• Journal of the Korean Data and Information Science Society
• /
• 제24권4호
• /
• pp.919-929
• /
• 2013

We compared two basic methods, combine-accumulate method and accumulate-combine method, using the past quality information in multivariate quality control procedure for monitoring mean vector of multivariate normal process. When small or moderate shifts have occurred, accumulate-combine method yields smaller average run length (ARL) and average time to signal (ATS) than combine-accumulate method. On the other hand, we have found from our numerical results that combine-accumulate method has better performances in terms of switching behavior than accumulate-combine method. In industry, a quality engineer could select one of the two method under the comprehensive consideration about the required time to signal, switching behavior, and other physical factors in the production process.

• Journal of the Korean Data and Information Science Society
• /
• 제28권4호
• /
• pp.937-945
• /
• 2017

The purpose of using a control chart is to detect any change that occurs in the process. When control charts are used to monitor processes, we want to identify this changes as quickly as possible. Many problems in quality control involve a vector of observations of several characteristics rather than a single characteristic. Multivariate CUSUM or EWMA charts have been developed to address the problem of monitoring covariance matrix or the joint monitoring of mean vector and covariance matrix. However, control charts tend to work poorly when we use the highly correlatted variables. In order to overcome it, Hawkins (1991) proposed the use of regression adjustment variables. In this paper, to monitor covariance matrix, we investigate the performance of MEWMA-type control charts with and without the use of regression adjusted variables.

• Nuclear Engineering and Technology
• /
• 제48권6호
• /
• pp.1315-1320
• /
• 2016

The present study aims to predict the heat transfer characteristics around a square cylinder with different corner radii using multivariate adaptive regression splines (MARS). Further, the MARS-generated objective function is optimized by particle swarm optimization. The data for the prediction are taken from the recently published article by the present authors [P. Dey, A. Sarkar, A.K. Das, Development of GEP and ANN model to predict the unsteady forced convection over a cylinder, Neural Comput. Appl. (2015) 1-13]. Further, the MARS model is compared with artificial neural network and gene expression programming. It has been found that the MARS model is very efficient in predicting the heat transfer characteristics. It has also been found that MARS is more efficient than artificial neural network and gene expression programming in predicting the forced convection data, and also particle swarm optimization can efficiently optimize the heat transfer rate.

• 한국산업융합학회 논문집
• /
• 제2권2호
• /
• pp.51-59
• /
• 1999

This study aims at the development of the techniques for the rainfall forecasting in river basins by applying neural network theory and compared with results of Multivariate Model (MVM). This study forecasts rainfall and compares with a observed values in the San Chung gauging stations of Nakdong river basin for the rainfall forecasting of river basin by proposed Neural Network Model(NNM). For it, a multi-layer Neural Network is constructed to forecast rainfall. The neural network learns continuous-valued input and output data. The result of rainfall forecasting by the Neural Network Model is superior to the results of Multivariate Model for rainfall forecasting in the river basin. So I think that the Neural Network Model is able to be much more reliable in the rainfall forecasting.

• Communications for Statistical Applications and Methods
• /
• 제24권6호
• /
• pp.641-649
• /
• 2017

Multivariate confidence regions were defined using a chi-square distribution function under a normal assumption and were represented with ellipse and ellipsoid types of bivariate and trivariate normal distribution functions. In this work, an alternative confidence region using the multivariate quantile vectors is proposed to define the normal distribution as well as any other distributions. These lower and upper bounds could be obtained using quantile vectors, and then the appropriate region between two bounds is referred to as the quantile confidence region. It notes that the upper and lower bounds of the bivariate and trivariate quantile confidence regions are represented as a curve and surface shapes, respectively. The quantile confidence region is obtained for various types of distribution functions that are both symmetric and asymmetric distribution functions. Then, its coverage rate is also calculated and compared. Therefore, we conclude that the quantile confidence region will be useful for the analysis of multivariate data, since it is found to have better coverage rates, even for asymmetric distributions.

• 품질경영학회지
• /
• 제39권2호
• /
• pp.234-243
• /
• 2011

Multivariate control charts are widely used to monitor the performance of a multivariate process over time to maintain control of the process. Although existing multivariate control charts provide control limits to monitor the process and detect any extraordinary events, it is a challenge to identify the causes of an out-of-control alarm when the number of process variables is large. Several fault identification methods have been developed to address this issue. However, these methods require a normality assumption of the process data. In the present study, we propose a bootstrapped-based $T^2$ decomposition technique that does not require any distributional assumption. A simulation study was conducted to examine the properties of the proposed fault identification method under various scenarios and compare it with the existing parametric $T^2$ decomposition method. The simulation results showed that the proposed method produced better results than the existing one, especially in nonnormal situations.

• 한국산학기술학회논문지
• /
• 제17권1호
• /
• pp.538-543
• /
• 2016

고품질의 제품과 조업 안전을 확보하기 위해서는 적절한 실시간 공정 감시 및 진단 시스템이 설치되어있는 것이 무엇보다 중요하다. 공정 감시 시스템과 결합된 신뢰도 높은 진단 시스템은 공정에서 발생한 특별한 사건이나 사고의 근본적인 원인과 공정 변수를 알려준다. 본 연구에서는 다변량 통계 분석과 분류기법에 기반한 공정진단 체계를 제시한다. 이 진단시스템은 비선형 데이터 표현과 필터링을 통한 지능적 데이터 표현으로 구성되어 있다. 진단 성능을 평가하기 위해 사례연구를 수행하였으며 다른 방법론과의 결과를 비교하기 위하여 진단 결과와 미래값 추정 방법을 평가하였다. 그 결과 본 연구에서 비교된 진단 방법론들에 비해 신뢰도 높은 진단 결과를 얻을 수 있었다.

• 지구물리와물리탐사
• /
• 제1권3호
• /
• pp.170-175
• /
• 1998

이 연구는 다변량 통계 기법을 이용한 물리검층 자료로부터의 암석물리학상 결정으로 암상을 예측하는 것이다. 기술 통계 분석으로 물리검층 자료의 특성을 파악하고 주성분 분석에 의한 다변량 검층 자료들의 상관도 분석을 통해 변수들을 변환시켜 새로운 변수인 주성분을 구하고 변수들의 차원을 축소한다. 통계적 방법에 의한 주성분 검층 자료의 구획에 의한 효율적 자료 축소와 계산의 효율성을 높여 양질의 해석결과를 얻을 수 있다. 구획된 주성분 검층 자료로부터 계보적 군집 분석에 의해 암석물리학상을 결정한다. 최적 암석물리학상의 수는 전체 변동과 군집내의 변동사이의 비와 코어자료 등에 의해 비교 결정된다. 이 연구에서 개발된 암석물리학상 결정법을 국내대륙붕 물리검층자료에 적용한 결과 결정된 암석물리학상은 시추 코어 및 시추 암편 분석에 의한 암상 구분화와 잘 일치하였다. 이러한 연구는 저류층 특성인자의 신뢰성 있고 정량적인 평가로 유전 개발 및 생산 계획 시 유용한 도구로 활용될 수 있을 것이다.

• 융합정보논문지
• /
• 제12권1호
• /
• pp.31-38
• /
• 2022

본 논문은 전문가 독립적 비지도 신경망 학습 기반 다변량 시계열 데이터 분석 모델인 MSCRED(Multi-Scale Convolutional Recurrent Encoder-Decoder)의 실제 현장에서의 적용과 Auto-encoder 기반인 MSCRED 모델의 한계인, 학습 데이터가 오염되지 않아야 된다는 점을 극복하기 위한 학습 데이터 샘플링 기법인 Subset Sampling Validation을 제시한다. 라벨 분류가 되어있는 발전소 장비의 진동 데이터를 이용하여 1) 학습 데이터에 비정상 데이터가 섞여 있는 상황을 재현하고, 이를 학습한 경우 2) 1과 같은 상황에서 Subset Sampling Validation 기법을 통해 학습 데이터에서 비정상 데이터를 제거한 경우의 Anomaly Score를 비교하여 MSCRED와 Subset Sampling Validation 기법을 유효성을 평가한다. 이를 통해 본 논문은 전문가 독립적이며 오류 데이터에 강한 이상 진단 프레임워크를 제시해, 다양한 다변량 시계열 데이터 분야에서의 간결하고 정확한 해결 방법을 제시한다.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2007년도 춘계학술대회A
• /
• pp.250-255
• /
• 2007

Steam generator tubes play an important role in safety because they constitute one of the primary barriers between the radioactive and non-radioactive sides of the nuclear power plant. For this reason, the integrity of the tubes is essential in minimizing the leakage possibility of radioactive water. The integrity of the tubes is evaluated based on NDE (non-destructive evaluation) inspection results. Especially ECT (eddy current test) method is usually used for detecting the flaws in steam generator tubes. However, detection capacity of the NDE is not perfect and all of the "real flaws" which actually existing in steam generator tunes is not known by NDE results. Therefore reliability of NDE system is one of the essential parts in assessing the integrity of steam generators. In this study POD (probability of detection) of ECT system for ODSCC in steam generator tubes is evaluated using multivariate logistic regression. The cracked tube specimens are made using the withdrawn steam generator tubes. Therefore the cracks are not artificial but real. Using the multivariate logistic regression method, continuous POD surfaces are evaluated from hit (detection) and miss (no detection) binary data obtained from destructive and non-destructive evaluation of the cracked tubes. Length and depth of cracks are considered in multivariate logistic regression and their effects on detection capacity are evaluated.