Test Regions Using Two or More Correlated Product Characteristics

Albers, Willem; Wim,; Arts, G.R.J.; Kallenberg, W.C.M.

doi:10.1080/00401706.1999.10485636

Cited by 6 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The studies of Healy, Kim, Chou, Albers, and Albers are perhaps most closely related to the focus of our work, as these studies also focus on calculating optimal guardbands or tolerance limits. However, these studies differ from ours in 2 major aspects: First, these articles have a slightly different focus than our study: While Kim specifically consider economic aspects concerned with the inspection procedure, Albers and Albers tackle the calculation of guardbands for a certain characteristic of a device that may be difficult or costly to measure. They do so by investigating how the measurements of a physical parameter can be bypassed by using the measurements of another parameter that is less costly to measure and is highly correlated with the parameter of interest.…”

Section: Introduction and Problem Descriptionmentioning

confidence: 98%

Determination of tolerance limits for the reliability of semiconductor devices using longitudinal data

Hofer

Leitner

Lewitschnig

et al. 2017

Quality & Reliability Eng

View full text Add to dashboard Cite

Design and production of semiconductor devices for the automotive industry are characterized by high reliability requirements, such that the proper functioning of these devices is ensured over the whole specified lifetime. Therefore, manufacturers let their products undergo extensive testing procedures that simulate the tough requirements their products have to withstand. Such tests typically are highly accelerated, to test the behavior of the products over the whole lifetime. In case of drift of electrical parameters, manufacturers then need to find appropriate tolerance limits for their final electrical product tests, such that the proper functioning of their devices over the whole specified lifetime is ensured. In this study, we present a statistical model for the determination of tolerance limits that minimize yield loss. The model considers longitudinal measurements of continuous features, based on censored data from stress tests. The tolerance limits are derived from multivariate distributions where the dependence structure is described by different copulas. Based on extensive numerical testing, we are able to provide insights into the properties of our model for different drift behaviors of the devices.

show abstract

Section: Introduction and Problem Descriptionmentioning

confidence: 98%

Determination of tolerance limits for the reliability of semiconductor devices using longitudinal data

Hofer

Leitner

Lewitschnig

et al. 2017

Quality & Reliability Eng

View full text Add to dashboard Cite

show abstract

“…In production contexts, there is typically a need to verify that a particular item or a product stream or lot of items meets performance/conformance goals of the producer and/or a consumer. Where one admits that individual conformance assessments are subject to uncertainty (possibly, as in Albers, Arts, and Kallenberg [1], because only indirect measurement of primary performance characteristics is possible or desirable) or only some of all items of interest will be inspected, statistical methods become useful. Traditionally, this was evident in the prominent place of methods of acceptance sampling in the engineering statistics literature.…”

Section: Statistics and (Sampling) Inspection And Acceptance Samplingmentioning

confidence: 99%

Engineering Statistics

Vardeman¹

2014

Wiley StatsRef: Statistics Reference Online

View full text Add to dashboard Cite

In this entry we seek to put into perspective some of the ways in which statistical methods contribute to modern engineering practice.Engineers design and oversee the production, operation, and maintenance of the products and systems that under-gird modern technological society. Their work is built on the foundation of physical (and increasingly biological) science. However, it is of necessity often highly empirical, because there simply isn't scientific theory complete and simple enough to effectively describe all of the myriad circumstances that arise even in engineering design, let alone those encountered in production, operation, and maintenance. As a consequence, engineering is an inherently statistical enterprise. Engineers must routinely collect, summarize, and draw inferences based on data, and it is hard to think of a statistical method that has no potential use in modern engineering.* The financial support of the Deutsche Forschungsgemeinschaft (SFB 475, "Reduction of Complexity in Multivariate Data Structures") through the University of Dortmund is gratefully acknowledged. The author thanks Max Morris, Bill Meeker and Huaiqing Wu for their comments on an ear lier draft of the entry.

show abstract

“…This implies that the difference in yield and consumer risk between T * and T also is o( l σ l ). Besides the fact that the test limits are more simple, another advantage of using the test region T instead of T , is that the test limit in T for the l th linear combination is similar to the test limit that occurs in Albers, Arts and Kallenberg (1998b), where one considers the inspection of one characteristic, by means of a linear combination of measurements of two or more correlated characteristics. Using the test region T instead of T , enables us to use these results on inspection of one characteristic, in case parameters are unknown.…”

Section: Optimal Test Regionmentioning

confidence: 99%

Simultaneous inspection of several product characteristics

Arts

Albers

Kallenberg

2001

Metrika

Self Cite

View full text Add to dashboard Cite

In this paper we consider the inspection of a product of which several characteristics have to satisfy given specification limits. A problem which occurs in the inspection process quite often is that a measurement error occurs in measuring the characteristics. Therefore, it is common practice to inspect each characteristic by comparing its measurement to a test limit which is slightly more strict than the corresponding specification limit. An item then is accepted if for each characteristic the measurement conforms to the corresponding test limit. However, instead of inspecting an individual characteristic merely using its own measurement, it is (much) more efficient to use the measurements of the other characteristics as well, especially if some of the characteristics are highly correlated. In this paper it is shown how the measurements of all the characteristics can be used to test whether an item is conforming.

show abstract

Test Regions Using Two or More Correlated Product Characteristics

Cited by 6 publications

References 12 publications

Determination of tolerance limits for the reliability of semiconductor devices using longitudinal data

Determination of tolerance limits for the reliability of semiconductor devices using longitudinal data

Engineering Statistics

Simultaneous inspection of several product characteristics

Contact Info

Product

Resources

About