• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.3
• /
• pp.18-30
• /
• 2022

Predicting remaining useful life (RUL) becomes significant to implement prognostics and health management of industrial systems. The relevant studies have contributed to creating RUL prediction models and validating their acceptable performance; however, they are confined to drive reasonable preventive maintenance strategies derived from and connected with such predictive models. This paper proposes a data-driven preventive maintenance method that predicts RUL of industrial systems and determines the optimal replacement time intervals to lead to cost minimization in preventive maintenance. The proposed method comprises: (1) generating RUL prediction models through learning historical process data by using machine learning techniques including random forest and extreme gradient boosting, and (2) applying the system failure time derived from the RUL prediction models to the Weibull distribution-based minimum-repair block replacement model for finding the cost-optimal block replacement time. The paper includes a case study to demonstrate the feasibility of the proposed method using an open dataset, wherein sensor data are generated and recorded from turbofan engine systems.

• IE interfaces
• /
• v.16 no.2
• /
• pp.229-239
• /
• 2003

The On-Line Analytical Processing (OLAP) tools access data from the data warehouse for complex data analysis, such as multidimensional data analysis, and decision support activities. Current research has lead to new developments in all aspects of data warehousing, however, there are still a number of problems that need to be solved for making data warehousing effective. View maintenance, one of them, is to maintain view in response to updates in source data. Keeping the view consistent with updates to the base relations, however, can be expensive, since it may involve querying external sources where the base relations reside. In order to reduce maintenance costs, it is possible to maintain the views using information that is strictly local to the data warehouse. This process is usually referred to as "self-maintenance of views". A number of algorithm have been proposed for self maintenance of views where they keep some additional information in data warehouse in the form of auxiliary views. But those algorithms did not consider a consistency of materialized views using view self-maintenance. The purpose of this paper is to research consistency problem when self-maintenance of views is implemented. The proposed "conveyor algorithm" will resolved a complete consistency of materialized view using self-maintenance with considering network delay. The rationale for conveyor algorithm and performance characteristics are described in detail.

• Journal of Korean Institute of Industrial Engineers
• /
• v.15 no.2
• /
• pp.87-91
• /
• 1989

A warranty is a contractual obligation incurred by a producer in connection with the sale of a product. The warranty specifies that producer agrees to remedy certain failures in the product sold. There have been many articles dealing with warranties, but they have studied about optimal warranty cost for the warranty period. In this study, an optimal preventive maintenance time interval is computed. The optimal preventive maintenance time interval minimizing warranty cost for the warranty period is discussed. It is assumed that failure rate is increasing and the failure rate after preventive maintenance or corrective maintenance lies between good as new and bad as old.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.17 no.32
• /
• pp.221-226
• /
• 1994

Almost preventive maintenance policies assumed that the system after pm has failure rate as before pm with probability p and as good as new with probability 1-p. This paper considers the s-expected cost of the model with imperfect periodic preventive maintenance that increasing minimal repair costs at failure and obtains the optimum periodic preventive maintenance time. Numerical example are shown in which the failure time of the system has gamma distribution.

• Journal of Industrial Technology
• /
• v.28 no.A
• /
• pp.43-49
• /
• 2008

The track of high-speed railway get deteriorated according as using it. In that case, the maintenance jobs are needed for improvement of track quality. A scheduling problem for the track maintenance of high-speed railway is to determine the jobs should be performed daily. In the problem, the set of jobs for maintenance is given. Each job has it's parameters such as due date, emergency level, and processing time. In addition, jobs can be worked during a certain fixed time when the train doesn't move. In this study, we developed a mathematical model of the scheduling problem for the maintenance of high-speed railway and solved the problem using the ILOG CPLEX library.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.18 no.36
• /
• pp.287-295
• /
• 1995

This paper is concerned with cost analysis model in periodic maintenance policy. Generally periodic maintenance policy in which item is repaired periodic interval times. And in the article minimal repair is considered. Mimimal repair means that if a unit fails, unit is instantaneously restored to same hazard rate curve as before failure. In the paper periodic maintenance policy with minimal repair is as follows; Operating unit is periodically replaced in periodic maintenance time, if a failure occurs between minimal repair and periodic maintenance time, unit is replaced by a new item until tile periodic maintenance time comes. Also unit undergoes minimal repair at failures in minimal-repair-for-failure interval. Then total expected cost per unit time is calculated according to scale parameter of failure distribution. Maintenance cost factors are included operating, fixed, minimal repair, periodic maintenance and new item replacement cost. Numerical example is shown in which failure time of system has weibull distribution.

• Journal of Korean Society for Quality Management
• /
• v.33 no.3
• /
• pp.114-125
• /
• 2005

Maintenance equipments, tools, manuals and documents are needed to maintain the weapon systems. At the time, a lot of technical materials are maintained and used individually at a various places and organizations. Thus, maintenance engineers can not get the necessary informations quickly and the efficiency of maintenance was low. In this paper, first we analyze the maintenance processes in weapon systems and define the total measure to evaluate the maintenance efficiency of weapon systems. Second, we propose a implementation procedure to integrated maintenance system.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.11
• /
• pp.3200-3206
• /
• 2009

This paper describes the problem of existing maintenance system for mail sorting machnies, and presents to-be considerations of maintenance system based on AHP (Analytic Hierarchy Process) analysis with efficiency and economic aspects. There are standard procedure for diagnosis and repair of mail sorting machine as preventive and operational maintenance, roles and missions of maintenance technical support center for upgrade of maintenance skill in this paper. The proposed maintenance system will be adapted for more safety and efficiency maintenance of mail sorting machine.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.9 no.2
• /
• pp.123-134
• /
• 1999

Hot-wire anemometers are most commonly used in measuring hood capture velocities due to their accuracy and convenience. But it was ques tionable whether they have an appropriate accuracy and they are well maintained. To answer these questions, as eries of survey and the performance test were performed. The average error turns out to be 16.93%. Many of them were out of order due to bad maintenance. They were not frequently calibrated even though the users of anemometers think the periodic calibration is necessary for maintaining the accuracy of anemometers. A possible efficient maintenance program was thus discussed.

• Smart Structures and Systems
• /
• v.22 no.2
• /
• pp.151-159
• /
• 2018

Maintenance activities are regarded as a key part of the repairable deteriorating system because they maintain the equipment in good condition. In practice, many maintenance policies are used in engineering fields to reduce unexpected failures and slow down the deterioration of the system. However, in traditional maintenance policies, maintenance activities have often been assumed to be performed at the same time interval, which may result in higher operational costs and more system failures. Thus, this study presents two non-periodic preventive maintenance (PM) policies for repairable deteriorating systems, employing the failure rate of the system as a conditional variable. In the proposed PM models, the failure rate of the system was restored via the failure rate reduction factors after imperfect PM activities. Operational costs were also considered, which increased along with the operating time of the system and the frequency of PM activities to reflect the deterioration process of the system. A numerical example was provided to illustrate the proposed PM policy. The results showed that PM activities performed at a low failure rate threshold slowed down the degradation of the system and thus extended the system lifetime. Moreover, when the operational cost was considered in the proposed maintenance scheme, the system replacement was more cost-effective than frequent PM activities in the severely degraded system.