• The Korean Journal of Applied Statistics
• /
• v.33 no.4
• /
• pp.467-482
• /
• 2020

We investigate a monitoring procedure for the early detection of parameter changes in location-scale time series models. We introduce a detector for monitoring procedure based on modified residual cumulative sum (CUSUM). The asymptotic properties of the monitoring procedure are established under the null and alternative hypotheses. Simulation results and data analysis are also provided for illustration.

• Korean Journal of Ecology and Environment
• /
• v.38 no.spc
• /
• pp.76-83
• /
• 2005

The marked increase in the number of environmental problems, combined with the increase in their intensity and spatial extent, has resulted in an ever-increasing need for constant monitoring. This is complicated by the occurrence of new and complicated environmental issues that often prevent a thorough understanding of the entire monitoring framework. In the present study, a diagrammatic method was developed to present the entire framework of a monitoring plan. The diagram was separated into three sections- "Problem Section", "Research Process and Data Section" and "Entities Section" - to clearly present the disparate relationships between monitoring objectives and the monitoring procedure. Notation of the diagrams was undertaken using Unified Modeling Language (UML). A hypothetical monitoring plan for an environmental problem was designed to assess usefulness of the diagrammatic method. The diagram was capable of reviewing and revising the monitoring plan and could be used to select a monitoring procedure according to the monitoring objectives of the plan. The results suggested that this diagrammatic method was effective for designing an appropriate monitoring plan for a given monitoring objective.

• The Korean Journal of Applied Statistics
• /
• v.29 no.7
• /
• pp.1429-1444
• /
• 2016

We suggest a monitoring procedure to detect changes in the mean of the stochastic process. The monitoring procedure is based on penalized least squares estimates. Unlike the fluctuation (FL) monitoring, we use the numbers of nonzero estimates not the fluctuations of sequential parameter estimates. We investigate the behavior of the proposed monitoring procedure by means of a simulation study and compare its performance with CUSUM monitoring.

• International Journal of Reliability and Applications
• /
• v.11 no.2
• /
• pp.69-87
• /
• 2010

The optimal replacement problem was investigated for a multi-state deteriorated system for which the true internal state cannot be observed directly except when the system breaks down completely. The internal state was assumed to be monitored incompletely by a monitor that gives information related to the true state of the system. The problem was formulated as a partially observable Markov decision process. The optimal procedure was found to be a monotone procedure with respect to stochastic increasing ordering of the state probability vectors under some assumptions. Limiting the optimal procedure to a monotone procedure would greatly reduce the tremendous amount of calculation time required to find the optimal procedure.

• The Korean Journal of Applied Statistics
• /
• v.37 no.2
• /
• pp.191-207
• /
• 2024

Many studies have been conducted to quickly detect out-of-control situations in autocorrelated processes. The most traditionally used method is a residual control chart, which uses residuals calculated from a fitted time series model. However, many procedures for monitoring autocorrelated processes using statistical learning methods have recently been proposed. In this paper, we propose a monitoring procedure using the latent vector of LSTM Autoencoder, a deep learning-based unsupervised learning method. We compare the performance of this procedure with the LSTM Autoencoder procedure based on the reconstruction error, the RNN classification procedure, and the residual charting procedure through simulation studies. Simulation results show that the performance of the proposed procedure and the RNN classification procedure are similar, but the proposed procedure has the advantage of being useful in processes where sufficient out-of-control data cannot be obtained, because it does not require out-of-control data for training.

• Journal of Korean Society for Quality Management
• /
• v.27 no.1
• /
• pp.35-45
• /
• 1999

A process monitoring procedure using a correlated variable is presented when a lower specification limit is given on the performance variable. Every item is inspected with a variable correlated with the performance variable. When an item is rejected in the screening inspection, the process is checked for change using the mean and variance of measurements of the correlated variable for n preceding items including the rejected one. The performance variable is assumed to be normally distributed. A linear relationship between the performance and surrogate variables is assumed with normally distributed error term. The monitoring procedure is designed so that the prespecified outgoing quality can be attained.

• The Korean Journal of Applied Statistics
• /
• v.16 no.1
• /
• pp.71-85
• /
• 2003

In the economic design of the process control procedure, where quality is measured at certain time intervals, its properties are difficult to derive due to the discreteness of the measurement intervals. In this paper a Markov chain representation of the process monitoring procedure is developed and used to derive its properties when the process follows an ARIMA(0,1,1) model, which is designed to describe the effect of the noise and the special cause in the process cycle. The properties of the Markov chain depend on the transition matrix, which is determined by the control procedure and the process distribution. The derived representation of the Markov chain can be adapted to most different types of control procedures and different kinds of process distributions by obtaining the corresponding transition matrix.

• Journal of Navigation and Port Research
• /
• v.32 no.2
• /
• pp.121-126
• /
• 2008

This paper presents hull stress monitoring system installed in LNGC damaged by a Typhoon Elongation/contraction of removed areas has been assessed in terms of possible residual stress that will take place in replaced blocks when the applied load is removed. The bending moment of a vessel changes actually in terms of loss of longitudinal members and the change of weight distribution in repair procedure. The change of bending moment affects mainly in hull stress of longitudinal members. Hull stress monitoring system was installed on upper deck to prove LNGC stable in the criteria to be less than 40MPa during the period of repair procedure. A temperature measuring system was also installed to exclude the additional stress due to thermal effect from the measured hull stress. As a result, the hull stress was modified with the data measured by the temperature measuring system. This hull stress considering thermal effect was used as a guide stress to check the safety of LNGC during the period of repair procedure.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.17 no.32
• /
• pp.145-154
• /
• 1994

In this paper, monitoring processor in a circuit switched network is considered. Monitoring processor monitors communication links, and offers a grade of service in each link to controller. Such an information is useful for an effective maintenance of system. Two links with nonsymmetric system Parameters are considered. each link is assumed independent M/M/1/1 type. The Markov process is introduced to compute busy and idle portions of monitoring processor and monitored rate of each link. Inter-idle times and inter-monitoring times of monitoring processor between two links are respectively computed. A recursive formula is introduced to make computational procedure rigorous.

• Communications for Statistical Applications and Methods
• /
• v.7 no.2
• /
• pp.435-446
• /
• 2000

Statistical process control(SPC) and engineering process control(EPC) are two strategies for quality improvement that have been developed independently. EPC seeks to minimize variability by adjusting compensatory variables in order to make the process level close to the target, while SPC seeks to reduce variability by monitoring and eliminating causes of variation. One purpose of this paper is to propose the IMA(0,1,1) model as the in-control process model. For the out-of-control process model we consider two cases; one is the case with a step shift in the level, and the other is the case with a change in the nonstationarity. Another purpose is to suggest the use of an integrated process control procedure with adjustment and monitoring, which can consider the proposed process model effectively. An integrated control procedure will improve the process control activity significantly for cases of the proposed model, when compared to the procedure of using either EPC or SPC, since EPC will keep the process close to the target and SPC will eliminate special causes.