An Analysis of Taguchi's On-Line Quality-Monitoring Procedures for Attributes

Nayebpour, Mohamad R.; Woodall, William H.

doi:10.1080/00401706.1993.10484993

Cited by 31 publications

(51 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To be specific, we can use the notation L 1 (m, p, π) in the case when retrospective inspection is performed and L 2 (m, p, π) when it is not. From Nayebpour and Woodall (1993), we have…”

Section: The Statistical Model and Optimization Problem For Case IImentioning

confidence: 99%

“…The cost component C a in the expression for L 1 (m, p, π) includes the cost of retrospective inspection, whereas that in L 2 (m, p, π) does not (see Nayebpour and Woodall 1993).…”

Section: Optimum Diagnosis Interval For Controlmentioning

confidence: 99%

“…Under the geometric PFM with a given p, explicit expressions for E(C) and E(T) can be computed (Nayebpour and Woodall 1993), and E(L) can be expressed as a convex function of m for given p Figure 1. An illustration of case II (•, nondefective item; ×, defective item; 1, inspected item).…”

Section: The Statistical Model and Optimization Problem For Case IImentioning

confidence: 99%

“…On one hand, frequent inspection requires more cost, time, and manpower, whereas on the other hand, reduced frequency of inspection may lead to the risk of rejection of a large number of items. The problem of developing economically based online control methods for attributes has been addressed in detail by Taguchi (1981Taguchi ( , 1984Taguchi ( , 1985, Taguchi, Elsayed, and Hsiang (1989), and Nayebpour and Woodall (1993). The basic idea is to inspect a single item after every m units of production, with a process adjustment made as soon as a defective item is found.…”

Section: Introductionmentioning

confidence: 99%

“…Whereas Taguchi did not explicitly assume a specific process failure mechanism (PFM), Nayebpour and Woodall (1993) considered a geometric PFM with a parameter p. This means that the duration of the process in the in-control state, measured by the number of items produced before a process shift occurs, is a geometric random variable with parameter p. The expected loss per item, E(L), is a function of p in case I and (p, π) in case II. Thus the task of obtaining the optimal sampling interval comprises of the following two stages: a.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Estimation of Process Parameters to Determine the Optimum Diagnosis Interval for Control of Defective Items

Dasgupta

Mandal

2008

Technometrics

View full text Add to dashboard Cite

The online quality monitoring procedure for attributes proposed by Taguchi has been critically studied and extended by a few researchers. Determination of the optimum diagnosis interval requires estimation of some parameters related to the process failure mechanism. Improper estimates of these parameters may lead to an incorrect choice of the diagnosis interval and thus huge economic penalties. We propose a Bayesian approach to estimate the process parameters under two different process models, commonly called as the case II and case III models in the literature. We discuss a systematic way to use available engineering knowledge in eliciting the prior for the parameters, and demonstrate the performance of the proposed method using extensive simulation and a case study from a hot rolling mill.

show abstract

“…To be specific, we can use the notation L 1 (m, p, π) in the case when retrospective inspection is performed and L 2 (m, p, π) when it is not. From Nayebpour and Woodall (1993), we have…”

Section: The Statistical Model and Optimization Problem For Case IImentioning

confidence: 99%

“…The cost component C a in the expression for L 1 (m, p, π) includes the cost of retrospective inspection, whereas that in L 2 (m, p, π) does not (see Nayebpour and Woodall 1993).…”

Section: Optimum Diagnosis Interval For Controlmentioning

confidence: 99%

Section: The Statistical Model and Optimization Problem For Case IImentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Estimation of Process Parameters to Determine the Optimum Diagnosis Interval for Control of Defective Items

Dasgupta

Mandal

2008

Technometrics

View full text Add to dashboard Cite

show abstract

Quality engineering for continuous performance improvement in products and processes: A review and reflections

Dabade

Ray

1996

Qual. Reliab. Engng. Int.

View full text Add to dashboard Cite

In the face of stiff and demanding competition internationally, there is a growing resolve in the industrial community to provide the customers and the market in general products and services of superior quality. Quality engineering has been established as an important continuous performance improvement methodology during the last decade. Consequently, numerous developments and innovative methods have been reported in the literature by researchers and practitioners alike. In this paper, a critical appraisal of recent developments, improvisations, and innovations in the field of quality engineering has been made. It is observed that there exists an immense body of knowledge in terms of better approaches, techniques, methodologies, aids, analysis tools, etc. However, most of these are oriented toward product improvement or process improvement in a localized manner, and a systematic approach for the application of quality engineering encompassing all the importnat functions in an organization is lacking. In view of this a comprehensive quality engineering methodology is also proposed in this paper so that the implementation of quality engineering in an organization will be more effective, and the benefits to be achieved will be substantial in real‐life situations.

show abstract