Concrete
• /
• 제29권 6호
• /
• pp.361-374
• /
• 2022

On the premise of ensuring that the automatic and quantitative discharging function of concrete conveyors is met, the accuracy of the weight forecast by the mathematical model of the screw conveying volume is improved, and the error of the weight of the concrete parts and the accumulation thickness is reduced. In this paper, the discrete element method (DEM) is used to simulate the macroscopic flow of concrete. Using the concrete discrete element model, the size of the screw conveyor is set, and establish the response model between the influencing factors (process and structure) and the concrete mass flow rate according to the design points of the screw discharging experiment. The nonlinear data fitting method is used to obtain the volumetric efficiency function under the influence of process and structural factors, and the traditional screw conveying volume model is improved. The mass flow rate of concrete predicted by the improved mathematical model of screw conveying volume is consistent with the test results. The model can accurately describe the conveying process of concrete and achieve the purpose of improving the accuracy of forecasting the weight of discharged concrete.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.37-46
• /
• 2023

The main aim of the article is to solve the problem of automating price monitoring using marketing forecasting methods and Excel functionality under martial law. The study used the method of algorithms, trend analysis, correlation and regression analysis, ANOVA, extrapolation, index method, etc. The importance of monitoring consumer price developments in market pricing at the macro and micro levels is proved. The introduction of a Dummy variable to account for the influence of martial law in market pricing is proposed, both in linear multiple regression modelling and in forecasting the components of the Consumer Price Index. Experimentally, the high reliability of forecasting based on a five-factor linear regression model with a Dummy variable was proved in comparison with a linear trend equation and a four-factor linear regression model. Pessimistic, realistic and optimistic scenarios were developed for forecasting the Consumer Price Index for the situation of the end of the Russian-Ukrainian war until the end of 2023 and separately until the end of 2024.

• International Journal of Computer Science & Network Security
• /
• 제24권4호
• /
• pp.147-154
• /
• 2024

The continuous increase in urban population due to migration of mases from rural areas to big cities has set urban water supply under serious stress. Urban water resources face scarcity of available water quantity, which ultimately effects the water supply. It is high time to address this challenging problem by taking appropriate measures for the improvement of water utility services linked with better understanding of demand side management (DSM), which leads to an effective state of water supply governance. We propose a dynamic framework for preventive DSM that results in optimization of water resource management. This paper uses Agent Based Modeling (ABM) with Digital Twin (DT) to model water consumption behavior of a population and consequently forecast water demand. DT creates a digital clone of the system using physical model, sensors, and data analytics to integrate multi-physical quantities. By doing so, the proposed model replicates the physical settings to perform the remote monitoring and controlling jobs on the digital format, whilst offering support in decision making to the relevant authorities.

• 한국컴퓨터정보학회논문지
• /
• 제17권4호
• /
• pp.163-172
• /
• 2012

현대 사회는 다양한 강력 범죄들이 발생하고 있다. 모든 범죄들은 발생한 후에 대처를 하는 것보다 사전에 범죄를 예방하는 것이 가장 중요하다. 이를 위해서 다양한 범죄를 예방하기 위한 연구가 진행되었다. 하지만 기존 연구 방법들은 사회학적, 심리학적인 요인들을 분석하여 범죄의 발생 확률과 발생 동기 등을 분석하여 예방하고자 하는 노력이 대부분이다. 그러므로 본 논문에서는 마코프 체인 방식을 사용하여 시간에 따른 범죄를 예측하기 위한 연구를 수행하고자 한다. 5대 강력 범죄인 강도, 살인, 강간, 절도, 폭력에 대하여 수집된 범죄 발생 건수 자료를 사용해 범죄 유형별 시간에 따른 범죄 발생 예측을 위한 모델링을 구현한다. 그리고 범죄 발생 유형별 범죄 발생 예측 값과 실제 발생 값을 비교해 본 논문에서 제안한 시간에 따른 범죄 발생 예측 모델링의 타당성을 검토하였다. 본 논문에서 제안한 범죄 발생 예측 기법이 실제로 강도, 살인, 강간 등과 같은 강력 범죄에 대해서는 최대 값을 임계값으로 적용하고, 나머지 범죄에 대해서는 평균값을 적용하는 방식을 사용함으로써 범죄 발생 예측확률을 높일 수 있을 것으로 연구되었다. 향후 범죄 유형별로 시간에 따른 범죄발생 예측율과 실제 값이 다르게 적용되는 사례들을 추가 조사하여 연구의 폭을 넓히고자 한다.

• KIEAE Journal
• /
• 제11권3호
• /
• pp.63-68
• /
• 2011

Building deterioration would be proceeded by various causes such as physical, social, economic degradation. The deterioration would be inevitably prevented or delayed to get the decent function and performance in various building part and components. The maintenance and management are continued to provide the decent living condition for the household. The maintenance means mainly a repair, including the on-time and longterm plan. The longterm repair would be conducted by the systemic preparation in management activity and a required cost. Therefore, the annual due for the longterm repair plan is important to prepare the repair cost in a required time. In this paper, it aimed at analyzing the longterm repair cost and modelling to forecast the required cost in total area, number of household and time elapse in apartment housing. The estimation model of a repair cost is used with a power function which has a good statistics. Results of this study are shown that the sample has a longterm repair due in a $2,032won/m^2{\cdot}yr$ averagely which is higher than $912won/m^2{\cdot}yr$ in domestic. Second, the longterm repair due is proportionally correlated with the time elapse in both a total area and the number of household. Third, the estimation model for the longterm repair amount is suitable for the power function which is most in any other estimation models. Fourth, the ration of the longterm plan repair due a year to the cumulated longterm amount is about 26%.

• 응용통계연구
• /
• 제20권3호
• /
• pp.541-550
• /
• 2007

시계열자료를 분석하는데 있어 중요한 목적 중에 하나가 미래값에 대한 예측이다. 일반적으로 자기회귀이동평균모형에서는 백색잡음이 정규분포를 따른다는 가정 하에서 모수의 추론과 예측 및 예측구간의 추정이 이루어지고 있다. 그러나 자료가 이러한 가정을 만족하지 않는 경우, 자료를 가정에 맞게 변환시킨 후 분석하는 방법을 생각해 볼 수 있다. 이 논문에서는 변환된 자료를 분석하여 얻은 결과를 이용하여 본래의 척도에서의 미래값에 대한 예측구간을 추정하는 문제에 대해 알아본다. 제안하는 방법에서는 먼저 적절한 변환을 이용하여 자료를 정규가정을 만족하도록 변환시키고 변환된 자료를 이용하여 미래값에 대한 예측구간을 추정한 후, 역변환을 이용하여 예측구간을 추정한다. 이 논문에서는 시계열분석에서 모델링이 상대적으로 어려운 왜도의 문제를 해결하기 위해 Yeo-Johnson 변환을 중심으로 한 방법론을 소개한다. 모의실험 결과 제안된 방법에 의한 단측예측구간의 포함확률이 변환을 사용하지 않은 구간보다 명목수준에 가까운 것을 확인하였다.