ISSN:0022-4065    

DOI:10.1080/00224065.1995.11979591

出版商:Taylor&Francis    

年代:1995

数据来源: Taylor

摘要:

The sensitivity of four tests on Shewhart typeQcharts and of specially designed EWMA and CUSUMQcharts to detect one-step permanent shifts of either a normal mean or standard deviation has been studied. The usual test that signals for one point beyond three standard deviations on a Shewhart chart is found to have poor sensitivity, generally. The test that signals when four out of five consecutive points are beyond one standard deviation in the same direction is found to be a good omnibus test. The EWMA and CUSUMQcharts are the most sensitive and are about comparable in overall performance.

ISSN:0022-4065    

DOI:10.1080/00224065.1995.11979592

出版商:Taylor&Francis    

年代:1995

数据来源: Taylor

摘要:

The sensitivity of four tests on ShewhartQcharts and of specially designed exponentially weighted moving average (EWMA) and cumulative sum (CUSUM)Qcharts to detect one-step permanent shifts of a binomial probability parameterphas been studied. The usual test that signals for one point beyond three standard deviations on a Shewhart chart is found to have poor sensitivity, generally. The test that signals when four out of five consecutive points are beyond one standard deviation in the same direction is found to be a good omnibus test. The EWMA and CUSUMQcharts are most sensitive and are about comparable in overall performance.

ISSN:0022-4065    

DOI:10.1080/00224065.1995.11979593

出版商:Taylor&Francis    

年代:1995

数据来源: Taylor

摘要:

A simple but effective method to aid in the design ofX̄control schemes is presented. Subgroup size, sampling frequency, and control limit selection is combined via a methodology that determines the optimum control scheme. Average production length (APL) is introduced as the criterion for measuring control scheme performance. APL is the total amount of production between a shift in the process mean and signal of the shift, a measure of the effectiveness of a control scheme in maintaining process characteristics as close to target as possible. The methodology recognizes that statistical process control (SPC) involves resource constraints which limit the rate at which a process can be sampled. A model is developed with a sampling rate and maximum false alarm rate as inputs to determine the optimum subgroup size, sampling frequency, and control limits as measured by APL. The methodology includes key elements of control scheme design without the complexity of economic models. The performance of our design method is compared to routine application of classicalX̄chart guidelines.

ISSN:0022-4065    

DOI:10.1080/00224065.1995.11979594

出版商:Taylor&Francis    

年代:1995

数据来源: Taylor

摘要:

Taguchi's product-array design consists of two portions: an inner array containing the design factors and an outer array containing noise factors. The function of the outer array is very different from that of the inner array, however. The outer array is most likely to sample or simulate the distribution of the noise factors, while the inner array is designated to facilitate the optimization. Since performance for each inner point is evaluated via its corresponding outer array points, the outer array plays an important role in robust design. We show here that the optimal representative point method via quantizer is superior to using other methods (including orthogonal array) to design outer array points. All optimal representative points are tabulated for practical use. The usage of these tables is demonstrated by examples.

ISSN:0022-4065    

DOI:10.1080/00224065.1995.11979595

出版商:Taylor&Francis    

年代:1995

数据来源: Taylor

摘要:

Variation in component properties and dimensions is the most widely recognized cause of product nonconformities. However, conventional statistical methods, like statistical process control (SPC), are ineffective in controlling mistakes. The distinction between mistakes and variation becomes increasingly important as the target nonconformity rates approach extremely low values as substantiated by Motorola's experience. Product complexity increases the likelihood of nonconformities due to both variation and mistakes and is thus a root source of nonconformities. We have shown that assembly complexity, quantified using design for assembly analysis, is highly correlated with nonconformity data in two widely different industries. These correlations and the ability to easily measure assembly complexity permits rapid comparison of the potential nonconformity rates of alternate design concepts.

ISSN:0022-4065    

DOI:10.1080/00224065.1995.11979596

出版商:Taylor&Francis    

年代:1995

数据来源: Taylor

摘要:

This paper presents a statistically constrained economic model for the optimal design of an exponentially weighted moving average (EWMA) control chart for controlling process means. The optimum design parameters include the sample size, control limit width, sampling interval, and EWMA weight. The parameters are obtained by minimizing a total cost function proposed by Lorenzen and Vance, subject to additional statistical constraints on average run length (ARL) or average time-to-signal (ATS). Sensitivity analysis of the minimum costs as they are affected by various ATS bounds shows that the cost is more sensitive to smaller out-of-control bounds on ATS or ARL, but relatively insensitive to larger bounds. Investigation of economic statistical design for the EWMA chart reveals that adding constraints does not significantly increase the cost and does provide better protection against shift sizes other than those expected. Cost comparisons between optimal economic designs and optimal economic statistical designs show no significant cost increase when imposing statistical constraints on the cost model.

ISSN:0022-4065    

DOI:10.1080/00224065.1995.11979597

出版商:Taylor&Francis    

年代:1995

数据来源: Taylor

摘要:

A computer program is presented for the statistically constrained economic design of exponentially weighted moving average control charts for controlling process means. The program finds the optimal sample size, control limit width, sampling interval, and weighting factor by minimizing a total cost function proposed by Lorenzen and Vance subject to additional statistical constraints on average run length (ARL) or average time-to-signal (ATS). The ARL values are determined by solving systems of linear algebraic equations using Gaussian quadrature, following the integration-equation approach outlined by Crowder.

ISSN:0022-4065    

DOI:10.1080/00224065.1995.11979598

出版商:Taylor&Francis    

年代:1995

数据来源: Taylor

ISSN:0022-4065    

DOI:10.1080/00224065.1995.11979599

出版商:Taylor&Francis    

年代:1995

数据来源: Taylor

ISSN:0022-4065    

DOI:10.1080/00224065.1995.11979600

出版商:Taylor&Francis    

年代:1995

数据来源: Taylor