• Journal of Korea Water Resources Association
• /
• v.54 no.8
• /
• pp.599-606
• /
• 2021

Water Distribution Networks, one of the social infrastructures buried underground, has the function of transporting and supplying purified water to customers. In recent years, as measurement capability is improved, a number of studies related to leak recognition and detection by applying a deep learning technique based on flow rate data have been conducted. In this study, a cognitive model for leak occurrence was developed using an LSTM-based deep learning algorithm that has not been applied to the waterworks field until now. The model was verified based on the assumed data, and it was found that all cases of leaks of 2% or more can be recognized. In the future, based on the proposed model, it is believed that more precise results can be derived in the prediction of flow data.

• Journal of Korean Society of Transportation
• /
• v.22 no.1 s.72
• /
• pp.43-62
• /
• 2004

Conventionally the estimation method of the origin-destination Matrix has been developed by implementing the expansion of sampled data obtained from roadside interview and household travel survey. In the survey process, the bigger the sample size is, the higher the level of limitation, due to taking time for an error test for a cost and a time. Estimating the O-D matrix from observed traffic count data has been applied as methods of over-coming this limitation, and a gradient model is known as one of the most popular techniques. However, in case of the gradient model, although it may be capable of minimizing the error between the observed and estimated traffic volumes, a prior O-D matrix structure cannot maintained exactly. That is to say, unwanted changes may be occurred. For this reason, this study adopts a conjugate gradient algorithm to take into account two factors: estimation of the O-D matrix from the conjugate gradient algorithm while reflecting the prior O-D matrix structure maintained. This development of the O-D matrix estimation model is to minimize the error between observed and estimated traffic volumes. This study validates the model using the simple network, and then applies it to a large scale network. There are several findings through the tests. First, as the consequence of consistency, it is apparent that the upper level of this model plays a key role by the internal relationship with lower level. Secondly, as the respect of estimation precision, the estimation error is lied within the tolerance interval. Furthermore, the structure of the estimated O-D matrix has not changed too much, and even still has conserved some attributes.

• Journal of Korean Society of Transportation
• /
• v.14 no.1
• /
• pp.81-99
• /
• 1996

This study aims to assess the potential competition among road, rail, and coastal transport under various scenarios concerning the future inland container transport systems in Pusan-KyungIn corridor. For this SP approaches are adopted to collect data from shippers and carriers, and multinomial logit models are estimated at disaggragate level. The results of the analysis indicate that the SP data are reliable, and that the mode choice models estimated are valid. The results also indicate that the most effective policy to divert the freight volume from road to other modes is to reduce freight rates for the railway, and is to transport time for the coastal water with improved reliability.

• IE interfaces
• /
• v.14 no.3
• /
• pp.255-262
• /
• 2001

Containerization of cargo transportation has been norm in the word wide maritime services, but containerized trades are typically unbalanced in terms of the number of inbound and outbound containers. Therefore it is critical for shipping companies to find operating policy such as the repositioning of empty containers or replenishing of short-term leasing containers from leasing companies to satisfy the freighter's demands of containers. This paper develops a simulation model using ARENA to establish shipping company's operational policy to relocate and replenish empty containers. Furthermore, this study proposes simple and heuristic empty container repositioning rules to minimize the relevant cost in terms of leasing, repositioning, and inventory holding costs.

• Proceedings of the KSR Conference
• /
• 2003.10b
• /
• pp.35-39
• /
• 2003

Effort has been given to improve demand forecast methodology of rail system since it can have great impact on project evaluation of rail system investment. However most of demand forecast softwares developed in western countries where concerns have been provided mostly to private transport and they should be updated in order to reflect our country's situation accurately. Therefore, this paper aims, especially focusing on rail system, to do comparison analysis of oversea's passenger demand forecast softwares and provide some ideas to develop the updated demand forecast system which enables to reflect our country's situation accurately. Main conclusions are that we will need to have well described model for real situation. So we will have to study for these aspects for travel demand forecasting system and develop the package architecture.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.27 no.2
• /
• pp.102-113
• /
• 2004

This paper addresses the transportation planning that is based on genetic algorithm for determining transportation time and transportation amount of minimizing cost of distribution system. The vehicle routing of minimizing the transportation distance of vehicle is determined. A distribution system is consisted of a distribution center and many retailers. The model is assumed that the time horizon is discrete and finite, and the demand of retailers is dynamic and deterministic. Products are transported from distribution center to retailers according to transportation planning. Cost factors are the transportation cost and the inventory cost, which transportation cost is proportional to transportation distance of vehicle when products are transported from distribution center to retailers, and inventory cost is proportional to inventory amounts of retailers. Transportation time to retailers is represented as a genetic string. The encoding of the solutions into binary strings is presented, as well as the genetic operators used by the algorithm. A mathematical model is developed. Genetic algorithm procedure is suggested, and a illustrative example is shown to explain the procedure.

• Journal of the Korean Crystal Growth and Crystal Technology
• /
• v.15 no.4
• /
• pp.129-134
• /
• 2005

A numerical analysis was performed on magnetic field effects of silicon melt motion in Czochralski crystal puller. The turbulent modeling was used to simulate the transport phenomena in 18' single crystal growing process. For small crucible angular velocity, the natural convection is dominant. As the crucible angular velocity is increased, the forced convection is increased and the distribution of temperature profiles is broadened. The cusp magnetic field reduces effectively the natural and forced convection near the crucible and the temperature profiles of the silicon fluids is similar in the case of conduction.

• IE interfaces
• /
• v.11 no.1
• /
• pp.1-14
• /
• 1998

Various problems on logistics systems have been dealt with recently as research issues since they were regarded critical for taking up a better position in the increasingly competitive global market. In particular, the freight transportation is considered as a key factor which affects the economic competitiveness of a whole nation as well as the production cost of individual companies. The objective of this study is to identify main issues and review recent foreign and domestic studies related to the freight transportation. The studies are classified into two categories according to the hierarchical level in the decision making process: infra structure design and transportation strategies, service design and operation. Main issues are introduced with a brief review on the related literature and methodologies applied.

• Journal of the Korean Society for Railway
• /
• v.12 no.3
• /
• pp.420-426
• /
• 2009

Although the amount of travel demand is a critical factor in a benefit-cost (B/C) analysis of railway investment, the travel demand changes especially for induced demand have not been considered. Therefore, the basic study of how to estimate travel demand changes after railway investment is worth investigating. This study reviews the methodologies for estimating diverted and induced demand generated after railway investment, and proposes appropriate approaches that will help railway planners to practically apply them in a case study. Further, the research stimulates the needs of consideration of the travel demand changes in the feasibility studies of railway planning.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.20 no.43
• /
• pp.25-36
• /
• 1997

The purpose of this paper is to structure a new integrated model that can minimize the total cost for the transportation and inventory systems between m origin points, where origin i has a supply of a commodity, such as distribution centers or warehouses, and n destination points, where destination j requires the commodity. In this case, demands of the destination points are assumed random variables which have a known probability distribution. We will find optimal distribution centers which transport the commodity to the destination points and suggest optimal inventory policy to the selected distribution center which find the optimal pair $$ and safety stock level that minimize total cost with back-ordered case. This new model is formulated as a 0-1 nonlinear integer programming problem. To solve the problem, this paper proposes heuristic computational procedures and program and provides numerical examples.