• Journal of the Korean Operations Research and Management Science Society
• /
• v.27 no.2
• /
• pp.33-49
• /
• 2002

CBM (Condition-Based Maintenance) has increasingly drawn attention in industry because of its many benefits. CBM Problem Is characterized as a state-dependent scheduling model that demands simultaneous maintenance actions, each for an attribute that influences on machine condition. This problem is very hard to solve within conventional Markov decision process framework. In this paper, we present an intelligent machine maintenance scheduler, for which a new incremental decision tree learning method as evolutionary system identification model and shortest path problem as schedule generation model are developed. Although our approach does not guarantee an optimal scheduling policy in mathematical viewpoint, we verified through simulation based experiment that the intelligent scheduler is capable of providing good scheduling policy that can be used in practice.

• Proceedings of the KSR Conference
• /
• 2008.06a
• /
• pp.1359-1370
• /
• 2008

In the track geometry such as rails, sleepers, ballasts and fastener, track deterioration occurs by repetitive train weight and the high-speed railway takes a trend faster than normal. Track deterioration of over threshold value harms ride comfort and furthermore affect in trains safety seriously. An organic and systematic track maintenance system is very important because a trend of the track deterioration effects on track life-cycle and running safety. Also costs of the railway track permanent way and its maintenance are extremely large, forming a significant part of the total infrastructure expenditure. Therefor reasonable and efficient track maintenance has to be planed on a budget. It is required to carry out not only corrective maintenance but preventive maintenance for the track maintenance. In order to perform maintenance jobs in the boundary of the machines and resources given regarding the type and amount jobs, it is necessary to determine feasible or optimal scheduling considering the priority. In this study, the system organization and required functions for the development of track maintenance system supported track deterioration prediction and optimal scheduling are proposed.

• Proceedings of the KIEE Conference
• /
• 2003.11a
• /
• pp.447-449
• /
• 2003

In competitive electricity markets, maintenance schedule is submitted by Genco's and Transco's, and coordinated by ISO with the adequacy criterion. This paper presents an alternative coordination procedure by ISO on the maintenance schedule.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.8
• /
• pp.1305-1310
• /
• 2008

Traditional maintenance planning is based on a constant maintenance interval for equipment life. In order to consider economic aspect for time based preventive maintenance, preventive maintenance is desirable to be scheduled by RCM(Reliability-Centered Maintenance) evaluation. The main objective of RCM is to reduce the maintenance cost, by focusing on the most important functions of the system and avoiding or removing maintenance actions that are not strictly necessary. So, Markov state model is utilized considering stochastic state in RCM. In this paper, a Markov state model which can be used for scheduling and optimization of maintenance is presented. The deterioration process of system condition is modeled by the stepwise Markov model in detail. Also, because the system is not continuously monitored, the inspection is considered. In case study, simulation results about RCM will be shown using the real historical data of combustion turbine generating unit in Korean power systems.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.12
• /
• pp.303-312
• /
• 2018

The university facility is made up of multiple buildings and has many maintenance items. In addition, administrative constraints need to be handled within a limited period. Most maintenance work is small scale and multi-work construction, such as waterproofing, needs to be organized. The facility manager makes annual unit price contract with a maintenance company and carries out the maintenance work. On the other hand, delay and rework is occurring because existing maintenance work performed without scheduling based on the manpower input. This study proposed a scheduling model that can support the facility manager to manage maintenance works of multiple university facilities at the program level. The model consists of three stages in order. In object analysis, details of the maintenance items were analyzed and the quantity is calculated based on the quantity takeoff sheet. In resource analysis, the craftsmen and construction period of detailed works are derived for the effective input of craftsmen. In scheduling, the priority of each work and the optimal manpower input are derived. The optimal schedule is selected according to the goodness of fit. The applicability and effectiveness of the prototype was evaluated through a case study and interviews with case participants. The model was found to be an effective tool to support the scheduling of maintenance works for the facility manager.

• Proceedings of the KIEE Conference
• /
• 2005.07a
• /
• pp.798-800
• /
• 2005

In competitive electricity markets, the System Operator (SO) coordinates the overall maintenance schedules whenever the collective maintenance schedule reported to SO by Gencos & Transco in the pool does not satisfy the specified operating criteria, such as system reliability or supply adequacy. We propose a two-layer mathematical algorithm amenable to maintenance scheduling problem into master problem and sub-problem. The master problem coordinates the scheduling, and sub-problem, DC optimal power flew, checks the adequacy. The proposed algorithm was demonstrated with a case study.

• Journal of the Korean Society for Railway
• /
• v.13 no.6
• /
• pp.601-607
• /
• 2010

The objective of this paper is to propose a fast and easy Binary Artificial Bee Colony (BABC) heuristic algorithm to optimize NP-hard scheduling problem of railway track maintenance considering real conditions. The optimal or best solutions can be found using proposed BABC within very short or user specified computation time. We can greatly maximize the objective value using this proposed method in 30, 60, 100 and 200 work size railway track maintenance scheduling problems for experiment and analysis.

• Proceedings of the KIEE Conference
• /
• 1988.07a
• /
• pp.855-858
• /
• 1988

Two methods for probabilistic maintenance scheduling are developed and compared ; one with operation and supplied-shortage cost and other with risk level of LOLP. Based on the real economic power dispatch, quadratic optimal maintenance conditions are obtained and simple amtrix equations are suggested for solutions. Both methods are compared in a sample system of 26,000 [MW] peak and 32,000 [MW] generation capacity.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.559-561
• /
• 1995

The cogeneration system has a strong merit in providing thermal and electrical energy simultaneously. Nowadays, cogeneration system is widely used in the point of efficient use of the energy resources And the installation of the system is expected to be greatly increased in each year. So, we need to develop an optimal operation planning for those systems. In this paper, we are used to result what studed at the my power system of room because it is in order to solve maintenance scheduling problem. Also we added a constraints to the proposed maintenance model for optimal maintenance rate. In the case study, we construct an multi-machine generated example system which operated in topping cycle, and calculate the yearly optimal production cost, marginal maintenance cost, and maintenance scheduling of the example system respectively.

• 제어로봇시스템학회:학술대회논문집
• /
• 1998.10a
• /
• pp.312-317
• /
• 1998

Reliable maintenance scheduling of main equipments is a crucial problem in thermal power stations in order to skirt overall losses of power generation resulted from severe failures of the equipments. A reasonable method was proposed to determine the maintenance scheduling of whole pump system in thermal power stations in order to reduce the maintenance cost by keeping the present avail-ability of the pump system throughout the operation. The dimensional reduction method was used to solve problems encountered due to few data which involved many operational factors in failure rate of pumps. The problem of bandlimited nature of data with time was solved by extrapolating future failures from presently available actual data with an aid of Weibull distribution. The results of the analysis identified the most suitable maintenance intervals of each pump type accordingly and hence reduce the cost of unnecessary maintenance with an acceptable range in the overall system availability.