• Proceedings of the Korean Vacuum Society Conference
• /
• 2011.02a
• /
• pp.36-36
• /
• 2011

반도체 공정 신호는 주기 신호와 비주기 신호로 구분된다. 특정 패턴을 가지는 주기 신호는 해당 파라미터(parameter)에 대해서 패턴 매칭을 수행하여 관리하는 연구가 진행되고 있다. 반면 비주기 신호 데이터의 경우에는 패턴 매칭 방법을 수행할 수 없다. 또한 반도체 공정에서 얻을 수 있는 두 개 타입의 데이터는 그 파라미터가 방대하기 때문에 현재 실제 공정에 적용되고 있는 방식인 각각 하나의 파라미터에 대해 관리도(control chart)를 구성해 관리하는 것은 많은 비용과 시간의 낭비를 초래한다. 따라서 두 타입 데이터의 여러 개의 파라미터를 동시에 관측할 수 있고 파라미터간의 내재된 상관관계를 고려할 수 있는 장점을 가진 분석 기법에 대한 연구가 필요하다. 주기 신호의 이상탐지를 위한 기존 연구는 신호를 구간으로 나누어 구간별로 SPC 차트적용 시키는 방법, 각 시점 마다 측정되는 값을 하나의 변수로 고려하여 Hotelling's T square, PCA, PLS 등과 같은 다변량 통계 분석을 적용 시키는 방법들이 제시되어 왔다. 이러한 방법들은 다양한 특성을 가지는 주기신호를 분석하고 이상을 탐지 하는데 많은 한계점을 가진다. 이에 본 논문은 다양한 형태를 가지는 신호의 특성을 반영하여 자기구상지도를 기반으로 신호의 분류와 공정의 이상을 탐지하는 기법을 제안한다. 제안하는 기법은 자기구상지도를 이용하여 복잡한(고차원, 시계열) 신호를 2차원 상의 노드로 맵핑시킴으로써 신호의 특질(feature)을 추출하고 새로 표현된 신호의 특질을 기반으로 Logistic regression을 적용시켜 이상을 탐지 한다. 다양한 이상 상황을 가진 반도체 공정 신호를 사용하여 제안한 이상탐지 성능을 평가하였다.

• Journal of the Korea Society for Simulation
• /
• v.20 no.4
• /
• pp.67-79
• /
• 2011

The statistical process control (SPC) assumes that observations follow the particular statistical distribution and they are independent to each other. However, the time-series data do not always follow the particular distribution, and most of cases are autocorrelated, therefore, it has limit to adopt the general SPC in tim series process. In this study, we propose a MPBC (Model Parameter Based Control-chart) method for fault detection in time-series processes. The MPBC builds up the process as a time-series model, and it can determine the faults by detecting changes parameters in the model. The process we analyze in the study assumes that the data follow the ARMA (p,q) model. The MPBC estimates model parameters using RLS (Recursive Least Square), and $K^2$-control chart is used for detecting out-of control process. The results of simulations support the idea that our proposed method performs better in time-series process.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.5
• /
• pp.841-852
• /
• 2010

An integrated process control (IPC) procedure is a scheme which simultaneously applies the engineering control procedure (EPC) and statistical control procedure (SPC) techniques to reduce the variation of a process. In the IPC procedure, the observed deviations are monitored during the process where adjustments are repeatedly done by its controller. Because the effects of the noise, the special cause, and the adjustment are mixed, the use and properties of the SPC procedure for the out-of-control process are complicated. This paper considers efficiency of EWMA charts for detecting special causes in an ARMA(1,1) noise model with a minimum mean squared error adjustment policy. And we propose the readjustment procedure after having a true signal. This procedure can be considered when the elimination of the special cause is not practically possible.

• The Korean Journal of Applied Statistics
• /
• v.34 no.1
• /
• pp.99-114
• /
• 2021

With the Fourth Industrial Revolution based on new technology, the semiconductor manufacturing industry researches various analysis methods such as detecting process abnormalities and predicting yield based on equipment sensor data generated in the manufacturing process. The semiconductor manufacturing process consists of hundreds of processes and thousands of measurement processes associated with them, each of which has properties that cannot be defined by chemical or physical equations. In the individual measurement process, the actual measurement ratio does not exceed 0.1% to 5% of the target product, and it cannot be kept constant for each measurement point. For this reason, efforts are being made to determine whether to manage by using equipment sensor data that can indirectly determine the normal state of each step of the process. In this study, the Functional Data Analysis (FDA) was proposed to define a process abnormality detection process based on equipment sensor data and compensate for the disadvantages of the currently applied statistics-based diagnosis method. Anomaly detection accuracy was compared using machine learning on actual field case data, and its effectiveness was verified.

• Journal of the Korea Society for Simulation
• /
• v.21 no.2
• /
• pp.79-90
• /
• 2012

In this paper, a feature signal extraction method is proposed in order to enhance the low performance of fault detection caused by unbalanced data which denotes the situations when severe disparity exists between the numbers of class instances. Most of the cyclic signals gathered during the process are recognized as normal, while only a few signals are regarded as fault; the majorities of cyclic signals data are unbalanced data. SOM(Self-Organizing Map)-based feature signal extraction method is considered to fix the adverse effects caused by unbalanced data. The weight neurons, mapped to the every node of SOM grid, are extracted as the feature signals of both class data which are used as a reference data set for fault detection. kNN(k-Nearest Neighbor) and SVM(Support Vector Machine) are considered to make fault detection models with comparisons to Hotelling's $T^2$ Control Chart, the most widely used method for fault detection. Experiments are conducted by using simulated process signals which resembles the frequent cyclic signals in semiconductor manufacturing.

• Proceedings of the Korean Statistical Society Conference
• /
• 2003.10a
• /
• pp.281-283
• /
• 2003

시계열 모형을 따르는 자료의 예측(Forecasting)이나 공정조정(Process Adjustment)의 경우, 자료의 마지막 부분에 발생한 이상치(Outlier)에 의해 크게 영향 받을 수 있다. 그러나 지금까지 제안된 이상치 탐지 방법은 주로 자료의 중간 부분에 발생한 이상치를 검출하는데 효율적이라고 알려져 왔다. 본 연구에서는 자료의 마지막 부분에 발생한 이상치에 대한 기존 탐지 방법의 검출력을 모의 실험을 통해 분석하였다 또한, 이를 개선할 수 있는 방안을 제시하고, 모의 실험을 통해 기존의 검출력과 비교하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.283-285
• /
• 2023

이상 탐지는 데이터에서 일반적인 범주에서 크게 벗어나는 인스턴스 또는 패턴을 식별하는 중요한 작업이다. 본 연구에서는 시계열 데이터의 특징 추출을 위한 비지도 학습 기반 방법과 정규화 흐름의 결합을 통한 이상 탐지 프레임워크를 제안한다. 특징 추출기는 1차원 합성곱 신경망 기반의 오토인코더로 구성되며, 정상적인 시퀀스로만 구성된 훈련 데이터를 압축하고 복원하는 과정을 통해 최적화된다. 추출된 시계열 데이터의 특징 맵은 가능도를 최대화하도록 훈련된 정규화 흐름의 입력으로 사용된다. 이와 같은 방식으로 훈련된 이상 탐지 시스템은 테스트 샘플에 대한 이상치를 계산하며, 최종적으로 임계값과의 비교를 통해 이상 여부를 예측한다. 성능 평가를 위해 시계열 이상 탐지를 위한 공개 데이터셋을 이용하여 공정하게 이상 탐지 성능을 비교하였으며, 실험 결과는 제안하는 정규화 흐름 기법이 시계열 이상 탐지 시스템에 활용될수 있는 잠재성을 시사한다.

• Communications for Statistical Applications and Methods
• /
• v.16 no.3
• /
• pp.429-436
• /
• 2009

This paper considers the integrated process control procedure for detecting special causes in an IMA(1,1) process that is being adjusted automatically after each observation using a minimum mean squared error adjustment policy. When the control chart signals after the occurrence of a special cause, the special cause will be detected and eliminated from the process by the rectifying action. However, when the elimination of the special cause costs high or is not practically possible, an alternative action is to readjust the process with appropriately modified adjustment scheme. In this paper, we propose the readjustment procedure after having a true signal, and show that the use of the readjustment can reduce the deviation of a process from the target.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.6
• /
• pp.1123-1135
• /
• 2011

This paper considers the multivariate integrated process control procedure for detecting special causes in a multivariate IMA(1, 1) process. When the multivariate control chart signals, the special cause will be detected and eliminated from the process. However, when the elimination of the special cause costs high or is not practically possible, an alternative action is to readjust the process with approximately modified adjustment scheme. In this paper, we propose the readjustment procedure after having a true signal, and show that the use of the readjustment can reduce the deviation of a process from the target.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.11
• /
• pp.806-818
• /
• 2009

Since the invention of the integrated circuit (IC) in 1950s, semiconductor technology has undergone dramatic development up to these days. A complete semiconductor is manufactured through a diversity of processes. For better semiconductor productivity, fault detection and classification (FDC) has been rigorously studied for finding faults even before the processes are completed. For FDC, various kinds of sensors are attached in many semiconductor manufacturing devices, and sensor values are collected in a periodic manner. The collection of sensor values consists of sequences of real numbers, and hence is regarded as a kind of time-series data. In this paper, we propose an algorithm for detecting and clustering faults in semiconductor processes. The proposed algorithm is a modification of the existing anomaly detection algorithm dealing with symbolically-represented time-series. The contributions of this paper are: (1) showing that a modification of the existing anomaly detection algorithm dealing with general time-series could be used for semiconductor process data and (2) presenting experimental results for improving correctness of fault detection and clustering. As a result of our experiment, the proposed algorithm caused neither false positive nor false negative.