An Analysis of Taguchi's On-Line Process-Control Procedure under a Random-Walk Model

Adams, Benjamin M.; Woodall, William H.

doi:10.2307/1269991

Cited by 36 publications

(20 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that ¼ 0.15 indicates that the IMA(1,1) process would behave similarly to a random walk process. Under this situation, the modified Taguchi's is expected to perform well when C a is larger than C m , see Adams and Woodall (1989) and Chou and Wang (1996). It is clear that the modified Taguchi's procedure performs worse when increases.…”

Section: Numerical Investigation and Discussionmentioning

confidence: 97%

“…By imposing the approximation 2 ffi d 2 0 =ARL 0 according to Adams and Woodall (1989) and replacing 2 by 2 d ¼ EðZ t À Z tÀ1 Þ 2 , Chou and Wang (1996) further modified (16a) and (16b) as follows:…”

Section: Numerical Investigation and Discussionmentioning

confidence: 99%

“…See, e.g., Box and Jenkins (1963), and Astrom (1970), who have initially investigated the problem for the chemical industry. Other related work includes Box et al (1974), Abraham and Box (1979), Crowder (1986), MacGregor (1987), Adams and Woodall (1989), Taguchi et al (1989), Box and Kramer (1992), Harris (1992), Vander Wiel et al (1992, Tucker et al (1993), Wang (1996, 2001), and Box and Luceno (1997). Although the purposes of SPC and APC are different, they are both important tools for continuous process control and quality improvement.…”

Section: Introductionmentioning

confidence: 99%

“…Taguchi et al (1989) proposed an approach to determine sampling intervals and control limits for an approximate random walk disturbance. Taguchi's procedure was further extended by Adams and Woodall (1989), Srivastava and Wu (1991), and Wang (1996, 2001). Box and Kramer (1992) investigated the on-line process control with an IMA process where all three costs-adjustment, monitoring and off-target costs-were important.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Simulated annealing procedure for on-line control with process dynamics

Chou

Wang

2007

International Journal of Systems Science

View full text Add to dashboard Cite

We study the problem of economic design for a control policy where the sampling interval ( m) and control limit (d) are determined by minimizing the expected total quality costs. In this article, we propose a simulated annealing scheme applicable to an economic design for a control policy where the disturbances can follow the autoregressive integrated moving average (ARIMA) processes and obtain the optimum d and m. Numerical investigations are conducted for a system with a first-order dynamics subjected to an IMA ( 1,1), and an ARI ( 1,1) random disturbance. The performance of the proposed simulated annealing scheme is very promising and compares favorably to other methods

show abstract

Section: Numerical Investigation and Discussionmentioning

confidence: 97%

Section: Numerical Investigation and Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Simulated annealing procedure for on-line control with process dynamics

Chou

Wang

2007

International Journal of Systems Science

View full text Add to dashboard Cite

show abstract

“…These methods will be referred to as Tuguchi's methods in this article. Taguchi's method for variables was studied by Adams and Woodall (1989), who concluded that his method and the associated expected-loss function can be misleading in some cases. The purpose of this article is to consider Taguchi's on-line methods for attributes.…”

mentioning

confidence: 99%

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

Nayebpour

Woodall

1993

Technometrics

Self Cite

View full text Add to dashboard Cite

Monitoring process for attributes with quality deterioration and diagnosis errors

Trindade¹,

Ho²,

Quinino

2007

Appl Stoch Models Bus & Ind

View full text Add to dashboard Cite

The aim of this paper is to present an online economical quality-control procedure for attributes in a process subject to quality deterioration after random shift and misclassification errors during inspections. The process starts in control (State I) and, in a random time, it shifts to out of control (State II). Once at State II, the non-conforming fraction increases according to a non-decreasing function (z), where z is the number of items produced after a shift. The monitoring procedure consists of inspecting a single item at every m produced items, which is examined r times independently to decide its condition. Once an inspected item is declared non-conforming, the process is stopped and adjusted. A direct search technique is used to find the optimum parameters which minimize the expected cost function. The proposed model is illustrated by a numerical example.conforming items) to the out-of-control state (the percentage of non-conforming items greater than 0%). Using mathematical symbols, the probability of non-conforming items shifts from p 1 = 0 (State I) to p 2 >0 (State II). The monitoring procedure consists of inspecting a single item at every m produced items. If the inspected item is judged conforming, the production process goes on; otherwise, the process is stopped for adjustment.This type of procedure to monitor process was studied by many authors as Adams and Woodall [2], Srivastava and Wu [3][4][5][6][7][8], Box and Kramer [9], Box and Luceno [10], Chou and Wang [11], Nandi and Sreehari [12,13], and Wang and Yue [14]. Examples that put into practice this kind of procedure may include the automatic process of soldering, production of semiconductors, production of diode, production of printed circuit boards and chemical processes [15][16][17]. Generally, production systems that employ some type of automatic control by collecting individual observations may be improved by the procedure here discussed.In Taguchi et al.[1], the authors assumed implicitly a uniform distribution to describe the shift from State I to State II. Such a condition provided a simpler cost function; however, it does not cover most practical situations. Nayebpour and Woodall [18] developed an alternative procedure assuming a geometric distribution to model the random shifts. They concluded that their approach was more appropriate than Taguchi's proposal mainly for p 2 >0. Nandi and Sreehari [12] developed a model under the assumption that the production process is subject to two assignable causes (in their paper, they are named minor and major).Borges et al. [19] noted that the procedures discussed in Taguchi et al.[1] and further papers may present inspection errors, compromising the determination of the optimum sampling interval. To this effect, they not only developed an approach that incorporates inspection errors but also evaluated the impact when those errors are not taken into account. About the effects of inspection errors on quality control, see Johnson et al. [20], Ranjan et al. [21], and Wang [22].Previous studies as...

show abstract

An Analysis of Taguchi's On-Line Process-Control Procedure under a Random-Walk Model

Cited by 36 publications

References 13 publications

Simulated annealing procedure for on-line control with process dynamics

Simulated annealing procedure for on-line control with process dynamics

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

Monitoring process for attributes with quality deterioration and diagnosis errors

Contact Info

Product

Resources

About