• Korean Journal of Construction Engineering and Management
• /
• v.21 no.6
• /
• pp.46-55
• /
• 2020

The maintenance cost for highway pavement is gradually increasing due to the continuous increase in road extension as well as increase in the number of old routes that have passed the public period. As a result, there is a need for a method of minimizing costs through preventative grievance Preventive maintenance requires the establishment of a strategic plan through accurate prediction old Highway pavement. herefore, in this study, the XGBoost among machine learning classification-based models was used to develop a highway pavement damage prediction model. First, we solved the imbalanced data issue through data sampling, then developed a predictive model using the XGBoost. This predictive model was evaluated through performance indicators such as accuracy and F1 score. As a result, the over-sampling method showed the best performance result. On the other hand, the main variables affecting road damage were calculated in the order of the number of years of service, ESAL, and the number of days below the minimum temperature -2 degrees Celsius. If the performance of the prediction model is improved through more data accumulation and detailed data pre-processing in the future, it is expected that more accurate prediction of maintenance-required sections will be possible. In addition, it is expected to be used as important basic information for estimating the highway pavement maintenance budget in the future.

• Journal of Information Technology Applications and Management
• /
• v.19 no.2
• /
• pp.181-196
• /
• 2012

The cost of software maintenance occupies about two thirds in the software lifecycle. However, it is not easy to estimate the cost of software maintenance because of various viewpoints about software maintenance, unclear estimation methods, and complex procedures. Until now, the cost estimation model has used compensation factors for software characteristic and environment on the basis of program size. Especially, most of existing models use maintenance rate of total software cost as a main variable. This paper suggests the software maintenance cost estimation model that uses the result of calculating real maintenance efforts. In this paper, we classify functional maintenance and non-functional maintenance as software maintenance activity type. For functional maintenance, present function point of target software is needed to evaluate. The suggested maintenance cost evaluation model is applied to a software case in public sector. This paper discusses some differences between our model and other modes.

• Korean Journal of Construction Engineering and Management
• /
• v.18 no.3
• /
• pp.12-21
• /
• 2017

From 1960, the government decided to build apartment houses on a large scale in order to resolve the rising housing problems. However, the maintenance issues that have arisen from the deterioration of housing has not received adequate attention. The policy focuses only on the supply of housing. By passing new laws, the durable period during which buildings allowed reconstruction was increased, and long term maintenance plans were treated as important issues. The government was then obligated to establish certain long term maintenance plans and costs by legislating a Housing Act and requiring it be adjusted every three years. However, when planning long-term repair costs, doing so without considering the time value of money would become a problem. In addition, if differences between the planned repair costs and actual costs occur, it becomes necessary to adjust the long-term repair costs but, as of yet, the criteria to adjust such things does not exist. For these reasons, if there is lack of money to execute large-scale repair work, a building is unlikely to respond to deterioration of housing; on the other hand, an unnecessary reserve or pool of money can lead to conflict among residents. Therefore, this paper will propose estimation and adjustment models considering the time value of money for long term maintenance costs of apartment houses.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2006.11a
• /
• pp.384-389
• /
• 2006

The needs for Light Railroad Transit(LRT) have been increased due to the heavy traffic congestions in large cities like Seoul, Korea. Korean government is seeking the LRT system development (including planning, designing, construction, and maintenance and operations) in terms of public-private-partnership (PPP). At the private sector side, it is crucial to estimate the life cycle cost (LCC) to project the cash flow during the O&M period. Since the most construction and O&M cost of LRT project is at the bridge construction, a cost analysis model and a cost breakdown structures (CBS) on LRT bridges are discussed through in depth literature reviews. Construction and maintenance cost of bridges are collected and analyzed. LCC is analyzed by types of bridge superstructures and historical data of repair and rehabilitation (R&R) is investigated. There have been scarce number of LCC analysis on railway bridges. This research delivers a well-defined CBS and maintenance cost data, which will be a great benefit to the systematic maintenance strategy development for railroad bridges.

• Journal of Korean Society of Transportation
• /
• v.31 no.2
• /
• pp.80-89
• /
• 2013

The purpose of this research is to optimize the line planning of the intercity passenger railway. In this study, the line planning problem has been formulated into a mixed integer programming by minimizing both user costs (passenger's total travel time) and operator costs (operation, maintenance and vehicle costs) with multiple train types. As a solution algorithm, the branch-and-bound method is used to solve this problem. The change of travel demand, train speed and the number of schedules have been tested through sensitivity analysis. The optimal stop-schedules and frequency as well as system split with respect to each train type have been found in the case study of Kyoung-bu railway line in Korea. The model and results of this research are useful to make a decision for railway operation strategy, to analyze the efficiency of new railway systems and to evaluate the social costs of users and operators.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.6 no.3
• /
• pp.174-182
• /
• 2007

There are not many studies on the maintenance and replacement for the ITS equipments. Most of ITS center has no comprehensive regulation on the equipment replacement. This study was focusing on estimation of equipment replacement period and the number of spare parts in stock using the actual failure data of Road Side Equipment (RSE) by Dedicated Short Range Communication (DSRC). The failure data showed a type of bath-tub curves. The data, however, did not fit to any probability distribution curve, which means that the preventive replacement cannot be strongly applied for the RSE. In the aspect of practical strategy, this study suggest that repairing cost and failure frequency be used for decision of replacement of RSE after the 1 or 2 year warrant period. The future study needs to include more RSE failure data as well as other equipments of the ITS.

• Korean Journal of Construction Engineering and Management
• /
• v.2 no.2 s.6
• /
• pp.59-67
• /
• 2001

The purpose of this study is to evaluate economics by the Life Cycle cost(LCC) analysis of Steel Box Girder and Prestressed Box Girder bridge types. The study has been performed as a case study. A questionnaire survey for the repair and replacement cycle has been done in order to predict operation and maintenance costs. For LCC analysis and comparison, the present value technique is used. The results of this study are summarized as follows: (1) A LCC analysis model of Steel Box Girder and Prestressed Box Girder bridge types is suggested through a case study. (2) The repair and replacement cycle of elements of them are investigated using a questionnaire survey. (3) As a result of LCC case study, the type of Prestressed Box Girder bridge is analyzed more economic than Steel Box Girder.

• Journal of Korea Water Resources Association
• /
• v.36 no.1
• /
• pp.45-59
• /
• 2003

The method in this study, which is more efficiency than the existing method, propose the optimal rehabilitation model based on the deterioration prediction of the laying pipe by using the deterioration survey method of the water distribution system. The deterioration prediction model divides the deterioration degree of each pipe into 5 degree by using the probabilistic neural network. Also, the optimal residual durability is estimated by the calculated deterioration degree in each pipe and pipe diameter. The optimal rehabilitation model by integer programming base on the shortest path can calculate a time and cost of maintenance, rehabilitation, and replacement. Also, the model is divided into budget constraint and no budget constraint. Consequently, the model proposed by the study can be utilized as the quantitative method for the management of the water distribution system.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.12
• /
• pp.8700-8706
• /
• 2015

The first driving device of the power bogies for the Korean high-speed railway vehicle consists of the traction motor (TM) and the motor reduction gears unit (MRU). Although TM and MRU are the mechanically integrated structures, their time between overhauls (TBO) have two separate intervals due to different technical requirements(i.e. TBO of MRU: $1.8{\times}10^6km$, TBO of TM: $2.5{\times}10^6km$). Therefore, to reduce the unnecessary number of preventive maintenances, it is important to evaluate the optimal TBO with a viewpoint of reliability-center maintenance towards cost-effective solution. In this study, derived from the field data in maintenance, fault tree analysis and failure rate of the subsystem considering criticality of the components are evaluated respectively. To minimize the conventional total maintenance cost, the same optimal TBO of the components is derived from genetic algorithm considering target reliability and improvement factor. In this algorithm, a chromosome which comprised of each individual is the minimum preventive maintenance interval. The fitness function of the individual in generation is acquired through the formulation using an inverse number of the total maintenance cost. Whereas the lowest common multiple method produces only a four percent reduction compared to what the existing method did, the optimal TBO of them using genetic algorithm is $2.25{\times}10^6$km, which is reduced to about 14% comparing the conventional method.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.6D
• /
• pp.663-671
• /
• 2012

The demand of CWR is rapidly increasing because of the adaptation of concrete track, the need for rapid and comfortable ride, and the reduction of maintenance cost. Because of short applying period of the concrete track, there is not a case of CWR fracture in Korea caused by repeated load of the train, which makes it difficult to calculate replacement period of rail based on rail fatigue life using an actual field data. This study thus inspected the bending stress at rail bottom through analyzing the vehicle/track interaction, performed multiple regression analysis on the data, deducted the bending stress prediction equations by the speed and the surface irregularity. Finally, the fatigue life of CWR on the concrete track was predicted based on the prediction equations for bending stress at rail bottom.