• 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.

• 대한전기학회논문지:전력기술부문A
• /
• 제50권3호
• /
• pp.105-111
• /
• 2001

The research presented in this paper focuses on a method for the detection of High Impedance Fault(HIF). The method will use the wavelet transform and neural network system. HIF on the multi-grounded three-phase four-wires primary distribution power system cannot be detected effectively by existing over current sensing devices. These paper describes the application of discrete wavelet transform to the various HIF data. These data were measured in actual 22-9kV distribution system. Wavelet transform analysis gives the frequency and time-scale information. The neural network system as a fault detector was trained to discriminate HIF from the normal status by a gradient descent method. The proposed method performed very well by proving the right state when it was applied staged fault data and normal load mimics HIF, such as arc-welder.

• International Journal of Control, Automation, and Systems
• /
• 제5권4호
• /
• pp.410-418
• /
• 2007

For the purpose of fault detection of the primary control surface, real-time estimation of the longitudinal stability and control derivatives of the DURUMI-II using the flight data is considered in this paper. The DURUM-II, a research UAV developed by KARI, is designed to have split control surfaces for the redundancy and to guarantee safety during the fault mode flight test. For fault mode analysis, the right elevator was deliberately fixed to the specified deflection condition. This study also mentions how to implement the multi-step control input efficiently, and how to switch between the normal mode and the fault mode during the flight test. As a realtime parameter estimation technique, Fourier transform regression method was used and the estimated data was compared with the results of the analytical method and the other available method. The aerodynamic derivatives estimated from the normal mode flight data and the fault mode data are compared and the possibility to detect the elevator fault by monitoring the control derivative estimated in real time by the computer onboard was discussed.

• 제어로봇시스템학회논문지
• /
• 제9권11호
• /
• pp.874-882
• /
• 2003

The condition assessment of engineering systems has increased in importance because the manpower needed to operate and supervise various plants has been reduced. Especially, induction motors are at the core of most engineering processes, and there is an indispensable need to monitor their health and performance. So detection and diagnosis of motor faults is a base to improve efficiency of the industrial plant. In this paper, a model-based fault detection system is developed for induction motors, using steady state vibration signals. Early various fault detection systems using vibration signals are a trivial method and those methods are prone to have missed fault or false alarms. The suggested motor fault detection system was developed using a model-based reference value. The stationary signal had been extracted from the non-stationary signal using a data segmentation method. The signal processing method applied in this research is FFT. A reference model with spectra signal is developed and then the residuals of the vibration signal are generated. The ratio of RMS values of vibration residuals is proposed as a fault indicator for detecting faults. The developed fault detection system is tested on 800 hp motor and it is shown to be effective for detecting faults in the air-gap eccentricities and broken rotor bars. The suggested system is shown to be effective for reducing missed faults and false alarms. Moreover, the suggested system has advantages in the automation of fault detection algorithms in a random signal system, and the reference model is not complicated.

• 자동차안전학회지
• /
• 제11권2호
• /
• pp.11-16
• /
• 2019

This paper suggests an algorithm for detecting fault of longitudinal controller in autonomous vehicles. Guaranteeing safety in fault situation is essential because electronic devices in vehicle are dependent each other. Several methods like alarm to driver, ceding control to driver, and emergency stop are considered to cope with fault. This research investigates the fault monitoring process in fail-safe system, for controller which is responsible for accelerating and decelerating control in vehicle. Residual is computed using desired acceleration control command and actual acceleration, and detection of its abnormal increase leads to the decision that system has fault. Before computing residual for controller, health monitoring process of acceleration signal is performed using hardware and analytic redundancy. In fault monitoring process for controller, a process model which is fitted using driving data is considered to improve the performance. This algorithm is simulated via MATLAB tool to verify performance.

• 한국정보통신학회논문지
• /
• 제10권5호
• /
• pp.962-969
• /
• 2006

현재 고밀도 반도체제작 환경에서는 반작용적인 이온 식각 과정(reactive ion etching)에서의 생산성을 극대화하기 위해서 비정상적인 공정장비를 발견하는 것이 매우 중요하다. 생산과정에서 오류발견의 중요성을 설명하기 위해 Support Vector Machine (SVM)은 실시간으로 공정오류에 대한 판단을 위해 사용되었다. 반작용적인 이온 식각도구 데이터는 59개 변수들로 구성된 반도체 공정장비로부터 얻는다. 각각의 변수들은 초당 10개의 데이터로 구성되어있다. 식각 런의 11개의 파라미터에 대한 모델을 만들기 위해 baseline런으로부터 얻은 데이터로 SVM모델을 구성하고 정상 런데이터와 비정상 런데이터로 SVM모델을 검증한다. 통계적 공정제어에서 흔히 이용되는 관리한계를 도입하여 정상데이터가 내재하고 있는 램덤변화율이 반영된 SVM 모델 기반의 관리 한계를 수립하고, 그 관리 한계를 바탕으로 오류발견을 실행한다. SVM을 이용함으로써 RIE의 오류발견은 run to run 기반에 정상 런데이터는 0% 오류율이 증명되었다.

• 한국지능시스템학회논문지
• /
• 제9권4호
• /
• pp.426-435
• /
• 1999

A high impedance fault(HIF) is one of the serious problems facing the electric utility industry today. Because of the high impedance of a downed conductor under some conditions these faults are not easily detected by over-current based protection devices and can cause fires and personal hazard. In this paper a new method for detection of HIF which uses adaptive neuro-fuzzy inference system (ANFIS) is proposed. Since arcing fault current shows different changes during high and low voltage portion of conductor voltage waveform we firstly divided one cycle of fault current into equal spanned four data windows according to the mangnitude of conductor voltage. Fast fourier transform(FFT) is applied to each data window and the frequency spectrum of current waveform are chosen asinputs of ANFIS after input selection method is preprocessed. Using staged fault and normal data ANFIS is trained to discriminate between normal and HIF status by hybrid learning algorithm. This algorithm adapted gradient descent and least square method and shows rapid convergence speed and improved convergence error. The proposed method represent good performance when applied to staged fault data and HIFLL(high impedance like load)such as arc-welder.

• Journal of Information Processing Systems
• /
• 제10권3호
• /
• pp.429-442
• /
• 2014

In this paper, we investigated the use of seasonal autoregressive integrated moving average (SARIMA) time series models for fault detection in semiconductor etch equipment data. The derivative dynamic time warping algorithm was employed for the synchronization of data. The models were generated using a set of data from healthy runs, and the established models were compared with the experimental runs to find the faulty runs. It has been shown that the SARIMA modeling for this data can detect faults in the etch tool data from the semiconductor industry with an accuracy of 80% and 90% using the parameter-wise error computation and the step-wise error computation, respectively. We found that SARIMA is useful to detect incipient faults in semiconductor fabrication.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.2335-2339
• /
• 2003

To prevent the critical situation due to the fault in the aircraft sensor system, the fault tolerant system with triple or quadruple redundancy can be made. However, if the faults are occurred in two or more than sensors simultaneously, the conventional fault detection process, such as cross-channel monitoring, may give the wrong fault alarm. For this case, we can detect the fault by estimating the state vector based on the system dynamics model, which is nonlinear for aircraft. In this paper, we propose the unscented Kalman filter to estimate the nonlinear state vector. This filter utilizes the so-called unscented transformation of sigma points featured the statistical characteristics of the random variable. For verification, we perform the simulations for F-16 aircraft with accelerometers, gyros, GPS and air data system.

• Nuclear Engineering and Technology
• /
• 제55권3호
• /
• pp.814-826
• /
• 2023

Sensor faults in nuclear power plant instrumentation have the potential to spread negative effects from wrong signals that can cause an accident misdiagnosis by plant operators. To detect sensor faults and make accurate accident diagnoses, prior studies have developed a supervised learning-based sensor fault detection model and an accident diagnosis model with faulty sensor isolation. Even though the developed neural network models demonstrated satisfactory performance, their diagnosis performance should be reevaluated considering real-time connection. When operating in real-time, the diagnosis model is expected to indiscriminately accept fault data before receiving delayed fault information transferred from the previous fault detection model. The uncertainty of neural networks can also have a significant impact following the sensor fault features. In the present work, a pilot study was conducted to connect two models and observe actual outcomes from a real-time application with an integrated system. While the initial results showed an overall successful diagnosis, some issues were observed. To recover the diagnosis performance degradations, additive logics were applied to minimize the diagnosis failures that were not observed in the previous validations of the separate models. The results of a case study were then analyzed in terms of the real-time diagnosis outputs that plant operators would actually face in an emergency situation.