• Journal of Information Processing Systems
• /
• 제16권3호
• /
• pp.530-540
• /
• 2020

In order to solve the problem of low tracking accuracy caused by complex noise in the fault diagnosis of complex nonlinear system, a fault diagnosis method of high precision cost reference particle filter (CRPF) is proposed. By optimizing the low confidence particles to replace the resampling process, this paper improved the problem of sample impoverishment caused by the sample updating based on risk and cost of CRPF algorithm. This paper attempts to improve the accuracy of state estimation from the essential level of obtaining samples. Then, we study the correlation between the current observation value and the prior state. By adjusting the density variance of state transitions adaptively, the adaptive ability of the algorithm to the complex noises can be enhanced, which is expected to improve the accuracy of fault state tracking. Through the simulation analysis of a fuel unit fault diagnosis, the results show that the accuracy of the algorithm has been improved obviously under the background of complex noise.

• Korean Chemical Engineering Research
• /
• 제60권2호
• /
• pp.223-228
• /
• 2022

화학공정에서 의도되지 않게 발생하는 이상은 큰 사고를 유발할 수 있다. 이러한 문제를 해결하기 위해, 신속하게 이상의 원인을 감지하고 판별하는 이상 진단 모델이 필요하다. 하지만, 이상 진단을 연구하는 대부분 연구의 경우, 상용프로그램에서 공정 시뮬레이션을 이용하여 이상 데이터를 생성하고 이를 이용하여 연구한 방법론을 적용하고 있다. 이는 실제 공정상에서 이상을 포함하는 실제 데이터를 얻는 데 많은 제약이 있음을 의미한다. 본 연구에서는 실제 폴리스티렌 반응기에서 얻은 이상 데이터와 정상 데이터를 분석하여 적절한 이상 진단 모델을 설계하고자 하였다. 먼저, 정상 데이터를 분석하여 세 가지의 조업 모드가 존재함을 확인하였으며, 모드 판별을 위한 모델을 SVM (Support Vector Machine)을 이용하여 만들었다. 각 조업 모드 별로 PCA (Principal Component Analysis)를 이용하여 이상 진단 모델을 만들었으며, 실제 이상 데이터를 이용하여 계산한 결과 신속하게 이상을 진단할 수 있음을 확인하였다. 본 연구에서 제안한 모델을 통해, 실제 사고가 발생하는 경우 신속한 대처가 가능하며, 이는 잠재적인 손실의 감소에 기여할 수 있음을 의미한다.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제49권12호
• /
• pp.643-650
• /
• 2000

Using neural network approach, the diagnosis of faults in industrial process that requires observing multiple data simultaneously are studied. Two-stage diagnosis is proposed to analyze system faults. By using neural network, the first stage detects the dynamic trend of each normalized date patterns by comparing a proposed pattern. Instead of using neural network, the difference between stored fault pattern and real time data is used for fault diagnosis in the second stage. This method reduces the amount of calculation and saves storing space. Also, we dealt with unknown faults by normalizing the data and calculating the difference between the value of steady state and the data in case of fault. A model of tank reactor is given to verify that the proposed method is useful and effective to noise.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.24-26
• /
• 2005

At present, KS-1000 which is one of a commercial measurement instrument for motor fault diagnosis has been used in industrial field. The measurement system of KS-1000 is composed of three part : harmonic acquisition, signal processing by KS-1000 algorithm, diagnosis for motor fault. First of all, voltage signal taken from harmonic sensor is analysed for frequency by KS-1000 algorithm. Then, based on the result values of analysis skilled expert makes a judgment about whether motor system is the abnormality or degradation state. But the expert system such a motor fault diagnosis is very difficult to bring the expectable results by mathematical modeling due to the complexity of judgment process. In this reason, we propose an automation system using fuzzy model based on genetic algorithm(GA) that builded a qualitative model of a system without priori knowledge about a system provided numerical input output data.

• 한국산학기술학회논문지
• /
• 제20권9호
• /
• pp.551-557
• /
• 2019

생산 공정에서 발생하는 비정상적인 이상 (fault)의 진단 (diagnosis)은 고품질의 제품을 생산함에 있어 필수적이라 할 수 있다. 회분식 공정 (batch process)과 같이 부가가치가 큰 반도체나 의약품 등의 첨단 제품을 생산하는 공정에서는 더욱 실시간 진단의 역할이 커지고 있다. 본 연구에서는 회분식 공정으로부터 얻은 측정 데이터와 비선형 분류(nonlinear classification)에 기초한 실시간 이상 진단 체계에 있어서 변수선택과 미래값 추정 기법이 진단 성능에 미치는 영향을 평가한다. 공정 변수 중 진단에 필수적이며 기여도가 높은 변수만을 선택하여 진단 모델 (diagnosis model)을 구성함으로써 진단 성능의 향상을 기대할 수 있다. 본 연구에서는 여러 변수선택 (variable selection) 기법들의 진단 성능을 비교 평가한다. 또한, 현재 진행 중인 회분식 조업 데이터는 종료되기 이전에는 진단에 필요한 전체 데이터를 얻을 수 없으므로 현재 시점에서 측정되지 못한 미래 측정값 (future observations)이 추정되어야 한다. 미래값 추정방법들의 선택이 변수선택과 분류기반 진단 관점에서 진단 성능에 어떻게 영향을 주는지 평가한다. 폴리염화비닐 회분식 공정에 대한 사례 연구를 수행하여 최적의 변수선택과 미래값 추정방법을 도출하였다. 변수선택 방법에 따라 최대 21.9%와 13.3%의 성능 향상을 보였으며 미래값 추정방법에 따라서는 최대 25.8%와 15.2% 향상됨을 알 수 있었다.

• 청정기술
• /
• 제9권2호
• /
• pp.63-69
• /
• 2003

도금산업은 제조 공정상 다량의 환경오염물질을 배출하는데 일반적으로 산 알칼리 폐수 뿐만아니라 크롬화합물, 시안화합물, 중금속류, 부식성물질, 독성물질 등이 발생하여 환경오염을 초래한다. 본 연구에서는 도금 산업에서 가장 환경오염부하가 크고 많이 적용하는 아연도금공정의 공정진단 및 분석을 통해 아연도금공정의 청정생산 실행효과가 큰 우선순위별 단위공정에 최적기술을 적용하여 현 도금공장의 열악한 근무환경과 환경오염을 개선하고자 하였다.

• 품질경영학회지
• /
• 제49권3호
• /
• pp.327-340
• /
• 2021

Purpose: The purpose of this study is to propose a system predicting whether an electricity distribution system is abnormal by analyzing the temperature of the deteriorated system. Traditional electricity distribution system abnormality diagnosis was mainly limited to post-inspection. This research presents a remote monitoring system for detecting thermal images of the deteriorated electricity distribution system efficiently hereby providing safe and efficient abnormal diagnosis to electricians. Methods: In this study, an object detection algorithm (YOLOv5) is performed using 16,866 thermal images of electricity distribution systems provided by KEPCO(Korea Electric Power Corporation). Abnormality/Normality of the extracted system images from the algorithm are classified via the limit temperature. Each classification model, Random Forest, Support Vector Machine, XGBOOST is performed to explore 463,053 temperature datasets. The process capability index is employed to indicate the quality of the electricity distribution system. Results: This research performs case study with transformers representing the electricity distribution systems. The case study shows the following states: accuracy 100%, precision 100%, recall 100%, F1-score 100%. Also the case study shows the process capability index of the transformers with the following states: steady state 99.47%, caution state 0.16%, and risk state 0.37%. Conclusion: The sum of caution and risk state is 0.53%, which is higher than the actual failure rate. Also most transformer abnormalities can be detected through this monitoring system.

• 전자공학회논문지B
• /
• 제32B권12호
• /
• pp.1545-1551
• /
• 1995

As the modern industrial processes become more complex, it is getting more difficult to model and control the processes. Naturally, an advanced type of DCS(Distributed Control System) with higher level functions is being sought. Advanced DCS is a DCS with advanced functions such as fault diagnosis, GPC(Generalized Predictive Control), NN(Neural Network), and Fuzzy Control. In this thesis, we have studied a fuzzy control algorithm for realizing an advanced DCS. Its algorithm is implemented in a form of function code which is a process control language, being used by the industrial engineers. To verify the realized function code of the fuzzy control, the function code is applied to a continuous casting process of the Pohang Iron & Steel Works in Kwangyang. The rules of the fuzzy control were collected via interviews of the field operators and their operation documents. Finally under a real-time operating system environment, usability of the function code of the fuzzy control is shown via simulation for the continuous casting process.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 B
• /
• pp.988-990
• /
• 1999

Using neural network approach, the diagnosis of faults in industrial process that requires observing multiple data simultaneously are studied in this paper. Two-stage diagnosis is proposed as the basic structure. The first stage detects the dynamic trend of each measurements and the second stage diagnosis the faults. This paper makes up for the disadvantage of neural about unknown faults. The potential of this approach is demonstrated in simulation using a model of tank reactor.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2004년도 ICEIC The International Conference on Electronics Informations and Communications
• /
• pp.371-375
• /
• 2004

Fault diagnosis is one of the most studied problems in process engineering. Recently, great research interest has been devoted to approaches that use classification methods to detect faults. This paper presents an application of a newly developed classification method - support vector machines - for fault diagnosis in an industrial case. A real set of operation data of a motor pump was used to train and test the support vector machines. The experiment results show that the support vector machines give higher correct detection rate of faults in comparison to rule-based diagnostics. In addition, the studied method can work with fewer training instances, what is important for online diagnostics.