摘要:

Experimental design techniques were applied to the task of characterizing the inspection capability of the machine vision component of an automated laser hole-drilling and inspection system for gas turbine engine manufacturing. The system uses a laser to drill very small cooling holes in gas turbine engine combustor rings and a machine vision component to inspect the holes. The machine is designed with a closed loop algorithm to adaptively control the laser drilling operation based on the inspection results. An experiment with blocking factors provided a disciplined framework for data collection to characterize the capability of the vision system component during the development phase. This experiment provided a better understanding of the system's capabilities and the user's design requirements, which has yielded system improvements.

ISSN:0022-4065    

DOI:10.1080/00224065.1994.11979493

出版商:Taylor&Francis    

年代:1994

数据来源: Taylor

摘要:

Robust-design experiments can be a very useful tool for improving quality. They enable engineers to reduce the variance of important quality characteristics by identifying design factors with dispersion effects and guiding the choice of nominal levels of those factors. Robust-design experiments are especially effective when it is possible to build some variation directly into the experiment by including noise factors–factors that are impossible or too expensive to control during actual production or use. When noise factors are included, it is important to model their effects explicitly in the subsequent analysis. We present two examples in which failure to do so leads to incorrect conclusions about dispersion effects.

ISSN:0022-4065    

DOI:10.1080/00224065.1994.11979494

出版商:Taylor&Francis    

年代:1994

数据来源: Taylor

摘要:

Calibration, in the sense of inverse regression, is widely used in measurement science and other applications. For univariate regression models, simultaneous calibration intervals enable one to construct confidence intervals for the unobserved values of the independent variable (x's) corresponding to an unlimited sequence (Yn+1, Yn+2,…) of future observations of the dependent variable. The intervals considered have the interpretation that if the initial training sample belongs to a specified setGof“good”outcomes, the conditional coverage probability for each future confidence interval will be at least the nominal value. The setGis constructed to occur with high probability. All methods for constructing calibration intervals currently in the literature are conservative in that they are obtained from simultaneous tolerance intervals for which the actual confidence level exceeds the nominal level. This work develops constant-width simultaneous tolerance intervals for which the bound on the nominal coverage probabilities is exact under normality. The resulting confidence intervals represent an attractive balance between efficiency and simplicity for linear calibration problems.

ISSN:0022-4065    

DOI:10.1080/00224065.1994.11979495

出版商:Taylor&Francis    

年代:1994

数据来源: Taylor

摘要:

Tests of hypotheses for variance components are often of interest in random effects analysis of variance models. However, in many applications, exact tests are not available and approximate methods must be used. Many investigators form approximate tests based on“quasi”Fratios. A different approach based on a confidence interval for the variance component is proposed in this paper. The approach is illustrated with a random effects three-factor crossed design, and guidelines are provided for application to other designs.

ISSN:0022-4065    

DOI:10.1080/00224065.1994.11979496

出版商:Taylor&Francis    

年代:1994

数据来源: Taylor

摘要:

Many new approaches and applications have been developed in the area of the economic design of process control charts. This article provides a survey and brief summary of the work on economic designs published during the period from 1981 through 1991.

ISSN:0022-4065    

DOI:10.1080/00224065.1994.11979497

出版商:Taylor&Francis    

年代:1994

数据来源: Taylor

摘要:

A BASIC program is presented for two procedures that deal with constructing two-sided confidence intervals on means of normal populations with unknown standard deviations. One gives the sample size for a specified-length confidence interval for which the length and the probability (the tolerance) of not exceeding the given length are both chosen by the user. The other implements Stein's sampling rule to give the sample size for a confidence interval of user-specified length for which the probability (the tolerance) of not exceeding that length is 100 percent.

ISSN:0022-4065    

DOI:10.1080/00224065.1994.11979498

出版商:Taylor&Francis    

年代:1994

数据来源: Taylor

ISSN:0022-4065    

DOI:10.1080/00224065.1994.11979499

出版商:Taylor&Francis    

年代:1994

数据来源: Taylor

ISSN:0022-4065    

DOI:10.1080/00224065.1994.11979500

出版商:Taylor&Francis    

年代:1994

数据来源: Taylor

ISSN:0022-4065    

DOI:10.1080/00224065.1994.11979501

出版商:Taylor&Francis    

年代:1994

数据来源: Taylor

ISSN:0022-4065    

DOI:10.1080/00224065.1994.11979502

出版商:Taylor&Francis    

年代:1994

数据来源: Taylor