Comparison of Novelty Score-Based Multivariate Control Charts

Tuerhong, Gulanbaier; Kim, Seoung Bum

doi:10.1080/03610918.2013.809098

Cited by 9 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Univariate control charts monitor a single quality characteristic, whereas multivariate control charts monitor one or more quality characteristics. Multivariable control charts can be used in order to examine the relationships between quality characteristics and control the multiple quality dimensions in one chart [6]. Multivariate control charts can be more effect in detecting the out-of-control processes than the traditional ones.…”

Section: Introductionmentioning

confidence: 99%

Design of Demerit Control Charts With Fuzzy C-Means Clustering and an Application in Textile Sector

Yilmaz

Yanık

2020

Tekstil Ve Konfeksiyon

View full text Add to dashboard Cite

Companies use process control to detect and prevent defects in production. One of the most commonly used technique is the control charts. To control multiple dimensions of quality on one control chart, multivariable control charts, control charts for attributes and demerit control charts are widely used. In this study, we use demerit control charts to monitor multiple defect types and propose to employ the fuzzy c-means method to cluster the defect types based on pre-specified criteria. The criteria are chosen to represent the severity of defect types and specified as (i) number of scraps, (ii) number of reworks and (iii) time of the rework. In order to test the proposed method, u and c attribute control charts and demerit control charts for six instances in a textile company are used and compared. It is observed that both the scrap and the repair rates are decreased when the proposed method of the demerit control chart is used.

show abstract

Section: Introductionmentioning

confidence: 99%

Design of Demerit Control Charts With Fuzzy C-Means Clustering and an Application in Textile Sector

Yilmaz

Yanık

2020

Tekstil Ve Konfeksiyon

View full text Add to dashboard Cite

show abstract

“…If a charting statistic is below or above the control limits, a process is considered as out of control. If the process is desired to be in an in‐control state, then corrective action is necessary (Tuerhong & Kim, ).…”

Section: Introductionmentioning

confidence: 99%

Fuzzy analytic hierarchy process‐integrated statistical process control: An application of demerit chart at furniture manufacturing company

Sağnak

Kazançoğlu

2019

Multi Criteria Decision Anal

View full text Add to dashboard Cite

Statistical process control techniques, especially control charts, have been popular tools for tracking and analysing the quality improvement process. Control charts make measurements in respect to the central line and the upper and lower control limits of a process and allow corrective action to be taken. It may be not adequate when the quality characteristics include properties requiring the usage of linguistic variables (e.g., very poor, poor, average, good, and very good) rather than identifying them just conforming or nonconforming. The demerit chart is a control chart for attributes that allows the arrangement of the relative exact weight (real number), consistent with the various levels of defects. In this paper, in order to hire linguistic weights, a demerit chart was integrated with fuzzy analytical hierarchy process, mainly through the determination of weights in accordance with the degrees of defects, after which the central line and upper and lower limits were calculated.

show abstract

“…They proposed the use of the novelty scores of OCC algorithms as the monitoring statistics of a control chart. OCCbased control charts have performed better than their alternatives in many nonnormal cases (Tuerhong et al, 2014;Kim et al, 2011;Sukchotrat et al, 2010;Sun and Tsung, 2003).…”

Section: Introductionmentioning

confidence: 99%

Adaptive nonparametric control chart for time-varying and multimodal processes

Kang

Kim

2016

Journal of Process Control

View full text Add to dashboard Cite

Multivariate statistical process control techniques have been widely used to improve processes by reducing variation and preventing defects. In modern manufacturing, because of the complexity and variability of processes, traditional multivariate control charts such as Hotelling's T 2 cannot efficiently handle situations in which the patterns of process observations are nonlinear, multimodal, and time varying. In the present study, we propose a nonparametric control chart, which is capable of adaptively monitoring time-varying and multimodal processes. Experiments with simulated and real process data from a thin film transistor-liquid crystal display (TFT-LCD) demonstrate the effectiveness and accuracy of the proposed method.

show abstract

Comparison of Novelty Score-Based Multivariate Control Charts

Cited by 9 publications

References 31 publications

Design of Demerit Control Charts With Fuzzy C-Means Clustering and an Application in Textile Sector

Design of Demerit Control Charts With Fuzzy C-Means Clustering and an Application in Textile Sector

Fuzzy analytic hierarchy process‐integrated statistical process control: An application of demerit chart at furniture manufacturing company

Adaptive nonparametric control chart for time-varying and multimodal processes

Contact Info

Product

Resources

About