• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1988년도 한국자동제어학술회의논문집(국내학술편); 한국전력공사연수원, 서울; 21-22 Oct. 1988
• /
• pp.197-201
• /
• 1988

A reliable Analytical Redundancy(AR) based Fault Detection Scheme(FDS) that can detect, discriminate sensor fault and process fault is presented. And a Fault Tolerant Control System ( FTCS ) with the FDS that performs original control objective without considerable loss of control performance in the face of sensor/process faults is constructed. These propositions are valuable in the sense that it resolves the well known sensitivity problem and that sensor/process faults can be detected, discriminated so that effects of any fault can be promptly accomodated by reconfiguring control system structure automatically.

• 제어로봇시스템학회논문지
• /
• 제7권6호
• /
• pp.494-501
• /
• 2001

In this paper an ANFIS(Adativo Neuro-Fuzzy Inference System)- based fault detection and diagnosis for a closed loop control system is proposed. The proposed diagnostic system contains two ANFIS. One is run as a parallel model within the model in closed loop control(MCL) and the other is run as a series-parallel model within the process in closed loop(PCL) for the generation of relevant symptoms for fault diagnosis. These symptoms are further processed by another classification logic with simple rules and neural network for process and controller fault diagnosis. Experimental results for a DC shunt motor control system illustrate the effectiveness of the proposed diagnostic scheme.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2006년도 춘계종합학술대회
• /
• pp.247-250
• /
• 2006

현재 고밀도 반도체제작 환경에서는 Reactive ion Etching (RIE) 과정에서의 생산성을 극대화하기 위해서 비이상적인 공정장비를 발견하는 것이 매우 중요하다. 생산과정에서 오류발견의 중요성을 설명하기 위해 Support Vector Machine (SVM)은 실시간으로 공정오류에 대한 판단에 대한 도움을 주기 위해 사용되었다. baseline run으로부터 얻은 데이터로 SVM 모델을 구성하고 정상인 run 데이터와 비정상 run 데이터로 SVM 모델을 검증한다. 통계적 공정제어에서 흔히 이용되는 control limits를 도입하여 정상데이터가 내재하고 있는 램덤 변화율이 반영된 SVM 모델 기반의 control limits를 수립하고, 그 control limits를 바탕으로 오류발견을 실행한다. SVM을 이용함으로써 RIE의 오류발견은 run to run 기반에 정상인 run데이터는 0% 오류율이 증명되었다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제9권2호
• /
• pp.20-26
• /
• 2017

Process control is crucial in many industries, especially in semiconductor manufacturing. In such large-volume multistage manufacturing systems, a product has to go through a very large number of processing steps with reentrant) before being completed. This manufacturing system has many machines of different types for processing a high mix of products. Each process step has specific quality standards and most of them have nonlinear dynamics due to physical and/or chemical reactions. Moreover, many of the processing steps suffer from drift or disturbance. To assure high stability and yield, on-line quality monitoring of the wafers is required. In this paper we develop a real-time fault detection system on semiconductor manufacturing process. Proposed system is superior to other incremental fault detection system and shows similar performance compared to batch way.

• 전기학회논문지P
• /
• 제58권2호
• /
• pp.136-141
• /
• 2009

An AC generator is an important components in producing a electric power and so it requires highly reliable protection relays to minimize the possibility of demage occurring under fault conditions. Conventionally, a DFT based RDR has been used for protecting the generator stator winding. However, when DFTs based on Fourier analysis are used, it has been pointed out that defects can occur during the process of transforming a time domain signal into a frequency domain one which can lead to loss of time domain information. This paper proposes the internal fault detection and fault type discrimination for the stator winding by applying the detailed coefficients by Daubechies Wavelet Transform to overcome the defects in the DFT process. For the case studies reported in the paper, a model system was established for the simulations utilizing the ATP, and this verified the effectiveness of the proposed technique through various off-line tests carried out on the collected data. The propose method is shown to be able to rapidly identify internal fault and did not operate a miss-operation for all the external fault tested.

• 반도체디스플레이기술학회지
• /
• 제19권4호
• /
• pp.121-125
• /
• 2020

With miniaturization of semiconductor, the manufacturing process become more complex, and undetected small changes in the state of the equipment have unexpectedly changed the process results. Fault detection classification (FDC) system that conducts more active data analysis is feasible to achieve more precise manufacturing process control with advanced machine learning method. However, applying machine learning, especially in supervised learning criteria, requires an arduous data labeling process for the construction of machine learning data. In this paper, we propose a semi-supervised learning to minimize the data labeling work for the data preprocessing. We employed equipment status variable identification (SVID) data and optical emission spectroscopy data (OES) in silicon etch with SF6/O2/Ar gas mixture, and the result shows as high as 95.2% of labeling accuracy with the suggested semi-supervised learning algorithm.

• Korean Chemical Engineering Research
• /
• 제58권3호
• /
• pp.408-415
• /
• 2020

본 연구에서는 auto-encoder와 self-organizing map을 결합한 auto-encoder with self-organizing map(AE-SOM) 기법을 이용하여 EVA 생산공정의 이상을 검출 및 진단하였고, Granger의 인과분석을 통해 이상 검출 데이터의 이상 전파 방향을 확인하였다. 분석 데이터는 1년 7개월 간의 조업데이터를 이용하였으며, autoclave 반응기의 조업 변수를 주로 분석하였다. 데이터 전처리 과정에서 데이터의 표준화를 먼저 진행하고, 조업의 각 grade의 sample 수를 동일하게 200개 임의로 추출하였다. 이후 AE-SOM을 적용하여 각 grade의 best matching unit (BMU)를 도출하였다. 각각의 BMU를 기준으로 조업 데이터가 얼마나 벗어났는지를 기준으로 데이터의 이상을 판별하였다. 공정 이상이 발견될 시 이상원인을 contribution plot을 이용하여 확인하였고 이상원인 변수의 인과성을 Granger의 인과분석을 통해 분석하였다. 그 결과 조업 시 발생한 2번의 셧다운의 전조를 모두 검출하였으며 이상이 발생한 원인변수에서 기인한 공정 이상의 전파 방향을 분석하였다.

• 제어로봇시스템학회논문지
• /
• 제6권12호
• /
• pp.1113-1119
• /
• 2000

To operate a process plant safely and economically, process monitoring is very important. Process monitoring is the task to identify the state of the system from sensor data. Process monitoring includes data acquisition, regulatory control, data reconciliation, fault detection, etc. This research focuses on the data recon-ciliation using scale-space filtering and fault detection using functional-link associative neural networks. Scale-space filtering is a multi-resolution signal analysis method. Scale-space filtering can extract highest frequency factors(noise) effectively. But scale-space filtering has too large calculation costs and end effect problems. This research reduces the calculation cost of scale-space filtering by applying the minimum limit to the gaussian kernel. And the end-effect that occurs at the end of the signal of the scale-space filtering is overcome by using extrapolation related with the clustering change detection method. Nonlinear principal component analysis methods using neural network have been reviewed and the separately expanded functional-link associative neural network is proposed for chemical process monitoring. The separately expanded functional-link associative neural network has better learning capabilities, generalization abilities and short learning time than the exiting-neural networks. Separately expanded functional-link associative neural network can express a statistical model similar to real process by expanding the input data separately. Combining the proposed methods-modified scale-space filtering and fault detection method using the separately expanded functional-link associative neural network-a process monitoring system is proposed in this research. the usefulness of the proposed method is proven by its application a boiler water supply unit.

• International Journal of Reliability and Applications
• /
• 제4권1호
• /
• pp.1-12
• /
• 2003

Many software reliability growth models (SRGM's) based on a nonhomogeneous Poisson process (NHPP) have been proposed by many researchers. Most of the SRGM's which have been proposed up to the present treat the event of software fault-detection in the testing and operational phases as a counting process. However, if the size of the software system is large, the number of software faults detected during the testing phase becomes large, and the change of the number of faults which are detected and removed through debugging activities becomes sufficiently small compared with the initial fault content at the beginning of the testing phase. Therefore, in such a situation, we can model the software fault-detection process as a stochastic process with a continuous state space. In this paper, we propose a new software reliability growth model describing the fault-detection process by applying a mathematical technique of stochastic differential equations of an Ito type. We also compare our model with the existing SRGM's in terms of goodness-of-fit for actual data sets.

• 전기학회논문지
• /
• 제62권7호
• /
• pp.994-1002
• /
• 2013

This study suggests a generalized availability and safety evaluation model to evaluate the influences to the system's fault tolerant capabilities depending on automatic fault detection function such as the automatic periodic testings. The conventional evaluation model of automatic fault detection function deals only with the self diagnostics, and supposes that the fault detection coverage of self diagnostics is always constant. But all of the fault detection methods could be degraded. For example, the periodic surveillance test has the potential human errors or test equipment errors, the self diagnostics has the potential degradation of built-in logics, and the automatic periodic testing has the potential degradation of automatic test facilities. The suggested evaluation models have incorporated the loss or erroneous behaviors of the automatic fault detection methods. The availability and the safety of each module of the safety grade platform have been evaluated as they were applied the automatic periodic test methodology and the fault tolerant evaluation models. The availability and safety of the safety grade platform were improved when applied the automatic periodic testing. Especially the fault tolerant capability of the processor module with a weak self-diagnostics and the process parameter input modules were dramatically improved compared to the conventional cases. In addition, as a result of the safety evaluation of the digital reactor protection system, the system safety of the digital parts was improved about 4 times compared to the conventional cases.