• Journal of Hydrogen and New Energy
• /
• v.28 no.3
• /
• pp.252-272
• /
• 2017

Fuel cell systems have to satisfy acceptable operating reliability, sufficient lifetime and price to enter the market in competition with existing products. Fuel cells are made up of complex element technologies and various problems related to the failure of the components can affect the reliability and safety of the system. This problem can be overcome by introducing a monitoring and supervisory control system in addition to automatic control to detect the failure of the fuel cell quickly and properly diagnose the performance degradation. For the fault detection and diagnosis of polymer electrolyte fuel cells, the model based method using the theoretical superposition value and the non-model based method of checking the signal tendency or the converted signal characteristic can be applied. The methods analyzed in this paper can contribute to the development of integrated monitoring and control technology for the whole system as well as the stack.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.27-28
• /
• 2018

본 논문에서는 구동 장치의 다양한 상태를 나타내는 소음과 진동으로부터 특징데이터를 추출하여 이를 학습 한 후 실시간으로 장치의 상태를 진단하는 하였다. 실제 현장에서 발생할 수 있는 예측 외 소음환경에 유연하게 대처하기 위해 CNN모델 사용과 소리, 진동 데이터의 Butterworth filter와 Kalman filter를 적용하여 노이즈 배제처리 하였다. 제안된 시스템의 유용성을 확인하기 위해 제안된 시스템과 기존 CNN기반 시스템을 소음환경에서 비교 실험하였다.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.518-523
• /
• 2023

The diagnosis of Inter Turn Short Circuits (ITSC) in induction motors is critical due to the escalating severity of faults resulting from even minor disruptions in the stator windings. However, diagnosing ITSC presents significant challenges due to similarities in noise and losses shared with 3-phase induction motors. Although artificial intelligence techniques have been explored for efficient diagnosis, practical applications heavily rely on model-based methods, necessitating further research to enhance diagnostic performance. This study proposed a diagnostic method applied the Clarke Transformation approach, focusing solely on current components while disregarding changes in rotating flux. Experimental results conducted over a 30-minute period, encompassing both normal and ITSC conditions, demonstrate the effectiveness of the proposed approach, with FAR(False Accept Rates) of 0.2% for normal-to-ITSC FRR(False Rejection Rates) and 0.26% for ITSC-to-normal FRR. These findings underscore the efficacy of the proposed approach.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.13 no.12
• /
• pp.1288-1296
• /
• 2001

A scheme for on-line fault detection and diagnosis of an air-handling unit is presented. The fault detection scheme uses residuals which are generated by comparing each measurement with analytical redundancies computed from the reference models. In this paper, artificial neural networks (ANNs) are used to estimate analytical redundancy and to classify faults. The Lebenburg-Marquardt algorithm is used to train feed forward ANNs that provide estimates of continuous states and diagnosis results. The simulation result demonstrated that the ANNs can effectively detect and diagnose faults in the highly non-linear and complex HVAC systems.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2012.08a
• /
• pp.101-101
• /
• 2012

본 논문은 현재 제품화 단계로 진행 중인 터보 분자펌프(turbo-molecular pump, TMP)와 극저온 펌프(cryopump)의 고장 방지 및 예지 보수를 위한 상태 진단 시스템에 대하여 소개를 한다. 본 상태 진단 시스템은 고진공 펌프들의 다중 상태변수 즉 흡/배기부의 진공 압력, 부위별 온도, 소비 전류(혹은 전력), 그리고 부위별 진동 신호들을 실시간으로 측정하는 상태변수 수집장치, 수집된 시계열 상태변수들이 저장된 database, 그리고 저장된 상태변수를 이용한 고진공펌프의 상태진단 프로그램으로 구성되어 있다. 금번 연구에서 구축한 상태변수 체계의 특징 중 하나는 진동신호를 상태변수로 측정하여 이를 상태진단에 활용하는 점이 기존의 접근방법과 상이한 점이다. 실시간 신호 수집장치는 NI사 PXI 시스템 기반의 16채널 24-bit 동시 전압신호 측정 모듈, 8부위의 온도 측정장치(Lakeshore 218S, RS-232C 통신), 그리고 펌프의 소비전류/전력 측정장치(Hioki 3169, RS-232C), 그리고 고진공 펌프의 흡입 및 배기구의 진공도 측정장치로 구성하였다. 신호 수집용 프로그램은 NI사 Labview를 이용하여 작성하였다. 본 장치는 Nano-Fab 센터의 협조 하에 turbo-molecular 펌프와 cryopump측정 단에 각각 1대를 설치 완료하였으며 현재까지 운용 중이다. PC에 저장된 시계열 상태변수 database는 기 개발된 적응형 인자모델을 이용한 매개변수로 변환되며, 상태진단은 변환된 매개변수를 이용하여 수행할 예정이다.

• Journal of the Korean Vacuum Society
• /
• v.15 no.4
• /
• pp.338-346
• /
• 2006

In semiconductor process, it is so hard to predict an exact failure point of the vacuum pump due to its harsh operation conditions and nonlinear properties, which may causes many problems, such as production of inferior goods or waste of unnecessary materials. Therefore it is very urgent and serious problem to develop diagnostic models which can monitor the operation conditions appropriately and recognize the failure point exactly, indicating when to replace the vacuum pump. In this study, many influencing factors are totally considered and eventually the monitoring model using multivariate statistical methods is suggested. The pivotal algorithms are Multiway Principal Component Analysis(MPCA), Dynamic Time Warping Algorithm(DTW Algorithm), etc.

• Journal of Hydrogen and New Energy
• /
• v.34 no.5
• /
• pp.478-489
• /
• 2023

In this study, fault diagnosis and detection methods developed to ensure the reliability of polymer electrolyte membrane (PEM) hydrogen electrolysis systems have been proposed. The proposed method consists of model development and data generation of the PEM hydrogen electrolysis system, and data-driven fault diagnosis learning model development. The developed fault diagnosis learning model describes how to detect and classify faults in the sensors and components of the system.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.281-286
• /
• 2007

유비쿼터스 컴퓨팅이란 사용자에게 지속적인 서비스를 제공해주는 컴퓨팅 환경을 말한다. 끊임없이 동적으로 변하는 유비쿼터스 환경에서 수많은 상황데이터가 발생을 하고 상황정보로 추상화하는 과정이 필수적이다. 상황인지시스템은 동적인 상황정보에 대한 생성, 조작, 공유 등이 일관성 있게 이루어져야 한다. 이러한 상황정보의 조작을 위한 수많은 상황인지 모델이 제시되고 연구되어 왔다. 본 논문에서는 유비쿼터스 환경을 위한 온톨로지 기반 상황인지 시스템을 제시한다. 상황정보에 대한 생성, 컨텍스트 추론, 지식의 공유을 위해 온톨로지 표준언어인 OWL을 사용한 컨텍스트 온톨로지를 생성한다. 디바이스의 상황정보 생성을 위해 SWRL 규칙언어를 사용하고 생성된 디바이스 상황에 고장진단 및 수리서비스를 제공하기 위해 규칙추론기반 언어인 Jess를 사용하고 OWL기반의 컨텍스트 온톨로지와의 연계를 위해 Jess Tab API를 사용한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.1
• /
• pp.75-84
• /
• 2018

Increasing the operation rate of components and stabilizing the operation through timely management of the core parts are crucial for improving the efficiency of the railroad maintenance industry. The demand for diagnosis technology to assess the condition of rolling stock components, which employs history management and automated big data analysis, has increased to satisfy both aspects of increasing reliability and reducing the maintenance cost of the core components to cope with the trend of rapid maintenance. This study developed a big data platform-based system to manage the rolling stock component condition to acquire, process, and analyze the big data generated at onboard and wayside devices of railroad cars in real time. The system can monitor the conditions of the railroad car component and system resources in real time. The study also proposed a machine learning technique that enabled the distributed and parallel processing of the acquired big data and automatic component fault diagnosis. The test, which used the virtual instance generation system of the Amazon Web Service, proved that the algorithm applying the distributed and parallel technology decreased the runtime and confirmed the fault diagnosis model utilizing the random forest machine learning for predicting the condition of the bearing and wheel parts with 83% accuracy.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.23-35
• /
• 2021

In the era of the 4th industrial revolution, smart factories have received great attention, where production and manufacturing technology and ICT converge. With the development of IoT technology and big data, automation of production systems has become possible. In the advanced manufacturing industry, production systems are subject to unscheduled performance degradation and downtime, and there is a demand to reduce safety risks by detecting and reparing potential errors as soon as possible. This study designs a model based on supervised and unsupervised learning for detecting anomalies. The accuracy of XGBoost, LightGBM, and CNN models was compared as a supervised learning analysis method. Through the evaluation index based on the confusion matrix, it was confirmed that LightGBM is most predictive (97%). In addition, as an unsupervised learning analysis method, MD, AE, and LSTM-AE models were constructed. Comparing three unsupervised learning analysis methods, the LSTM-AE model detected 75% of anomalies and showed the best performance. This study aims to contribute to the advancement of the smart factory by combining supervised and unsupervised learning techniques to accurately diagnose equipment failures and predict when abnormal situations occur, thereby laying the foundation for preemptive responses to abnormal situations. do.