• Journal of Information Processing Systems
• /
• 제8권2호
• /
• pp.213-240
• /
• 2012

Safety critical systems, real time systems, and event-based systems have a complex set of events and their own interdependency, which makes them difficult to test ma Safety critic Safety critical systems, real time systems, and event-based systems have a complex set of events and their own interdependency, which makes them difficult to test manually. In order to cut down on costs, save time, and increase reliability, the model based testing approach is the best solution. Such an approach does not require applications or codes prior to generating test cases, so it leads to the early detection of faults, which helps in reducing the development time. Several model-based testing approaches have used different UML models but very few works have been reported to show the generation of test cases that use events. Test cases that use events are an apt choice for these types of systems. However, these works have considered events that happen at a user interface level in a system while other events that happen in a system are not considered. Such works have limited applications in testing the GUI of a system. In this paper, a novel model-based testing approach is presented using business events, state events, and control events that have been captured directly from requirement specifications. The proposed approach documents events in event templates and then builds an event-flow model and a fault model for a system. Test coverage criterion and an algorithm are designed using these models to generate event sequence based test scenarios and test cases. Unlike other event based approaches, our approach is able to detect the proposed faults in a system. A prototype tool is developed to automate and evaluate the applicability of the entire process. Results have shown that the proposed approach and supportive tool is able to successfully derive test scenarios and test cases from the requirement specifications of safety critical systems, real time systems, and event based systems.

• 한국소음진동공학회논문집
• /
• 제21권2호
• /
• pp.146-153
• /
• 2011

Model based machine condition diagnosis methods are generally using a normal and many failure models which need sufficient data to train the models. However, data, especially for failure modes of interest, is very hard to get in real applications. So their industrial applications are either severely limited or impossible when the failure models cannot be trained. In this paper, continuous hidden Markov model(CHMM) with only a normal model has been suggested as a very promising machine condition diagnosis method which can be easily used for industrial applications. Generally hidden Markov model also uses many pattern models to recognize specific patterns and the recognition results of CHMM show the likelihood trend of models. By observing this likelihood trend of a normal model, it is possible to detect failures. This method has been successively applied to arc weld defect diagnosis. The result shows CHMM's big potential as a machine condition monitoring method.

• 한국지능시스템학회논문지
• /
• 제10권2호
• /
• pp.94-102
• /
• 2000

본 논문에서는 미지의 비선형 계통에 대한 동적 퍼지모델 기반 고장 검출 및 진단(FDI) 계통 설계 기법을 제시한다. 비선형 계통에 대한 일반적인 모델 기반 FDI 계통에서는 선형화된 모델을 이용하고 있다 이러한 방법은 계통에 대한 정확한 수학적 모델을 요구하게 되어 복잡한 비선형 계통에의 적용시 많은 어려움이 있다 제안되는 FDI계통에서는 미지의 비선형 계통을 다수의 선형 모델을 갖는 동적 퍼지모델 형태로 식별한다. 잔차벡터는 온라인 알고리즘에 의해 추정되는 파라미터의 변동치와 비선형 계통의 동작 영역을 나타내는 퍼지 규칙들의 소속값들로 구성된다. 계통의 고장 검출 및 진단은 잔차벡터와 고장종류간의 관계를 학습한 신경망 분류기에 의해 수행된다. 제안된 FDI 계통 설계법을 이용하여 2 탱크 계통에 대한 FDI 계통을 설계하고 시뮬레이션 연구를 통하여 그 유용성을 보였다.

• 한국물환경학회지
• /
• 제24권1호
• /
• pp.91-98
• /
• 2008

This work was performed to develop a model possible to predict the influent flow and influent components, which are one of main disturbances causing process problems at the operation of municipal wastewater treatment plant. In this study, artificial neural network (ANN) was used in order to develop a model that was able to predict the influent flow, $COD_{Mn}$, SS, TN 1 day-ahead, 2day-ahead and 3 day ahead. Multi-layer feed-forward back-propagation network was chosen as neural network type, and tanh-sigmoid function was used as activation function to transport signal at the neural network. And Levenberg-Marquart (LM) algorithm was used as learning algorithm to train neural network. Among 420 data sets except missing data, which were collected between 2005 and 2006 at field plant, 210 data sets were used for training, and other 210 data sets were used for validation. As result of it, ANN model for predicting the influent flow and components 1-3day ahead could be developed successfully. It is expected that this developed model can be practically used as follows: Detecting the fault related to effluent concentration that can be happened in the future by combining with other models to predict process performance in advance, and minimization of the process fault through the establishment of various control strategies based on the detection result.

• 한국융합학회논문지
• /
• 제13권3호
• /
• pp.23-31
• /
• 2022

본 연구는 H해운사에서 제공받은 Starcool사의 실제 냉동 컨테이너 운영데이터를 분석하였다. H사의 현장 전문가와 인터뷰를 통해 4가지 고장 알람 중 Critical 및 Fatal Alarm만 고장으로 정의하였고, 냉동 컨테이너 특성상 모든 변수를 사용하는 것은 비용측면에서 비효율을 초래하는 것을 확인하였다. 이에 본 연구는 특성 중요도 및 PCA 기법을 통한 냉동 컨테이너 고장 탐지 방법을 제시한다. 모델의 성능 향상을 위해 XGBoost, LGBoost 등과 같은 트리계열 모델을 통해 변수 중요도(Feature Importance)를 기반으로 변수 선택(Feature selcetion)을 하고 선택되지 않은 변수는 PCA를 사용하여 전체 변수의 차원을 축소시켜 각 모델별로 지도학습을 수행한다. 부스팅 기반의 XGBoost, LGBoost 기법은 본 연구에서 제안하는 모델의 결과가 62개의 모든 변수를 사용한 지도 학습의 결과보다 재현율(Recall)이 각각 0.36, 0.39씩 향상되는 되는 결과를 보였다.

• 한국정밀공학회지
• /
• 제18권3호
• /
• pp.68-74
• /
• 2001

A lane detection based on a road model or feature all needs correct acquirement of information on the lane in an image. It is inefficient to implement a lane detection algorithm through the full range of an image when it is applied to a real road in real time because of the calculating time. This paper defines two (other proper terms including"modes") for detecting lanes on a road. First is searching mode that is searching the lane without any prior information of a road. Second is recognition mode, which is able to reduce the size and change the position of a searching range by predicting the position of a lane through the acquired information in a previous frame. It allows to extract accurately and efficiently the edge candidate points of a lane without any unnecessary searching. By means of inverse perspective transform which removes the perspective effect on the edge candidate points, we transform the edge candidate information in the Image Coordinate System(ICS) into the plan-view image in the World Coordinate System(WCS). We define a linear approximation filter and remove faulty edge candidate points by using it. This paper aims at approximating more correctly the lane of an actual road by applying the least-mean square method with the fault-removed edge information for curve fitting.e fitting.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2006년도 International Symposium on GPS/GNSS Vol.2
• /
• pp.255-260
• /
• 2006

Safety-critical navigation systems have to provide 'reliable' position solutions, i.e., they must detect and exclude measurement or system faults and estimate the uncertainty of the solution. To obtain more accurate and reliable navigation systems, various filtering methods have been employed to reduce measurement noise level, or integrate sensors, such as global navigation satellite system/inertial navigation system (GNSS/INS) integration. Recently, particle filters have attracted attention, because they can deal with nonlinear/non-Gaussian systems. In most GNSS applications, the GNSS measurement noise is assumed to follow a Gaussian distribution, but this is not true. Therefore, we have proposed a fault detection and exclusion method using particle filters assuming non-Gaussian measurement noise. The performance of our method was contrasted with that of conventional Kalman filter methods with an assumed Gaussian noise. Since the Kalman filters presume that measurement noise follows a Gaussian distribution, they used an overbounded standard deviation to represent the measurement noise distribution, and since the overbound standard deviations were too conservative compared to the actual distributions, this degraded the integrity-monitoring performance of the filters. A simulation was performed to show the improvement in performance of our proposed particle filter method by not using the sigma overbounding. The results show that our method could detect smaller measurement biases and reduced the protection level by 30% versus the Kalman filter method based on an overbound sigma, which motivates us to use an actual noise model instead of the overbounding or improve the overbounding methods.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2017년도 추계학술대회
• /
• pp.103-104
• /
• 2017

영구자석 전동기는 전력 밀도가 높고 효율이 좋은 특징으로 견인, 의료, 군사 분야 등 다양한 산업 분야에서 사용되고 있다. 이러한 분야에서 사용되는 전동기 구동 시스템은 높은 신뢰성이 요구되므로 인버터에서 발생하는 전력 반도체 스위치 고장을 빠르게 감지해야한다. 본 논문에서는 제어기 상전압 지령과 추정된 상전압 사이의 오차를 통해 전력 반도체 개방 고장을 감지하고 진단하는 방법을 제시하였다. 제안된 방법은 추가적인 측정 회로 없이 제어기 내부 값을 사용하여 개방 고장을 감지하고 개방된 스위치를 진단할 수 있다. 특히 부하 변동을 고려한 감지 방법을 제안하여 고장 감지의 신뢰성을 개선한다.

• 한국군사과학기술학회지
• /
• 제8권4호
• /
• pp.24-31
• /
• 2005

This paper presents an implementation of a real-time multi-sensor data fusion algorithm for Flight Test Computer. The sensor data consist of positional information of the target from a radar, a GPS receiver and an INS. The data fusion algorithm is designed by the 21st order distributed Kalman Filter which is based on the PVA model with sensor bias states. A fault detection and correction logics are included in the algorithm for bad measurements and sensor faults. The statistical parameters for the states are obtained from Monte Carlo simulations and covariance analysis using test tracking data. The designed filter is verified by using real data both in post processing and real-time processing.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 춘계학술발표대회
• /
• pp.459-462
• /
• 2021

본 연구는 반도체 제조 공정중 발생하는 센서 데이터를 활용하여 딥러닝기반으로 불량을 예측하는 모델을 제안한다. 반도체 공장에서는 FDC((Fault Detection and Classification)라는 불량을 예측하는 시스템이 있지만, 공정의 복잡도가 높고 센서의 종류가 많아 공정 관리자가 모든 센서의 기준을 설정 및 관리하는데 한계가 있다. 이를 해결하기 위해 공정 설비의 센서 데이터를 딥러닝을 활용하여 학습시켜 센서 기준정보로 임계치를 제공하고, 가공중 발생하는 센서 데이터가 입력되면 정상 여부를 판정하는 모델을 제안한다.