• 한국소음진동공학회논문집
• /
• 제18권6호
• /
• pp.619-623
• /
• 2008

As higher reliability and accuracy on production facilities are required to detect incipient faults, a diagnostic system for predictive maintenance of the facility is highly recommended. In this paper, it presents a study on the application of vibration signals to diagnose faults for a rotating machinery using the Mahalanobis distance-Taguchi system. RMS, crest factor and Kurtosis that is known as the statistical methods and the spectrum analysis are used to diagnose faults as parameters of Mahalanobis distance.

• KNOM Review
• /
• 제24권1호
• /
• pp.13-19
• /
• 2021

최근 산업 분야에서는 공장 자동화 뿐만 아니라 장애 진단/예측을 통해 고장/사고를 사전에 방지하여 생산량을 극대화하기 위한 연구가 진행되고 있으며, 이를 구성하기 위해 많은 양의 데이터 축적을 위한 클라우드 기술, 데이터 처리를 위한 빅 데이터 기술, 그리고 데이터 분석을 쉽게 진행하기 위한 AI(Artificial Intelligence)기술이 도입되고 있다. 또한 최근에는 장애 진단/예측의 발전으로 인해 설비 유지보수(PM: Productive Maintenance) 방식도 정기적으로 설비를 유지보수 하는 방식인 TBM(Time Based Maintenance)에서 설비 상태에 따라 유지보수 하는 방식인 CBM(Condition Based Maintenance)을 조합하는 방식으로 발전하고 있다. CBM 기반 유지보수를 수행하기 위하여 설비의 상태(condition)의 정의와 분석이 필요하다. 따라서 본 논문에서는 머신 러닝(Machine Learning) 기반의 장애 진단을 위한 시스템 및 데이터 모델(Data Model)을 제안하며, 이를 기반으로 장애를 사전 예측한 사례를 제시하고자 한다.

• Nuclear Engineering and Technology
• /
• 제52권9호
• /
• pp.1998-2008
• /
• 2020

Solenoid operated valves (SOV) play important roles in industrial process to control the flow of fluids. Solenoid valves can be found in so many industries as well as the nuclear plant. The ability to be able to detect the presence of faults and predicting the remaining useful life (RUL) of the SOV is important in maintenance planning and also prevent unexpected interruptions in the flow of process fluids. This paper proposes a fault diagnosis method for the alternating current (AC) powered SOV. Previous research work have been focused on direct current (DC) powered SOV where the current waveform or vibrations are monitored. There are many features hidden in the AC waveform that require further signal analysis. The analysis of the AC powered SOV waveform was done in the time and frequency domain. A total of sixteen features were obtained and these were used to classify the different operating modes of the SOV by applying a machine learning technique for classification. Also, a deep neural network (DNN) was developed for the prediction of RUL based on the failure modes of the SOV. The results of this paper can be used to improve on the condition based monitoring of the SOV.

• 품질경영학회지
• /
• 제19권2호
• /
• pp.96-107
• /
• 1991

At the design stage of a plant, the plausible causes and pathways of release of hazardous materials are not clearly known. Thus there exist large amount of uncertainties on the consequences resulting from the operation of a fusion plant. In order to better handle such uncertain circumstances, we utilize the Probabilistic Risk Assessment(PRA) for the safety analyses on fusion power plant. In this paper, we concentrate on the tritium release accident. We develop a simple model that describes the process and flow of tritium, by which we figure out the locations of tritium inventory and their vulnerability. We construct event tree models that lead to various levels of tritium release from abnormal initiating events. Branch parameters on the event tree are assessed from the fault tree analysis. Based on the event tree models we construct influence diagram models which are more useful for the parameter updating and analysis. We briefly discuss the parameter updating scheme, and finally develop the methodology to obtain the predictive distribution of consequences resulting from the operating a fusion power plant. We also discuss the way to utilize the results of testing on sub-systems to reduce the uncertain ties on over all system.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2006년도 추계학술대회 논문집
• /
• pp.1436-1441
• /
• 2006

In this paper, Computer-aided Maintenance Equipments, which are being used in High Speed Line Train Control System, are applied to analyze failures in train control systems, resulting in long time delays of trains. It can be expected to extend and apply CAMS(Computer Aided Maintenance System) in the hereafter efficient operation and maintenance of high speed railway train control systems, by comparison between the analysis result of fundamental causes, from high speed railway train control system failure occurred during the operational process, and predictive result of failure causes, based on the recording data of CAMS when failures were occurred.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.251-266
• /
• 2022

Structural Health Monitoring (SHM) of critical infrastructure comprises a major pillar of maintenance management, shielding public safety and economic sustainability. Although SHM is usually associated with data-driven metrics and thresholds, expert judgement is essential, especially in cases where erroneous predictions can bear casualties or substantial economic loss. Considering that visual inspections are time consuming and potentially subjective, artificial-intelligence tools may be leveraged in order to minimize the inspection effort and provide objective outcomes. In this context, timely detection of sensor malfunctioning is crucial in preventing inaccurate assessment and false alarms. The present work introduces a sensor-fault detection and interpretation framework, based on the well-established support-vector machine scheme for anomaly detection, combined with a coalitional game-theory approach. The proposed framework is implemented in two datasets, provided along the 1st International Project Competition for Structural Health Monitoring (IPC-SHM 2020), comprising acceleration and cable-load measurements from two real cable-stayed bridges. The results demonstrate good predictive performance and highlight the potential for seamless adaption of the algorithm to intrinsically different data domains. For the first time, the term "decision trajectories", originating from the field of cognitive sciences, is introduced and applied in the context of SHM. This provides an intuitive and comprehensive illustration of the impact of individual features, along with an elaboration on feature dependencies that drive individual model predictions. Overall, the proposed framework provides an easy-to-train, application-agnostic and interpretable anomaly detector, which can be integrated into the preprocessing part of various SHM and condition-monitoring applications, offering a first screening of the sensor health prior to further analysis.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 1999년도 춘계학술대회 논문집
• /
• pp.403-405
• /
• 1999

Power transformers have a tendency of ultra-high voltage and huge capacity as power demand increases day after day. Therefore, the fault by insulation destruction gives rise to large area of power failure in huge capacity transformers. On-line predictive diagnostics is very important In power transformers because of economic loss and its spreading effect. Hence, this study presents experiments of partial discharge method using ultrasonic sensor in order to confirm the possibility of ultrasonic sensor in power transformers. It carries out the experiments of measuring delay time between ultrasonic sensor and transducer, sensitiities by temperature change of oil and by barriers inside transformers. It is also Included wave analysis by ultrasonic sensor for needle-plate electrode powered on through high-voltage equipments.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 C
• /
• pp.1903-1905
• /
• 2000

Power transformers have a tendency of ultra-high voltage capacity as power demand increases day after day KEPCO also will have plan to supply transmission power from 345KV to 765KV in the early of 2000. Therefore, the fault by insulation destruction gives rise to large area of power failure in huge capacity transformers. On-line predictive diagnostics is very important in power transformers because of economic loss and its spreading effect. This study presents the algorithm for transformer oil analysis used KEPCO code, IEC code, gas pattern method and Dornenburg & Roger Ratio method. We also describe the MMI display of expert system programmed by Element Expert Tool(Neuron Data Inc.).

• 한국IT서비스학회지
• /
• 제20권3호
• /
• pp.1-12
• /
• 2021

Reactor Coolant Pump (RCP) is core part of nuclear power plant to provide the forced circulation of reactor coolant for the removal of core heat. Properly monitoring vibration of RCP is a key activity of a successful predictive maintenance and can lead to a decrease in failure, optimization of machine performance, and a reduction of repair and maintenance costs. Here, we developed real-time RCP Vibration Analysis System (VAS) that web based platform using NoSQL DB (Mongo DB) to handle vibration data of RCP. In this paper, we explain how to implement digital signal process of vibration data from time domain to frequency domain using Fast Fourier transform and how to design NoSQL DB structure, how to implement web service using Java spring framework, JavaScript, High-Chart. We have implement various plot according to standard of the American Society of Mechanical Engineers (ASME) and it can show on web browser based on HTML 5. This data analysis platform shows a upgraded method to real-time analyze vibration data and easily uses without specialist. Furthermore to get better precision we have plan apply to additional machine learning technology.

• 한국안전학회지
• /
• 제38권5호
• /
• pp.43-50
• /
• 2023

With the advent of industrialization, consumers and end-users demand more reliable products. Meeting these demands requires a comprehensive approach, involving tasks such as market information collection, planning, reliable raw material procurement, accurate reliability design, and prediction, including various reliability tests. Moreover, this encompasses aspects like reliability management during manufacturing, operational maintenance, and systematic failure information collection, interpretation, and feedback. Improving product reliability requires prioritizing it from the initial development stage. Failure mode and effect analysis (FMEA) is a widely used method to increase product reliability. In this study, we reanalyzed using the FMEA method and proposed an improved method. Domestic railways lack an accurate measurement method or system for maintenance, so maintenance decisions rely on the opinions of experienced personnel, based on their experience with past faults. However, the current selection method is flawed as it relies on human experience and memory capacity, which are limited and ineffective. Therefore, in this study, we further specify qualitative contents to systematically accumulate failure modes based on the Failure Modes Table and create a standardized form based on the Master FMEA form to newly systematize it.