• 산업경영시스템학회지
• /
• 제38권3호
• /
• pp.100-107
• /
• 2015

Recently as the manufacturers want competitiveness in dynamically changing environment, they are trying a lot of efforts to be efficient with their production systems, which may be achieved by diminishing unplanned operation stops. The operation stops and maintenance cost are known to be significantly decreased by adopting proper maintenance strategy. Therefore, the manufacturers were more getting interested in scheduling of exact maintenance scheduling to keep smooth operation and prevent unexpected stops. In this paper, we proposedan integrated maintenance approach in injection molding manufacturing line. It consists of predictive and preventive maintenance approach. The predictive maintenance uses the statistical process control technique with the real-time data and the preventive maintenance is based on the checking period of machine components or equipment. For the predictive maintenance approach, firstly, we identified components or equipment that are required maintenance, and then machine parameters that are related with the identified components or equipment. Second, we performed regression analysis to select the machine parameters that affect the quality of the manufactured products and are significant to the quality of the products. By this analysis, we can exclude the insignificant parameters from monitoring parameters and focus on the significant parameters. Third, we developed the statistical prediction models for the selected machine parameters. Current models include regression, exponential smoothing and so on. We used these models to decide abnormal patternand to schedule maintenance. Finally, for other components or equipment which is not covered by predictive approach, we adoptedpreventive maintenance approach. To show feasibility we developed an integrated maintenance support system in LabView Watchdog Agent and SQL Server environment and validated our proposed methodology with experimental data.

• 대한산업공학회지
• /
• 제42권3호
• /
• pp.241-248
• /
• 2016

Plant life cycle consists of design, construction, certification, operation, and maintenance phases, and various and enormous plant life cycle data is involved in each phase. Plant life cycle data should be linked with each other based on its proper relationships, so that plant operators can access necessary plant data during their regular operations and maintenance works. Currently, the relationships of plant life cycle data may not be defined explicitly, or they are scattered over several plant information systems. This paper proposes high level design of a plant life cycle data management system based on pre-defined plant life cycle database design. ISO-15926 standard is adapted for the database design. User-interface designs of the plant life cycle data management system are explained based on analysis of plant owners' requirements. A conceptual design of the database is also described with the entity-relationship diagram.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2002년도 춘계학술대회 논문집
• /
• pp.53-60
• /
• 2002

This paper introduces KTX RCM(Reliability-Centered Maintenance) project which is for development of a decision making support system on the KTX maintenance framework. The functionality of the system is composed of ( i ) Fundamental Data Management, ( ⅱ ) Maintenance Goal Management, ( ⅲ ) Maintenance Program Management, ( ⅳ ) Cost-Effect Analysis, ( v ) Parameter Management. This system may improve existing maintenance Management procedure for rolling stock of KNR.

• 산업경영시스템학회지
• /
• 제45권3호
• /
• 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.

• 한국철도학회논문집
• /
• 제15권5호
• /
• pp.459-466
• /
• 2012

기존의 철도교량 유지관리체계는 주로 정보누락, 문서위주 관리 및 유선기반의 정보수집 등으로 인하여 다양한 현장의 환경변화에 실시간 대응이 곤란하여 능동적인 철도교량 유지관리 전략 수립에 제약을 갖고 있다. 본 연구에서는 유비쿼터스 기반의 철도교량 유지관리 정보운용체계 구축을 위한 실무 활용모형과 건설 생애주기의 통합 정보관리체계인 BIM (Building Information Modeling) 개념을 적용하여 유지관리 통합 운용모형을 제안하고 있다. 이의 개발 및 실무적 적용의 타당성 확보를 위해 설문분석에 의한 정량적 평가를 수행하였다. 최근 철도교량의 지능형 유지관리 운영체계가 확대될 것을 고려하면, 본 연구의 제안사항은 운영체계 구축을 위한 통합 프레임워크로 활용될 수 있을 것이다.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2007년도 추계학술대회 논문집
• /
• pp.1158-1164
• /
• 2007

Recently, the demand on the practical application of life-cycle cost effectiveness for design and rehabilitation of civil infrastructure is rapidly growing unprecedentedly in civil engineering practice. Accordingly, it is expected that the life-cycle cost in the 21st century will become a new paradigm for all engineering decision problems in practice. However, in spite of impressive progress in the researches on the LCC, so far, most researches in Koreahave only focused on roadway bridges, which are not applicable to railway bridges. Thus, this paper presents the formulation models and methods for uncertainty-based LCCA for railroad bridges consideringboth objective statistical data available in the agency database of railroad bridges management and subjective data obtained form interviews with experts of the railway agency, which are used to anew uncertainty-based expected maintenance/repair costs including lifetime indirect costs. For reliable assessment of the life-cycle maintenance/repair costs, statistical analysis considering maintenance history data and survey data including the subjective judgments of railway experts on maintenance/management of railroad bridges, are performed to categorize critical maintenance items and associated expected costs and uncertainty-based deterioration models are developed. Finally, the formulation for simulation-based LCC analysis of railway bridges with uncertainty-based deterioration models are applied to the design-decision problem, which is to select an optimal bridge type having minimum Life-Cycle cost among various railway bridges types such as steel plate girder bridge, and prestressed concrete girder bridge in the basic design phase.

• 전기학회논문지
• /
• 제57권8호
• /
• 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.

• 소음진동
• /
• 제4권4호
• /
• pp.459-467
• /
• 1994

Various maintenance programs and techniques have been implemented for roating machineries, since machines were invented for commerical use. The earliest type of maintenance was run-to-failure, where the machine was run until a fault caused to fail in service. It was obviously an expensive approach due to the unpredictability of the machine condition. Another type is the periodic maintenance, where machines are disassembled and overhauled on regular schedules. With the advent of reliable data collectors including FFT analyzer and developing of versatile supporting software such as ExpertALERT system, the predictive maintenance is known to be the most feasible maintenance type these days. The vibration analysis enables for a maintenance crew to find the exact cause of fault on a machine and to make a proper maintenance schedule with a trend analysis. The predicitive maintenance is considered to be the most important part of pro-active maintenance.

• 한국BIM학회 논문집
• /
• 제10권3호
• /
• pp.1-11
• /
• 2020

The introduction of BIM technology is expanding not only in the field of design and construction, but also in the maintenance and use stage. In particular, researchers are looking to build a smart facility management system that integrates advanced IT technology and BIM. This study proposes the parts to be used and added to the BIM information, focusing on information generated and exchanged in the application case that is an issue during the current facility maintenance work by introducing the smart facility management technology and its use cases. The effectiveness of this proposal is compared with the scenario in which BIM-based facility safety management is applied and the current business scenario. In conclusion, the requirements for smart facility management are analyzed, and linkable parts between facility management tasks and BIM data that should be reflected in the facility management system are presented. In the maintenance phase, through the use case scenario, the facility management phase is subdivided according to the characteristics and contents of the work. In addition, information about the facilities required for each task is specified. Furthermore, it is examined whether BIM data and IT information can be linked with existing facility management systems. It is a process and guideline that can be provided to practitioners who want to introduce BIM and smart technology to facility management. It can define the required data items and levels according to the required information step by step based on the maintenance case.

• 대한안전경영과학회지
• /
• 제25권4호
• /
• pp.141-151
• /
• 2023

Recently, due to the expansion of the logistics industry, demand for logistics automation equipment is increasing. The modern logistics industry is a high-tech industry that combines various technologies. In general, as various technologies are grafted, the complexity of the system increases, and the occurrence rate of defects and failures also increases. As such, it is time for a predictive maintenance model specialized for logistics automation equipment. In this paper, in order to secure the operational safety and reliability of the parcel loading system, a predictive maintenance platform was implemented based on the Naive Bayes-LSTM(Long Short Term Memory) model. The predictive maintenance platform presented in this paper works by collecting data and receiving data based on a RabbitMQ, loading data in an InMemory method using a Redis, and managing snapshot DB in real time. Also, in this paper, as a verification of the Naive Bayes-LSTM predictive maintenance platform, the function of measuring the time for data collection/storage/processing and determining outliers/normal values was confirmed. The predictive maintenance platform can contribute to securing reliability and safety by identifying potential failures and defects that may occur in the operation of the parcel loading system in the future.